arXiv Papers with Code in Computer Science (November 2025)

Abstract:
Reasoning over dynamic visual content remains a central challenge for multimodal large language models. Recent thinking models generate explicit reasoning traces for interpretability; however, their reasoning often appears convincing while being logically inconsistent or weakly grounded in visual evidence. We identify and formalize these issues through two diagnostic metrics: Think Answer Consistency (TAC), which measures the alignment between reasoning and answers, and Video Attention Score (VAS), which captures the extent to which reasoning depends on visual versus textual cues. Analysis across 11 video reasoning benchmarks shows that current models rely heavily on linguistic priors rather than visual content. To address this, we propose a reinforcement learning approach that enhances both temporal precision and reasoning consistency. Our approach combines timestamp aware supervised fine tuning with Group Relative Policy Optimization (GRPO) guided by a novel Temporal Alignment Reward (TAR). This dual step post training stage encourages temporally aligned and causally coherent video reasoning. The resulting model, Video R2, achieves consistently higher TAC, VAS, and accuracy across multiple benchmarks, demonstrating that improvements in temporal alignment and reasoning coherence lead to more accurate and trustworthy video understanding. Code: https://github.com/mbzuai-oryx/Video-R2

Paperid: 2, https://arxiv.org/pdf/2511.23477.pdf GitHub

Abstract:
Recent multimodal large language models (MLLMs) have advanced video understanding, yet most still "think about videos" ie once a video is encoded, reasoning unfolds entirely in text, treating visual input as a static context. This passive paradigm creates a semantic bottleneck: models cannot rewatch, refocus, or verify evidence, leading to shallow visual reasoning on tasks requiring fine grained spatio temporal understanding. In this work, we introduce Interactive Video Reasoning, a new paradigm that transforms video into an active cognitive workspace, enabling models to "think with videos". Our model, Video CoM, reasons through a Chain of Manipulations (CoM), performing iterative visual actions to gather and refine evidence. To support this behavior, we construct Video CoM Instruct, an 18K instruction tuning dataset curated for multi step manipulation reasoning. Beyond supervised learning, we further optimize the manipulation policy via reinforcement learning with reasoning aware Group Relative Policy Optimization (GRPO). Unlike prior work that relies solely on sparse answer rewards, our method introduces step level reasoning rewards, guiding the model toward grounded and consistent reasoning. Video CoM achieves strong results across nine video reasoning benchmarks, improving average performance by 3.6 percent over recent state of the art models, while training on only 25K SFT and 3K GRPO video samples, significantly fewer than comparable large scale models. Ablation studies demonstrate that reasoning aware rewards improve both accuracy and interpretability. Code: https://github.com/mbzuai-oryx/Video-CoM

Paperid: 3, https://arxiv.org/pdf/2511.23475.pdf GitHub

Abstract:
Recently, multi-person video generation has started to gain prominence. While a few preliminary works have explored audio-driven multi-person talking video generation, they often face challenges due to the high costs of diverse multi-person data collection and the difficulty of driving multiple identities with coherent interactivity. To address these challenges, we propose AnyTalker, a multi-person generation framework that features an extensible multi-stream processing architecture. Specifically, we extend Diffusion Transformer's attention block with a novel identity-aware attention mechanism that iteratively processes identity-audio pairs, allowing arbitrary scaling of drivable identities. Besides, training multi-person generative models demands massive multi-person data. Our proposed training pipeline depends solely on single-person videos to learn multi-person speaking patterns and refines interactivity with only a few real multi-person clips. Furthermore, we contribute a targeted metric and dataset designed to evaluate the naturalness and interactivity of the generated multi-person videos. Extensive experiments demonstrate that AnyTalker achieves remarkable lip synchronization, visual quality, and natural interactivity, striking a favorable balance between data costs and identity scalability.

Paperid: 4, https://arxiv.org/pdf/2511.23473.pdf GitHub

Abstract:
Recent advances in large language models (LLMs) have enabled breakthroughs in mathematical discovery, exemplified by AlphaEvolve, a closed-source system that evolves programs to improve bounds on open problems. However, it relies on ensembles of frontier LLMs to achieve new bounds and is a pure inference system that models cannot internalize the evolving strategies. We introduce ThetaEvolve, an open-source framework that simplifies and extends AlphaEvolve to efficiently scale both in-context learning and Reinforcement Learning (RL) at test time, allowing models to continually learn from their experiences in improving open optimization problems. ThetaEvolve features a single LLM, a large program database for enhanced exploration, batch sampling for higher throughput, lazy penalties to discourage stagnant outputs, and optional reward shaping for stable training signals, etc. ThetaEvolve is the first evolving framework that enable a small open-source model, like DeepSeek-R1-0528-Qwen3-8B, to achieve new best-known bounds on open problems (circle packing and first auto-correlation inequality) mentioned in AlphaEvolve. Besides, across two models and four open tasks, we find that ThetaEvolve with RL at test-time consistently outperforms inference-only baselines, and the model indeed learns evolving capabilities, as the RL-trained checkpoints demonstrate faster progress and better final performance on both trained target task and other unseen tasks. We release our code publicly: https://github.com/ypwang61/ThetaEvolve

Paperid: 5, https://arxiv.org/pdf/2511.23469.pdf GitHub

Abstract:
Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned with language. However, it remains underexplored whether these representations, optimized for multimodal understanding tasks, harbor an inherent potential for visual generation. In this paper, we propose VGT, Visual Generation Tuning, a novel paradigm designed to stimulate the underlying capabilities of visual generation within any vision language models. By performing efficient visual generation tuning on well-pretrained VLMs, we significantly mitigate the alignment costs and accelerate the convergence of autoregressive modeling in the continuous space (20x speedup). Specifically, we dismiss the entangled pixel-level VAEs designed for diffusion transformers and formulate VGT-AE through aligning the semantic encoders from pretrained VLMs with the latent representations of pixel decoders. In image reconstruction tasks, we achieve 26.67 PSNR and 0.50 rFID at a 28x compression ratio, outperforming specialized VAEs; in visual generation tasks, we achieve state-of-the-art outcomes among autoregressive models, 0.77 on GenEval and 78.73 on DPG-Bench. Furthermore, our proposed VGT showcases significant scaling promise and is versatile for endowing any VLMs trained for multimodal understanding with the capabilities of visual generation, which paves the new avenue to explore next-generation unified multimodal foundation models. Models and codes are available at https://github.com/hustvl/VGT.

Paperid: 6, https://arxiv.org/pdf/2511.23439.pdf GitHub

Abstract:
Peer-review venues have increasingly adopted open reviewing policies that publicly release anonymized reviews and permit public commenting. Venues have adopted a variety of policies, and there is still ongoing debate about the benefits and drawbacks of decisions. To inform this debate, we surveyed 2,385 reviewers, authors, and other peer-review participants in machine learning to understand their experiences and opinions. Our key findings are: (a) Preferences: Over 80% of respondents support releasing reviews for accepted papers and allowing public comments. However, only 27.1% support releasing rejected manuscripts. (b) Benefits: Respondents cite improved public understanding (75.3%) and reviewer education (57.8%), increased fairness (56.6%), and stronger incentives for high-quality reviews (48.0%). (c) Challenges: The top concern is resubmission bias, where rejection history biases future reviewers (ranked top impact of open reviewing by 41% of respondents, and mentioned in over 50% of free responses). Other challenges include fear of reviewer de-anonymization (33.2%) and potential commenting abuse. (d) AI and open peer review: Participants believe open policies deter "AI slop" submissions (71.9%) and AI-generated reviews (38.9%). Respondents are split regarding peer-review venues generating official AI reviews, with 56.0% opposed and 44.0% supportive. Finally, we use AI to annotate 4,244 reviews from ICLR (fully open) and NeurIPS (partially open). We find that the fully open venue (ICLR) has higher levels of correctness and completeness than the partially open venue (NeurIPS). The effect size is small for correctness and very small for completeness, and both are statistically significant. We also find that there is no statistically significant difference in the level of substantiation. We release the full dataset at https://github.com/justinpayan/OpenReviewAnalysis.

Paperid: 7, https://arxiv.org/pdf/2511.23428.pdf GitHub

Abstract:
Recent advances in text-to-video (T2V) and image-to-video (I2V) models, have enabled the creation of visually compelling and dynamic videos from simple textual descriptions or initial frames. However, these models often fail to provide an explicit representation of motion separate from content, limiting their applicability for content creators. To address this gap, we propose DisMo, a novel paradigm for learning abstract motion representations directly from raw video data via an image-space reconstruction objective. Our representation is generic and independent of static information such as appearance, object identity, or pose. This enables open-world motion transfer, allowing motion to be transferred across semantically unrelated entities without requiring object correspondences, even between vastly different categories. Unlike prior methods, which trade off motion fidelity and prompt adherence, are overfitting to source structure or drifting from the described action, our approach disentangles motion semantics from appearance, enabling accurate transfer and faithful conditioning. Furthermore, our motion representation can be combined with any existing video generator via lightweight adapters, allowing us to effortlessly benefit from future advancements in video models. We demonstrate the effectiveness of our method through a diverse set of motion transfer tasks. Finally, we show that the learned representations are well-suited for downstream motion understanding tasks, consistently outperforming state-of-the-art video representation models such as V-JEPA in zero-shot action classification on benchmarks including Something-Something v2 and Jester. Project page: https://compvis.github.io/DisMo

Paperid: 8, https://arxiv.org/pdf/2511.23397.pdf GitHub

Abstract:
Small and medium-sized enterprises (SMEs) in Iran increasingly leverage Telegram for sales, where real-time engagement is essential for conversion. However, developing AI-driven chatbots for this purpose requires large, high-quality question-and-answer (Q&A) datasets, which are typically expensive and resource-intensive to produce, especially for low-resource languages like Persian. In this paper, we introduce MegaChat, the first fully synthetic Persian Q&A dataset designed to evaluate intelligent sales chatbots in Telegram-based e-commerce. We propose a novel, automated multi-agent architecture that generates persona-aware Q&A pairs by collecting data from active Telegram shopping channels. The system employs specialized agents for question generation, validation, and refinement, ensuring the production of realistic and diverse conversational data. To evaluate answer generation, we compare three classic retrieval-augmented generation (RAG) models with our advanced agentic system, which features multi-query retrieval, reranking, and persona-aligned response synthesis. Using GPT-5.1 for evaluation across six quality dimensions, our results show that the agentic architecture outperformed traditional RAG models in 4 out of 5 diverse channels, demonstrating its ability to generate scalable, high-quality datasets without relying on expensive human annotation or complex fine-tuning. MegaChat provides SMEs with an efficient, cost-effective solution for building intelligent customer engagement systems in specialized commercial domains, enabling advancements in multilingual conversational AI for low-resource languages. Download: https://github.com/MegaChat-Tech/MegaChat-DataSet

Paperid: 9, https://arxiv.org/pdf/2511.23377.pdf GitHub

Abstract:
Diffusion-based image editing has made semantic level image manipulation easy for general users, but it also enables realistic local forgeries that are hard to localize. Existing benchmarks mainly focus on the binary detection of generated images or the localization of manually edited regions and do not reflect the properties of diffusion-based edits, which often blend smoothly into the original content. We present Diffusion-Based Image Editing Area Localization Dataset (DEAL-300K), a large scale dataset for diffusion-based image manipulation localization (DIML) with more than 300,000 annotated images. We build DEAL-300K by using a multi-modal large language model to generate editing instructions, a mask-free diffusion editor to produce manipulated images, and an active-learning change detection pipeline to obtain pixel-level annotations. On top of this dataset, we propose a localization framework that uses a frozen Visual Foundation Model (VFM) together with Multi Frequency Prompt Tuning (MFPT) to capture both semantic and frequency-domain cues of edited regions. Trained on DEAL-300K, our method reaches a pixel-level F1 score of 82.56% on our test split and 80.97% on the external CoCoGlide benchmark, providing strong baselines and a practical foundation for future DIML research.The dataset can be accessed via https://github.com/ymhzyj/DEAL-300K.

Paperid: 10, https://arxiv.org/pdf/2511.23342.pdf GitHub

Abstract:
Flow-based generative models have recently demonstrated strong performance, yet sampling typically relies on expensive numerical integration of ordinary differential equations (ODEs). Rectified Flow enables one-step sampling by learning nearly straight probability paths, but achieving such straightness requires multiple computationally intensive reflow iterations. MeanFlow achieves one-step generation by directly modeling the average velocity over time; however, when trained on highly curved flows, it suffers from slow convergence and noisy supervision. To address these limitations, we propose Rectified MeanFlow, a framework that models the mean velocity field along the rectified trajectory using only a single reflow step. This eliminates the need for perfectly straightened trajectories while enabling efficient training. Furthermore, we introduce a simple yet effective truncation heuristic that aims to reduce residual curvature and further improve performance. Extensive experiments on ImageNet at 64, 256, and 512 resolutions show that Re-MeanFlow consistently outperforms prior one-step flow distillation and Rectified Flow methods in both sample quality and training efficiency. Code is available at https://github.com/Xinxi-Zhang/Re-MeanFlow.

Paperid: 11, https://arxiv.org/pdf/2511.23332.pdf GitHub GitHub

Abstract:
Instruction-driven segmentation in remote sensing generates masks from guidance, offering great potential for accessible and generalizable applications. However, existing methods suffer from fragmented task formulations and limited instruction data, hindering effective understanding and generalization. To address these issues, we introduce GeoSeg-1M, the first million-scale dataset for remote sensing instruction-driven segmentation, constructed via an automatic mask filtering and instruction generation pipeline that synthesizes referring, interactive, and reasoning segmentation instructions from multiple public datasets. GeoSeg-1M contains 590K images, 117 categories, and 1.1M image-mask-instruction triplets. Building upon this foundation, we further curate GeoSeg-Bench, a challenging benchmark designed to evaluate contextual understanding and reasoning capabilities across diverse instruction-driven tasks and complex geospatial scenes. Furthermore, we present UniGeoSeg, a unified framework that serves as a strong baseline, incorporating task-aware text enhancement, latent knowledge memory, and a progressive training strategy to facilitate multi-task learning. Extensive experiments demonstrate the state-of-the-art performance of UniGeoSeg across GeoSeg-Bench and diverse public benchmarks, while exhibiting strong zero-shot generalization. Datasets and source code were released at https://github.com/MiliLab/UniGeoSeg.

Paperid: 12, https://arxiv.org/pdf/2511.23276.pdf GitHub

Abstract:
Effective surveillance of hand, foot and mouth disease (HFMD) requires forecasts accounting for epidemiological patterns and contextual drivers like school calendars and weather. While classical models and recent foundation models (e.g., Chronos, TimesFM) incorporate covariates, they often lack the semantic reasoning to interpret the causal interplay between conflicting drivers. In this work, we propose a two-agent framework decoupling contextual interpretation from probabilistic forecasting. An LLM "event interpreter" processes heterogeneous signals-including school schedules, meteorological summaries, and reports-into a scalar transmission-impact signal. A neuro-symbolic core then combines this with historical case counts to produce calibrated probabilistic forecasts. We evaluate the framework on real-world HFMD datasets from Hong Kong (2023-2024) and Lishui, China (2024). Compared to traditional and foundation-model baselines, our approach achieves competitive point forecasting accuracy while providing robust 90% prediction intervals (coverage 0.85-1.00) and human-interpretable rationales. Our results suggest that structurally integrating domain knowledge through LLMs can match state-of-the-art performance while yielding context-aware forecasts that align with public health workflows. Code is available at https://github.com/jw-chae/forecast_MED .

Paperid: 13, https://arxiv.org/pdf/2511.23260.pdf GitHub

Abstract:
Deep neural network-based time series prediction models have recently demonstrated superior capabilities in capturing complex temporal dependencies. However, it is challenging for these models to account for uncertainty associated with their predictions, because they directly output scalar values at each time step. To address such a challenge, we propose a novel model named interleaved dual-branch Probability Distribution Network (interPDN), which directly constructs discrete probability distributions per step instead of a scalar. The regression output at each time step is derived by computing the expectation of the predictive distribution on a predefined support set. To mitigate prediction anomalies, a dual-branch architecture is introduced with interleaved support sets, augmented by coarse temporal-scale branches for long-term trend forecasting. Outputs from another branch are treated as auxiliary signals to impose self-supervised consistency constraints on the current branch's prediction. Extensive experiments on multiple real-world datasets demonstrate the superior performance of interPDN.

Paperid: 14, https://arxiv.org/pdf/2511.23191.pdf GitHub

Abstract:
Previous works leveraging video models for image-to-3D scene generation tend to suffer from geometric distortions and blurry content. In this paper, we renovate the pipeline of image-to-3D scene generation by unlocking the potential of geometry models and present our GeoWorld. Instead of exploiting geometric information obtained from a single-frame input, we propose to first generate consecutive video frames and then take advantage of the geometry model to provide full-frame geometry features, which contain richer information than single-frame depth maps or camera embeddings used in previous methods, and use these geometry features as geometrical conditions to aid the video generation model. To enhance the consistency of geometric structures, we further propose a geometry alignment loss to provide the model with real-world geometric constraints and a geometry adaptation module to ensure the effective utilization of geometry features. Extensive experiments show that our GeoWorld can generate high-fidelity 3D scenes from a single image and a given camera trajectory, outperforming prior methods both qualitatively and quantitatively. Project Page: https://peaes.github.io/GeoWorld/.

Paperid: 15, https://arxiv.org/pdf/2511.23186.pdf GitHub

Abstract:
Successful robotic grasping in cluttered environments not only requires a model to visually ground a target object but also to reason about obstructions that must be cleared beforehand. While current vision-language embodied reasoning models show emergent spatial understanding, they remain limited in terms of obstruction reasoning and accessibility planning. To bridge this gap, we present UNOGrasp, a learning-based vision-language model capable of performing visually-grounded obstruction reasoning to infer the sequence of actions needed to unobstruct the path and grasp the target object. We devise a novel multi-step reasoning process based on obstruction paths originated by the target object. We anchor each reasoning step with obstruction-aware visual cues to incentivize reasoning capability. UNOGrasp combines supervised and reinforcement finetuning through verifiable reasoning rewards. Moreover, we construct UNOBench, a large-scale dataset for both training and benchmarking, based on MetaGraspNetV2, with over 100k obstruction paths annotated by humans with obstruction ratios, contact points, and natural-language instructions. Extensive experiments and real-robot evaluations show that UNOGrasp significantly improves obstruction reasoning and grasp success across both synthetic and real-world environments, outperforming generalist and proprietary alternatives. Project website: https://tev-fbk.github.io/UnoGrasp/.

Paperid: 16, https://arxiv.org/pdf/2511.23173.pdf GitHub

Abstract:
Monitoring physical exercises is vital for health promotion, with automated systems becoming standard in personal health surveillance. However, sensor placement variability and unconstrained movements limit their effectiveness. This study proposes the team "3KA"'s one-sensor workout activity recognition method using feature extraction and data augmentation in 2ndWEAR Dataset Challenge. From raw acceleration, angle and signal magnitude vector features were derived, followed by extraction of statistical, fractal/spectral, and higher-order differential features. A fused dataset combining left/right limb data was created, and augmented via sensor rotation and axis inversion. We utilized a soft voting model combining Hist Gradient Boosting with balanced weights and Extreme Gradient Boosting without. Under group 5-fold evaluation, the model achieved 58.83\% macro F1 overall (61.72% arm, 55.95% leg). ANOVA F-score showed fractal/spectral features were most important for arm-based recognition but least for leg-based. The code to reproduce the experiments is publicly available via: https://github.com/Khanghcmut/WEAR\_3K

Paperid: 17, https://arxiv.org/pdf/2511.23162.pdf GitHub

Abstract:
Event-related potentials (ERP) are measurements of brain activity with wide applications in basic and clinical neuroscience, that are typically estimated using the average of many trials of electroencephalography signals (EEG) to sufficiently reduce noise and signal variability. We introduce EEG2ERP, a novel uncertainty-aware autoencoder approach that maps an arbitrary number of EEG trials to their associated ERP. To account for the ERP uncertainty we use bootstrapped training targets and introduce a separate variance decoder to model the uncertainty of the estimated ERP. We evaluate our approach in the challenging zero-shot scenario of generalizing to new subjects considering three different publicly available data sources; i) the comprehensive ERP CORE dataset that includes over 50,000 EEG trials across six ERP paradigms from 40 subjects, ii) the large P300 Speller BCI dataset, and iii) a neuroimaging dataset on face perception consisting of both EEG and magnetoencephalography (MEG) data. We consistently find that our method in the few trial regime provides substantially better ERP estimates than commonly used conventional and robust averaging procedures. EEG2ERP is the first deep learning approach to map EEG signals to their associated ERP, moving toward reducing the number of trials necessary for ERP research. Code is available at https://github.com/andersxa/EEG2ERP

Paperid: 18, https://arxiv.org/pdf/2511.23151.pdf GitHub

Abstract:
Video Temporal Grounding (VTG) aims to localize a temporal segment in a video corresponding to a natural language query. However, existing VTG models assume that a relevant segment always exists, causing them to always predict a target segment even when the query is irrelevant to the video. While recent approaches attempt to handle irrelevant queries, they can only reject those that are entirely unrelated to the video and still fail to handle hard-irrelevant queries that are semantically similar but not actually relevant. To address this, we propose Refusal-Aware Reinforcement Fine-Tuning (RA-RFT) to effectively refuse hard-irrelevant queries in VTG. Our method is based on the Group Relative Policy Optimization (GRPO) framework and integrates four reward objectives-format, refuse-IoU, explain, and query correction-to improve both relevance discrimination and fine-grained semantic reasoning. In addition, to effectively support RA-RFT, we construct a Hard-Irrelevant VTG (HI-VTG) dataset, which includes hard-irrelevant queries and their refusal answers. We demonstrate the effectiveness of our method across various relevance-aware VTG scenarios, including hard-irrelevant VTG, simply-shuffled RA-VTG, and human-annotated RA-VTG settings. We also show that the proposed method is scalable by applying it to various LVLM-based VTG models. Our code is available at https://github.com/JINSUBY/RA-RFT.

Paperid: 19, https://arxiv.org/pdf/2511.23150.pdf GitHub

Abstract:
Document rectification in real-world scenarios poses significant challenges due to extreme variations in camera perspectives and physical distortions. Driven by the insight that complex transformations can be decomposed and resolved progressively, we introduce a novel multi-stage framework that progressively reverses distinct distortion types in a coarse-to-fine manner. Specifically, our framework first performs a global affine transformation to correct perspective distortions arising from the camera's viewpoint, then rectifies geometric deformations resulting from physical paper curling and folding, and finally employs a content-aware iterative process to eliminate fine-grained content distortions. To address limitations in existing evaluation protocols, we also propose two enhanced metrics: layout-aligned OCR metrics (AED/ACER) for a stable assessment that decouples geometric rectification quality from the layout analysis errors of OCR engines, and masked AD/AAD (AD-M/AAD-M) tailored for accurately evaluating geometric distortions in documents with incomplete boundaries. Extensive experiments show that our method establishes new state-of-the-art performance on multiple challenging benchmarks, yielding a substantial reduction of 14.1\%--34.7\% in the AAD metric and demonstrating superior efficacy in real-world applications. The code will be publicly available at https://github.com/chaoyunwang/ArbDR.

Paperid: 20, https://arxiv.org/pdf/2511.23127.pdf GitHub

Abstract:
This paper presents DualCamCtrl, a novel end-to-end diffusion model for camera-controlled video generation. Recent works have advanced this field by representing camera poses as ray-based conditions, yet they often lack sufficient scene understanding and geometric awareness. DualCamCtrl specifically targets this limitation by introducing a dual-branch framework that mutually generates camera-consistent RGB and depth sequences. To harmonize these two modalities, we further propose the Semantic Guided Mutual Alignment (SIGMA) mechanism, which performs RGB-depth fusion in a semantics-guided and mutually reinforced manner. These designs collectively enable DualCamCtrl to better disentangle appearance and geometry modeling, generating videos that more faithfully adhere to the specified camera trajectories. Additionally, we analyze and reveal the distinct influence of depth and camera poses across denoising stages and further demonstrate that early and late stages play complementary roles in forming global structure and refining local details. Extensive experiments demonstrate that DualCamCtrl achieves more consistent camera-controlled video generation, with over 40\% reduction in camera motion errors compared with prior methods. Our project page: https://soyouthinkyoucantell.github.io/dualcamctrl-page/

Paperid: 21, https://arxiv.org/pdf/2511.23113.pdf GitHub

Abstract:
Scaling Diffusion Transformer (DiT) inference via sequence parallelism is critical for reducing latency in visual generation, but is severely hampered by workload imbalance when applied to models employing block-wise sparse attention. The imbalance stems from the inherent variation in sparsity across attention heads and the irregular distribution of dense blocks within the sparse mask, when sequence parallelism is applied along the head dimension (as in Ulysses) or the block dimension (as in Ring Attention). In this paper, we formalize a sparse imbalance ratio to quantify the imbalance, and propose db-SP, a sparsity-aware sequence parallelism technique that tackles the challenge. db-SP contains a dual-level partitioning approach that achieves near-perfect workload balance at both the head and block levels with negligible overhead. Furthermore, to handle the evolving sparsity patterns across denoising steps and layers, db-SP dynamically determines the parallel degrees for the head and block dimensions at runtime. Experimental results demonstrate that db-SP delivers an end-to-end speedup of 1.25x and an attention-specific speedup of 1.40x over state-of-the-art sequence parallel methods on average. Code is available at https://github.com/thu-nics/db-SP.

Paperid: 22, https://arxiv.org/pdf/2511.23112.pdf GitHub

Abstract:
Recent advances in Vision-Language Models (VLMs) have achieved impressive progress in multimodal mathematical reasoning. Yet, how much visual information truly contributes to reasoning remains unclear. Existing benchmarks report strong overall performance but seldom isolate the role of the image modality, leaving open whether VLMs genuinely leverage visual understanding or merely depend on linguistic priors. To address this, we present MathSight, a university-level multimodal mathematical reasoning benchmark designed to disentangle and quantify the effect of visual input. Each problem includes multiple visual variants -- original, hand-drawn, photo-captured -- and a text-only condition for controlled comparison. Experiments on state-of-the-art VLMs reveal a consistent trend: the contribution of visual information diminishes with increasing problem difficulty. Remarkably, Qwen3-VL without any image input surpasses both its multimodal variants and GPT-5, underscoring the need for benchmarks like MathSight to advance genuine vision-grounded reasoning in future models.

Paperid: 23, https://arxiv.org/pdf/2511.23051.pdf GitHub

Abstract:
We present GOATex, a diffusion-based method for 3D mesh texturing that generates high-quality textures for both exterior and interior surfaces. While existing methods perform well on visible regions, they inherently lack mechanisms to handle occluded interiors, resulting in incomplete textures and visible seams. To address this, we introduce an occlusion-aware texturing framework based on the concept of hit levels, which quantify the relative depth of mesh faces via multi-view ray casting. This allows us to partition mesh faces into ordered visibility layers, from outermost to innermost. We then apply a two-stage visibility control strategy that progressively reveals interior regions with structural coherence, followed by texturing each layer using a pretrained diffusion model. To seamlessly merge textures obtained across layers, we propose a soft UV-space blending technique that weighs each texture's contribution based on view-dependent visibility confidence. Empirical results demonstrate that GOATex consistently outperforms existing methods, producing seamless, high-fidelity textures across both visible and occluded surfaces. Unlike prior works, GOATex operates entirely without costly fine-tuning of a pretrained diffusion model and allows separate prompting for exterior and interior mesh regions, enabling fine-grained control over layered appearances. For more qualitative results, please visit our project page: https://goatex3d.github.io/.

Paperid: 24, https://arxiv.org/pdf/2511.23034.pdf GitHub

Abstract:
Learning transferable latent actions from large-scale object manipulation videos can significantly enhance generalization in downstream robotics tasks, as such representations are agnostic to different robot embodiments. Existing approaches primarily rely on visual reconstruction objectives while neglecting physical priors, leading to sub-optimal performance in learning universal representations. To address these challenges, we propose a Universal Latent Action Learning framework that takes task instructions and multiple frames as inputs, and optimizes both future frame reconstruction and action sequence prediction. Unlike prior works, incorporating action predictions (e.g., gripper or hand trajectories and orientations) allows the model to capture richer physical priors such as real-world distances and orientations, thereby enabling seamless transferability to downstream tasks. We further decompose the latent actions into learnable motion and scene tokens to distinguish the robot's active movements from environmental changes, thus filtering out irrelevant dynamics. By distilling the learned latent actions into the latest VLA models, we achieve strong performance across both simulated (SIMPLER and LIBERO) and real-world robot settings. Notably, with only 10 real-world trajectories per task collected on a Franka robot, our approach successfully completes all five challenging tasks, demonstrating strong few-shot transferability in robotic manipulation.

Paperid: 25, https://arxiv.org/pdf/2511.22989.pdf GitHub

Abstract:
Recent text-to-image generation models have acquired the ability of multi-reference generation and editing; the ability to inherit the appearance of subjects from multiple reference images and re-render them under new contexts. However, the existing benchmark datasets often focus on the generation with single or a few reference images, which prevents us from measuring the progress on how model performance advances or pointing out their weaknesses, under different multi-reference conditions. In addition, their task definitions are still vague, typically limited to axes such as "what to edit" or "how many references are given", and therefore fail to capture the intrinsic difficulty of multi-reference settings. To address this gap, we introduce $\textbf{MultiBanana}$, which is carefully designed to assesses the edge of model capabilities by widely covering multi-reference-specific problems at scale: (1) varying the number of references, (2) domain mismatch among references (e.g., photo vs. anime), (3) scale mismatch between reference and target scenes, (4) references containing rare concepts (e.g., a red banana), and (5) multilingual textual references for rendering. Our analysis among a variety of text-to-image models reveals their superior performances, typical failure modes, and areas for improvement. MultiBanana will be released as an open benchmark to push the boundaries and establish a standardized basis for fair comparison in multi-reference image generation. Our data and code are available at https://github.com/matsuolab/multibanana .

Paperid: 26, https://arxiv.org/pdf/2511.22982.pdf GitHub

Abstract:
We introduce $\textbf{Ovis-Image}$, a 7B text-to-image model specifically optimized for high-quality text rendering, designed to operate efficiently under stringent computational constraints. Built upon our previous Ovis-U1 framework, Ovis-Image integrates a diffusion-based visual decoder with the stronger Ovis 2.5 multimodal backbone, leveraging a text-centric training pipeline that combines large-scale pre-training with carefully tailored post-training refinements. Despite its compact architecture, Ovis-Image achieves text rendering performance on par with significantly larger open models such as Qwen-Image and approaches closed-source systems like Seedream and GPT4o. Crucially, the model remains deployable on a single high-end GPU with moderate memory, narrowing the gap between frontier-level text rendering and practical deployment. Our results indicate that combining a strong multimodal backbone with a carefully designed, text-focused training recipe is sufficient to achieve reliable bilingual text rendering without resorting to oversized or proprietary models.

Paperid: 27, https://arxiv.org/pdf/2511.22973.pdf GitHub

Abstract:
Generating minute-long videos is a critical step toward developing world models, providing a foundation for realistic extended scenes and advanced AI simulators. The emerging semi-autoregressive (block diffusion) paradigm integrates the strengths of diffusion and autoregressive models, enabling arbitrary-length video generation and improving inference efficiency through KV caching and parallel sampling. However, it yet faces two enduring challenges: (i) KV-cache-induced long-horizon error accumulation, and (ii) the lack of fine-grained long-video benchmarks and coherence-aware metrics. To overcome these limitations, we propose BlockVid, a novel block diffusion framework equipped with semantic-aware sparse KV cache, an effective training strategy called Block Forcing, and dedicated chunk-wise noise scheduling and shuffling to reduce error propagation and enhance temporal consistency. We further introduce LV-Bench, a fine-grained benchmark for minute-long videos, complete with new metrics evaluating long-range coherence. Extensive experiments on VBench and LV-Bench demonstrate that BlockVid consistently outperforms existing methods in generating high-quality, coherent minute-long videos. In particular, it achieves a 22.2% improvement on VDE Subject and a 19.4% improvement on VDE Clarity in LV-Bench over the state of the art approaches. Project website: https://ziplab.co/BlockVid. Inferix (Code): https://github.com/alibaba-damo-academy/Inferix.

Paperid: 28, https://arxiv.org/pdf/2511.22950.pdf GitHub

Abstract:
Accurate robot segmentation is a fundamental capability for robotic perception. It enables precise visual servoing for VLA systems, scalable robot-centric data augmentation, accurate real-to-sim transfer, and reliable safety monitoring in dynamic human-robot environments. Despite the strong capabilities of modern segmentation models, surprisingly it remains challenging to segment robots. This is due to robot embodiment diversity, appearance ambiguity, structural complexity, and rapid shape changes. Embracing these challenges, we introduce RobotSeg, a foundation model for robot segmentation in image and video. RobotSeg is built upon the versatile SAM 2 foundation model but addresses its three limitations for robot segmentation, namely the lack of adaptation to articulated robots, reliance on manual prompts, and the need for per-frame training mask annotations, by introducing a structure-enhanced memory associator, a robot prompt generator, and a label-efficient training strategy. These innovations collectively enable a structure-aware, automatic, and label-efficient solution. We further construct the video robot segmentation (VRS) dataset comprising over 2.8k videos (138k frames) with diverse robot embodiments and environments. Extensive experiments demonstrate that RobotSeg achieves state-of-the-art performance on both images and videos, establishing a strong foundation for future advances in robot perception.

Paperid: 29, https://arxiv.org/pdf/2511.22948.pdf GitHub

Abstract:
Domain generalization in semantic segmentation faces challenges from domain shifts, particularly under adverse conditions. While diffusion-based data generation methods show promise, they introduce inherent misalignment between generated images and semantic masks. This paper presents FLEX-Seg (FLexible Edge eXploitation for Segmentation), a framework that transforms this limitation into an opportunity for robust learning. FLEX-Seg comprises three key components: (1) Granular Adaptive Prototypes that captures boundary characteristics across multiple scales, (2) Uncertainty Boundary Emphasis that dynamically adjusts learning emphasis based on prediction entropy, and (3) Hardness-Aware Sampling that progressively focuses on challenging examples. By leveraging inherent misalignment rather than enforcing strict alignment, FLEX-Seg learns robust representations while capturing rich stylistic variations. Experiments across five real-world datasets demonstrate consistent improvements over state-of-the-art methods, achieving 2.44% and 2.63% mIoU gains on ACDC and Dark Zurich. Our findings validate that adaptive strategies for handling imperfect synthetic data lead to superior domain generalization. Code is available at https://github.com/VisualScienceLab-KHU/FLEX-Seg.

Paperid: 30, https://arxiv.org/pdf/2511.22940.pdf GitHub GitHub

Abstract:
Recent advances in diffusion models have greatly improved pose-driven character animation. However, existing methods are limited to spatially aligned reference-pose pairs with matched skeletal structures. Handling reference-pose misalignment remains unsolved. To address this, we present One-to-All Animation, a unified framework for high-fidelity character animation and image pose transfer for references with arbitrary layouts. First, to handle spatially misaligned reference, we reformulate training as a self-supervised outpainting task that transforms diverse-layout reference into a unified occluded-input format. Second, to process partially visible reference, we design a reference extractor for comprehensive identity feature extraction. Further, we integrate hybrid reference fusion attention to handle varying resolutions and dynamic sequence lengths. Finally, from the perspective of generation quality, we introduce identity-robust pose control that decouples appearance from skeletal structure to mitigate pose overfitting, and a token replace strategy for coherent long-video generation. Extensive experiments show that our method outperforms existing approaches. The code and model are available at https://github.com/ssj9596/One-to-All-Animation.

Paperid: 31, https://arxiv.org/pdf/2511.22939.pdf GitHub

Abstract:
Burst denoising methods are crucial for enhancing images captured on handheld devices, but they often struggle with large motion or suffer from prohibitive computational costs. In this paper, we propose DenoiseGS, the first framework to leverage the efficiency of 3D Gaussian Splatting for burst denoising. Our approach addresses two key challenges when applying feedforward Gaussian reconsturction model to noisy inputs: the degradation of Gaussian point clouds and the loss of fine details. To this end, we propose a Gaussian self-consistency (GSC) loss, which regularizes the geometry predicted from noisy inputs with high-quality Gaussian point clouds. These point clouds are generated from clean inputs by the same model that we are training, thereby alleviating potential bias or domain gaps. Additionally, we introduce a log-weighted frequency (LWF) loss to strengthen supervision within the spectral domain, effectively preserving fine-grained details. The LWF loss adaptively weights frequency discrepancies in a logarithmic manner, emphasizing challenging high-frequency details. Extensive experiments demonstrate that DenoiseGS significantly exceeds the state-of-the-art NeRF-based methods on both burst denoising and novel view synthesis under noisy conditions, while achieving 250$\times$ faster inference speed. Code and models are released at https://github.com/yscheng04/DenoiseGS.

Paperid: 32, https://arxiv.org/pdf/2511.22935.pdf GitHub

Abstract:
Electrocardiogram (ECG) analysis plays a vital role in the early detection, monitoring, and management of various cardiovascular conditions. While existing models have achieved notable success in ECG interpretation, they fail to leverage the interrelated nature of various cardiac abnormalities. Conversely, developing a specific model capable of extracting all relevant features for multiple ECG tasks remains a significant challenge. Large-scale foundation models, though powerful, are not typically pretrained on ECG data, making full re-training or fine-tuning computationally expensive. To address these challenges, we propose EnECG(Mixture of Experts-based Ensemble Learning for ECG Multi-tasks), an ensemble-based framework that integrates multiple specialized foundation models, each excelling in different aspects of ECG interpretation. Instead of relying on a single model or single task, EnECG leverages the strengths of multiple specialized models to tackle a variety of ECG-based tasks. To mitigate the high computational cost of full re-training or fine-tuning, we introduce a lightweight adaptation strategy: attaching dedicated output layers to each foundation model and applying Low-Rank Adaptation (LoRA) only to these newly added parameters. We then adopt a Mixture of Experts (MoE) mechanism to learn ensemble weights, effectively combining the complementary expertise of individual models. Our experimental results demonstrate that by minimizing the scope of fine-tuning, EnECG can help reduce computational and memory costs while maintaining the strong representational power of foundation models. This framework not only enhances feature extraction and predictive performance but also ensures practical efficiency for real-world clinical applications. The code is available at https://github.com/yuhaoxu99/EnECG.git.

Paperid: 33, https://arxiv.org/pdf/2511.22911.pdf GitHub

Abstract:
Orthopantomogram (OPGs) and Cone-Beam Computed Tomography (CBCT) are vital for dentistry, but creating large datasets for automated tooth segmentation is hindered by the labor-intensive process of manual instance-level annotation. This research aimed to benchmark and advance semi-supervised learning (SSL) as a solution for this data scarcity problem. We organized the 2nd Semi-supervised Teeth Segmentation (STS 2024) Challenge at MICCAI 2024. We provided a large-scale dataset comprising over 90,000 2D images and 3D axial slices, which includes 2,380 OPG images and 330 CBCT scans, all featuring detailed instance-level FDI annotations on part of the data. The challenge attracted 114 (OPG) and 106 (CBCT) registered teams. To ensure algorithmic excellence and full transparency, we rigorously evaluated the valid, open-source submissions from the top 10 (OPG) and top 5 (CBCT) teams, respectively. All successful submissions were deep learning-based SSL methods. The winning semi-supervised models demonstrated impressive performance gains over a fully-supervised nnU-Net baseline trained only on the labeled data. For the 2D OPG track, the top method improved the Instance Affinity (IA) score by over 44 percentage points. For the 3D CBCT track, the winning approach boosted the Instance Dice score by 61 percentage points. This challenge confirms the substantial benefit of SSL for complex, instance-level medical image segmentation tasks where labeled data is scarce. The most effective approaches consistently leveraged hybrid semi-supervised frameworks that combined knowledge from foundational models like SAM with multi-stage, coarse-to-fine refinement pipelines. Both the challenge dataset and the participants' submitted code have been made publicly available on GitHub (https://github.com/ricoleehduu/STS-Challenge-2024), ensuring transparency and reproducibility.

Paperid: 34, https://arxiv.org/pdf/2511.22908.pdf GitHub

Abstract:
Point cloud registration is a fundamental task in 3D vision. Most existing methods only use geometric information for registration. Recently proposed RGB-D registration methods primarily focus on feature fusion or improving feature learning, which limits their ability to exploit image information and hinders their practical applicability. In this paper, we propose ViGG, a robust RGB-D registration method using mutual guidance. First, we solve clique alignment in a visual-geometric combination form, employing a geometric guidance design to suppress ambiguous cliques. Second, to mitigate accuracy degradation caused by noise in visual matches, we propose a visual-guided geometric matching method that utilizes visual priors to determine the search space, enabling the extraction of high-quality, noise-insensitive correspondences. This mutual guidance strategy brings our method superior robustness, making it applicable for various RGB-D registration tasks. The experiments on 3DMatch, ScanNet and KITTI datasets show that our method outperforms recent state-of-the-art methods in both learning-free and learning-based settings. Code is available at https://github.com/ccjccjccj/ViGG.

Paperid: 35, https://arxiv.org/pdf/2511.22906.pdf GitHub

Abstract:
Video moment retrieval (MR) and highlight detection (HD) with natural language queries aim to localize relevant moments and key highlights in a video clips. However, existing methods overlook the importance of individual words, treating the entire text query and video clips as a black-box, which hinders contextual understanding. In this paper, we propose a novel approach that enables fine-grained clip filtering by identifying and prioritizing important words in the query. Our method integrates image-text scene understanding through Multimodal Large Language Models (MLLMs) and enhances the semantic understanding of video clips. We introduce a feature enhancement module (FEM) to capture important words from the query and a ranking-based filtering module (RFM) to iteratively refine video clips based on their relevance to these important words. Extensive experiments demonstrate that our approach significantly outperforms existing state-of-the-art methods, achieving superior performance in both MR and HD tasks. Our code is available at: https://github.com/VisualAIKHU/SRF.

Paperid: 36, https://arxiv.org/pdf/2511.22897.pdf GitHub

Abstract:
Multimodal Prompt Learning (MPL) has emerged as a pivotal technique for adapting large-scale Visual Language Models (VLMs). However, current MPL methods are fundamentally limited by their optimization of a single, static point representation. This paradigm is inherently brittle, leads to overfitting on base classes, and generalizes poorly to novel or ambiguous categories. We challenge this point paradigm, proposing that robust generalization requires learning a semantic cloud (i.e., a distribution over the embedding space). To achieve this, we introduce Points-to-Clouds (P2C), a novel framework inspired by diffusion models that reframes prompt learning as a dynamic denoising task. At the core of P2C is a dual denoising mechanism: a Dynamic Prompt Denoising (DPD) mechanism perturbs text prompts with sophisticated, annealed noise to learn a smoother semantic landscape, while an auxiliary V-L Mapper denoising loss re-tasks the mapper as a denoising autoencoder. This forces the mapper to reconstruct clean visual prompts from noisy text inputs, ensuring robust cross-modal alignment. Extensive experiments across 11 datasets demonstrate that P2C consistently outperforms strong baselines. On the base-to-novel generalization benchmark, our method achieves a Harmonic Mean of 79.7%, representing a relative improvement of 1.4% over the baseline. The code and models are available at https://vranlee.github.io/P2C/.

Paperid: 37, https://arxiv.org/pdf/2511.22896.pdf GitHub

Abstract:
Multi-object tracking (MOT) is a fundamental task in computer vision with critical applications in autonomous driving and robotics. Multimodal MOT that integrates visible light and thermal infrared information is particularly essential for robust autonomous driving systems. However, effectively fusing these heterogeneous modalities is challenging. Simple strategies like concatenation or addition often fail to bridge the significant non-linear distribution gap between their feature representations, which can lead to modality conflicts and degrade tracking accuracy. Drawing inspiration from the connection between multimodal MOT and the iterative refinement in diffusion models, this paper proposes DM$^3$T, a novel framework that reformulates multimodal fusion as an iterative feature alignment process to generate accurate and temporally coherent object trajectories. Our approach performs iterative cross-modal harmonization through a proposed Cross-Modal Diffusion Fusion (C-MDF) module. In this process, features from both modalities provide mutual guidance, iteratively projecting them onto a shared, consistent feature manifold. This enables the learning of complementary information and achieves deeper fusion compared to conventional methods. Additionally, we introduce a plug-and-play Diffusion Refiner (DR) to enhance and refine the unified feature representation. To further improve tracking robustness, we design a Hierarchical Tracker that adaptively handles confidence estimation. DM$^3$T unifies object detection, state estimation, and data association into a comprehensive online tracking framework without complex post-processing. Extensive experiments on the VT-MOT benchmark demonstrate that our method achieves 41.7 HOTA, representing a 1.54% relative improvement over existing state-of-the-art methods. The code and models are available at https://vranlee.github.io/DM-3-T/.

Paperid: 38, https://arxiv.org/pdf/2511.22889.pdf GitHub

Abstract:
The deployment of Large Language Models (LLMs) on consumer edge devices is throttled by the "Memory Wall" -- the prohibitive bandwidth and energy cost of fetching gigabytes of model weights from DRAM for every token generated. Current architectures (GPUs, NPUs) treat model weights as mutable software data, incurring massive energy penalties to maintain general-purpose programmability. We propose The Immutable Tensor Architecture (ITA), a paradigm shift that treats model weights not as data, but as physical circuit topology. By encoding parameters directly into the metal interconnects and logic of mature-node ASICs (28nm/40nm), ITA eliminates the memory hierarchy entirely. We present a "Split-Brain" system design where a host CPU manages dynamic KV-cache operations while the ITA ASIC acts as a stateless, ROM-embedded dataflow engine.

Paperid: 39, https://arxiv.org/pdf/2511.22862.pdf GitHub

Abstract:
Test-time adaptation (TTA) enables online model adaptation using only unlabeled test data, aiming to bridge the gap between source and target distributions. However, in multimodal scenarios, varying degrees of distribution shift across different modalities give rise to a complex coupling effect of unimodal shallow feature shift and cross-modal high-level semantic misalignment, posing a major obstacle to extending existing TTA methods to the multimodal field. To address this challenge, we propose a novel multimodal test-time adaptation (MMTTA) framework, termed as Bridging Modalities via Progressive Re-alignment (BriMPR). BriMPR, consisting of two progressively enhanced modules, tackles the coupling effect with a divide-and-conquer strategy. Specifically, we first decompose MMTTA into multiple unimodal feature alignment sub-problems. By leveraging the strong function approximation ability of prompt tuning, we calibrate the unimodal global feature distributions to their respective source distributions, so as to achieve the initial semantic re-alignment across modalities. Subsequently, we assign the credible pseudo-labels to combinations of masked and complete modalities, and introduce inter-modal instance-wise contrastive learning to further enhance the information interaction among modalities and refine the alignment. Extensive experiments on MMTTA tasks, including both corruption-based and real-world domain shift benchmarks, demonstrate the superiority of our method. Our source code is available at [this URL](https://github.com/Luchicken/BriMPR).

Paperid: 40, https://arxiv.org/pdf/2511.22854.pdf GitHub

Abstract:
When people reason about cause and effect, they often consider many competing "what if" scenarios before deciding which explanation fits best. Analogously, advanced language models capable of causal inference can consider multiple interventions and counterfactuals to judge the validity of causal claims. Crucially, this type of reasoning is less like a single calculation and more like an internal dialogue between alternative hypotheses. In this paper, we make this dialogue explicit through a dual-agent debate framework where one model provides a structured causal inference, and the other critically examines this reasoning for logical flaws. When disagreements arise, agents attempt to persuade each other, challenging each other's logic and revising their conclusions until they converge on a mutually agreed answer. To take advantage of this deliberative process, we specifically use reasoning language models, whose strengths in both causal inference and adversarial debate remain under-explored relative to standard large language models. We evaluate our approach on the CLadder dataset, a benchmark linking natural language questions to formally defined causal graphs across all three rungs of Pearl's ladder of causation. With Qwen3 and DeepSeek-R1 as debater agents, we demonstrate that multi-agent debate improves DeepSeek-R1's overall accuracy in causal inference from 78.03% to 87.45%, with the counterfactual category specifically improving from 67.94% to 80.04% accuracy. Similarly, Qwen3's overall accuracy improves from 84.16% to 89.41%, and counterfactual questions from 71.53% to 80.35%, showing that strong models can still benefit greatly from debate with weaker agents. Our results highlight the potential of reasoning models as building blocks for multi-agent systems in causal inference, and demonstrate the importance of diverse perspectives in causal problem-solving.

Paperid: 41, https://arxiv.org/pdf/2511.22813.pdf GitHub

Abstract:
Biological neurons exhibit remarkable intelligence: they maintain internal states, communicate selectively with other neurons, and self-organize into complex graphs rather than rigid hierarchical layers. What if artificial intelligence could emerge from similarly intelligent computational units? We introduce Intelligent Neural Networks (INN), a paradigm shift where neurons are first-class entities with internal memory and learned communication patterns, organized in complete graphs rather than sequential layers. Each Intelligent Neuron combines selective state-space dynamics (knowing when to activate) with attention-based routing (knowing to whom to send signals), enabling emergent computation through graph-structured interactions. On the standard Text8 character modeling benchmark, INN achieves 1.705 Bit-Per-Character (BPC), significantly outperforming a comparable Transformer (2.055 BPC) and matching a highly optimized LSTM baseline. Crucially, a parameter-matched baseline of stacked Mamba blocks fails to converge (>3.4 BPC) under the same training protocol, demonstrating that INN's graph topology provides essential training stability. Ablation studies confirm this: removing inter-neuron communication degrades performance or leads to instability, proving the value of learned neural routing. This work demonstrates that neuron-centric design with graph organization is not merely bio-inspired -- it is computationally effective, opening new directions for modular, interpretable, and scalable neural architectures.

Paperid: 42, https://arxiv.org/pdf/2511.22812.pdf GitHub

Abstract:
Land-cover underpins ecosystem services, hydrologic regulation, disaster-risk reduction, and evidence-based land planning; timely, accurate land-cover maps are therefore critical for environmental stewardship. Remote sensing-based land-cover classification offers a scalable route to such maps but is hindered by scarce and imbalanced annotations and by geometric distortions in high-resolution scenes. We propose LC4-DViT (Land-cover Creation for Land-cover Classification with Deformable Vision Transformer), a framework that combines generative data creation with a deformation-aware Vision Transformer. A text-guided diffusion pipeline uses GPT-4o-generated scene descriptions and super-resolved exemplars to synthesize class-balanced, high-fidelity training images, while DViT couples a DCNv4 deformable convolutional backbone with a Vision Transformer encoder to jointly capture fine-scale geometry and global context. On eight classes from the Aerial Image Dataset (AID)-Beach, Bridge, Desert, Forest, Mountain, Pond, Port, and River-DViT achieves 0.9572 overall accuracy, 0.9576 macro F1-score, and 0.9510 Cohen' s Kappa, improving over a vanilla ViT baseline (0.9274 OA, 0.9300 macro F1, 0.9169 Kappa) and outperforming ResNet50, MobileNetV2, and FlashInternImage. Cross-dataset experiments on a three-class SIRI-WHU subset (Harbor, Pond, River) yield 0.9333 overall accuracy, 0.9316 macro F1, and 0.8989 Kappa, indicating good transferability. An LLM-based judge using GPT-4o to score Grad-CAM heatmaps further shows that DViT' s attention aligns best with hydrologically meaningful structures. These results suggest that description-driven generative augmentation combined with deformation-aware transformers is a promising approach for high-resolution land-cover mapping.

Paperid: 43, https://arxiv.org/pdf/2511.22805.pdf GitHub

Abstract:
While Multimodal Large Language Models (MLLMs) are adept at answering what is in an image-identifying objects and describing scenes-they often lack the ability to understand how an image feels to a human observer. This gap is most evident when considering subjective cognitive properties, such as what makes an image memorable, funny, aesthetically pleasing, or emotionally evocative. To systematically address this challenge, we introduce CogIP-Bench, a comprehensive benchmark for evaluating MLLMs on such image cognitive properties. Our evaluation reveals a significant gap: current models are poorly aligned with human perception of these nuanced properties. We then demonstrate that a post-training phase can effectively bridge this gap, significantly enhancing the model's alignment with human judgments. Furthermore, we show that this learned cognitive alignment is not merely predictive but also transferable to downstream creative tasks. By integrating our cognitively-aligned MLLM into an image generation pipeline, we can guide the synthesis process to produce images that better embody desired traits, such as being more memorable or visually appealing. Our work provides a benchmark to measure this human-like perception, a post-training pipeline to enhance it, and a demonstration that this alignment unlocks more human-centric AI.

Paperid: 44, https://arxiv.org/pdf/2511.22793.pdf GitHub GitHub

Abstract:
Channel state information (CSI) is essential for adaptive beamforming and maintaining robust links in wireless communication systems. However, acquiring CSI incurs significant overhead, consuming up to 25\% of spectrum resources in 5G networks due to frequent pilot transmissions at sub-millisecond intervals. Recent approaches aim to reduce this burden by reconstructing CSI from spatiotemporal RF measurements, such as signal strength and direction-of-arrival. While effective in offline settings, these methods often suffer from inference latencies in the 5--100~ms range, making them impractical for real-time systems. We present GSpaRC: Gaussian Splatting for Real-time Reconstruction of RF Channels, the first algorithm to break the 1 ms latency barrier while maintaining high accuracy. GSpaRC represents the RF environment using a compact set of 3D Gaussian primitives, each parameterized by a lightweight neural model augmented with physics-informed features such as distance-based attenuation. Unlike traditional vision-based splatting pipelines, GSpaRC is tailored for RF reception: it employs an equirectangular projection onto a hemispherical surface centered at the receiver to reflect omnidirectional antenna behavior. A custom CUDA pipeline enables fully parallelized directional sorting, splatting, and rendering across frequency and spatial dimensions. Evaluated on multiple RF datasets, GSpaRC achieves similar CSI reconstruction fidelity to recent state-of-the-art methods while reducing training and inference time by over an order of magnitude. By trading modest GPU computation for a substantial reduction in pilot overhead, GSpaRC enables scalable, low-latency channel estimation suitable for deployment in 5G and future wireless systems. The code is available here: \href{https://github.com/Nbhavyasai/GSpaRC-WirelessGaussianSplatting.git}{GSpaRC}.

Paperid: 45, https://arxiv.org/pdf/2511.22751.pdf GitHub GitHub

Abstract:
We explore the possibility of exact algorithmic learning with gradient-based methods and introduce a differentiable framework capable of strong length generalization on arithmetic tasks. Our approach centers on Differentiable Finite-State Transducers (DFSTs), a Turing-complete model family that avoids the pitfalls of prior architectures by enabling constant-precision, constant-time generation, and end-to-end log-parallel differentiable training. Leveraging policy-trajectory observations from expert agents, we train DFSTs to perform binary and decimal addition and multiplication. Remarkably, models trained on tiny datasets generalize without error to inputs thousands of times longer than the training examples. These results show that training differentiable agents on structured intermediate supervision could pave the way towards exact gradient-based learning of algorithmic skills. Code available at \href{https://github.com/dngfra/differentiable-exact-algorithmic-learner.git}{https://github.com/dngfra/differentiable-exact-algorithmic-learner.git}.

Paperid: 46, https://arxiv.org/pdf/2511.22715.pdf GitHub

Abstract:
Multimodal Large Language Models (MLLMs) have shown impressive capabilities in jointly understanding text, images, and videos, often evaluated via Visual Question Answering (VQA). However, even state-of-the-art MLLMs struggle with domain-specific or knowledge-intensive queries, where relevant information is underrepresented in pre-training data. Knowledge-based VQA (KB-VQA) addresses this by retrieving external documents to condition answer generation, but current retrieval-augmented approaches suffer from low precision, noisy passages, and limited reasoning. To address this, we propose ReAG, a novel Reasoning-Augmented Multimodal RAG approach that combines coarse- and fine-grained retrieval with a critic model that filters irrelevant passages, ensuring high-quality additional context. The model follows a multi-stage training strategy leveraging reinforcement learning to enhance reasoning over retrieved content, while supervised fine-tuning serves only as a cold start. Extensive experiments on Encyclopedic-VQA and InfoSeek demonstrate that ReAG significantly outperforms prior methods, improving answer accuracy and providing interpretable reasoning grounded in retrieved evidence. Our source code is publicly available at: https://github.com/aimagelab/ReAG.

Paperid: 47, https://arxiv.org/pdf/2511.22707.pdf GitHub

Abstract:
In web environments, user preferences are often refined progressively as users move from browsing broad categories to exploring specific items. However, existing generative recommenders overlook this natural refinement process. Generative recommendation formulates next-item prediction as autoregressive generation over tokenized user histories, where each item is represented as a sequence of discrete tokens. Prior models typically fuse heterogeneous attributes such as ID, category, title, and description into a single embedding before quantization, which flattens the inherent semantic hierarchy of items and fails to capture the gradual evolution of user intent during web interactions. To address this limitation, we propose CoFiRec, a novel generative recommendation framework that explicitly incorporates the Coarse-to-Fine nature of item semantics into the tokenization process. Instead of compressing all attributes into a single latent space, CoFiRec decomposes item information into multiple semantic levels, ranging from high-level categories to detailed descriptions and collaborative filtering signals. Based on this design, we introduce the CoFiRec Tokenizer, which tokenizes each level independently while preserving structural order. During autoregressive decoding, the language model is instructed to generate item tokens from coarse to fine, progressively modeling user intent from general interests to specific item-level interests. Experiments across multiple public benchmarks and backbones demonstrate that CoFiRec outperforms existing methods, offering a new perspective for generative recommendation. Theoretically, we prove that structured tokenization leads to lower dissimilarity between generated and ground truth items, supporting its effectiveness in generative recommendation. Our code is available at https://github.com/YennNing/CoFiRec.

Paperid: 48, https://arxiv.org/pdf/2511.22704.pdf GitHub

Abstract:
We present Splat-SAP, a feed-forward approach to render novel views of human-centered scenes from binocular cameras with large sparsity. Gaussian Splatting has shown its promising potential in rendering tasks, but it typically necessitates per-scene optimization with dense input views. Although some recent approaches achieve feed-forward Gaussian Splatting rendering through geometry priors obtained by multi-view stereo, such approaches still require largely overlapped input views to establish the geometry prior. To bridge this gap, we leverage pixel-wise point map reconstruction to represent geometry which is robust to large sparsity for its independent view modeling. In general, we propose a two-stage learning strategy. In stage 1, we transform the point map into real space via an iterative affinity learning process, which facilitates camera control in the following. In stage 2, we project point maps of two input views onto the target view plane and refine such geometry via stereo matching. Furthermore, we anchor Gaussian primitives on this refined plane in order to render high-quality images. As a metric representation, the scale-aware point map in stage 1 is trained in a self-supervised manner without 3D supervision and stage 2 is supervised with photo-metric loss. We collect multi-view human-centered data and demonstrate that our method improves both the stability of point map reconstruction and the visual quality of free-viewpoint rendering.

Paperid: 49, https://arxiv.org/pdf/2511.22693.pdf GitHub

Abstract:
We present Generative Anchored Fields (GAF), a generative model that learns independent endpoint predictors $J$ (noise) and $K$ (data) rather than a trajectory predictor. The velocity field $v=K-J$ emerges from their time-conditioned disagreement. This factorization enables \textit{Transport Algebra}: algebraic operation on learned $\{(J_n,K_n)\}_{n=1}^N$ heads for compositional control. With class-specific $K_n$ heads, GAF supports a rich family of directed transport maps between a shared base distribution and multiple modalities, enabling controllable interpolation, hybrid generation, and semantic morphing through vector arithmetic. We achieve strong sample quality (FID 7.5 on CelebA-HQ $64\times 64$) while uniquely providing compositional generation as an architectural primitive. We further demonstrate, GAF has lossless cyclic transport between its initial and final state with LPIPS=$0.0$. Code available at https://github.com/IDLabMedia/GAF

Paperid: 50, https://arxiv.org/pdf/2511.22677.pdf GitHub

Abstract:
Diffusion model distillation has emerged as a powerful technique for creating efficient few-step and single-step generators. Among these, Distribution Matching Distillation (DMD) and its variants stand out for their impressive performance, which is widely attributed to their core mechanism of matching the student's output distribution to that of a pre-trained teacher model. In this work, we challenge this conventional understanding. Through a rigorous decomposition of the DMD training objective, we reveal that in complex tasks like text-to-image generation, where CFG is typically required for desirable few-step performance, the primary driver of few-step distillation is not distribution matching, but a previously overlooked component we identify as CFG Augmentation (CA). We demonstrate that this term acts as the core ``engine'' of distillation, while the Distribution Matching (DM) term functions as a ``regularizer'' that ensures training stability and mitigates artifacts. We further validate this decoupling by demonstrating that while the DM term is a highly effective regularizer, it is not unique; simpler non-parametric constraints or GAN-based objectives can serve the same stabilizing function, albeit with different trade-offs. This decoupling of labor motivates a more principled analysis of the properties of both terms, leading to a more systematic and in-depth understanding. This new understanding further enables us to propose principled modifications to the distillation process, such as decoupling the noise schedules for the engine and the regularizer, leading to further performance gains. Notably, our method has been adopted by the Z-Image ( https://github.com/Tongyi-MAI/Z-Image ) project to develop a top-tier 8-step image generation model, empirically validating the generalization and robustness of our findings.

Paperid: 51, https://arxiv.org/pdf/2511.22664.pdf GitHub

Abstract:
Vision-language models (VLMs), such as CLIP, have shown strong generalization under zero-shot settings, yet adapting them to downstream tasks with limited supervision remains a significant challenge. Existing multi-modal prompt learning methods typically rely on fixed, shared prompts and deterministic parameters, which limits their ability to capture instance-level variation or model uncertainty across diverse tasks and domains. To tackle this issue, we propose a novel Variational Multi-Modal Prompt Learning (VaMP) framework that enables sample-specific, uncertainty-aware prompt tuning in multi-modal representation learning. VaMP generates instance-conditioned prompts by sampling from a learned posterior distribution, allowing the model to personalize its behavior based on input content. To further enhance the integration of local and global semantics, we introduce a class-aware prior derived from the instance representation and class prototype. Building upon these, we formulate prompt tuning as variational inference over latent prompt representations and train the entire framework end-to-end through reparameterized sampling. Experiments on few-shot and domain generalization benchmarks show that VaMP achieves state-of-the-art performance, highlighting the benefits of modeling both uncertainty and task structure in our method. Project page: https://visual-ai.github.io/vamp

Paperid: 52, https://arxiv.org/pdf/2511.22663.pdf GitHub GitHub

Abstract:
Unified multimodal models for image generation and understanding represent a significant step toward AGI and have attracted widespread attention from researchers. The main challenge of this task lies in the difficulty in establishing an optimal training paradigm due to inherent conflicting targets in understanding and generation tasks. To alleviate these conflicts and pursue higher performance, many researchers adopt varying degrees of model decoupling (e.g., Double image encoders, MOE/MOT architecture, or frozen MLLM). However, excessive model decoupling can lead to the loss of interleave generation ability, undermining the original intent of unified models. In this work, we aim to explore how to mitigate task conflicts without resorting to model decoupling. Firstly, we analyze why decoupling alleviates conflicts by studying the cross-modal attention behavior of models. We observe that model decoupling essentially drives models toward task-specific multimodal interaction patterns, as seen in Qwen-VL and HunyuanImage, and that the more thorough the decoupling, the more consistent the behavior becomes. Motivated by this observation, we propose Attention Interaction Alignment (AIA) loss, which explicitly learns Task-Specific multimodal interaction patterns during training. To demonstrate the generalizability of our AIA loss, we apply it to Emu3 and Janus-Pro during SFT and post-training stage respectively. Without bells and whistles, AIA not only refines cross-modal attention patterns, but also boosts both generation and understanding performance.

Paperid: 53, https://arxiv.org/pdf/2511.22645.pdf GitHub GitHub

Abstract:
Multimodal large language models (MLLMs) have undergone rapid development in advancing geospatial scene understanding. Recent studies have sought to enhance the reasoning capabilities of remote sensing MLLMs, typically through cold-start training with elaborately curated chain-of-thought (CoT) data. However, this approach not only incurs substantial annotation costs but also introduces human biases that may limit the diversity of model reasoning. To address these challenges, we propose GeoZero, a framework that enables MLLMs to perform geospatial reasoning without any predefined CoT supervision. Specifically, we construct two datasets, GeoZero-Instruct and GeoZero-Hard. GeoZero-Instruct allows the model to acquire preliminary geospatial knowledge through supervised fine-tuning, while GeoZero-Hard stimulates deep reasoning during the subsequent reinforcement learning stage. Furthermore, we introduce Answer-Anchored Group Relative Policy Optimization (A$^2$GRPO), where the reasoning process is regularized by the model's own answers, encouraging diverse yet accurate thinking. Extensive experiments on multiple remote sensing vision-language benchmarks demonstrate that GeoZero not only surpasses existing state-of-the-art methods but also fosters universal emergent reasoning capabilities across diverse geospatial tasks. Code,data,and models will be publicly available at https://github.com/MiliLab/GeoZero.

Paperid: 54, https://arxiv.org/pdf/2511.22625.pdf GitHub

Abstract:
Recent advances in image editing models have shown remarkable progress. A common architectural design couples a multimodal large language model (MLLM) encoder with a diffusion decoder, as seen in systems such as Step1X-Edit and Qwen-Image-Edit, where the MLLM encodes both the reference image and the instruction but remains frozen during training. In this work, we demonstrate that unlocking the reasoning capabilities of MLLM can further push the boundaries of editing models. Specifically, we explore two reasoning mechanisms, thinking and reflection, which enhance instruction understanding and editing accuracy. Based on that, our proposed framework enables image editing in a thinking-editing-reflection loop: the thinking mechanism leverages the world knowledge of MLLM to interpret abstract instructions, while the reflection reviews editing results, automatically corrects unintended manipulations, and identifies the stopping round. Extensive experiments demonstrate that our reasoning approach achieves significant performance gains, with improvements of ImgEdit (+4.3%), GEdit (+4.7%), and Kris (+8.2%) when initializing our DiT from the Step1X-Edit (ReasonEdit-S), and also outperforms previous open-source methods on both GEdit and Kris when integrated with Qwen-Image-Edit (ReasonEdit-Q).

Paperid: 55, https://arxiv.org/pdf/2511.22598.pdf GitHub

Abstract:
Large language models (LLMs) such as ChatGPT o1, ChatGPT o3, and DeepSeek R1 have shown great potential in solving difficult problems. However, current LLM evaluation benchmarks are limited to one-step interactions. Some of the existing sequence decision-making environments, such as TextStarCraftII and LLM-PySC2, are too complicated and require hours of interaction to complete a game. In this paper, we introduce LLM-Cave, a benchmark and light environment for LLM reasoning and decision-making systems. This environment is a classic instance in the era of Symbolism. Artificial intelligence enables the agent to explore the environment and avoid potential losses by reasoning about nearby dangers using partial observable state information. In the experiment, we evaluated the sequential reasoning ability, decision-making performance and computational efficiency of mainstream large language models (LLMs) such as GPT-4o-mini, o1-mini, and DeepSeek-R1. Experiments show that while Deepseek-R1 achieved the highest success rate on complex reasoning tasks, smaller models like 4o-mini significantly narrowed the performance gap on challenges by employing Chain of Speculation and Planner-Critic strategies, at the expense of reduced computational efficiency. This indicates that structured, multi-step reasoning combined with an LLM-based feedback mechanism can substantially enhance an LLM's decision-making capabilities, providing a promising direction for improving reasoning in weaker models and suggesting a new reasoning-centered benchmark for LLM assessment. Our code is open-sourced in https://github.com/puleya1277/CaveEnv.

Paperid: 56, https://arxiv.org/pdf/2511.22595.pdf GitHub

Abstract:
Zero-shot industrial anomaly detection (ZSAD) methods typically yield coarse anomaly maps as vision transformers (ViTs) extract patch-level features only. To solve this, recent solutions attempt to predict finer anomalies using features from ZSAD, but they still struggle to recover fine-grained anomalies without missed detections, mainly due to the gap between randomly synthesized training anomalies and real ones. We observe that anomaly score maps exactly provide complementary spatial cues that are largely absent from ZSAD's image features, a fact overlooked before. Inspired by this, we propose an anomaly-aware refiner (AnoRefiner) that can be plugged into most ZSAD models and improve patch-level anomaly maps to the pixel level. First, we design an anomaly refinement decoder (ARD) that progressively enhances image features using anomaly score maps, reducing the reliance on synthetic anomaly data. Second, motivated by the mass production paradigm, we propose a progressive group-wise test-time training (PGT) strategy that trains ARD in each product group for the refinement process in the next group, while staying compatible with any ZSAD method. Experiments on the MVTec AD and VisA datasets show that AnoRefiner boosts various ZSAD models by up to a 5.2\% gain in pixel-AP metrics, which can also be directly observed in many visualizations. The code will be available at https://github.com/HUST-SLOW/AnoRefiner.

Paperid: 57, https://arxiv.org/pdf/2511.22594.pdf GitHub

Abstract:
Contrastive Language-Image Pre-training (CLIP) has demonstrated remarkable generalization ability and strong performance across a wide range of vision-language tasks. However, due to the lack of region-level supervision, CLIP exhibits limited fine-grained semantic understanding. Although several methods attempt to mitigate this issue, they unintentionally disrupt the global alignment, resulting in a persistent trade-off where improving local perception simultaneously degrades global coherence. In this paper, we propose HarmoCLIP, a novel framework designed to harmonize global and region representations within CLIP. We first identify that the absence of direct alignment between local textual and visual semantics is the fundamental cause of the trade-off. To address this, HarmoCLIP introduces an explicit fine-grained semantic supervision term that directly aligns textual segments with their corresponding visual regions, effectively bridging the image region space and the textual space. To further strengthen the representation capability at the local level, our method introduces a novel Region-Language Alignment supervision strategy that promotes fine-grained semantic learning without compromising global semantic consistency. Extensive experiments demonstrate that HarmoCLIP achieves state-of-the-art (improvement up to 69.78%) performance on the global task of retrieval and yields a substantial 3.2% improvement in Top-1 accuracy on the region task of bounding-box classification, consistently outperforming prior approaches while providing a balanced, efficient, and plug-and-play solution to the global-local trade-off in CLIP. Code is available at https://github.com/Erosist/HarmoCLIP.

Paperid: 58, https://arxiv.org/pdf/2511.22553.pdf GitHub

Abstract:
We present a unified framework for reconstructing animatable 3D human avatars from a single portrait across head, half-body, and full-body inputs. Our method tackles three bottlenecks: pose- and framing-sensitive feature representations, limited scalable data, and unreliable proxy-mesh estimation. We introduce a Dual-UV representation that maps image features to a canonical UV space via Core-UV and Shell-UV branches, eliminating pose- and framing-induced token shifts. We also build a factorized synthetic data manifold combining 2D generative diversity with geometry-consistent 3D renderings, supported by a training scheme that improves realism and identity consistency. A robust proxy-mesh tracker maintains stability under partial visibility. Together, these components enable strong in-the-wild generalization. Trained only on half-body synthetic data, our model achieves state-of-the-art head and upper-body reconstruction and competitive full-body results. Extensive experiments and analyses further validate the effectiveness of our approach.

Paperid: 59, https://arxiv.org/pdf/2511.22549.pdf GitHub

Abstract:
Image compression methods are usually optimized isolatedly for human perception or machine analysis tasks. We reveal fundamental commonalities between these objectives: preserving accurate semantic information is paramount, as it directly dictates the integrity of critical information for intelligent tasks and aids human understanding. Concurrently, enhanced perceptual quality not only improves visual appeal but also, by ensuring realistic image distributions, benefits semantic feature extraction for machine tasks. Based on this insight, we propose Diff-ICMH, a generative image compression framework aiming for harmonizing machine and human vision in image compression. It ensures perceptual realism by leveraging generative priors and simultaneously guarantees semantic fidelity through the incorporation of Semantic Consistency loss (SC loss) during training. Additionally, we introduce the Tag Guidance Module (TGM) that leverages highly semantic image-level tags to stimulate the pre-trained diffusion model's generative capabilities, requiring minimal additional bit rates. Consequently, Diff-ICMH supports multiple intelligent tasks through a single codec and bitstream without any task-specific adaptation, while preserving high-quality visual experience for human perception. Extensive experimental results demonstrate Diff-ICMH's superiority and generalizability across diverse tasks, while maintaining visual appeal for human perception. Code is available at: https://github.com/RuoyuFeng/Diff-ICMH.

Paperid: 60, https://arxiv.org/pdf/2511.22490.pdf GitHub

Abstract:
As the number of scientific papers continues to grow, there is a demand for approaches that can effectively convey research findings, with posters serving as a key medium for presenting paper contents. Poster layouts determine how effectively research is communicated and understood, highlighting their growing importance. In particular, a gap remains in understanding how papers correspond to the layouts that present them, which calls for datasets with paired annotations at scale. To bridge this gap, we introduce SciPostGen, a large-scale dataset for understanding and generating poster layouts from scientific papers. Our analyses based on SciPostGen show that paper structures are associated with the number of layout elements in posters. Based on this insight, we explore a framework, Retrieval-Augmented Poster Layout Generation, which retrieves layouts consistent with a given paper and uses them as guidance for layout generation. We conducted experiments under two conditions: with and without layout constraints typically specified by poster creators. The results show that the retriever estimates layouts aligned with paper structures, and our framework generates layouts that also satisfy given constraints.

Paperid: 61, https://arxiv.org/pdf/2511.22466.pdf GitHub

Abstract:
Understanding mid-level road semantics, which capture the structural and contextual cues that link low-level perception to high-level planning, is essential for reliable autonomous driving and digital map construction. However, existing benchmarks primarily target perception tasks such as detection or segmentation, overlooking the reasoning capabilities required to infer road topology and dynamic scene structure. To address this gap, we present RoadSceneBench, a lightweight yet information-rich benchmark designed to evaluate and advance visual reasoning in complex road environments. Unlike large-scale perception datasets, RoadSceneBench emphasizes relational understanding and structural consistency, encouraging models to capture the underlying logic of real-world road scenes. Furthermore, to enhance reasoning reliability, we propose Hierarchical Relational Reward Propagation with Temporal Consistency (HRRP-T), a training framework for Vision-Language Models (VLMs) in which reward signals adaptively promote spatial coherence and semantic alignment throughout the reasoning process. This paradigm enables models to move beyond static recognition toward geometry-aware and temporally consistent reasoning. Extensive experiments demonstrate that our method achieves state-of-the-art performance across diverse road configurations. RoadSceneBench thus provides a compact yet powerful foundation for studying mid-level road semantics and fostering structure-aware autonomous perception. Our dataset is available at https://github.com/XiyanLiu/RoadSceneBench.

Paperid: 62, https://arxiv.org/pdf/2511.22456.pdf GitHub

Abstract:
We explore inference-time scaling in text-guided 3D diffusion models to enhance generative quality without additional training. To this end, we introduce ITS3D, a framework that formulates the task as an optimization problem to identify the most effective Gaussian noise input. The framework is driven by a verifier-guided search algorithm, where the search algorithm iteratively refines noise candidates based on verifier feedback. To address the inherent challenges of 3D generation, we introduce three techniques for improved stability, efficiency, and exploration capability. 1) Gaussian normalization is applied to stabilize the search process. It corrects distribution shifts when noise candidates deviate from a standard Gaussian distribution during iterative updates. 2) The high-dimensional nature of the 3D search space increases computational complexity. To mitigate this, a singular value decomposition-based compression technique is employed to reduce dimensionality while preserving effective search directions. 3) To further prevent convergence to suboptimal local minima, a singular space reset mechanism dynamically updates the search space based on diversity measures. Extensive experiments demonstrate that ITS3D enhances text-to-3D generation quality, which shows the potential of computationally efficient search methods in generative processes. The source code is available at https://github.com/ZhenglinZhou/ITS3D.

Paperid: 63, https://arxiv.org/pdf/2511.22433.pdf GitHub

Abstract:
Recent advances in skeleton-based action recognition increasingly leverage semantic priors from Large Language Models (LLMs) to enrich skeletal representations. However, the LLM is typically queried in isolation from the recognition model and receives no performance feedback. As a result, it often fails to deliver the targeted discriminative cues critical to distinguish similar actions. To overcome these limitations, we propose SkeletonAgent, a novel framework that bridges the recognition model and the LLM through two cooperative agents, i.e., Questioner and Selector. Specifically, the Questioner identifies the most frequently confused classes and supplies them to the LLM as context for more targeted guidance. Conversely, the Selector parses the LLM's response to extract precise joint-level constraints and feeds them back to the recognizer, enabling finer-grained cross-modal alignment. Comprehensive evaluations on five benchmarks, including NTU RGB+D, NTU RGB+D 120, Kinetics-Skeleton, FineGYM, and UAV-Human, demonstrate that SkeletonAgent consistently outperforms state-of-the-art benchmark methods. The code is available at https://github.com/firework8/SkeletonAgent.

Paperid: 64, https://arxiv.org/pdf/2511.22429.pdf GitHub GitHub

Abstract:
We present Fin3R, a simple, effective, and general fine-tuning method for feed-forward 3D reconstruction models. The family of feed-forward reconstruction model regresses pointmap of all input images to a reference frame coordinate system, along with other auxiliary outputs, in a single forward pass. However, we find that current models struggle with fine geometry and robustness due to (\textit{i}) the scarcity of high-fidelity depth and pose supervision and (\textit{ii}) the inherent geometric misalignment from multi-view pointmap regression. Fin3R jointly tackles two issues with an extra lightweight fine-tuning step. We freeze the decoder, which handles view matching, and fine-tune only the image encoder-the component dedicated to feature extraction. The encoder is enriched with fine geometric details distilled from a strong monocular teacher model on large, unlabeled datasets, using a custom, lightweight LoRA adapter. We validate our method on a wide range of models, including DUSt3R, MASt3R, CUT3R, and VGGT. The fine-tuned models consistently deliver sharper boundaries, recover complex structures, and achieve higher geometric accuracy in both single- and multi-view settings, while adding only the tiny LoRA weights, which leave test-time memory and latency virtually unchanged. Project page: \href{http://visual-ai.github.io/fin3r}{https://visual-ai.github.io/fin3r}

Paperid: 65, https://arxiv.org/pdf/2511.22396.pdf GitHub

Abstract:
Recent multimodal reasoning models, inspired by DeepSeek-R1, have significantly advanced vision-language systems. However, in remote sensing (RS) tasks, we observe widespread pseudo reasoning: models narrate the process of reasoning rather than genuinely reason toward the correct answer based on visual evidence. We attribute this to the Glance Effect, where a single, coarse perception of large-scale RS imagery results in incomplete understanding and reasoning based on linguistic self-consistency instead of visual evidence. To address this, we propose RS-EoT (Remote Sensing Evidence-of-Thought), a language-driven, iterative visual evidence-seeking paradigm. To instill this paradigm, we propose SocraticAgent, a self-play multi-agent system that synthesizes reasoning traces via alternating cycles of reasoning and visual inspection. To enhance and generalize these patterns, we propose a two-stage progressive RL strategy: first, RL on fine-grained Grounding tasks to enhance RS-EoT capabilities, followed by RL on RS VQA to generalize to broader understanding scenarios. Experiments show RS-EoT achieves state-of-the-art performance on multiple RS VQA and grounding benchmarks. Analyses reveal clear iterative cycles of reasoning and evidence seeking, confirming RS-EoT mitigates the Glance Effect and enables genuine evidence-grounded reasoning. Our code, data, and models are available at https://geox-lab.github.io/Asking_like_Socrates

Paperid: 66, https://arxiv.org/pdf/2511.22378.pdf GitHub

Abstract:
Geospatial observational datasets are often limited to point measurements, making temporal prediction and spatial interpolation essential for constructing continuous fields. This study evaluates two deep learning strategies for addressing this challenge: (1) a grid-to-grid approach, where gridded predictors are used to model rasterised targets (aggregation before modelling), and (2) a grid-to-point approach, where gridded predictors model point targets, followed by kriging interpolation to fill the domain (aggregation after modelling). Using groundwater storage data from Bangladesh as a case study, we compare the effcacy of these approaches. Our findings indicate that spatial interpolation is substantially more difficult than temporal prediction. In particular, nearest neighbours are not always the most similar, and uncertainties in geology strongly influence point temporal behaviour. These insights motivate future work on advanced interpolation methods informed by clustering locations based on time series dynamics. Demonstrated on groundwater storage, the conclusions are applicable to other environmental variables governed by indirectly observable factors. Code is available at https://github.com/pazolka/interpolation-prediction-gwsa.

Paperid: 67, https://arxiv.org/pdf/2511.22357.pdf GitHub

Abstract:
Training-free 3D editing aims to modify 3D shapes based on human instructions without model finetuning. It plays a crucial role in 3D content creation. However, existing approaches often struggle to produce strong or geometrically stable edits, largely due to inconsistent latent anchors introduced by timestep-dependent noise during diffusion sampling. To address these limitations, we introduce AnchorFlow, which is built upon the principle of latent anchor consistency. Specifically, AnchorFlow establishes a global latent anchor shared between the source and target trajectories, and enforces coherence using a relaxed anchor-alignment loss together with an anchor-aligned update rule. This design ensures that transformations remain stable and semantically faithful throughout the editing process. By stabilizing the latent reference space, AnchorFlow enables more pronounced semantic modifications. Moreover, AnchorFlow is mask-free. Without mask supervision, it effectively preserves geometric fidelity. Experiments on the Eval3DEdit benchmark show that AnchorFlow consistently delivers semantically aligned and structurally robust edits across diverse editing types. Code is at https://github.com/ZhenglinZhou/AnchorFlow.

Paperid: 68, https://arxiv.org/pdf/2511.22345.pdf GitHub

Abstract:
Normalizing Flows (NFs) are a class of generative models distinguished by a mathematically invertible architecture, where the forward pass transforms data into a latent space for density estimation, and the reverse pass generates new samples from this space. This characteristic creates an intrinsic synergy between representation learning and data generation. However, the generative quality of standard NFs is limited by poor semantic representations from log-likelihood optimization. To remedy this, we propose a novel alignment strategy that creatively leverages the invertibility of NFs: instead of regularizing the forward pass, we align the intermediate features of the generative (reverse) pass with representations from a powerful vision foundation model, demonstrating superior effectiveness over naive alignment. We also introduce a novel training-free, test-time optimization algorithm for classification, which provides a more intrinsic evaluation of the NF's embedded semantic knowledge. Comprehensive experiments demonstrate that our approach accelerates the training of NFs by over 3.3$\times$, while simultaneously delivering significant improvements in both generative quality and classification accuracy. New state-of-the-art results for NFs are established on ImageNet 64$\times$64 and 256$\times$256. Our code is available at https://github.com/MCG-NJU/FlowBack.

Paperid: 69, https://arxiv.org/pdf/2511.22338.pdf GitHub

Abstract:
Nonholonomic constraints restrict feasible velocities without reducing configuration-space dimension, which makes collision-free geometric paths generally non-executable for car-like robots. Ackermann steering further imposes curvature bounds and forbids in-place rotation, so escaping from narrow dead ends typically requires tightly sequenced forward and reverse maneuvers. Classical planners that decouple global search and local steering struggle in these settings because narrow passages occupy low-measure regions and nonholonomic reachability shrinks the set of valid connections, which degrades sampling efficiency and increases sensitivity to clearances. We study nonholonomic narrow dead-end escape for Ackermann vehicles and contribute three components. First, we construct a generator that samples multi-phase forward-reverse trajectories compatible with Ackermann kinematics and inflates their envelopes to synthesize families of narrow dead ends that are guaranteed to admit at least one feasible escape. Second, we construct a training environment that enforces kinematic constraints and train a policy using the soft actor-critic algorithm. Third, we evaluate against representative classical planners that combine global search with nonholonomic steering. Across parameterized dead-end families, the learned policy solves a larger fraction of instances, reduces maneuver count, and maintains comparable path length and planning time while under the same sensing and control limits. We provide our project as open source at https://github.com/gitagitty/cisDRL-RobotNav.git

Paperid: 70, https://arxiv.org/pdf/2511.22314.pdf GitHub

Abstract:
We curate the DeXposure dataset, the first large-scale dataset for inter-protocol credit exposure in decentralized financial networks, covering global markets of 43.7 million entries across 4.3 thousand protocols, 602 blockchains, and 24.3 thousand tokens, from 2020 to 2025. A new measure, value-linked credit exposure between protocols, is defined as the inferred financial dependency relationships derived from changes in Total Value Locked (TVL). We develop a token-to-protocol model using DefiLlama metadata to infer inter-protocol credit exposure from the token's stock dynamics, as reported by the protocols. Based on the curated dataset, we develop three benchmarks for machine learning research with financial applications: (1) graph clustering for global network measurement, tracking the structural evolution of credit exposure networks, (2) vector autoregression for sector-level credit exposure dynamics during major shocks (Terra and FTX), and (3) temporal graph neural networks for dynamic link prediction on temporal graphs. From the analysis, we observe (1) a rapid growth of network volume, (2) a trend of concentration to key protocols, (3) a decline of network density (the ratio of actual connections to possible connections), and (4) distinct shock propagation across sectors, such as lending platforms, trading exchanges, and asset management protocols. The DeXposure dataset and code have been released publicly. We envision they will help with research and practice in machine learning as well as financial risk monitoring, policy analysis, DeFi market modeling, amongst others. The dataset also contributes to machine learning research by offering benchmarks for graph clustering, vector autoregression, and temporal graph analysis.

Paperid: 71, https://arxiv.org/pdf/2511.22281.pdf GitHub

Abstract:
Observing certain patches in an image reduces the uncertainty of others. Their realization lowers the distribution entropy of each remaining patch feature, analogous to collapsing a particle's wave function in quantum mechanics. This phenomenon can intuitively be called patch collapse. To identify which patches are most relied on during a target region's collapse, we learn an autoencoder that softly selects a subset of patches to reconstruct each target patch. Graphing these learned dependencies for each patch's PageRank score reveals the optimal patch order to realize an image. We show that respecting this order benefits various masked image modeling methods. First, autoregressive image generation can be boosted by retraining the state-of-the-art model MAR. Next, we introduce a new setup for image classification by exposing Vision Transformers only to high-rank patches in the collapse order. Seeing 22\% of such patches is sufficient to achieve high accuracy. With these experiments, we propose patch collapse as a novel image modeling perspective that promotes vision efficiency. Our project is available at https://github.com/wguo-ai/CoP .

Paperid: 72, https://arxiv.org/pdf/2511.22265.pdf GitHub

Abstract:
Federated learning (FL) enables collaborative training across clients without compromising privacy. While most existing FL methods assume homogeneous model architectures, client heterogeneity in data and resources renders this assumption impractical, motivating model-heterogeneous FL. To address this problem, we propose Federated Representation Entanglement (FedRE), a framework built upon a novel form of client knowledge termed entangled representation. In FedRE, each client aggregates its local representations into a single entangled representation using normalized random weights and applies the same weights to integrate the corresponding one-hot label encodings into the entangled-label encoding. Those are then uploaded to the server to train a global classifier. During training, each entangled representation is supervised across categories via its entangled-label encoding, while random weights are resampled each round to introduce diversity, mitigating the global classifier's overconfidence and promoting smoother decision boundaries. Furthermore, each client uploads a single cross-category entangled representation along with its entangled-label encoding, mitigating the risk of representation inversion attacks and reducing communication overhead. Extensive experiments demonstrate that FedRE achieves an effective trade-off among model performance, privacy protection, and communication overhead. The codes are available at https://github.com/AIResearch-Group/FedRE.

Paperid: 73, https://arxiv.org/pdf/2511.22242.pdf GitHub

Abstract:
A prominent approach to test-time scaling for text-to-image diffusion models formulates the problem as a search over multiple noise seeds, selecting the one that maximizes a certain image-reward function. The effectiveness of this strategy heavily depends on the number and diversity of noise seeds explored. However, verifying each candidate is computationally expensive, because each must be fully denoised before a reward can be computed. This severely limits the number of samples that can be explored under a fixed budget. We propose test-time scaling with noise-aware pruning (TTSnap), a framework that prunes low-quality candidates without fully denoising them. The key challenge is that reward models are learned in the clean image domain, and the ranking of rewards predicted for intermediate estimates are often inconsistent with those predicted for clean images. To overcome this, we train noise-aware reward models via self-distillation to align the reward for intermediate estimates with that of the final clean images. To stabilize learning across different noise levels, we adopt a curriculum training strategy that progressively shifts the data domain from clean images to noise images. In addition, we introduce a new metric that measures reward alignment and computational budget utilization. Experiments demonstrate that our approach improves performance by over 16\% compared with existing methods, enabling more efficient and effective test-time scaling. It also provides orthogonal gains when combined with post-training techniques and local test-time optimization. Code: https://github.com/TerrysLearning/TTSnap/.

Paperid: 74, https://arxiv.org/pdf/2511.22235.pdf GitHub

Abstract:
The rapid development of large vision-language model (VLM) has greatly promoted the research of GUI agent. However, GUI agents still face significant challenges in handling long-horizon tasks. First, single-agent models struggle to balance high-level capabilities and low-level execution capability, facing prevalent issues of responsibility coupling and capability conflicts. Second, agents lack awareness of the task state, leading to progress loss in long-horizon tasks. To address these challenges, we propose a staged execution-feedback reinforcement learning algorithm. Unlike training a unified policy model, we focus on training high-level scheduling models. Specifically, we propose and train two agents: a Coordinator, responsible for the strategic planning and task decomposition; and a State Tracker, responsible for context compression and information management to maintain the task's state and coherence. Based on this, we built the Coordinator-Executor-State Tracker (CES) multi-agent framework, which can be integrated with any low-level Executor model, assisting the Executor in solving long-horizon tasks through task scheduling and state management. Experiments on long-horizon task benchmarks demonstrate that CES significantly enhances the system's planning and state management capabilities. Furthermore, analysis confirms that our trained high-level scheduling module is a generalizable, plug-and-play module that significantly enhances the long-horizon capabilities of various Executors. Code can be available at https://github.com/hehehahi4/CES.

Paperid: 75, https://arxiv.org/pdf/2511.22194.pdf GitHub

Abstract:
Recently, the impressive generative capabilities of diffusion models have been demonstrated, producing images with remarkable fidelity. Particularly, existing methods for the 3D object generation tasks, which is one of the fastest-growing segments in computer vision, pre-dominantly use text-to-image diffusion models with textual inversion which train a pseudo text prompt to describe the given image. In practice, various text-to-image generative models employ textual inversion to learn concepts or styles of target object in the pseudo text prompt embedding space, thereby generating sophisticated outputs. However, textual inversion requires additional training time and lacks control ability. To tackle this issues, we propose two innovative methods: (1) using an off-the-shelf image adapter that generates 3D objects without textual inversion, offering enhanced control over conditions such as depth, pose, and text. (2) a depth conditioned warmup strategy to enhance 3D consistency. In experimental results, ours show qualitatively and quantitatively comparable performance and improved 3D consistency to the existing text-inversion-based alternatives. Furthermore, we conduct a user study to assess (i) how well results match the input image and (ii) whether 3D consistency is maintained. User study results show that our model outperforms the alternatives, validating the effectiveness of our approaches. Our code is available at GitHub repository:https://github.com/Seooooooogi/Control3D_IP/

Paperid: 76, https://arxiv.org/pdf/2511.22173.pdf GitHub

Abstract:
Can language models (LMs) self-refine their own responses? This question is increasingly relevant as a wide range of real-world user interactions involve refinement requests. However, prior studies have largely tested LMs' refinement abilities on verifiable tasks such as competition math or symbolic reasoning with simplified scaffolds, whereas users often pose open-ended queries and provide varying degrees of feedback on what they desire. The recent advent of reasoning models that exhibit self-reflection patterns in their chains-of-thought further motivates this question. To analyze this, we introduce RefineBench, a benchmark of 1,000 challenging problems across 11 domains paired with a checklist-based evaluation framework. We evaluate two refinement modes: (1) guided refinement, where an LM is provided natural language feedback, and (2) self-refinement, where LMs attempt to improve without guidance. In the self-refinement setting, even frontier LMs such as Gemini 2.5 Pro and GPT-5 achieve modest baseline scores of 31.3% and 29.1%, respectively, and most models fail to consistently improve across iterations (e.g., Gemini-2.5-Pro gains only +1.8%, while DeepSeek-R1 declines by -0.1%). By contrast, in guided refinement, both proprietary LMs and large open-weight LMs (>70B) can leverage targeted feedback to refine responses to near-perfect levels within five turns. These findings suggest that frontier LMs require breakthroughs to self-refine their incorrect responses, and that RefineBench provides a valuable testbed for tracking progress.

Paperid: 77, https://arxiv.org/pdf/2511.22146.pdf GitHub GitHub

Abstract:
Autoregressive (AR) language models and Diffusion Language Models (DLMs) constitute the two principal paradigms of large language models. However, both paradigms suffer from insufficient reasoning capabilities. Human reasoning inherently relies on causal knowledge and thought, which are reflected in natural language. But in the AR paradigm, language is modeled as next token prediction (a strictly left-to-right, token-by-token order), whereas natural language itself exhibits more flexible causal structures. In the DLM paradigm, the attention mechanism is fully connected, which entirely disregards causal order. To fill this gap, we propose a \underline{\textbf{C}}ausal \underline{\textbf{C}}oncept-Guided \underline{\textbf{D}}iffusion \underline{\textbf{L}}anguage \underline{\textbf{M}}odel (C$^2$DLM). Starting from DLM's fully connected attention, C$^2$DLM first obtains a concept-level causal graph from the teacher model, and then explicitly guides attention to learn causal relationships between concepts. By focusing on causal relationships and avoiding interference from difficult subgoals involving causal inversion, C$^2$DLM improves 12\% with about 3.2 times training speedup in the COT-OrderPerturb task, and achieves an average gain of 1.31\% across six downstream reasoning tasks. More details in the repository ~\href{https://github.com/Kairong-Han/C-2-DLM}{here}.

Paperid: 78, https://arxiv.org/pdf/2511.22142.pdf GitHub

Abstract:
In the field of autonomous driving, camera-based perception models are mostly trained on clear weather data. Models that focus on addressing specific weather challenges are unable to adapt to various weather changes and primarily prioritize their weather removal characteristics. Our study introduces a semantic-enabled network for object detection in diverse weather conditions. In our analysis, semantics information can enable the model to generate plausible content for missing areas, understand object boundaries, and preserve visual coherency and realism across both filled-in and existing portions of the image, which are conducive to image transformation and object recognition. Specific in implementation, our architecture consists of a Preprocessing Unit (PPU) and a Detection Unit (DTU), where the PPU utilizes a U-shaped net enriched by semantics to refine degraded images, and the DTU integrates this semantic information for object detection using a modified YOLO network. Our method pioneers the use of semantic data for all-weather transformations, resulting in an increase between 1.47\% to 8.80\% in mAP compared to existing methods across benchmark datasets of different weather. This highlights the potency of semantics in image enhancement and object detection, offering a comprehensive approach to improving object detection performance. Code will be available at https://github.com/EnisZuo/SemOD.

Paperid: 79, https://arxiv.org/pdf/2511.22134.pdf GitHub

Abstract:
To build a generalizable Vision-Language-Action (VLA) model with strong reasoning ability, a common strategy is to first train a specialist VLA on robot demonstrations to acquire reliable manipulation skills, and then incorporate mixed annotated robot data together with multimodal data to restore broader reasoning capabilities. However, we observe that the resulting reasoning VLA often suffers from degraded action performance compared to the specialist model before fine-tuning, a phenomenon we refer to as action degeneration. To address this issue, we propose DualVLA, which enhances action performance through carefully designed post-training while still preserving reasoning capability. We first introduce a dual-layer data pruning method that removes redundant embodied reasoning, preventing it from adversely influencing action learning. To further strengthen action generation, we design a dual-teacher adaptive distillation strategy that assigns different supervision signals to different data domains while maintaining reasoning ability. To fill the evaluation gap for generalist VLAs, we also propose VLA Score, which decouples VLA capability into reasoning, intention, action, and alignment dimensions for a more fine-grained assessment. Experiments show that DualVLA achieves an average success rate of 61.0 in SimplerEnv and an average score of 65.4 across eight competitive multimodal benchmarks, demonstrating a stronger balance between precise action execution and multimodal understanding. Project Website: https://costaliya.github.io/DualVLA/.

Paperid: 80, https://arxiv.org/pdf/2511.22121.pdf GitHub

Abstract:
Humans and traditional computer vision methods rely on a diverse set of monocular cues to infer 3D structure from a single image, such as shading, texture, silhouette, etc. While recent deep generative models have dramatically advanced single-image 3D generation, it remains unclear which image cues these methods actually exploit. We introduce Cue3D, the first comprehensive, model-agnostic framework for quantifying the influence of individual image cues in single-image 3D generation. Our unified benchmark evaluates seven state-of-the-art methods, spanning regression-based, multi-view, and native 3D generative paradigms. By systematically perturbing cues such as shading, texture, silhouette, perspective, edges, and local continuity, we measure their impact on 3D output quality. Our analysis reveals that shape meaningfulness, not texture, dictates generalization. Geometric cues, particularly shading, are crucial for 3D generation. We further identify over-reliance on provided silhouettes and diverse sensitivities to cues such as perspective and local continuity across model families. By dissecting these dependencies, Cue3D advances our understanding of how modern 3D networks leverage classical vision cues, and offers directions for developing more transparent, robust, and controllable single-image 3D generation models.

Paperid: 81, https://arxiv.org/pdf/2511.22120.pdf GitHub

Abstract:
Convolutional neural networks (CNNs) suffer from rapidly increasing storage and computational costs as their depth grows, which severely hinders their deployment on resource-constrained edge devices. Pruning is a practical approach for network compression, among which structured pruning is the most effective for inference acceleration. Although existing work has applied the $\ell_p$-norm to pruning, it only considers unstructured pruning with $p\in (0, 1)$ and has low computational efficiency. To overcome these limitations, we propose an accelerated structured pruning method called GoPrune. Our method employs the $\ell_{2,p}$-norm for sparse network learning, where the value of $p$ is extended to $[0, 1)$. Moreover, we develop an efficient optimization algorithm based on the proximal alternating minimization (PAM), and the resulting subproblems enjoy closed-form solutions, thus improving compression efficiency. Experiments on the CIFAR datasets using ResNet and VGG models demonstrate the superior performance of the proposed method in network pruning. Our code is available at https://github.com/xianchaoxiu/GoPrune.

Paperid: 82, https://arxiv.org/pdf/2511.22119.pdf GitHub

Abstract:
Text-to-image (T2I) generative models such as Stable Diffusion and FLUX can synthesize realistic, high-quality images directly from textual prompts. The resulting image quality depends critically on well-crafted prompts that specify both subjects and stylistic modifiers, which have become valuable digital assets. However, the rising value and ubiquity of high-quality prompts expose them to security and intellectual-property risks. One key threat is the prompt stealing attack, i.e., the task of recovering the textual prompt that generated a given image. Prompt stealing enables unauthorized extraction and reuse of carefully engineered prompts, yet it can also support beneficial applications such as data attribution, model provenance analysis, and watermarking validation. Existing approaches often assume white-box gradient access, require large-scale labeled datasets for supervised training, or rely solely on captioning without explicit optimization, limiting their practicality and adaptability. To address these challenges, we propose PROMPTMINER, a black-box prompt stealing framework that decouples the task into two phases: (1) a reinforcement learning-based optimization phase to reconstruct the primary subject, and (2) a fuzzing-driven search phase to recover stylistic modifiers. Experiments across multiple datasets and diffusion backbones demonstrate that PROMPTMINER achieves superior results, with CLIP similarity up to 0.958 and textual alignment with SBERT up to 0.751, surpassing all baselines. Even when applied to in-the-wild images with unknown generators, it outperforms the strongest baseline by 7.5 percent in CLIP similarity, demonstrating better generalization. Finally, PROMPTMINER maintains strong performance under defensive perturbations, highlighting remarkable robustness. Code: https://github.com/aaFrostnova/PromptMiner

Paperid: 83, https://arxiv.org/pdf/2511.22116.pdf GitHub

Abstract:
Handling missing data remains a fundamental challenge in real-world tabular datasets, especially when data are heterogeneous with both numerical and categorical features. Existing imputation methods often fail to capture complex structural dependencies and handle heterogeneous data effectively. We present \textbf{IVGAE}, a Variational Graph Autoencoder framework for robust imputation of incomplete heterogeneous data. IVGAE constructs a bipartite graph to represent sample-feature relationships and applies graph representation learning to model structural dependencies. A key innovation is its \textit{dual-decoder architecture}, where one decoder reconstructs feature embeddings and the other models missingness patterns, providing structural priors aware of missing mechanisms. To better encode categorical variables, we introduce a Transformer-based heterogeneous embedding module that avoids high-dimensional one-hot encoding. Extensive experiments on 16 real-world datasets show that IVGAE achieves consistent improvements in RMSE and downstream F1 across MCAR, MAR, and MNAR missing scenarios under 30\% missing rates. Code and data are available at: https://github.com/echoid/IVGAE.

Paperid: 84, https://arxiv.org/pdf/2511.22112.pdf GitHub

Abstract:
The solar wind, a continuous stream of charged particles from the Sun's corona, shapes the heliosphere and impacts space systems near Earth. Variations such as high-speed streams and coronal mass ejections can disrupt satellites, power grids, and communications, making accurate modeling essential for space weather forecasting. While 3D magnetohydrodynamic (MHD) models are used to simulate and investigate these variations in the solar wind, they tend to be computationally expensive, limiting their usefulness in investigating the impacts of boundary condition uncertainty. In this work, we develop a surrogate for steady state solar wind modeling, using a Spherical Fourier Neural Operator (SFNO). We compare our model to a previously developed numerical surrogate for this task called HUX, and we show that the SFNO achieves comparable or better performance across several metrics. Though HUX retains advantages in physical smoothness, this underscores the need for improved evaluation criteria rather than a flaw in SFNO. As a flexible and trainable approach, SFNO enables efficient real-time forecasting and can improve with more data. The source code and more visual results are available at https://github.com/rezmansouri/solarwind-sfno-velocity.

Paperid: 85, https://arxiv.org/pdf/2511.22080.pdf GitHub

Abstract:
In federated learning (FL), models must \emph{converge quickly} under tight communication budgets while \emph{generalizing} across non-IID client distributions. These twin requirements have naturally led to two widely used techniques: client/server \emph{momentum} to accelerate progress, and \emph{sharpness-aware minimization} (SAM) to prefer flat solutions. However, simply combining momentum and SAM leaves two structural issues unresolved in non-IID FL. We identify and formalize two failure modes: \emph{local-global curvature misalignment} (local SAM directions need not reflect the global loss geometry) and \emph{momentum-echo oscillation} (late-stage instability caused by accumulated momentum). To our knowledge, these failure modes have not been jointly articulated and addressed in the FL literature. We propose \textbf{FedWMSAM} to address both failure modes. First, we construct a momentum-guided global perturbation from server-aggregated momentum to align clients' SAM directions with the global descent geometry, enabling a \emph{single-backprop} SAM approximation that preserves efficiency. Second, we couple momentum and SAM via a cosine-similarity adaptive rule, yielding an early-momentum, late-SAM two-phase training schedule. We provide a non-IID convergence bound that \emph{explicitly models the perturbation-induced variance} $σ_ρ^2=σ^2+(Lρ)^2$ and its dependence on $(S, K, R, N)$ on the theory side. We conduct extensive experiments on multiple datasets and model architectures, and the results validate the effectiveness, adaptability, and robustness of our method, demonstrating its superiority in addressing the optimization challenges of Federated Learning. Our code is available at https://github.com/Huang-Yongzhi/NeurlPS_FedWMSAM.

Paperid: 86, https://arxiv.org/pdf/2511.22043.pdf GitHub

Abstract:
Although quadrotor navigation has achieved high performance in trajectory planning and control, real-time adaptability in unknown complex environments remains a core challenge. This difficulty mainly arises because most existing planning frameworks operate in an open-loop manner, making it hard to cope with environmental uncertainties such as wind disturbances or external perturbations. This paper presents a unified real-time navigation framework for quadrotors in unknown complex environments, based on the online construction of guiding vector fields (GVFs) from discrete reference path points. In the framework, onboard perception modules build a Euclidean Signed Distance Field (ESDF) representation of the environment, which enables obstacle awareness and path distance evaluation. The system first generates discrete, collision-free path points using a global planner, and then parameterizes them via uniform B-splines to produce a smooth and physically feasible reference trajectory. An adaptive GVF is then synthesized from the ESDF and the optimized B-spline trajectory. Unlike conventional approaches, the method adopts a closed-loop navigation paradigm, which significantly enhances robustness under external disturbances. Compared with conventional GVF methods, the proposed approach directly accommodates discretized paths and maintains compatibility with standard planning algorithms. Extensive simulations and real-world experiments demonstrate improved robustness against external disturbances and superior real-time performance.

Paperid: 87, https://arxiv.org/pdf/2511.22033.pdf GitHub

Abstract:
Diabetic retinopathy (DR) grading plays a critical role in early clinical intervention and vision preservation. Recent explorations predominantly focus on visual lesion feature extraction through data processing and domain decoupling strategies. However, they generally overlook domain-invariant pathological patterns and underutilize the rich contextual knowledge of foundation models, relying solely on visual information, which is insufficient for distinguishing subtle pathological variations. Therefore, we propose integrating fine-grained pathological descriptions to complement prototypes with additional context, thereby resolving ambiguities in borderline cases. Specifically, we propose a Hierarchical Anchor Prototype Modulation (HAPM) framework to facilitate DR grading. First, we introduce a variance spectrum-driven anchor prototype library that preserves domain-invariant pathological patterns. We further employ a hierarchical differential prompt gating mechanism, dynamically selecting discriminative semantic prompts from both LVLM and LLM sources to address semantic confusion between adjacent DR grades. Finally, we utilize a two-stage prototype modulation strategy that progressively integrates clinical knowledge into visual prototypes through a Pathological Semantic Injector (PSI) and a Discriminative Prototype Enhancer (DPE). Extensive experiments across eight public datasets demonstrate that our approach achieves pathology-guided prototype evolution while outperforming state-of-the-art methods. The code is available at https://github.com/zhcz328/HAPM.

Paperid: 88, https://arxiv.org/pdf/2511.22031.pdf GitHub

Abstract:
The electric power sector is a leading source of air pollutant emissions, impacting the public health of nearly every community. Although regulatory measures have reduced air pollutants, fossil fuels remain a significant component of the energy supply, highlighting the need for more advanced demand-side approaches to reduce the public health impacts. To enable health-informed demand-side management, we introduce HealthPredictor, a domain-specific AI model that provides an end-to-end pipeline linking electricity use to public health outcomes. The model comprises three components: a fuel mix predictor that estimates the contribution of different generation sources, an air quality converter that models pollutant emissions and atmospheric dispersion, and a health impact assessor that translates resulting pollutant changes into monetized health damages. Across multiple regions in the United States, our health-driven optimization framework yields substantially lower prediction errors in terms of public health impacts than fuel mix-driven baselines. A case study on electric vehicle charging schedules illustrates the public health gains enabled by our method and the actionable guidance it can offer for health-informed energy management. Overall, this work shows how AI models can be explicitly designed to enable health-informed energy management for advancing public health and broader societal well-being. Our datasets and code are released at: https://github.com/Ren-Research/Health-Impact-Predictor.

Paperid: 89, https://arxiv.org/pdf/2511.22019.pdf GitHub

Abstract:
Vision-language models (VLMs), such as CLIP, have gained popularity for their strong open vocabulary classification performance, but they are prone to assigning high confidence scores to misclassifications, limiting their reliability in safety-critical applications. We introduce a training-free, post-hoc uncertainty estimation method for contrastive VLMs that can be used to detect erroneous predictions. The key to our approach is to measure visual feature consistency within a class, using feature projection combined with multivariate Gaussians to create class-specific probabilistic embeddings. Our method is VLM-agnostic, requires no fine-tuning, demonstrates robustness to distribution shift, and works effectively with as few as 10 training images per class. Extensive experiments on ImageNet, Flowers102, Food101, EuroSAT and DTD show state-of-the-art error detection performance, significantly outperforming both deterministic and probabilistic VLM baselines. Code is available at https://github.com/zhenxianglin/ICPE.

Paperid: 90, https://arxiv.org/pdf/2511.22009.pdf GitHub

Abstract:
New technologies such as Rectified Flow and Flow Matching have significantly improved the performance of generative models in the past two years, especially in terms of control accuracy, generation quality, and generation efficiency. However, due to some differences in its theory, design, and existing diffusion models, the existing acceleration methods cannot be directly applied to the Rectified Flow model. In this article, we have comprehensively implemented an overall acceleration pipeline from the aspects of theory, design, and reasoning strategies. This pipeline uses new methods such as batch processing with a new velocity field, vectorization of heterogeneous time-step batch processing, and dynamic TensorRT compilation for the new methods to comprehensively accelerate related models based on flow models. Currently, the existing public methods usually achieve an acceleration of 18%, while experiments have proved that our new method can accelerate the 512*512 image generation speed to up to 611%, which is far beyond the current non-generalized acceleration methods.

Paperid: 91, https://arxiv.org/pdf/2511.21998.pdf GitHub

Abstract:
Multi-modal Large Language Models (LLM) have advanced conversational abilities but struggle with providing live, interactive step-by-step guidance, a key capability for future AI assistants. Effective guidance requires not only delivering instructions but also detecting their successful execution, as well as identifying and alerting users to mistakes, all of which has to happen in real-time. This requires models that are not turn-based, but that can react asynchronously to a video stream, as well as video data showing users performing tasks including mistakes and their corrections. To this end, we introduce Qualcomm Interactive Cooking, a new benchmark and dataset built upon CaptainCook4D, which contains user mistakes during task execution. Our dataset and benchmark features densely annotated, timed instructions and feedback messages, specifically including mistake alerts precisely timestamped to their visual occurrence in the video. We evaluate state-of-the-art multi-modal LLMs on the Qualcomm Interactive Cooking benchmark and introduce LiveMamba, a streaming multi-modal LLM designed for interactive instructional guidance. This work provides the first dedicated benchmark and a strong baseline for developing and evaluating on live, situated coaching.

Paperid: 92, https://arxiv.org/pdf/2511.21982.pdf GitHub

Abstract:
The precise reading recognition of pointer meters plays a key role in smart power systems, but existing approaches remain fragile due to challenges like reflections, occlusions, dynamic viewing angles, and overly between thin pointers and scale markings. Up to now, this area still lacks large-scale datasets to support the development of robust algorithms. To address these challenges, this paper first presents a new large-scale benchmark dataset for dial reading, termed RPM-10K, which contains 10730 meter images that fully reflect the aforementioned key challenges. Built upon the dataset, we propose a novel vision-language model for pointer meter reading recognition, termed MRLM, based on physical relation injection. Instead of exhaustively learning image-level correlations, MRLM explicitly encodes the geometric and causal relationships between the pointer and the scale, aligning perception with physical reasoning in the spirit of world-model perspectives. Through cross-attentional fusion and adaptive expert selection, the model learns to interpret dial configurations and generate precise numeric readings. Extensive experiments fully validated the effectiveness of our proposed framework on the newly proposed benchmark dataset. Both the dataset and source code will be released on https://github.com/Event-AHU/DialBench

Paperid: 93, https://arxiv.org/pdf/2511.21937.pdf GitHub

Abstract:
Multimodal approaches that integrate histology and genomics hold strong potential for precision oncology. However, phenotypic and genotypic heterogeneity limits the quality of intra-modal representations and hinders effective inter-modal integration. Furthermore, most existing methods overlook real-world clinical scenarios where genomics may be partially missing or entirely unavailable. We propose a flexible multimodal prototyping framework to integrate whole slide images and incomplete genomics for precision oncology. Our approach has four key components: 1) Biological Prototyping using text prompting and prototype-wise weighting; 2) Multiview Alignment through sample- and distribution-wise alignments; 3) Bipartite Fusion to capture both shared and modality-specific information for multimodal fusion; and 4) Semantic Genomics Imputation to handle missing data. Extensive experiments demonstrate the consistent superiority of the proposed method compared to other state-of-the-art approaches on multiple downstream tasks. The code is available at https://github.com/helenypzhang/Interpretable-Multimodal-Prototyping.

Paperid: 94, https://arxiv.org/pdf/2511.21923.pdf GitHub

Abstract:
Understanding how backdoor data influences neural network training dynamics remains a complex and underexplored challenge. In this paper, we present a rigorous analysis of the impact of backdoor data on the learning process, with a particular focus on the distinct behaviors between the target class and other clean classes. Leveraging the Information Bottleneck (IB) principle connected with clustering of internal representation, We find that backdoor attacks create unique mutual information (MI) signatures, which evolve across training phases and differ based on the attack mechanism. Our analysis uncovers a surprising trade-off: visually conspicuous attacks like BadNets can achieve high stealthiness from an information-theoretic perspective, integrating more seamlessly into the model than many visually imperceptible attacks. Building on these insights, we propose a novel, dynamics-based stealthiness metric that quantifies an attack's integration at the model level. We validate our findings and the proposed metric across multiple datasets and diverse attack types, offering a new dimension for understanding and evaluating backdoor threats. Our code is available in: https://github.com/XinyuLiu71/Information_Bottleneck_Backdoor.git.

Paperid: 95, https://arxiv.org/pdf/2511.21919.pdf GitHub

Abstract:
Snarls and superbubbles are fundamental pangenome decompositions capturing variant sites. These bubble-like structures underpin key tasks in computational pangenomics, including structural-variant genotyping, distance indexing, haplotype sampling, and variant annotation. Snarls can be quadratically-many in the size of the graph, and since their introduction in 2018 with the vg toolkit, there has been no work on identifying all snarls in linear time. Moreover, while it is known how to find superbubbles in linear time, this result is a highly specialized solution only achieved after a long series of papers. We present the first algorithm identifying all snarls in linear time. This is based on a new representation of all snarls, of size linear in the input graph size, and which can be computed in linear time. Our algorithm is based on a unified framework that also provides a new linear-time algorithm for finding superbubbles. An observation behind our results is that all such structures are separated from the rest of the graph by two vertices (except for cases which are trivially computable), i.e. their endpoints are a 2-separator of the underlying undirected graph. Based on this, we employ the well-known SPQR tree decomposition, which encodes all 2-separators, to guide a traversal that finds the bubble-like structures efficiently. We implemented our algorithms in C++ (available at https://github.com/algbio/BubbleFinder) and evaluated them on various pangenomic datasets. Our algorithms outcompete or they are on the same level of existing methods. For snarls, we are up to two times faster than vg, while identifying all snarls. When computing superbubbles, we are up to 50 times faster than BubbleGun. Our SPQR tree framework provides a unifying perspective on bubble-like structures in pangenomics, together with a template for finding other bubble-like structures efficiently.

Paperid: 96, https://arxiv.org/pdf/2511.21915.pdf GitHub GitHub

Abstract:
Most scientific domains elicit the development of efficient algorithms and accessible scientific software. This thesis unifies our developments in three broad domains: Quasi-Monte Carlo (QMC) methods for efficient high-dimensional integration, Gaussian process (GP) regression for high-dimensional interpolation with built-in uncertainty quantification, and scientific machine learning (sciML) for modeling partial differential equations (PDEs) with mesh-free solvers. For QMC, we built new algorithms for vectorized error estimation and developed QMCPy (https://qmcsoftware.github.io/QMCSoftware/): an open-source Python interface to randomized low-discrepancy sequence generators, automatic variable transforms, adaptive error estimation procedures, and diverse use cases. For GPs, we derived new digitally-shift-invariant kernels of higher-order smoothness, developed novel fast multitask GP algorithms, and produced the scalable Python software FastGPs (https://alegresor.github.io/fastgps/). For sciML, we developed a new algorithm capable of machine precision recovery of PDEs with random coefficients. We have also studied a number of applications including GPs for probability of failure estimation, multilevel GPs for the Darcy flow equation, neural surrogates for modeling radiative transfer, and fast GPs for Bayesian multilevel QMC.

Paperid: 97, https://arxiv.org/pdf/2511.21761.pdf GitHub GitHub

Abstract:
Large Language Models (LLMs) have demonstrated strong translation abilities through prompting, even without task-specific training. However, their effectiveness in dialectal and low-resource contexts remains underexplored. This study presents the first systematic investigation of LLM-based machine translation (MT) for Sylheti, a dialect of Bangla that is itself low-resource. We evaluate five advanced LLMs (GPT-4.1, GPT-4.1, LLaMA 4, Grok 3, and DeepSeek V3.2) across both translation directions (Bangla $\Leftrightarrow$ Sylheti), and find that these models struggle with dialect-specific vocabulary. To address this, we introduce Sylheti-CAP (Context-Aware Prompting), a three-step framework that embeds a linguistic rulebook, a dictionary (2{,}260 core vocabulary items and idioms), and an authenticity check directly into prompts. Extensive experiments show that Sylheti-CAP consistently improves translation quality across models and prompting strategies. Both automatic metrics and human evaluations confirm its effectiveness, while qualitative analysis reveals notable reductions in hallucinations, ambiguities, and awkward phrasing, establishing Sylheti-CAP as a scalable solution for dialectal and low-resource MT. Dataset link: \href{https://github.com/TabiaTanzin/LLMs-for-Low-Resource-Dialect-Translation-Using-Context-Aware-Prompting-A-Case-Study-on-Sylheti.git}{https://github.com/TabiaTanzin/LLMs-for-Low-Resource-Dialect-Translation-Using-Context-Aware-Prompting-A-Case-Study-on-Sylheti.git}

Paperid: 98, https://arxiv.org/pdf/2511.21742.pdf GitHub

Abstract:
With the growing use of Large Language Model (LLM)-based Question-Answering (QA) systems in education, it is critical to evaluate their performance across individual pipeline components. In this work, we introduce {\model}, a modular function-calling LLM pipeline, and present a comprehensive evaluation along three key axes: function calling strategies, retrieval methods, and generative language models. Our framework enables fine-grained analysis by isolating and assessing each component. We benchmark function-calling performance across LLMs, compare our novel structure-aware retrieval method to vector-based and LLM-scoring baselines, and evaluate various LLMs for response synthesis. This modular approach reveals specific failure modes and performance patterns, supporting the development of interpretable and effective educational QA systems. Our findings demonstrate the value of modular function calling in improving system transparency and pedagogical alignment. Website and Supplementary Material: https://chancharikmitra.github.io/EduMod-LLM-website/

Paperid: 99, https://arxiv.org/pdf/2511.21737.pdf GitHub

Abstract:
Advances in unsupervised probes such as Contrast-Consistent Search (CCS), which reveal latent beliefs without relying on token outputs, raise the question of whether these methods can reliably assess model alignment. We investigate this by examining the sensitivity of CCS to harmful vs. safe statements and by introducing Polarity-Aware CCS (PA-CCS), a method for evaluating whether a model's internal representations remain consistent under polarity inversion. We propose two alignment-oriented metrics, Polar-Consistency and the Contradiction Index, to quantify the semantic robustness of a model's latent knowledge. To validate PA-CCS, we curate two main datasets and one control dataset containing matched harmful-safe sentence pairs constructed using different methodologies (concurrent and antagonistic statements). We apply PA-CCS to 16 language models. Our results show that PA-CCS identifies both architectural and layer-specific differences in the encoding of latent harmful knowledge. Notably, replacing the negation token with a meaningless marker degrades PA-CCS scores for models with well-aligned internal representations, while models lacking robust internal calibration do not exhibit this degradation. Our findings highlight the potential of unsupervised probing for alignment evaluation and emphasize the need to incorporate structural robustness checks into interpretability benchmarks. Code and datasets are available at: https://github.com/SadSabrina/polarity-probing. WARNING: This paper contains potentially sensitive, harmful, and offensive content.

Paperid: 100, https://arxiv.org/pdf/2511.21733.pdf GitHub

Abstract:
Fine-tuning large language models is essential for task-specific adaptation, yet it remains computationally prohibitive. Parameter-Efficient Fine-Tuning (PEFT) methods have emerged as a solution, but current approaches typically ignore the distinct roles of model components and the heterogeneous importance across layers, thereby limiting adaptation efficiency. Motivated by the observation that Rotary Position Embeddings (RoPE) induce critical activations in the low-frequency dimensions of attention states, we propose RoPE-aware Selective Adaptation (RoSA), a novel PEFT framework that allocates trainable parameters in a more targeted and effective manner. RoSA comprises a RoPE-aware Attention Enhancement (RoAE) module, which selectively enhances the low-frequency components of RoPE-influenced attention states, and a Dynamic Layer Selection (DLS) strategy that adaptively identifies and updates the most critical layers based on LayerNorm gradient norms. By combining dimension-wise enhancement with layer-wise adaptation, RoSA achieves more targeted and efficient fine-tuning. Extensive experiments on fifteen commonsense and arithmetic benchmarks demonstrate that RoSA outperforms existing mainstream PEFT methods under comparable trainable parameters. The code is available to ease reproducibility at https://github.com/Applied-Machine-Learning-Lab/RoSA.

Paperid: 101, https://arxiv.org/pdf/2511.21730.pdf GitHub

Abstract:
Current AI agents excel in familiar settings, but fail sharply when faced with novel tasks with unseen vocabularies -- a core limitation of procedural memory systems. We present the first benchmark that isolates procedural memory retrieval from task execution, evaluating whether agents can recognize functionally equivalent procedures that span different object instantiations. Using ALFWorld, we construct dual corpora of expert and LLM-generated trajectories and evaluate six retrieval methods using systematically stratified queries. Our results expose a clear generalization cliff: embedding-based methods perform strongly on familiar contexts, yet degrade considerably on novel ones, while LLM-generated procedural abstractions demonstrate reliable cross-context transfer. Controlled ablations show that although embeddings capture some lexical-level abstraction, they fundamentally treat procedures as unordered bags of words, discarding temporal structure necessary for cross-context transfer. Corpus scale delivers far larger gains than representation enrichment, revealing an architectural ceiling in current encoders. Our benchmark offers the first diagnostic framework separating genuine procedural understanding from surface-level memorization and gives tools for developing retrieval systems capable of dependable generalization. Resources available at our GitHub repository (https://github.com/qpiai/Proced_mem_bench).

Paperid: 102, https://arxiv.org/pdf/2511.21726.pdf GitHub

Abstract:
How to enable human-like long-term memory in large language models (LLMs) has been a central question for unlocking more general capabilities such as few-shot generalization. Existing memory frameworks and benchmarks focus on finding the optimal memory compression algorithm for higher performance in tasks that require recollection and sometimes further reasoning. However, such efforts have ended up building more human bias into the compression algorithm, through the search for the best prompts and memory architectures that suit specific benchmarks, rather than finding a general solution that would work on other data distributions. On the other hand, goal-directed search on uncompressed information could potentially exhibit superior performance because compression is lossy, and a predefined compression algorithm will not fit all raw data distributions. Here we present SUMER (Search in Uncompressed Memory via Experience Replay), an end-to-end reinforcement learning agent with verifiable reward (RLVR) that learns to use search tools to gather information and answer a target question. On the LoCoMo dataset for long-context conversation understanding, SUMER with Qwen2.5-7B-Instruct learned to use search tools and outperformed all other biased memory compression approaches and also the full-context baseline, reaching SOTA performance (43% gain over the prior best). We demonstrate that a simple search method applied to raw data outperforms goal-agnostic and biased compression algorithms in current long-context memory tasks, arguing for new paradigms and benchmarks that are more dynamic and autonomously scalable. Code for SUMER and all implemented baselines is publicly available at https://github.com/zycyc/SUMER.

Paperid: 103, https://arxiv.org/pdf/2511.21714.pdf GitHub

Abstract:
LLMs are sensitive to prompting, with task performance often hinging on subtle, sometimes imperceptible variations in phrasing. As a result, crafting effective prompts manually remains challenging and time-consuming. Recent automatic prompting methods mitigate this difficulty but face three key limitations: (i) for each new task, they require large datasets to train good prompts;(ii) they rely on costly optimization loops that may take hours; (iii)they typically produce a single task-level prompt that does not adapt to the individual input problem to be solved. We propose GPS, the first general-purpose, per-sample prompting method. Without any task-specific tuning, GPS generates a tailored prompt for each unseen input, improving performance across diverse tasks. The prompter is trained with reinforcement learning on a suite of training tasks and includes a novel regularization for effectively adapting to per-sample prompting. Finally, we employ Minimum Bayes Risk decoding to stabilize inference. Empirically, GPS demonstrates competitive performance: we attain second best results among baselines on text simplification, third best results on summarization and on-par results on classification, while not training on any of these tasks, in contrast to the baselines. For in-domain prompting, we obtain sota on GSM8K. Our work shows the potential of a novel and effective paradigm for automatic prompting: generating adaptive, input-specific prompts without extensive optimization and without access to a task-specific training set. Our code is available at https://github.com/Batorskq/GPS.

Paperid: 104, https://arxiv.org/pdf/2511.21712.pdf GitHub

Abstract:
Environmental, Social, and Governance (ESG) reports have become central to how companies communicate climate risk, social impact, and governance practices, yet they are still published primarily as long, heterogeneous PDF documents. This makes it difficult to systematically answer seemingly simple questions. Existing tools either rely on brittle rule-based extraction or treat ESG reports as generic text, without explicitly modelling the underlying reporting standards. We present \textbf{EulerESG}, an LLM-powered system for automating ESG disclosure analysis with explicit awareness of ESG frameworks. EulerESG combines (i) dual-channel retrieval and LLM-driven disclosure analysis over ESG reports, and (ii) an interactive dashboard and chatbot for exploration, benchmarking, and explanation. Using four globally recognised companies and twelve SASB sub-industries, we show that EulerESG can automatically populate standard-aligned metric tables with high fidelity (up to 0.95 average accuracy) while remaining practical in end-to-end runtime, and we compare several recent LLM models in this setting. The full implementation, together with a demonstration video, is publicly available at https://github.com/UNSW-database/EulerESG.

Paperid: 105, https://arxiv.org/pdf/2511.21702.pdf GitHub GitHub

Abstract:
Large language models face significant computational bottlenecks during inference due to the expensive output layer computation over large vocabularies. We present CSV-Decode, a novel approach that uses geometric upper bounds to construct small sub-vocabularies for each decoding step, enabling efficient sparse computation while maintaining dual correctness guarantees: exact top-$k$ certification and $\varepsilon$-certified softmax approximations. Our method clusters vocabulary embeddings offline and uses centroid-plus-radius bounds to identify which tokens can be safely omitted from computation. We provide a complete system implementation with sparse GEMV kernels, multi-GPU sharding, and CUDA Graph optimization. Experimental results demonstrate significant speedup over full vocabulary decoding while maintaining distributional guarantees and low fallback rates. Our code implementation available at \href{https://github.com/FastLM/CSV-Decode}{https://github.com/FastLM/CSV-Decode}.

Paperid: 106, https://arxiv.org/pdf/2511.21697.pdf GitHub

Abstract:
We present a unique system for large-scale, multi-performer, high resolution 4D volumetric capture providing realistic free-viewpoint video up to and including 4K resolution facial closeups. To achieve this, we employ a novel volumetric capture, reconstruction and rendering pipeline based on Dynamic Gaussian Splatting and Diffusion-based Detail Enhancement. We design our pipeline specifically to meet the demands of high-end media production. We employ two capture rigs: the Scene Rig, which captures multi-actor performances at a resolution which falls short of 4K production quality, and the Face Rig, which records high-fidelity single-actor facial detail to serve as a reference for detail enhancement. We first reconstruct dynamic performances from the Scene Rig using 4D Gaussian Splatting, incorporating new model designs and training strategies to improve reconstruction, dynamic range, and rendering quality. Then to render high-quality images for facial closeups, we introduce a diffusion-based detail enhancement model. This model is fine-tuned with high-fidelity data from the same actors recorded in the Face Rig. We train on paired data generated from low- and high-quality Gaussian Splatting (GS) models, using the low-quality input to match the quality of the Scene Rig, with the high-quality GS as ground truth. Our results demonstrate the effectiveness of this pipeline in bridging the gap between the scalable performance capture of a large-scale rig and the high-resolution standards required for film and media production.

Paperid: 107, https://arxiv.org/pdf/2511.21691.pdf GitHub

Abstract:
While modern diffusion models excel at generating high-quality and diverse images, they still struggle with high-fidelity compositional and multimodal control, particularly when users simultaneously specify text prompts, subject references, spatial arrangements, pose constraints, and layout annotations. We introduce Canvas-to-Image, a unified framework that consolidates these heterogeneous controls into a single canvas interface, enabling users to generate images that faithfully reflect their intent. Our key idea is to encode diverse control signals into a single composite canvas image that the model can directly interpret for integrated visual-spatial reasoning. We further curate a suite of multi-task datasets and propose a Multi-Task Canvas Training strategy that optimizes the diffusion model to jointly understand and integrate heterogeneous controls into text-to-image generation within a unified learning paradigm. This joint training enables Canvas-to-Image to reason across multiple control modalities rather than relying on task-specific heuristics, and it generalizes well to multi-control scenarios during inference. Extensive experiments show that Canvas-to-Image significantly outperforms state-of-the-art methods in identity preservation and control adherence across challenging benchmarks, including multi-person composition, pose-controlled composition, layout-constrained generation, and multi-control generation.

Paperid: 108, https://arxiv.org/pdf/2511.21688.pdf GitHub

Abstract:
Vision-Language Models (VLMs) still lack robustness in spatial intelligence, demonstrating poor performance on spatial understanding and reasoning tasks. We attribute this gap to the absence of a visual geometry learning process capable of reconstructing 3D space from 2D images. We present G$^2$VLM, a geometry grounded vision-language model that bridges two fundamental aspects of spatial intelligence: spatial 3D reconstruction and spatial understanding. G$^2$VLM natively leverages learned 3D visual geometry features to directly predict 3D attributes and enhance spatial reasoning tasks via in-context learning and interleaved reasoning. Our unified design is highly scalable for spatial understanding: it trains on abundant multi-view image and video data, while simultaneously leveraging the benefits of 3D visual priors that are typically only derived from hard-to-collect annotations. Experimental results demonstrate G$^2$VLM is proficient in both tasks, achieving comparable results to state-of-the-art feed-forward 3D reconstruction models and achieving better or competitive results across spatial understanding and reasoning tasks. By unifying a semantically strong VLM with low-level 3D vision tasks, we hope G$^2$VLM can serve as a strong baseline for the community and unlock more future applications, such as 3D scene editing.

Paperid: 109, https://arxiv.org/pdf/2511.21678.pdf GitHub

Abstract:
MLLMs exhibit strong reasoning on isolated queries, yet they operate de novo -- solving each problem independently and often repeating the same mistakes. Existing memory-augmented agents mainly store past trajectories for reuse. However, trajectory-based memory suffers from brevity bias, gradually losing essential domain knowledge. More critically, even in truly multimodal problem-solving settings, it records only a single-modality trace of past behavior, failing to preserve how visual attention and logical reasoning jointly contributed to the solution. This is fundamentally misaligned with human cognition: semantic memory is both multimodal and integrated, preserving visual and abstract knowledge through coordinated but distinct representational streams. We thus introduce ViLoMem, a dual-stream memory framework that constructs compact, schema-based memory. It separately encodes visual distraction patterns and logical reasoning errors, enabling MLLMs to learn from their successful and failed experiences. Following a grow-and-refine principle, the system incrementally accumulates and updates multimodal semantic knowledge -- preserving stable, generalizable strategies while avoiding catastrophic forgetting. Across six multimodal benchmarks, ViLoMem consistently improves pass@1 accuracy and substantially reduces repeated visual and logical errors. Ablations confirm the necessity of dual-stream memory with explicit distraction--hallucination separation, demonstrating the value of error-aware multimodal memory for lifelong and cross-domain agentic learning. Our project page will be available at https://weihao-bo.github.io/ViLoMeo-page.

Paperid: 110, https://arxiv.org/pdf/2511.21666.pdf GitHub GitHub

Abstract:
Quantifying the uncertainty of an object's pose estimate is essential for robust control and planning. Although pose estimation is a well-studied robotics problem, attaching statistically rigorous uncertainty is not well understood without strict distributional assumptions. We develop distribution-free pose uncertainty bounds about a given pose estimate in the monocular setting. Our pose uncertainty only requires high probability noise bounds on pixel detections of 2D semantic keypoints on a known object. This noise model induces an implicit, non-convex set of pose uncertainty constraints. Our key contribution is SLUE (S-Lemma Uncertainty Estimation), a convex program to reduce this set to a single ellipsoidal uncertainty bound that is guaranteed to contain the true object pose with high probability. SLUE solves a relaxation of the minimum volume bounding ellipsoid problem inspired by the celebrated S-lemma. It requires no initial guess of the bound's shape or size and is guaranteed to contain the true object pose with high probability. For tighter uncertainty bounds at the same confidence, we extend SLUE to a sum-of-squares relaxation hierarchy which is guaranteed to converge to the minimum volume ellipsoidal uncertainty bound for a given set of keypoint constraints. We show this pose uncertainty bound can easily be projected to independent translation and axis-angle orientation bounds. We evaluate SLUE on two pose estimation datasets and a real-world drone tracking scenario. Compared to prior work, SLUE generates substantially smaller translation bounds and competitive orientation bounds. We release code at https://github.com/MIT-SPARK/PoseUncertaintySets.

Paperid: 111, https://arxiv.org/pdf/2511.21654.pdf GitHub

Abstract:
We introduce EvilGenie, a benchmark for reward hacking in programming settings. We source problems from LiveCodeBench and create an environment in which agents can easily reward hack, such as by hardcoding test cases or editing the testing files. We measure reward hacking in three ways: held out unit tests, LLM judges, and test file edit detection. We verify these methods against human review and each other. We find the LLM judge to be highly effective at detecting reward hacking in unambiguous cases, and observe only minimal improvement from the use of held out test cases. In addition to testing many models using Inspect's basic_agent scaffold, we also measure reward hacking rates for three popular proprietary coding agents: OpenAI's Codex, Anthropic's Claude Code, and Google's Gemini CLI Using GPT-5, Claude Sonnet 4, and Gemini 2.5 Pro, respectively. We observe explicit reward hacking by both Codex and Claude Code, and misaligned behavior by all three agents. Our codebase can be found at https://github.com/JonathanGabor/EvilGenie.

Paperid: 112, https://arxiv.org/pdf/2511.21653.pdf GitHub

Abstract:
Action Quality Assessment (AQA) predicts fine-grained execution scores from action videos and is widely applied in sports, rehabilitation, and skill evaluation. Long-term AQA, as in figure skating or rhythmic gymnastics, is especially challenging since it requires modeling extended temporal dynamics while remaining robust to contextual confounders. Existing approaches either depend on costly annotations or rely on unidirectional temporal modeling, making them vulnerable to spurious correlations and unstable long-term representations. To this end, we propose CaFlow, a unified framework that integrates counterfactual de-confounding with bidirectional time-conditioned flow. The Causal Counterfactual Regularization (CCR) module disentangles causal and confounding features in a self-supervised manner and enforces causal robustness through counterfactual interventions, while the BiT-Flow module models forward and backward dynamics with a cycle-consistency constraint to produce smoother and more coherent representations. Extensive experiments on multiple long-term AQA benchmarks demonstrate that CaFlow achieves state-of-the-art performance. Code is available at https://github.com/Harrison21/CaFlow

Paperid: 113, https://arxiv.org/pdf/2511.21635.pdf GitHub GitHub

Abstract:
Deeper Vision Transformers often perform worse than shallower ones, which challenges common scaling assumptions. Through a systematic empirical analysis of ViT-S, ViT-B, and ViT-L on ImageNet, we identify a consistent three-phase Cliff-Plateau-Climb pattern that governs how representations evolve with depth. We observe that better performance is associated with progressive marginalization of the [CLS] token, originally designed as a global aggregation hub, in favor of distributed consensus among patch tokens. We quantify patterns of information mixing with an Information Scrambling Index, and show that in ViT-L the information-task tradeoff emerges roughly 10 layers later than in ViT-B, and that these additional layers correlate with increased information diffusion rather than improved task performance. Taken together, these results suggest that transformer architectures in this regime may benefit more from carefully calibrated depth that executes clean phase transitions than from simply increasing parameter count. The Information Scrambling Index provides a useful diagnostic for existing models and suggests a potential design target for future architectures. All code is available at: https://github.com/AnanthaPadmanaban-KrishnaKumar/Cliff-Plateau-Climb.

Paperid: 114, https://arxiv.org/pdf/2511.21624.pdf GitHub

Abstract:
Large Language Models (LLMs) have recently revolutionized machine learning on text-attributed graphs, but the application of LLMs to graph outlier detection, particularly in the context of fake news detection, remains significantly underexplored. One of the key challenges is the scarcity of large-scale, realistic, and well-annotated datasets that can serve as reliable benchmarks for outlier detection. To bridge this gap, we introduce TAGFN, a large-scale, real-world text-attributed graph dataset for outlier detection, specifically fake news detection. TAGFN enables rigorous evaluation of both traditional and LLM-based graph outlier detection methods. Furthermore, it facilitates the development of misinformation detection capabilities in LLMs through fine-tuning. We anticipate that TAGFN will be a valuable resource for the community, fostering progress in robust graph-based outlier detection and trustworthy AI. The dataset is publicly available at https://huggingface.co/datasets/kayzliu/TAGFN and our code is available at https://github.com/kayzliu/tagfn.

Paperid: 115, https://arxiv.org/pdf/2511.21594.pdf GitHub

Abstract:
Large language models (LLMs) achieve state-of-the-art results across many natural language tasks, but their internal mechanisms remain difficult to interpret. In this work, we extract, process, and visualize latent state geometries in Transformer-based language models through dimensionality reduction. We capture layerwise activations at multiple points within Transformer blocks and enable systematic analysis through Principal Component Analysis (PCA) and Uniform Manifold Approximation (UMAP). We demonstrate experiments on GPT-2 and LLaMa models, where we uncover interesting geometric patterns in latent space. Notably, we identify a clear separation between attention and MLP component outputs across intermediate layers, a pattern not documented in prior work to our knowledge. We also characterize the high norm of latent states at the initial sequence position and visualize the layerwise evolution of latent states. Additionally, we demonstrate the high-dimensional helical structure of GPT-2's positional embeddings, the sequence-wise geometric patterns in LLaMa, and experiment with repeating token sequences. We aim to support systematic analysis of Transformer internals with the goal of enabling further reproducible interpretability research. We make our code available at https://github.com/Vainateya/Feature_Geometry_Visualization.

Paperid: 116, https://arxiv.org/pdf/2511.21592.pdf GitHub

Abstract:
Video diffusion models achieve strong frame-level fidelity but still struggle with motion coherence, dynamics and realism, often producing jitter, ghosting, or implausible dynamics. A key limitation is that the standard denoising MSE objective provides no direct supervision on temporal consistency, allowing models to achieve low loss while still generating poor motion. We propose MoGAN, a motion-centric post-training framework that improves motion realism without reward models or human preference data. Built atop a 3-step distilled video diffusion model, we train a DiT-based optical-flow discriminator to differentiate real from generated motion, combined with a distribution-matching regularizer to preserve visual fidelity. With experiments on Wan2.1-T2V-1.3B, MoGAN substantially improves motion quality across benchmarks. On VBench, MoGAN boosts motion score by +7.3% over the 50-step teacher and +13.3% over the 3-step DMD model. On VideoJAM-Bench, MoGAN improves motion score by +7.4% over the teacher and +8.8% over DMD, while maintaining comparable or even better aesthetic and image-quality scores. A human study further confirms that MoGAN is preferred for motion quality (52% vs. 38% for the teacher; 56% vs. 29% for DMD). Overall, MoGAN delivers significantly more realistic motion without sacrificing visual fidelity or efficiency, offering a practical path toward fast, high-quality video generation. Project webpage is: https://xavihart.github.io/mogan.

Paperid: 117, https://arxiv.org/pdf/2511.21581.pdf GitHub

Abstract:
Latent reasoning represents a new development in Transformer language models that has shown potential in compressing reasoning lengths compared to chain-of-thought reasoning. By directly passing the information-rich previous final latent state into the next sequence, latent reasoning removes the restriction to human language tokens as the medium for reasoning. We develop adaptive-length latent reasoning models and introduce a post-SFT reinforcement-learning methodology to optimize latent reasoning length by minimizing reasoning length while maintaining accuracy. This, in turn, further reduces compute usage and raises the bar on the compressive capabilities of latent reasoning models. Experiments on the Llama 3.2 1B model and the GSM8K-Aug dataset show a $52\%$ drop in total reasoning length with no penalty to accuracy. In future work, we plan to extend to additional models and datasets, analyze relationships between training coefficients, experiment with architecture variations, and continue our knowledge distillation for latent reasoning SFT efforts. We make our code and pretrained weights available at https://github.com/apning/adaptive-latent-reasoning.

Paperid: 118, https://arxiv.org/pdf/2511.21523.pdf GitHub

Abstract:
Recent advances in foundation models have shown great promise in domains such as natural language processing and computer vision, and similar efforts are now emerging in the Earth Observation community. These models aim to generalize across tasks with limited supervision, reducing the need for training separate models for each task. However, current strategies, which largely focus on scaling model size and dataset volume, require prohibitive computational and data resources, limiting accessibility to only a few large institutions. Moreover, this paradigm of ever-larger models stands in stark contrast with the principles of sustainable and environmentally responsible AI, as it leads to immense carbon footprints and resource inefficiency. In this work, we present a novel and efficient alternative: an Ensemble-of-Specialists framework for building Remote Sensing Foundation Models (RSFMs). Our method decomposes the training process into lightweight, task-specific ConvNeXtV2 specialists that can be frozen and reused. This modular approach offers strong advantages in efficiency, interpretability, and extensibility. Moreover, it naturally supports federated training, pruning, and continuous specialist integration, making it particularly well-suited for collaborative and resource-constrained settings. Our framework sets a new direction for building scalable and efficient RSFMs. All codes and pretrained models are available at https://github.com/pierreadorni/EoS-FM.

Paperid: 119, https://arxiv.org/pdf/2511.21519.pdf GitHub

Abstract:
Antinuclear antibody (ANA) testing is a crucial method for diagnosing autoimmune disorders, including lupus, Sjögren's syndrome, and scleroderma. Despite its importance, manual ANA detection is slow, labor-intensive, and demands years of training. ANA detection is complicated by over 100 coexisting antibody types, resulting in vast fluorescent pattern combinations. Although machine learning and deep learning have enabled automation, ANA detection in real-world clinical settings presents unique challenges as it involves multi-instance, multi-label (MIML) learning. In this paper, a novel framework for ANA detection is proposed that handles the complexities of MIML tasks using unaltered microscope images without manual preprocessing. Inspired by human labeling logic, it identifies consistent ANA sub-regions and assigns aggregated labels accordingly. These steps are implemented using three task-specific components: an instance sampler, a probabilistic pseudo-label dispatcher, and self-paced weight learning rate coefficients. The instance sampler suppresses low-confidence instances by modeling pattern confidence, while the dispatcher adaptively assigns labels based on instance distinguishability. Self-paced learning adjusts training according to empirical label observations. Our framework overcomes limitations of traditional MIML methods and supports end-to-end optimization. Extensive experiments on one ANA dataset and three public medical MIML benchmarks demonstrate the superiority of our framework. On the ANA dataset, our model achieves up to +7.0% F1-Macro and +12.6% mAP gains over the best prior method, setting new state-of-the-art results. It also ranks top-2 across all key metrics on public datasets, reducing Hamming loss and one-error by up to 18.2% and 26.9%, respectively. The source code can be accessed at https://github.com/fletcherjiang/ANA-SelfPacedLearning.

Paperid: 120, https://arxiv.org/pdf/2511.21510.pdf GitHub

Abstract:
This study proposes Tool-RoCo, a novel benchmark for evaluating large language models (LLMs) in long-term multi-agent cooperation based on RoCo, a multi-robot cooperative benchmark. Recent research on LLM-based multi-agent systems has relied on predefined orchestration, while ignoring agent autonomy. Tool-RoCo treats other agents as tools and introduces cooperative tools, leveraging tool usage to evaluate multi-agent cooperation and self-organization. Tool usage means that each agent (LLM) selects a tool from a candidate set based on the current state, receives feedback, and adjusts its selection in subsequent rounds. To evaluate different autonomy levels, we propose four LLM paradigms: (1) centralized cooperation, where a single LLM allocates tools to all agents; (2) centralized self-organization, where a central LLM autonomously activates agents while keeping others inactive; (3) decentralized cooperation, where each agent has its own LLM and calls tools based on local information; and (4) self-organization, where a randomly chosen initial agent can request collaboration, activating additional agents via tool calls. Tool-RoCo includes three multi-robot tasks, SORT, PACK, and CABINET, to measure format and parameter accuracy and agent coordination through tool usage. The results using several LLMs showed that cooperative tools accounted for only 7.09% of all tools, indicating that LLM-based agents rarely invoked others as assistants. Moreover, activation tools accounted for 96.42%, suggesting that current LLMs tend to maintain active agents while seldom deactivating them for adaptive coordination. Tool-RoCo provides a systematic benchmark to evaluate LLM autonomy and cooperation in multi-agent tasks. Code and Demo: https://github.com/ColaZhang22/Tool-Roco

Paperid: 121, https://arxiv.org/pdf/2511.21507.pdf GitHub

Abstract:
The effectiveness of deepfake detection methods often depends less on their core design and more on implementation details such as data preprocessing, augmentation strategies, and optimization techniques. These factors make it difficult to fairly compare detectors and to understand which factors truly contribute to their performance. To address this, we systematically investigate how different design choices influence the accuracy and generalization capabilities of deepfake detection models, focusing on aspects related to training, inference, and incremental updates. By isolating the impact of individual factors, we aim to establish robust, architecture-agnostic best practices for the design and development of future deepfake detection systems. Our experiments identify a set of design choices that consistently improve deepfake detection and enable state-of-the-art performance on the AI-GenBench benchmark.

Paperid: 122, https://arxiv.org/pdf/2511.21503.pdf GitHub

Abstract:
We propose Cross-Attention-based Non-local Knowledge Distillation (CanKD), a novel feature-based knowledge distillation framework that leverages cross-attention mechanisms to enhance the knowledge transfer process. Unlike traditional self-attention-based distillation methods that align teacher and student feature maps independently, CanKD enables each pixel in the student feature map to dynamically consider all pixels in the teacher feature map. This non-local knowledge transfer more thoroughly captures pixel-wise relationships, improving feature representation learning. Our method introduces only an additional loss function to achieve superior performance compared with existing attention-guided distillation methods. Extensive experiments on object detection and image segmentation tasks demonstrate that CanKD outperforms state-of-the-art feature and hybrid distillation methods. These experimental results highlight CanKD's potential as a new paradigm for attention-guided distillation in computer vision tasks. Code is available at https://github.com/tori-hotaru/CanKD

Paperid: 123, https://arxiv.org/pdf/2511.21475.pdf GitHub GitHub

Abstract:
Recently, video generation has witnessed rapid advancements, drawing increasing attention to image-to-video (I2V) synthesis on mobile devices. However, the substantial computational complexity and slow generation speed of diffusion models pose significant challenges for real-time, high-resolution video generation on resource-constrained mobile devices. In this work, we propose MobileI2V, a 270M lightweight diffusion model for real-time image-to-video generation on mobile devices. The core lies in: (1) We analyzed the performance of linear attention modules and softmax attention modules on mobile devices, and proposed a linear hybrid architecture denoiser that balances generation efficiency and quality. (2) We design a time-step distillation strategy that compresses the I2V sampling steps from more than 20 to only two without significant quality loss, resulting in a 10-fold increase in generation speed. (3) We apply mobile-specific attention optimizations that yield a 2-fold speed-up for attention operations during on-device inference. MobileI2V enables, for the first time, fast 720p image-to-video generation on mobile devices, with quality comparable to existing models. Under one-step conditions, the generation speed of each frame of 720p video is less than 100 ms. Our code is available at: https://github.com/hustvl/MobileI2V.

Paperid: 124, https://arxiv.org/pdf/2511.21459.pdf GitHub

Abstract:
Efficient and scalable 3D surface reconstruction from range data remains a core challenge in computer graphics and vision, particularly in real-time and resource-constrained scenarios. Traditional volumetric methods based on fixed-resolution voxel grids or hierarchical structures like octrees often suffer from memory inefficiency, computational overhead, and a lack of GPU support. We propose a novel variance-adaptive, multi-resolution voxel grid that dynamically adjusts voxel size based on the local variance of signed distance field (SDF) observations. Unlike prior multi-resolution approaches that rely on recursive octree structures, our method leverages a flat spatial hash table to store all voxel blocks, supporting constant-time access and full GPU parallelism. This design enables high memory efficiency and real-time scalability. We further demonstrate how our representation supports GPU-accelerated rendering through a parallel quad-tree structure for Gaussian Splatting, enabling effective control over splat density. Our open-source CUDA/C++ implementation achieves up to 13x speedup and 4x lower memory usage compared to fixed-resolution baselines, while maintaining on par results in terms of reconstruction accuracy, offering a practical and extensible solution for high-performance 3D reconstruction.

Paperid: 125, https://arxiv.org/pdf/2511.21439.pdf GitHub

Abstract:
Event cameras produce asynchronous event streams that are spatially sparse yet temporally dense. Mainstream event representation learning algorithms typically use event frames, voxels, or tensors as input. Although these approaches have achieved notable progress, they struggle to address the undersampling problem caused by spatial sparsity. In this paper, we propose a novel hypergraph-guided spatio-temporal event stream completion mechanism, which connects event tokens across different times and spatial locations via hypergraphs and leverages contextual information message passing to complete these sparse events. The proposed method can flexibly incorporate RGB tokens as nodes in the hypergraph within this completion framework, enabling multi-modal hypergraph-based information completion. Subsequently, we aggregate hypergraph node information across different time steps through self-attention, enabling effective learning and fusion of multi-modal features. Extensive experiments on both single- and multi-label event classification tasks fully validated the effectiveness of our proposed framework. The source code of this paper will be released on https://github.com/Event-AHU/EvRainDrop.

Paperid: 126, https://arxiv.org/pdf/2511.21420.pdf GitHub

Abstract:
Remote sensing change captioning is an emerging and popular research task that aims to describe, in natural language, the content of interest that has changed between two remote sensing images captured at different times. Existing methods typically employ CNNs/Transformers to extract visual representations from the given images or incorporate auxiliary tasks to enhance the final results, with weak region awareness and limited temporal alignment. To address these issues, this paper explores the use of the SAM (Segment Anything Model) foundation model to extract region-level representations and inject region-of-interest knowledge into the captioning framework. Specifically, we employ a CNN/Transformer model to extract global-level vision features, leverage the SAM foundation model to delineate semantic- and motion-level change regions, and utilize a specially constructed knowledge graph to provide information about objects of interest. These heterogeneous sources of information are then fused via cross-attention, and a Transformer decoder is used to generate the final natural language description of the observed changes. Extensive experimental results demonstrate that our method achieves state-of-the-art performance across multiple widely used benchmark datasets. The source code of this paper will be released on https://github.com/Event-AHU/SAM_ChangeCaptioning

Paperid: 127, https://arxiv.org/pdf/2511.21416.pdf GitHub

Abstract:
Text-attributed graphs require models to effectively combine strong textual understanding with structurally informed reasoning. Existing approaches either rely on GNNs--limited by over-smoothing and hop-dependent diffusion--or employ Transformers that overlook graph topology and treat nodes as isolated sequences. We propose Odin (Oriented Dual-module INtegration), a new architecture that injects graph structure into Transformers at selected depths through an oriented dual-module mechanism. Unlike message-passing GNNs, Odin does not rely on multi-hop diffusion; instead, multi-hop structures are integrated at specific Transformer layers, yielding low-, mid-, and high-level structural abstraction aligned with the model's semantic hierarchy. Because aggregation operates on the global [CLS] representation, Odin fundamentally avoids over-smoothing and decouples structural abstraction from neighborhood size or graph topology. We further establish that Odin's expressive power strictly contains that of both pure Transformers and GNNs. To make the design efficient in large-scale or low-resource settings, we introduce Light Odin, a lightweight variant that preserves the same layer-aligned structural abstraction for faster training and inference. Experiments on multiple text-rich graph benchmarks show that Odin achieves state-of-the-art accuracy, while Light Odin delivers competitive performance with significantly reduced computational cost. Together, Odin and Light Odin form a unified, hop-free framework for principled structure-text integration. The source code of this model has been released at https://github.com/hongkaifeng/Odin.

Paperid: 128, https://arxiv.org/pdf/2511.21402.pdf GitHub

Abstract:
Recent divide-and-conquer reasoning approaches, particularly those based on Chain-of-Thought (CoT), have substantially improved the Text-to-SQL capabilities of Large Language Models (LLMs). However, when applied to complex enterprise databases, such methods struggle to maintain coherent reasoning due to limited context capacity, unreliable schema linking, and weak grounding in database semantics. To overcome these issues, we introduce DSR-SQL, a \textbf{D}ual-\textbf{S}tate \textbf{R}easoning framework that models Text-to-SQL as an interaction between an adaptive context state and a progressive generation state. The first constructs a compact, semantically faithful environment by refining large schemas and selecting relevant structures, while the second formalizes SQL synthesis as feedback-guided state transitions, enabling the model to self-correct and align with user intent. Without any post-training or in-context examples, DSR-SQL achieves competitive performance, reaching 35.28\% execution accuracy on Spider 2.0-Snow and 68.32\% on BIRD development set. Our implementation will be open-sourced at: https://github.com/DMIRLAB-Group/DSR-SQL.

Paperid: 129, https://arxiv.org/pdf/2511.21395.pdf GitHub

Abstract:
"Thinking with images" has emerged as an effective paradigm for advancing visual reasoning, extending beyond text-only chains of thought by injecting visual evidence into intermediate reasoning steps. However, existing methods fall short of human-like abstract visual thinking, as their flexibility is fundamentally limited by external tools. In this work, we introduce Monet, a training framework that enables multimodal large language models (MLLMs) to reason directly within the latent visual space by generating continuous embeddings that function as intermediate visual thoughts. We identify two core challenges in training MLLMs for latent visual reasoning: high computational cost in latent-vision alignment and insufficient supervision over latent embeddings, and address them with a three-stage distillation-based supervised fine-tuning (SFT) pipeline. We further reveal a limitation of applying GRPO to latent reasoning: it primarily enhances text-based reasoning rather than latent reasoning. To overcome this, we propose VLPO (Visual-latent Policy Optimization), a reinforcement learning method that explicitly incorporates latent embeddings into policy gradient updates. To support SFT, we construct Monet-SFT-125K, a high-quality text-image interleaved CoT dataset containing 125K real-world, chart, OCR, and geometry CoTs. Our model, Monet-7B, shows consistent gains across real-world perception and reasoning benchmarks and exhibits strong out-of-distribution generalization on challenging abstract visual reasoning tasks. We also empirically analyze the role of each training component and discuss our early unsuccessful attempts, providing insights for future developments in visual latent reasoning. Our model, data, and code are available at https://github.com/NOVAglow646/Monet.

Paperid: 130, https://arxiv.org/pdf/2511.21356.pdf GitHub

Abstract:
Adversarial Inverse Reinforcement Learning (AIRL) has shown promise in addressing the sparse reward problem in reinforcement learning (RL) by inferring dense reward functions from expert demonstrations. However, its performance in highly complex, imperfect-information settings remains largely unexplored. To explore this gap, we evaluate AIRL in the context of Heads-Up Limit Hold'em (HULHE) poker, a domain characterized by sparse, delayed rewards and significant uncertainty. In this setting, we find that AIRL struggles to infer a sufficiently informative reward function. To overcome this limitation, we contribute Hybrid-AIRL (H-AIRL), an extension that enhances reward inference and policy learning by incorporating a supervised loss derived from expert data and a stochastic regularization mechanism. We evaluate H-AIRL on a carefully selected set of Gymnasium benchmarks and the HULHE poker setting. Additionally, we analyze the learned reward function through visualization to gain deeper insights into the learning process. Our experimental results show that H-AIRL achieves higher sample efficiency and more stable learning compared to AIRL. This highlights the benefits of incorporating supervised signals into inverse RL and establishes H-AIRL as a promising framework for tackling challenging, real-world settings.

Paperid: 131, https://arxiv.org/pdf/2511.21216.pdf GitHub

Abstract:
Low-Rank Adaptation (LoRA) offers an efficient paradigm for customizing diffusion models, but its ease of redistribution raises concerns over unauthorized use and the generation of untraceable content. Existing watermarking techniques either target base models or verify LoRA modules themselves, yet they fail to propagate watermarks to generated images, leaving a critical gap in traceability. Moreover, traceability watermarking designed for base models is not tightly coupled with stylization and often introduces visual degradation or high false-positive detection rates. To address these limitations, we propose AuthenLoRA, a unified watermarking framework that embeds imperceptible, traceable watermarks directly into the LoRA training process while preserving stylization quality. AuthenLoRA employs a dual-objective optimization strategy that jointly learns the target style distribution and the watermark-induced distribution shift, ensuring that any image generated with the watermarked LoRA reliably carries the watermark. We further design an expanded LoRA architecture for enhanced multi-scale adaptation and introduce a zero-message regularization mechanism that substantially reduces false positives during watermark verification. Extensive experiments demonstrate that AuthenLoRA achieves high-fidelity stylization, robust watermark propagation, and significantly lower false-positive rates compared with existing approaches. Open-source implementation is available at: https://github.com/ShiFangming0823/AuthenLoRA

Paperid: 132, https://arxiv.org/pdf/2511.21193.pdf GitHub

Abstract:
Recent deep clustering models have produced impressive clustering performance. However, a common issue with existing methods is the disparity between global and local feature structures. While local structures typically show strong consistency and compactness within class samples, global features often present intertwined boundaries and poorly separated clusters. Motivated by this observation, we propose DCBoost, a parameter-free plug-in designed to enhance the global feature structures of current deep clustering models. By harnessing reliable local structural cues, our method aims to elevate clustering performance effectively. Specifically, we first identify high-confidence samples through adaptive $k$-nearest neighbors-based consistency filtering, aiming to select a sufficient number of samples with high label reliability to serve as trustworthy anchors for self-supervision. Subsequently, these samples are utilized to compute a discriminative loss, which promotes both intra-class compactness and inter-class separability, to guide network optimization. Extensive experiments across various benchmark datasets showcase that our DCBoost significantly improves the clustering performance of diverse existing deep clustering models. Notably, our method improves the performance of current state-of-the-art baselines (e.g., ProPos) by more than 3% and amplifies the silhouette coefficient by over $7\times$. Code is available at .

Paperid: 133, https://arxiv.org/pdf/2511.21188.pdf GitHub

Abstract:
Existing prompt learning methods, which are built upon CLIP models, leverage textual tokens as anchors to guide the learnable soft tokens. This guidance improves CLIP generalizations. However, these anchors-static in both value and position-lack cross-task and stage-adaptive flexibility. To address this limitation, we propose AnchorOPT, a dynamic anchor-based prompt learning framework. Specifically, AnchorOPT introduces dynamism in two key dimensions: (i) anchor values eschew handcrafted explicit textual tokens (e.g., "shape", "color"), instead learning dynamically from task-specific data; and (ii) the positional relationship between anchor and soft tokens is no longer fixed but adaptively optimized via a learnable position matrix conditioned on the training stage and task context. Training occurs in two stages: we first learn the anchor tokens, then freeze and transfer them to the second stage for optimization of soft tokens and the position matrix. Extensive experiments demonstrate that using only a simple learnable anchor and position matrix achieves performance comparable to or exceeding some methods incorporating additional learnable modules or regularization techniques. As a plug-and-play module, AnchorOPT integrates seamlessly into existing frameworks, yielding consistent performance gains across diverse datasets. Code is publicly available at https://github.com/zhengli97/ATPrompt.

Paperid: 134, https://arxiv.org/pdf/2511.21161.pdf GitHub

Abstract:
The development of embodied agents for complex commercial environments is hindered by a critical gap in existing robotics datasets and benchmarks, which primarily focus on household or tabletop settings with short-horizon tasks. To address this limitation, we introduce MarketGen, a scalable simulation platform with automatic scene generation for complex supermarket environments. MarketGen features a novel agent-based Procedural Content Generation (PCG) framework. It uniquely supports multi-modal inputs (text and reference images) and integrates real-world design principles to automatically generate complete, structured, and realistic supermarkets. We also provide an extensive and diverse 3D asset library with a total of 1100+ supermarket goods and parameterized facilities assets. Building on this generative foundation, we propose a novel benchmark for assessing supermarket agents, featuring two daily tasks in a supermarket: (1) Checkout Unloading: long-horizon tabletop tasks for cashier agents, and (2) In-Aisle Item Collection: complex mobile manipulation tasks for salesperson agents. We validate our platform and benchmark through extensive experiments, including the deployment of a modular agent system and successful sim-to-real transfer. MarketGen provides a comprehensive framework to accelerate research in embodied AI for complex commercial applications.

Paperid: 135, https://arxiv.org/pdf/2511.21136.pdf GitHub

Abstract:
Human video generation has advanced rapidly with the development of diffusion models, but the high computational cost and substantial memory consumption associated with training these models on high-resolution, multi-frame data pose significant challenges. In this paper, we propose Entropy-Guided Prioritized Progressive Learning (Ent-Prog), an efficient training framework tailored for diffusion models on human video generation. First, we introduce Conditional Entropy Inflation (CEI) to assess the importance of different model components on the target conditional generation task, enabling prioritized training of the most critical components. Second, we introduce an adaptive progressive schedule that adaptively increases computational complexity during training by measuring the convergence efficiency. Ent-Prog reduces both training time and GPU memory consumption while maintaining model performance. Extensive experiments across three datasets, demonstrate the effectiveness of Ent-Prog, achieving up to 2.2$\times$ training speedup and 2.4$\times$ GPU memory reduction without compromising generative performance.

Paperid: 136, https://arxiv.org/pdf/2511.21135.pdf GitHub

Abstract:
Embodied navigation that adheres to social norms remains an open research challenge. Our \textbf{SocialNav} is a foundational model for socially-aware navigation with a hierarchical "brain-action" architecture, capable of understanding high-level social norms and generating low-level, socially compliant trajectories. To enable such dual capabilities, we construct the SocNav Dataset, a large-scale collection of 7 million samples, comprising (1) a Cognitive Activation Dataset providing social reasoning signals such as chain-of-thought explanations and social traversability prediction, and (2) an Expert Trajectories Pyramid aggregating diverse navigation demonstrations from internet videos, simulated environments, and real-world robots. A multi-stage training pipeline is proposed to gradually inject and refine navigation intelligence: we first inject general navigation skills and social norms understanding into the model via imitation learning, and then refine such skills through a deliberately designed Socially-Aware Flow Exploration GRPO (SAFE-GRPO), the first flow-based reinforcement learning framework for embodied navigation that explicitly rewards socially compliant behaviors. SocialNav achieves +38% success rate and +46% social compliance rate compared to the state-of-the-art method, demonstrating strong gains in both navigation performance and social compliance. Our project page: https://amap-eai.github.io/SocialNav/

Paperid: 137, https://arxiv.org/pdf/2511.21132.pdf GitHub

Abstract:
It is well-known that if a network aims to learn how to deblur, it should understand the blur process. Blurring is naturally caused by the convolution of the sharp image with the blur kernel. Thus, allowing the network to learn the blur process in the kernel-level can significantly improve the image deblurring performance. But, current deep networks are still at the pixel-level learning stage, either performing end-to-end pixel-level restoration or stage-wise pseudo kernel-level restoration, failing to enable the deblur model to understand the essence of the blur. To this end, we propose Fourier Kernel Estimator (FKE), which considers the activation operation in Fourier space and converts the convolution problem in the spatial domain to a multiplication problem in Fourier space. Our FKE, jointly optimized with the deblur model, enables the network to learn the kernel-level blur process with low complexity and without any additional supervision. Furthermore, we change the convolution object of the kernel from ``image" to network extracted ``feature", whose rich semantic and structural information is more suitable to blur process learning. With the convolution of the feature and the estimated kernel, our model can learn the essence of blur in kernel-level. To further improve the efficiency of feature extraction, we design a decoupled multi-scale architecture with multiple hierarchical sub-unets with a reversible strategy, which allows better multi-scale encoding and decoding in low training memory. Extensive experiments indicate that our method achieves state-of-the-art motion deblurring results and show potential for handling other kernel-related problems. Analysis also shows our kernel estimator is able to learn physically meaningful kernels. The code will be available at https://github.com/DeepMed-Lab-ECNU/Single-Image-Deblur.

Paperid: 138, https://arxiv.org/pdf/2511.21129.pdf GitHub

Abstract:
We tackle the dual challenges of video understanding and controllable video generation within a unified diffusion framework. Our key insights are two-fold: geometry-only cues (e.g., depth, edges) are insufficient: they specify layout but under-constrain appearance, materials, and illumination, limiting physically meaningful edits such as relighting or material swaps and often causing temporal drift. Enriching the model with additional graphics-based modalities (intrinsics and semantics) provides complementary constraints that both disambiguate understanding and enable precise, predictable control during generation. However, building a single model that uses many heterogeneous cues introduces two core difficulties. Architecturally, the model must accept any subset of modalities, remain robust to missing inputs, and inject control signals without sacrificing temporal consistency. Data-wise, training demands large-scale, temporally aligned supervision that ties real videos to per-pixel multimodal annotations. We then propose CtrlVDiff, a unified diffusion model trained with a Hybrid Modality Control Strategy (HMCS) that routes and fuses features from depth, normals, segmentation, edges, and graphics-based intrinsics (albedo, roughness, metallic), and re-renders videos from any chosen subset with strong temporal coherence. To enable this, we build MMVideo, a hybrid real-and-synthetic dataset aligned across modalities and captions. Across understanding and generation benchmarks, CtrlVDiff delivers superior controllability and fidelity, enabling layer-wise edits (relighting, material adjustment, object insertion) and surpassing state-of-the-art baselines while remaining robust when some modalities are unavailable.

Paperid: 139, https://arxiv.org/pdf/2511.21122.pdf GitHub

Abstract:
Large-scale vision generative models, including diffusion and flow models, have demonstrated remarkable performance in visual generation tasks. However, transferring these pre-trained models to downstream tasks often results in significant parameter redundancy. In this paper, we propose EntPruner, an entropy-guided automatic progressive pruning framework for diffusion and flow models. First, we introduce entropy-guided pruning, a block-level importance assessment strategy specifically designed for generative models. Unlike discriminative models, generative models require preserving the diversity and condition-fidelity of the output distribution. As the importance of each module can vary significantly across downstream tasks, EntPruner prioritizes pruning of less important blocks using data-dependent Conditional Entropy Deviation (CED) as a guiding metric. CED quantifies how much the distribution diverges from the learned conditional data distribution after removing a block. Second, we propose a zero-shot adaptive pruning framework to automatically determine when and how much to prune during training. This dynamic strategy avoids the pitfalls of one-shot pruning, mitigating mode collapse, and preserving model performance. Extensive experiments on DiT and SiT models demonstrate the effectiveness of EntPruner, achieving up to 2.22$\times$ inference speedup while maintaining competitive generation quality on ImageNet and three downstream datasets.

Paperid: 140, https://arxiv.org/pdf/2511.21120.pdf GitHub

Abstract:
Understanding how chemical perturbations propagate through biological systems is essential for robust molecular property prediction. While most existing methods focus on chemical structures alone, recent advances highlight the crucial role of cellular responses such as morphology and gene expression in shaping drug effects. However, current cell-aware approaches face two key limitations: (1) modality incompleteness in external biological data, and (2) insufficient modeling of hierarchical dependencies across molecular, cellular, and genomic levels. We propose CHMR (Cell-aware Hierarchical Multi-modal Representations), a robust framework that jointly models local-global dependencies between molecules and cellular responses and captures latent biological hierarchies via a novel tree-structured vector quantization module. Evaluated on nine public benchmarks spanning 728 tasks, CHMR outperforms state-of-the-art baselines, yielding average improvements of 3.6% on classification and 17.2% on regression tasks. These results demonstrate the advantage of hierarchy-aware, multimodal learning for reliable and biologically grounded molecular representations, offering a generalizable framework for integrative biomedical modeling. The code is in https://github.com/limengran98/CHMR.

Paperid: 141, https://arxiv.org/pdf/2511.21113.pdf GitHub

Abstract:
In controllable driving-scene reconstruction and 3D scene generation, maintaining geometric fidelity while synthesizing visually plausible appearance under large viewpoint shifts is crucial. However, effective fusion of geometry-based 3DGS and appearance-driven diffusion models faces inherent challenges, as the absence of pixel-wise, 3D-consistent editing criteria often leads to over-restoration and geometric drift. To address these issues, we introduce \textbf{FaithFusion}, a 3DGS-diffusion fusion framework driven by pixel-wise Expected Information Gain (EIG). EIG acts as a unified policy for coherent spatio-temporal synthesis: it guides diffusion as a spatial prior to refine high-uncertainty regions, while its pixel-level weighting distills the edits back into 3DGS. The resulting plug-and-play system is free from extra prior conditions and structural modifications.Extensive experiments on the Waymo dataset demonstrate that our approach attains SOTA performance across NTA-IoU, NTL-IoU, and FID, maintaining an FID of 107.47 even at 6 meters lane shift. Our code is available at https://github.com/wangyuanbiubiubiu/FaithFusion.

Paperid: 142, https://arxiv.org/pdf/2511.21097.pdf GitHub

Abstract:
Iris authentication algorithms have achieved impressive recognition performance, making them highly promising for real-world applications such as border control, citizen identification, and both criminal investigations and commercial systems. However, their robustness is still challenged by variations in rotation, scale, specular reflections, and defocus blur. In addition, most existing approaches rely on straightforward point-to-point comparisons, typically using cosine or L2 distance, without effectively leveraging the spatio-spatial-temporal structure of iris patterns. To address these limitations, we propose a novel and generalized matching pipeline that learns rich spatio-spatial-temporal representations of iris features. Our approach first splits each iris image along one dimension, generating a sequence of sub-images that serve as input to a 3D-CNN, enabling the network to capture both spatial and spatio-spatial-temporal cues. To further enhance the modeling of spatio-spatial-temporal feature dynamics, we train the model in curriculum manner. This design allows the network to embed temporal dependencies directly into the feature space, improving discriminability in the deep metric domain. The framework is trained end-to-end with triplet and ArcFace loss in a curriculum manner, enforcing highly discriminative embeddings despite challenges like rotation, scale, reflections, and blur. This design yields a robust and generalizable solution for iris authentication.Github code: https://github.com/GeetanjaliGTZ/CLRecogEye

Paperid: 143, https://arxiv.org/pdf/2511.21066.pdf GitHub

Abstract:
Detecting sarcasm remains a challenging task in the areas of Natural Language Processing (NLP) despite recent advances in neural network approaches. Currently, Pre-trained Language Models (PLMs) and Large Language Models (LLMs) are the preferred approach for sarcasm detection. However, the complexity of sarcastic text, combined with linguistic diversity and cultural variation across communities, has made the task more difficult even for PLMs and LLMs. Beyond that, those models also exhibit unreliable detection of words or tokens that require extra grounding for analysis. Building on a state-of-the-art prompting method in LLMs for sarcasm detection called Pragmatic Metacognitive Prompting (PMP), we introduce a retrieval-aware approach that incorporates retrieved contextual information for each target text. Our pipeline explores two complementary ways to provide context: adding non-parametric knowledge using web-based retrieval when the model lacks necessary background, and eliciting the model's own internal knowledge for a self-knowledge awareness strategy. We evaluated our approach with three datasets, such as Twitter Indonesia Sarcastic, SemEval-2018 Task 3, and MUStARD. Non-parametric retrieval resulted in a significant 9.87% macro-F1 improvement on Twitter Indonesia Sarcastic compared to the original PMP method. Self-knowledge retrieval improves macro-F1 by 3.29% on Semeval and by 4.08% on MUStARD. These findings highlight the importance of context in enhancing LLMs performance in sarcasm detection task, particularly the involvement of culturally specific slang, references, or unknown terms to the LLMs. Future work will focus on optimizing the retrieval of relevant contextual information and examining how retrieval quality affects performance. The experiment code is available at: https://github.com/wllchrst/sarcasm-detection_pmp_knowledge-base.

Paperid: 144, https://arxiv.org/pdf/2511.21063.pdf GitHub

Abstract:
We propose a novel randomized algorithm for constructing binary neural networks with tunable accuracy. This approach is motivated by hyperdimensional computing (HDC), which is a brain-inspired paradigm that leverages high-dimensional vector representations, offering efficient hardware implementation and robustness to model corruptions. Unlike traditional low-precision methods that use quantization, we consider binary embeddings of data as points in the hypercube equipped with the Hamming distance. We propose a novel family of floating-point neural networks, G-Nets, which are general enough to mimic standard network layers. Each floating-point G-Net has a randomized binary embedding, an embedded hyperdimensional (EHD) G-Net, that retains the accuracy of its floating-point counterparts, with theoretical guarantees, due to the concentration of measure. Empirically, our binary models match convolutional neural network accuracies and outperform prior HDC models by large margins, for example, we achieve almost 30\% higher accuracy on CIFAR-10 compared to prior HDC models. G-Nets are a theoretically justified bridge between neural networks and randomized binary neural networks, opening a new direction for constructing robust binary/quantized deep learning models. Our implementation is available at https://github.com/GNet2025/GNet.

Paperid: 145, https://arxiv.org/pdf/2511.21038.pdf GitHub GitHub

Abstract:
Can in-context learning (ICL) override pre-trained label semantics, or does it merely refine an existing semantic backbone? We address this question by treating LLMs as prompt-induced classifiers and contrasting their behavior under \emph{natural} demonstrations (with correct labels) and \emph{inverted} demonstrations (systematically flipping label meanings). We decompose ICL behavior into three alignment metrics (truth, prior, and prompt alignment) and introduce a semantic override rate, defined as correctness under flipped semantics. Across eight classification tasks and eight open-source LLMs (1--12B parameters), we find consistent evidence for a semantic anchor view. With natural demonstrations, ICL improves accuracy while maintaining strong prior alignment; most correct predictions coincide with zero-shot behavior, even when the prior is weak. With inverted demonstrations, models cannot learn coherent anti-semantic classifiers: prompt alignment increases only by sacrificing accuracy, and semantic override rates remain exactly zero in our few-shot 1--12B setting. Rather than flexibly remapping label meanings, ICL primarily adjusts how inputs project onto stable semantic directions learned during pre-training, clarifying fundamental limits of few-shot prompting and suggesting that overriding label semantics at these scales requires interventions beyond ICL. All code is available at: https://github.com/AnanthaPadmanaban-KrishnaKumar/semantic-anchors-icl.

Paperid: 146, https://arxiv.org/pdf/2511.21032.pdf GitHub

Abstract:
Temporal distribution shift (TDS) erodes the long-term accuracy of recommender systems, yet industrial practice still relies on periodic incremental training, which struggles to capture both stable and transient patterns. Existing approaches such as invariant learning and self-supervised learning offer partial solutions but often suffer from unstable temporal generalization, representation collapse, or inefficient data utilization. To address these limitations, we propose ELBO$_\text{TDS}$, a probabilistic framework that integrates seamlessly into industry-scale incremental learning pipelines. First, we identify key shifting factors through statistical analysis of real-world production data and design a simple yet effective data augmentation strategy that resamples these time-varying factors to extend the training support. Second, to harness the benefits of this extended distribution while preventing representation collapse, we model the temporal recommendation scenario using a causal graph and derive a self-supervised variational objective, ELBO$_\text{TDS}$, grounded in the causal structure. Extensive experiments supported by both theoretical and empirical analysis demonstrate that our method achieves superior temporal generalization, yielding a 2.33\% uplift in GMV per user and has been successfully deployed in Shopee Product Search. Code is available at https://github.com/FuCongResearchSquad/ELBO4TDS.

Paperid: 147, https://arxiv.org/pdf/2511.21028.pdf GitHub

Abstract:
We propose deep parameter interpolation (DPI), a general-purpose method for transforming an existing deep neural network architecture into one that accepts an additional scalar input. Recent deep generative models, including diffusion models and flow matching, employ a single neural network to learn a time- or noise level-dependent vector field. Designing a network architecture to accurately represent this vector field is challenging because the network must integrate information from two different sources: a high-dimensional vector (usually an image) and a scalar. Common approaches either encode the scalar as an additional image input or combine scalar and vector information in specific network components, which restricts architecture choices. Instead, we propose to maintain two learnable parameter sets within a single network and to introduce the scalar dependency by dynamically interpolating between the parameter sets based on the scalar value during training and sampling. DPI is a simple, architecture-agnostic method for adding scalar dependence to a neural network. We demonstrate that our method improves denoising performance and enhances sample quality for both diffusion and flow matching models, while achieving computational efficiency comparable to standard scalar conditioning techniques. Code is available at https://github.com/wustl-cig/parameter_interpolation.

Paperid: 148, https://arxiv.org/pdf/2511.21025.pdf GitHub

Abstract:
Image captions serve as efficient surrogates for visual content in multimodal systems such as retrieval, recommendation, and multi-step agentic inference pipelines. Yet current evaluation practices miss a fundamental question: Can captions stand-in for images in real downstream tasks? We propose a utility-based benchmark, CaptionQA, to evaluate model-generated captions, where caption quality is measured by how well it supports downstream tasks. CaptionQA is an extensible domain-dependent benchmark covering 4 domains--Natural, Document, E-commerce, and Embodied AI--each with fine-grained taxonomies (25 top-level and 69 subcategories) that identify useful information for domain-specific tasks. CaptionQA builds 33,027 densely annotated multiple-choice questions (50.3 per image on average) that explicitly require visual information to answer, providing a comprehensive probe of caption utility. In our evaluation protocol, an LLM answers these questions using captions alone, directly measuring whether captions preserve image-level utility and are utilizable by a downstream LLM. Evaluating state-of-the-art MLLMs reveals substantial gaps between the image and its caption utility. Notably, models nearly identical on traditional image-QA benchmarks lower by up to 32% in caption utility. We release CaptionQA along with an open-source pipeline for extension to new domains. The code is available at https://github.com/bronyayang/CaptionQA.

Paperid: 149, https://arxiv.org/pdf/2511.20989.pdf GitHub

Abstract:
Referring Camouflaged Object Detection (Ref-COD) segments specified camouflaged objects in a scene by leveraging a small set of referring images. Though effective, current systems adopt a dual-branch design that requires reference images at test time, which limits deployability and adds latency and data-collection burden. We introduce a Ref-COD framework that distills references into a class-prototype memory during training and synthesizes a reference vector at inference via a query-conditioned mixture of prototypes. Concretely, we maintain an EMA-updated prototype per category and predict mixture weights from the query to produce a guidance vector without any test-time references. To bridge the representation gap between reference statistics and camouflaged query features, we propose a bidirectional attention alignment module that adapts both the query features and the class representation. Thus, our approach yields a simple, efficient path to Ref-COD without mandatory references. We evaluate the proposed method on the large-scale R2C7K benchmark. Extensive experiments demonstrate competitive or superior performance of the proposed method compared with recent state-of-the-arts. Code is available at https://github.com/yuhuan-wu/RefOnce.

Paperid: 150, https://arxiv.org/pdf/2511.20972.pdf GitHub

Abstract:
With recent advances in automatic speech recognition (ASR), large language models (LLMs), and text-to-speech (TTS) technologies, spoken dialogue systems (SDS) have become widely accessible. However, most existing SDS are limited to conventional spoken responses. We present SingingSDS, a cascaded SDS that responds through singing rather than speaking, fostering more affective, memorable, and pleasurable interactions in character-based roleplay and interactive entertainment scenarios. SingingSDS employs a modular ASR-LLM-SVS pipeline and supports a wide range of configurations across character personas, ASR and LLM backends, SVS models, melody sources, and voice profiles, tailored to different needs in terms of latency, quality, and musical style. SingingSDS is available as a plug-and-play web demo, featuring modular, open-source code that supports customization and extension. Demo: https://huggingface.co/spaces/espnet/SingingSDS. Code: https://github.com/SingingSDS/SingingSDS.

Paperid: 151, https://arxiv.org/pdf/2511.20956.pdf GitHub

Abstract:
Automated radiology report generation (RRG) for breast ultrasound (BUS) is limited by the lack of paired image-report datasets and the risk of hallucinations from large language models. We propose BUSTR, a multitask vision-language framework that generates BUS reports without requiring paired image-report supervision. BUSTR constructs reports from structured descriptors (e.g., BI-RADS, pathology, histology) and radiomics features, learns descriptor-aware visual representations with a multi-head Swin encoder trained using a multitask loss over dataset-specific descriptor sets, and aligns visual and textual tokens via a dual-level objective that combines token-level cross-entropy with a cosine-similarity alignment loss between input and output representations. We evaluate BUSTR on two public BUS datasets, BrEaST and BUS-BRA, which differ in size and available descriptors. Across both datasets, BUSTR consistently improves standard natural language generation metrics and clinical efficacy metrics, particularly for key targets such as BI-RADS category and pathology. Our results show that this descriptor-aware vision model, trained with a combined token-level and alignment loss, improves both automatic report metrics and clinical efficacy without requiring paired image-report data. The source code can be found at https://github.com/AAR-UNLV/BUSTR

Paperid: 152, https://arxiv.org/pdf/2511.20955.pdf GitHub

Abstract:
This empirical investigation elucidates the limitations of deterministic, unidimensional productivity heuristics by operationalizing the SPACE framework through extensive repository mining. Utilizing a dataset derived from open-source repositories, the study employs rigorous statistical methodologies including Generalized Linear Mixed Models (GLMM) and RoBERTa-based sentiment classification to synthesize a holistic, multi-faceted productivity metric. Analytical results reveal a statistically significant positive correlation between negative affective states and commit frequency, implying a cycle of iterative remediation driven by frustration. Furthermore, the investigation has demonstrated that analyzing the topology of contributor interactions yields superior fidelity in mapping collaborative dynamics compared to traditional volume-based metrics. Ultimately, this research posits a Composite Productivity Score (CPS) to address the heterogeneity of developer efficacy.

Paperid: 153, https://arxiv.org/pdf/2511.20937.pdf GitHub

Abstract:
Embodied cognition argues that intelligence arises from sensorimotor interaction rather than passive observation. It raises an intriguing question: do modern vision-language models (VLMs), trained largely in a disembodied manner, exhibit signs of embodied cognition? We introduce ENACT, a benchmark that casts evaluation of embodied cognition as world modeling from egocentric interaction in a visual question answering (VQA) format. Framed as a partially observable Markov decision process (POMDP) whose actions are scene graph changes, ENACT comprises two complementary sequence reordering tasks: forward world modeling (reorder shuffled observations given actions) and inverse world modeling (reorder shuffled actions given observations). While conceptually simple, solving these tasks implicitly demands capabilities central to embodied cognition-affordance recognition, action-effect reasoning, embodied awareness, and interactive, long-horizon memory from partially observable egocentric input, while avoiding low-level image synthesis that could confound the evaluation. We provide a scalable pipeline that synthesizes QA pairs from robotics simulation (BEHAVIOR) and evaluates models on 8,972 QA pairs spanning long-horizon home-scale activities. Experiments reveal a performance gap between frontier VLMs and humans that widens with interaction horizon. Models consistently perform better on the inverse task than the forward one and exhibit anthropocentric biases, including a preference for right-handed actions and degradation when camera intrinsics or viewpoints deviate from human vision. Website at https://enact-embodied-cognition.github.io/.

Paperid: 154, https://arxiv.org/pdf/2511.20928.pdf GitHub

Abstract:
We propose a smooth regularization technique that instills a strong temporal inductive bias in video recognition models, particularly benefiting lightweight architectures. Our method encourages smoothness in the intermediate-layer embeddings of consecutive frames by modeling their changes as a Gaussian Random Walk (GRW). This penalizes abrupt representational shifts, thereby promoting low-acceleration solutions that better align with the natural temporal coherence inherent in videos. By leveraging this enforced smoothness, lightweight models can more effectively capture complex temporal dynamics. Applied to such models, our technique yields a 3.8% to 6.4% accuracy improvement on Kinetics-600. Notably, the MoViNets model family trained with our smooth regularization improves the current state of the art by 3.8% to 6.1% within their respective FLOP constraints, while MobileNetV3 and the MoViNets-Stream family achieve gains of 4.9% to 6.4% over prior state-of-the-art models with comparable memory footprints. Our code and models are available at https://github.com/gilgoldm/grw-smoothing.

Paperid: 155, https://arxiv.org/pdf/2511.20924.pdf GitHub

Abstract:
Implicit Neural Representations (INRs) have become an essential tool for modeling continuous 2D images, enabling high-fidelity reconstruction, super-resolution, and compression. Popular architectures such as SIREN, WIRE, and FINER demonstrate the potential of INR for capturing fine-grained image details. However, traditional INRs often lack explicit geometric structure and have limited capabilities for local editing or integration with physical simulation, restricting their applicability in dynamic or interactive settings. To address these limitations, we propose GaINeR: Geometry-Aware Implicit Network Representation, a novel framework for 2D images that combines trainable Gaussian distributions with a neural network-based INR. For a given image coordinate, the model retrieves the K nearest Gaussians, aggregates distance-weighted embeddings, and predicts the RGB value via a neural network. This design enables continuous image representation, interpretable geometric structure, and flexible local editing, providing a foundation for physically aware and interactive image manipulation. The official implementation of our method is publicly available at https://github.com/WJakubowska/GaINeR.

Paperid: 156, https://arxiv.org/pdf/2511.20893.pdf GitHub

Abstract:
We study streaming data with categorical features where the vocabulary of categorical feature values is changing and can even grow unboundedly over time. Feature hashing is commonly used as a pre-processing step to map these categorical values into a feature space of fixed size before learning their embeddings. While these methods have been developed and evaluated for offline or batch settings, in this paper we consider online settings. We show that deterministic embeddings are sensitive to the arrival order of categories and suffer from forgetting in online learning, leading to performance deterioration. To mitigate this issue, we propose a probabilistic hash embedding (PHE) model that treats hash embeddings as stochastic and applies Bayesian online learning to learn incrementally from data. Based on the structure of PHE, we derive a scalable inference algorithm to learn model parameters and infer/update the posteriors of hash embeddings and other latent variables. Our algorithm (i) can handle an evolving vocabulary of categorical items, (ii) is adaptive to new items without forgetting old items, (iii) is implementable with a bounded set of parameters that does not grow with the number of distinct observed values on the stream, and (iv) is invariant to the item arrival order. Experiments in classification, sequence modeling, and recommendation systems in online learning setups demonstrate the superior performance of PHE while maintaining high memory efficiency (consumes as low as 2~4 memory of a one-hot embedding table). Supplementary materials are at https://github.com/aodongli/probabilistic-hash-embeddings

Paperid: 157, https://arxiv.org/pdf/2511.20867.pdf GitHub

Abstract:
With the rise of large language models (LLMs), generative engines are becoming powerful alternatives to traditional search, reshaping retrieval tasks. In e-commerce, for instance, conversational shopping agents now guide consumers to relevant products. This shift has created the need for generative engine optimization (GEO)--improving content visibility and relevance for generative engines. Yet despite its growing importance, current GEO practices are ad hoc, and their impacts remain poorly understood, especially in e-commerce. We address this gap by introducing E-GEO, the first benchmark built specifically for e-commerce GEO. E-GEO contains over 7,000 realistic, multi-sentence consumer product queries paired with relevant listings, capturing rich intent, constraints, preferences, and shopping contexts that existing datasets largely miss. Using this benchmark, we conduct the first large-scale empirical study of e-commerce GEO, evaluating 15 common rewriting heuristics and comparing their empirical performance. To move beyond heuristics, we further formulate GEO as a tractable optimization problem and develop a lightweight iterative prompt-optimization algorithm that can significantly outperform these baselines. Surprisingly, the optimized prompts reveal a stable, domain-agnostic pattern--suggesting the existence of a "universally effective" GEO strategy. Our data and code are publicly available at https://github.com/psbagga17/E-GEO.

Paperid: 158, https://arxiv.org/pdf/2511.20865.pdf GitHub

Abstract:
We propose a method which, given a sequence of stereo foggy images, estimates the parameters of a fog model and updates them dynamically. In contrast with previous approaches, which estimate the parameters sequentially and thus are prone to error propagation, our algorithm estimates all the parameters simultaneously by solving a novel optimisation problem. By assuming that fog is only locally homogeneous, our method effectively handles real-world fog, which is often globally inhomogeneous. The proposed algorithm can be easily used as an add-on module in existing visual Simultaneous Localisation and Mapping (SLAM) or odometry systems in the presence of fog. In order to assess our method, we also created a new dataset, the Stereo Driving In Real Fog (SDIRF), consisting of high-quality, consecutive stereo frames of real, foggy road scenes under a variety of visibility conditions, totalling over 40 minutes and 34k frames. As a first-of-its-kind, SDIRF contains the camera's photometric parameters calibrated in a lab environment, which is a prerequisite for correctly applying the atmospheric scattering model to foggy images. The dataset also includes the counterpart clear data of the same routes recorded in overcast weather, which is useful for companion work in image defogging and depth reconstruction. We conducted extensive experiments using both synthetic foggy data and real foggy sequences from SDIRF to demonstrate the superiority of the proposed algorithm over prior methods. Our method not only produces the most accurate estimates on synthetic data, but also adapts better to real fog. We make our code and SDIRF publicly available\footnote{https://github.com/SenseRoboticsLab/estimating-fog-parameters} to the community with the aim of advancing the research on visual perception in fog.

Paperid: 159, https://arxiv.org/pdf/2511.20841.pdf GitHub

Abstract:
To manipulate objects in novel, unstructured environments, robots need task-oriented grasps that target object parts based on the given task. Geometry-based methods often struggle with visually defined parts, occlusions, and unseen objects. We introduce OVAL-Grasp, a zero-shot open-vocabulary approach to task-oriented, affordance based grasping that uses large-language models and vision-language models to allow a robot to grasp objects at the correct part according to a given task. Given an RGB image and a task, OVAL-Grasp identifies parts to grasp or avoid with an LLM, segments them with a VLM, and generates a 2D heatmap of actionable regions on the object. During our evaluations, we found that our method outperformed two task oriented grasping baselines on experiments with 20 household objects with 3 unique tasks for each. OVAL-Grasp successfully identifies and segments the correct object part 95% of the time and grasps the correct actionable area 78.3% of the time in real-world experiments with the Fetch mobile manipulator. Additionally, OVAL-Grasp finds correct object parts under partial occlusions, demonstrating a part selection success rate of 80% in cluttered scenes. We also demonstrate OVAL-Grasp's efficacy in scenarios that rely on visual features for part selection, and show the benefit of a modular design through our ablation experiments. Our project webpage is available at https://ekjt.github.io/OVAL-Grasp/

Paperid: 160, https://arxiv.org/pdf/2511.20839.pdf GitHub

Abstract:
We present Primal, a deterministic feature mapping framework that harnesses the number-theoretic independence of prime square roots to construct robust, tunable vector representations. Diverging from standard stochastic projections (e.g., Random Fourier Features), our method exploits the Besicovitch property to create irrational frequency modulations that guarantee infinite non-repeating phase trajectories. We formalize two distinct algorithmic variants: (1) StaticPrime, a sequence generation method that produces temporal position encodings empirically approaching the theoretical Welch bound for quasi-orthogonality; and (2) DynamicPrime, a tunable projection layer for input-dependent feature mapping. A central novelty of the dynamic framework is its ability to unify two disparate mathematical utility classes through a single scaling parameter σ. In the low-frequency regime, the method acts as an isometric kernel map, effectively linearizing non-convex geometries (e.g., spirals) to enable high-fidelity signal reconstruction and compressive sensing. Conversely, the high-frequency regime induces chaotic phase wrapping, transforming the projection into a maximum-entropy one-way hash suitable for Hyperdimensional Computing and privacy-preserving Split Learning. Empirical evaluations demonstrate that our framework yields superior orthogonality retention and distribution tightness compared to normalized Gaussian baselines, establishing it as a computationally efficient, mathematically rigorous alternative to random matrix projections. The code is available at https://github.com/VladimerKhasia/primal

Paperid: 161, https://arxiv.org/pdf/2511.20836.pdf GitHub GitHub

Abstract:
As language models (LMs) are increasingly adopted across domains, high-quality benchmarking frameworks that accurately estimate performance are essential for guiding deployment decisions. While frameworks such as Holistic Evaluation of Language Models (HELM) enable broad evaluation across tasks, they often rely on fixed prompts that fail to generalize across LMs, yielding unrepresentative performance estimates. Unless we approximate each LM's ceiling (maximum achievable via changes to the prompt), we risk underestimating performance. Declarative prompting frameworks, such as DSPy, offer a scalable alternative to manual prompt engineering by crafting structured prompts that can be optimized per task. However, such frameworks have not been systematically evaluated across established benchmarks. We present a reproducible DSPy+HELM framework that introduces structured prompting methods which elicit reasoning, enabling more accurate LM benchmarking. Using four prompting methods, we evaluate four frontier LMs across seven benchmarks (general/medical domain) against existing HELM baseline scores. We find that without structured prompting: (i) HELM underestimates LM performance (by 4% average), (ii) performance estimates vary more across benchmarks ($+$2% standard deviation), (iii) performance gaps are misrepresented (leaderboard rankings flip on 3/7 benchmarks), and (iv) introducing chain-of-thought reduces LM sensitivity to prompt design (smaller $Δ$ across prompts). To our knowledge, this is the first benchmarking study to systematically integrate structured prompting into an established evaluation framework, demonstrating how scalable performance-ceiling approximation yields more robust, decision-useful benchmarks. We open-source (i) DSPy+HELM Integration (https://github.com/stanford-crfm/helm/pull/3893) and (ii) Prompt Optimization Pipeline (https://github.com/StanfordMIMI/dspy-helm).

Paperid: 162, https://arxiv.org/pdf/2511.20830.pdf GitHub

Abstract:
The solar wind, a continuous outflow of charged particles from the Sun's corona, shapes the heliosphere and impacts space systems near Earth. Accurate prediction of features such as high-speed streams and coronal mass ejections is critical for space weather forecasting, but traditional three-dimensional magnetohydrodynamic (MHD) models are computationally expensive, limiting rapid exploration of boundary condition uncertainties. We introduce the first autoregressive machine learning surrogate for steady-state solar wind radial velocity using the Spherical Fourier Neural Operator (SFNO). By predicting a limited radial range and iteratively propagating the solution outward, the model improves accuracy in distant regions compared to a single-step approach. Compared with the numerical HUX surrogate, SFNO demonstrates superior or comparable performance while providing a flexible, trainable, and data-driven alternative, establishing a novel methodology for high-fidelity solar wind modeling. The source code and additional visual results are available at https://github.com/rezmansouri/solarwind-sfno-velocity-autoregressive.

Paperid: 163, https://arxiv.org/pdf/2511.20798.pdf GitHub

Abstract:
Recent advances in mechanistic interpretability have revealed that large language models (LLMs) develop internal representations corresponding not only to concrete entities but also distinct, human-understandable abstract concepts and behaviour. Moreover, these hidden features can be directly manipulated to steer model behaviour. However, it remains an open question whether this phenomenon is unique to models trained on inherently structured data (ie. language, images) or if it is a general property of foundation models. In this work, we investigate the internal representations of a large physics-focused foundation model. Inspired by recent work identifying single directions in activation space for complex behaviours in LLMs, we extract activation vectors from the model during forward passes over simulation datasets for different physical regimes. We then compute "delta" representations between the two regimes. These delta tensors act as concept directions in activation space, encoding specific physical features. By injecting these concept directions back into the model during inference, we can steer its predictions, demonstrating causal control over physical behaviours, such as inducing or removing some particular physical feature from a simulation. These results suggest that scientific foundation models learn generalised representations of physical principles. They do not merely rely on superficial correlations and patterns in the simulations. Our findings open new avenues for understanding and controlling scientific foundation models and has implications for AI-enabled scientific discovery.

Paperid: 164, https://arxiv.org/pdf/2511.20793.pdf GitHub

Abstract:
Liver tumor segmentation, dynamic enhancement regression, and classification are critical for clinical assessment and diagnosis. However, no prior work has attempted to achieve these tasks simultaneously in an end-to-end framework, primarily due to the lack of an effective framework that captures inter-task relevance for mutual improvement and the absence of a mechanism to extract dynamic MRI information effectively. To address these challenges, we propose the Multi-Task Interaction adversarial learning Network (MTI-Net), a novel integrated framework designed to tackle these tasks simultaneously. MTI-Net incorporates Multi-domain Information Entropy Fusion (MdIEF), which utilizes entropy-aware, high-frequency spectral information to effectively integrate features from both frequency and spectral domains, enhancing the extraction and utilization of dynamic MRI data. The network also introduces a task interaction module that establishes higher-order consistency between segmentation and regression, thus fostering inter-task synergy and improving overall performance. Additionally, we designed a novel task-driven discriminator (TDD) to capture internal high-order relationships between tasks. For dynamic MRI information extraction, we employ a shallow Transformer network to perform positional encoding, which captures the relationships within dynamic MRI sequences. In experiments on a dataset of 238 subjects, MTI-Net demonstrates high performance across multiple tasks, indicating its strong potential for assisting in the clinical assessment of liver tumors. The code is available at: https://github.com/xiaojiao929/MTI-Net.

Paperid: 165, https://arxiv.org/pdf/2511.20785.pdf GitHub

Abstract:
Large multimodal models (LMMs) have shown great potential for video reasoning with textual Chain-of-Thought. However, they remain vulnerable to hallucinations, especially when processing long-form videos where evidence is sparse and temporally dispersed. Inspired by how humans comprehend long videos - by first skimming globally and then examining relevant clips for details - we introduce LongVT, an end-to-end agentic framework that enables "Thinking with Long Videos" via interleaved Multimodal Chain-of-Tool-Thought. Specifically, we exploit LMMs' inherent temporal grounding ability as a native video cropping tool to zoom in on a specific video clip and resample finer-grained video frames. This global-to-local reasoning loop continues until answers are grounded in retrieved visual evidence. Given the scarcity of fine-grained question-answering (QA) data for the long video reasoning task, we curate and will release a data suite named VideoSIAH to facilitate both training and evaluation. Specifically, our training dataset consists of 247.9K samples for tool-integrated cold-start supervised fine-tuning, 1.6K samples for agentic reinforcement learning, and 15.4K samples for agentic reinforcement fine-tuning, respectively. Our evaluation benchmark consists of 1,280 QA pairs that are carefully curated through a semi-automatic data pipeline with human-in-the-loop validation. With a meticulously designed three-stage training strategy and extensive empirical validation, LongVT consistently outperforms existing strong baselines across four challenging long-video understanding and reasoning benchmarks. Our codes, data, and model checkpoints are publicly available at https://github.com/EvolvingLMMs-Lab/LongVT .

Paperid: 166, https://arxiv.org/pdf/2511.20766.pdf GitHub

Abstract:
Reliability is key to realizing the promise of autonomous UI-Agents, multimodal agents that directly interact with apps in the same manner as humans, as users must be able to trust an agent to complete a given task. Current evaluations rely on fixed environments, often clones of existing apps, which are limited in that they can only shed light on whether or how often an agent can complete a task within a specific environment. When deployed however, agents are likely to encounter variations in app design and content that can affect an agent's ability to complete a task. To address this blind spot of measuring agent reliability across app variations, we develop OpenApps, a light-weight open-source ecosystem with six apps (messenger, calendar, maps, etc.) that are configurable in appearance and content. OpenApps requires just a single CPU to run, enabling easy generation and deployment of thousands of versions of each app. Specifically, we run more than 10,000 independent evaluations to study reliability across seven leading multimodal agents. We find that while standard reliability within a fixed app is relatively stable, reliability can vary drastically when measured across app variations. Task success rates for many agents can fluctuate by more than $50\%$ across app variations. For example, Kimi-VL-3B's average success across all tasks fluctuates from $63\%$ to just $4\%$ across app versions. We also find agent behaviors such as looping or hallucinating actions can differ drastically depending on the environment configuration. These initial findings highlight the importance of measuring reliability along this new dimension of app variations. OpenApps is available at https://facebookresearch.github.io/OpenApps/

Paperid: 167, https://arxiv.org/pdf/2511.20703.pdf GitHub

Abstract:
Recent advances in Large Language Models (LLMs) have sparked concerns over their potential to acquire and misuse dangerous or high-risk capabilities, posing frontier risks. Current safety evaluations primarily test for what a model \textit{can} do - its capabilities - without assessing what it $\textit{would}$ do if endowed with high-risk capabilities. This leaves a critical blind spot: models may strategically conceal capabilities or rapidly acquire them, while harboring latent inclinations toward misuse. We argue that $\textbf{propensity}$ - the likelihood of a model to pursue harmful actions if empowered - is a critical, yet underexplored, axis of safety evaluation. We present $\textbf{PropensityBench}$, a novel benchmark framework that assesses the proclivity of models to engage in risky behaviors when equipped with simulated dangerous capabilities using proxy tools. Our framework includes 5,874 scenarios with 6,648 tools spanning four high-risk domains: cybersecurity, self-proliferation, biosecurity, and chemical security. We simulate access to powerful capabilities via a controlled agentic environment and evaluate the models' choices under varying operational pressures that reflect real-world constraints or incentives models may encounter, such as resource scarcity or gaining more autonomy. Across open-source and proprietary frontier models, we uncover 9 alarming signs of propensity: models frequently choose high-risk tools when under pressure, despite lacking the capability to execute such actions unaided. These findings call for a shift from static capability audits toward dynamic propensity assessments as a prerequisite for deploying frontier AI systems safely. Our code is available at https://github.com/scaleapi/propensity-evaluation.

Paperid: 168, https://arxiv.org/pdf/2511.20693.pdf GitHub

Abstract:
Large language models (LLMs) have shown strong potential in automating the design of agentic workflows. However, existing methods still rely heavily on manually predefined operators, limiting generalization and scalability. To address this issue, we propose $A^2Flow$, a fully automated framework for agentic workflow generation based on self-adaptive abstraction operators. $A^2Flow$ employs a three-stage operator extraction process: 1) Case-based Initial Operator Generation: leveraging expert demonstrations and LLM reasoning to generate case-specific operators; 2) Operator Clustering and Preliminary Abstraction: grouping similar operators across tasks to form preliminary abstractions; and 3) Deep Extraction for Abstract Execution Operators: applying long chain-of-thought prompting and multi-path reasoning to derive compact and generalizable execution operators. These operators serve as reusable building blocks for workflow construction without manual predefinition. Furthermore, we enhance node-level workflow search with an operator memory mechanism, which retains historical outputs to enrich context and improve decision-making. Experiments on general and embodied benchmarks show that $A^2Flow$ achieves a 2.4\% and 19.3\% average performance improvement and reduces resource usage by 37\% over state-of-the-art baselines. Homepage:https://github.com/pandawei-ele/A2FLOW

Paperid: 169, https://arxiv.org/pdf/2511.20652.pdf GitHub GitHub

Abstract:
The increasing trust in large language models (LLMs), especially in the form of chatbots, is often undermined by the lack of their extrinsic evaluation. This holds particularly true in nutrition, where randomised controlled trials (RCTs) are the gold standard, and experts demand them for evidence-based deployment. LLMs have shown promising results in this field, but these are limited to intrinsic setups. We address this gap by running the first RCT involving LLMs for nutrition. We augment a rule-based chatbot with two LLM-based features: (1) message rephrasing for conversational variety and engagement, and (2) nutritional counselling through a fine-tuned model. In our seven-week RCT (n=81), we compare chatbot variants with and without LLM integration. We measure effects on dietary outcome, emotional well-being, and engagement. Despite our LLM-based features performing well in intrinsic evaluation, we find that they did not yield consistent benefits in real-world deployment. These results highlight critical gaps between intrinsic evaluations and real-world impact, emphasising the need for interdisciplinary, human-centred approaches.\footnote{We provide all of our code and results at: \\ \href{https://github.com/saeshyra/diet-chatbot-trial}{https://github.com/saeshyra/diet-chatbot-trial}}

Paperid: 170, https://arxiv.org/pdf/2511.20650.pdf GitHub

Abstract:
Traditional object detection models in medical imaging operate within a closed-set paradigm, limiting their ability to detect objects of novel labels. Open-vocabulary object detection (OVOD) addresses this limitation but remains underexplored in medical imaging due to dataset scarcity and weak text-image alignment. To bridge this gap, we introduce MedROV, the first Real-time Open Vocabulary detection model for medical imaging. To enable open-vocabulary learning, we curate a large-scale dataset, Omnis, with 600K detection samples across nine imaging modalities and introduce a pseudo-labeling strategy to handle missing annotations from multi-source datasets. Additionally, we enhance generalization by incorporating knowledge from a large pre-trained foundation model. By leveraging contrastive learning and cross-modal representations, MedROV effectively detects both known and novel structures. Experimental results demonstrate that MedROV outperforms the previous state-of-the-art foundation model for medical image detection with an average absolute improvement of 40 mAP50, and surpasses closed-set detectors by more than 3 mAP50, while running at 70 FPS, setting a new benchmark in medical detection. Our source code, dataset, and trained model are available at https://github.com/toobatehreem/MedROV.

Paperid: 171, https://arxiv.org/pdf/2511.20648.pdf GitHub

Abstract:
To act in the world, a model must name what it sees and know where it is in 3D. Today's vision-language models (VLMs) excel at open-ended 2D description and grounding, yet multi-object 3D detection remains largely missing from the VLM toolbox. We present LocateAnything3D, a VLM-native recipe that casts 3D detection as a next-token prediction problem. The key is a short, explicit Chain-of-Sight (CoS) sequence that mirrors how human reason from images: find an object in 2D, then infer its distance, size, and pose. The decoder first emits 2D detections as a visual chain-of-thought, then predicts 3D boxes under an easy-to-hard curriculum: across objects, a near-to-far order reduces early ambiguity and matches ego-centric utility; within each object, a center-from-camera, dimensions, and rotation factorization ranks information by stability and learnability. This VLM-native interface preserves open-vocabulary and visual-prompting capability without specialized heads. On the challenging Omni3D benchmark, our model achieves state-of-the-art results, with 49.89 AP_3D, surpassing the previous best by +15.51 absolute improvement even when the baseline is given ground-truth 2D boxes. It also generalizes zero-shot to held-out categories with strong robustness. By turning 3D detection into a disciplined next-token problem, LocateAnything3D offers a practical foundation for models to perceive in 3D.

Paperid: 172, https://arxiv.org/pdf/2511.20646.pdf GitHub

Abstract:
This paper addresses the challenge of training a single network to jointly perform multiple dense prediction tasks, such as segmentation and depth estimation, i.e., multi-task learning (MTL). Current approaches mainly capture cross-task relations in the 2D image space, often leading to unstructured features lacking 3D-awareness. We argue that 3D-awareness is vital for modeling cross-task correlations essential for comprehensive scene understanding. We propose to address this problem by integrating correlations across views, i.e., cost volume, as geometric consistency in the MTL network. Specifically, we introduce a lightweight Cross-view Module (CvM), shared across tasks, to exchange information across views and capture cross-view correlations, integrated with a feature from MTL encoder for multi-task predictions. This module is architecture-agnostic and can be applied to both single and multi-view data. Extensive results on NYUv2 and PASCAL-Context demonstrate that our method effectively injects geometric consistency into existing MTL methods to improve performance.

Paperid: 173, https://arxiv.org/pdf/2511.20640.pdf GitHub

Abstract:
While generative video models have achieved remarkable fidelity and consistency, applying these capabilities to video editing remains a complex challenge. Recent research has explored motion controllability as a means to enhance text-to-video generation or image animation; however, we identify precise motion control as a promising yet under-explored paradigm for editing existing videos. In this work, we propose modifying video motion by directly editing sparse trajectories extracted from the input. We term the deviation between input and output trajectories a "motion edit" and demonstrate that this representation, when coupled with a generative backbone, enables powerful video editing capabilities. To achieve this, we introduce a pipeline for generating "motion counterfactuals", video pairs that share identical content but distinct motion, and we fine-tune a motion-conditioned video diffusion architecture on this dataset. Our approach allows for edits that start at any timestamp and propagate naturally. In a four-way head-to-head user study, our model achieves over 65 percent preference against prior work. Please see our project page: https://ryanndagreat.github.io/MotionV2V

Paperid: 174, https://arxiv.org/pdf/2511.20639.pdf GitHub GitHub

Abstract:
Multi-agent systems (MAS) extend large language models (LLMs) from independent single-model reasoning to coordinative system-level intelligence. While existing LLM agents depend on text-based mediation for reasoning and communication, we take a step forward by enabling models to collaborate directly within the continuous latent space. We introduce LatentMAS, an end-to-end training-free framework that enables pure latent collaboration among LLM agents. In LatentMAS, each agent first performs auto-regressive latent thoughts generation through last-layer hidden embeddings. A shared latent working memory then preserves and transfers each agent's internal representations, ensuring lossless information exchange. We provide theoretical analyses establishing that LatentMAS attains higher expressiveness and lossless information preservation with substantially lower complexity than vanilla text-based MAS. In addition, empirical evaluations across 9 comprehensive benchmarks spanning math and science reasoning, commonsense understanding, and code generation show that LatentMAS consistently outperforms strong single-model and text-based MAS baselines, achieving up to 14.6% higher accuracy, reducing output token usage by 70.8%-83.7%, and providing 4x-4.3x faster end-to-end inference. These results demonstrate that our new latent collaboration framework enhances system-level reasoning quality while offering substantial efficiency gains without any additional training. Code and data are fully open-sourced at https://github.com/Gen-Verse/LatentMAS.

Paperid: 175, https://arxiv.org/pdf/2511.20635.pdf GitHub GitHub

Abstract:
Pre-trained video models learn powerful priors for generating high-quality, temporally coherent content. While these models excel at temporal coherence, their dynamics are often constrained by the continuous nature of their training data. We hypothesize that by injecting the rich and unconstrained content diversity from image data into this coherent temporal framework, we can generate image sets that feature both natural transitions and a far more expansive dynamic range. To this end, we introduce iMontage, a unified framework designed to repurpose a powerful video model into an all-in-one image generator. The framework consumes and produces variable-length image sets, unifying a wide array of image generation and editing tasks. To achieve this, we propose an elegant and minimally invasive adaptation strategy, complemented by a tailored data curation process and training paradigm. This approach allows the model to acquire broad image manipulation capabilities without corrupting its invaluable original motion priors. iMontage excels across several mainstream many-in-many-out tasks, not only maintaining strong cross-image contextual consistency but also generating scenes with extraordinary dynamics that surpass conventional scopes. Find our homepage at: https://kr1sjfu.github.io/iMontage-web/.

Paperid: 176, https://arxiv.org/pdf/2511.20633.pdf GitHub

Abstract:
Vision-Language-Action (VLA) policies excel in aligning language, perception, and robot control. However, most VLAs are trained purely by imitation, which overfits to demonstrations, and is brittle under distribution shift. Reinforcement learning (RL) directly optimizes task reward and thus addresses this misalignment, but real-robot interaction is expensive and conventional simulators are hard to engineer and transfer. We address both data efficiency and optimization stability in VLA post-training via a learned world model and an RL procedure tailored to flow-based action heads. Specifically, we introduce Prophet, a unified action-to-video robot actuation pretrained across large-scale, heterogeneous robot data to learn reusable action-outcome dynamics. It is able to few-shot adapt to new robots, objects, and environments, yielding a rollout-ready simulator. Upon Prophet, we reinforce action policies with Flow-action-GRPO (FA-GRPO), which adapts Flow-GRPO to operate on VLA actions, and with FlowScale, a stepwise reweighting that rescales per-step gradients in the flow head. Together, Prophet, FA-GRPO, and FlowScale constitute ProphRL, a practical, data- and compute-efficient path to VLA post-training. Experiments show 5-17% success gains on public benchmarks and 24-30% gains on real robots across different VLA variants.

Paperid: 177, https://arxiv.org/pdf/2511.20626.pdf GitHub

Abstract:
The optimization of large language models (LLMs) remains a critical challenge, particularly as model scaling exacerbates sensitivity to algorithmic imprecision and training instability. Recent advances in optimizers have improved convergence efficiency through momentum orthogonalization, but suffer from two key robustness limitations: dimensional fragility in orthogonalization precision and vulnerability to outlier-induced noise. To address these robustness challenges, we introduce ROOT, a Robust Orthogonalized Optimizer that enhances training stability through dual robustness mechanisms. First, we develop a dimension-robust orthogonalization scheme using adaptive Newton iterations with fine-grained coefficients tailored to specific matrix sizes, ensuring consistent precision across diverse architectural configurations. Second, we introduce an optimization-robust framework via proximal optimization that suppresses outlier noise while preserving meaningful gradient directions. Extensive experiments demonstrate that ROOT achieves significantly improved robustness, with faster convergence and superior final performance compared to both Muon and Adam-based optimizers, particularly in noisy and non-convex scenarios. Our work establishes a new paradigm for developing robust and precise optimizers capable of handling the complexities of modern large-scale model training. The code will be available at https://github.com/huawei-noah/noah-research/tree/master/ROOT.

Paperid: 178, https://arxiv.org/pdf/2511.20620.pdf GitHub

Abstract:
Reproducible closed-loop evaluation remains a major bottleneck in Embodied AI such as visual navigation. A promising path forward is high-fidelity simulation that combines photorealistic sensor rendering with geometrically grounded interaction in complex, open-world urban environments. Although recent video-3DGS methods ease open-world scene capturing, they are still unsuitable for benchmarking due to large visual and geometric sim-to-real gaps. To address these challenges, we introduce Wanderland, a real-to-sim framework that features multi-sensor capture, reliable reconstruction, accurate geometry, and robust view synthesis. Using this pipeline, we curate a diverse dataset of indoor-outdoor urban scenes and systematically demonstrate how image-only pipelines scale poorly, how geometry quality impacts novel view synthesis, and how all of these adversely affect navigation policy learning and evaluation reliability. Beyond serving as a trusted testbed for embodied navigation, Wanderland's rich raw sensor data further allows benchmarking of 3D reconstruction and novel view synthesis models. Our work establishes a new foundation for reproducible research in open-world embodied AI. Project website is at https://ai4ce.github.io/wanderland/.

Paperid: 179, https://arxiv.org/pdf/2511.20614.pdf GitHub

Abstract:
Previous works have explored various customized generation tasks given a reference image, but they still face limitations in generating consistent fine-grained details. In this paper, our aim is to solve the inconsistency problem of generated images by applying a reference-guided post-editing approach and present our ImageCritic. We first construct a dataset of reference-degraded-target triplets obtained via VLM-based selection and explicit degradation, which effectively simulates the common inaccuracies or inconsistencies observed in existing generation models. Furthermore, building on a thorough examination of the model's attention mechanisms and intrinsic representations, we accordingly devise an attention alignment loss and a detail encoder to precisely rectify inconsistencies. ImageCritic can be integrated into an agent framework to automatically detect inconsistencies and correct them with multi-round and local editing in complex scenarios. Extensive experiments demonstrate that ImageCritic can effectively resolve detail-related issues in various customized generation scenarios, providing significant improvements over existing methods.

Paperid: 180, https://arxiv.org/pdf/2511.20612.pdf GitHub

Abstract:
Many consequential real-world systems, like wind fields and ocean currents, are dynamic and hard to model. Learning their governing dynamics remains a central challenge in scientific machine learning. Dynamic Mode Decomposition (DMD) provides a simple, data-driven approximation, but practical use is limited by sparse/noisy observations from continuous fields, reliance on linear approximations, and the lack of principled uncertainty quantification. To address these issues, we introduce Stochastic NODE-DMD, a probabilistic extension of DMD that models continuous-time, nonlinear dynamics while remaining interpretable. Our approach enables continuous spatiotemporal reconstruction at arbitrary coordinates and quantifies predictive uncertainty. Across four benchmarks, a synthetic setting and three physics-based flows, it surpasses a baseline in reconstruction accuracy when trained from only 10% observation density. It further recovers the dynamical structure by aligning learned modes and continuous-time eigenvalues with ground truth. Finally, on datasets with multiple realizations, our method learns a calibrated distribution over latent dynamics that preserves ensemble variability rather than averaging across regimes. Our code is available at: https://github.com/sedan-group/Stochastic-NODE-DMD

Paperid: 181, https://arxiv.org/pdf/2511.20606.pdf GitHub

Abstract:
Conventional models of matching markets assume that monetary transfers can clear markets by compensating for utility differentials. However, empirical patterns show that such transfers often fail to close structural preference gaps. This paper introduces a market microstructure framework that models matching decisions as a limit order book system with rigid bid ask spreads. Individual preferences are represented by a latent preference state matrix, where the spread between an agent's internal ask price (the unconditional maximum) and the market's best bid (the reachable maximum) creates a structural liquidity constraint. We establish a Threshold Impossibility Theorem showing that linear compensation cannot close these spreads unless it induces a categorical identity shift. A dynamic discrete choice execution model further demonstrates that matches occur only when the market to book ratio crosses a time decaying liquidity threshold, analogous to order execution under inventory pressure. Numerical experiments validate persistent slippage, regional invariance of preference orderings, and high tier zero spread executions. The model provides a unified microstructure explanation for matching failures, compensation inefficiency, and post match regret in illiquid order driven environments.

Paperid: 182, https://arxiv.org/pdf/2511.20565.pdf GitHub

Abstract:
Recent advances in visual generation have highlighted the rise of Latent Generative Models (LGMs), which rely on effective visual tokenizers to bridge pixels and semantics. However, existing tokenizers are typically trained from scratch and struggle to balance semantic representation and reconstruction fidelity, particularly in high-dimensional latent spaces. In this work, we introduce DINO-Tok, a DINO-based visual tokenizer that unifies hierarchical representations into an information-complete latent space. By integrating shallow features that retain fine-grained details with deep features encoding global semantics, DINO-Tok effectively bridges pretrained representations and visual generation. We further analyze the challenges of vector quantization (VQ) in this high-dimensional space, where key information is often lost and codebook collapse occurs. We thus propose a global PCA reweighting mechanism to stabilize VQ and preserve essential information across dimensions. On ImageNet 256$\times$256, DINO-Tok achieves state-of-the-art reconstruction performance, reaching 28.54 PSNR for autoencoding and 23.98 PSNR for VQ-based modeling, significantly outperforming prior tokenizers and comparable to billion-level data trained models (such as Hunyuan and Wan). These results demonstrate that adapting powerful pretrained vision models like DINO for tokenization enables semantically aligned and high-fidelity latent representations, enabling next-generation visual generative models. Code will be publicly available at https://github.com/MKJia/DINO-Tok.

Paperid: 183, https://arxiv.org/pdf/2511.20561.pdf GitHub

Abstract:
Recent years have witnessed significant progress in Unified Multimodal Models, yet a fundamental question remains: Does understanding truly inform generation? To investigate this, we introduce UniSandbox, a decoupled evaluation framework paired with controlled, synthetic datasets to avoid data leakage and enable detailed analysis. Our findings reveal a significant understanding-generation gap, which is mainly reflected in two key dimensions: reasoning generation and knowledge transfer. Specifically, for reasoning generation tasks, we observe that explicit Chain-of-Thought (CoT) in the understanding module effectively bridges the gap, and further demonstrate that a self-training approach can successfully internalize this ability, enabling implicit reasoning during generation. Additionally, for knowledge transfer tasks, we find that CoT assists the generative process by helping retrieve newly learned knowledge, and also discover that query-based architectures inherently exhibit latent CoT-like properties that affect this transfer. UniSandbox provides preliminary insights for designing future unified architectures and training strategies that truly bridge the gap between understanding and generation. Code and data are available at https://github.com/PKU-YuanGroup/UniSandBox

Paperid: 184, https://arxiv.org/pdf/2511.20515.pdf GitHub GitHub

Abstract:
Assessing image-text alignment models such as CLIP is crucial for bridging visual and linguistic representations. Yet existing benchmarks rely on rule-based perturbations or short captions, limiting their ability to measure fine-grained alignment. We introduce AlignBench, a benchmark that provides a new indicator of image-text alignment by evaluating detailed image-caption pairs generated by diverse image-to-text and text-to-image models. Each sentence is annotated for correctness, enabling direct assessment of VLMs as alignment evaluators. Benchmarking a wide range of decoder-based VLMs reveals three key findings: (i) CLIP-based models, even those tailored for compositional reasoning, remain nearly blind; (ii) detectors systematically over-score early sentences; and (iii) they show strong self-preference, favoring their own outputs and harming detection performance. Our project page will be available at https://dahlian00.github.io/AlignBench/.

Paperid: 185, https://arxiv.org/pdf/2511.20501.pdf GitHub

Abstract:
Accurate extraction and segmentation of the cerebral arteries from digital subtraction angiography (DSA) sequences is essential for developing reliable clinical management models of complex cerebrovascular diseases. Conventional loss functions often rely solely on pixel-wise overlap, overlooking the geometric and physical consistency of vascular boundaries, which can lead to fragmented or unstable vessel predictions. To overcome this limitation, we propose a novel \textit{Physics-Informed Loss} (PIL) that models the interaction between the predicted and ground-truth boundaries as an elastic process inspired by dislocation theory in materials physics. This formulation introduces a physics-based regularization term that enforces smooth contour evolution and structural consistency, allowing the network to better capture fine vascular geometry. The proposed loss is integrated into several segmentation architectures, including U-Net, U-Net++, SegFormer, and MedFormer, and evaluated on two public benchmarks: DIAS and DSCA. Experimental results demonstrate that PIL consistently outperforms conventional loss functions such as Cross-Entropy, Dice, Active Contour, and Surface losses, achieving superior sensitivity, F1 score, and boundary coherence. These findings confirm that the incorporation of physics-based boundary interactions into deep neural networks improves both the precision and robustness of vascular segmentation in dynamic angiographic imaging. The implementation of the proposed method is publicly available at https://github.com/irfantahir301/Physicsis_loss.

Paperid: 186, https://arxiv.org/pdf/2511.20492.pdf GitHub

Abstract:
We introduce Kleinkram, a free and open-source system designed to solve the challenge of managing massive, unstructured robotic datasets. Designed as a modular, on-premises cloud solution, Kleinkram enables scalable storage, indexing, and sharing of datasets, ranging from individual experiments to large-scale research collections. Kleinkram natively integrates with standard formats such as ROS bags and MCAP and utilises S3-compatible storage for flexibility. Beyond storage, Kleinkram features an integrated "Action Runner" that executes customizable Docker-based workflows for data validation, curation, and benchmarking. Kleinkram has successfully managed over 30 TB of data from diverse robotic systems, streamlining the research lifecycle through a modern web interface and a robust Command Line Interface (CLI).

Paperid: 187, https://arxiv.org/pdf/2511.20462.pdf GitHub GitHub

Abstract:
Normalizing flows (NFs) are end-to-end likelihood-based generative models for continuous data, and have recently regained attention with encouraging progress on image generation. Yet in the video generation domain, where spatiotemporal complexity and computational cost are substantially higher, state-of-the-art systems almost exclusively rely on diffusion-based models. In this work, we revisit this design space by presenting STARFlow-V, a normalizing flow-based video generator with substantial benefits such as end-to-end learning, robust causal prediction, and native likelihood estimation. Building upon the recently proposed STARFlow, STARFlow-V operates in the spatiotemporal latent space with a global-local architecture which restricts causal dependencies to a global latent space while preserving rich local within-frame interactions. This eases error accumulation over time, a common pitfall of standard autoregressive diffusion model generation. Additionally, we propose flow-score matching, which equips the model with a light-weight causal denoiser to improve the video generation consistency in an autoregressive fashion. To improve the sampling efficiency, STARFlow-V employs a video-aware Jacobi iteration scheme that recasts inner updates as parallelizable iterations without breaking causality. Thanks to the invertible structure, the same model can natively support text-to-video, image-to-video as well as video-to-video generation tasks. Empirically, STARFlow-V achieves strong visual fidelity and temporal consistency with practical sampling throughput relative to diffusion-based baselines. These results present the first evidence, to our knowledge, that NFs are capable of high-quality autoregressive video generation, establishing them as a promising research direction for building world models. Code and generated samples are available at https://github.com/apple/ml-starflow.

Paperid: 188, https://arxiv.org/pdf/2511.20457.pdf GitHub

Abstract:
Modeling nonlinear systems with Volterra series is challenging because the number of kernel coefficients grows exponentially with the model order. This work introduces Bayesian Tensor Network Volterra kernel machines (BTN-V), extending the Bayesian Tensor Network framework to Volterra system identification. BTN-V represents Volterra kernels using canonical polyadic decomposition, reducing model complexity from O(I^D) to O(DIR). By treating all tensor components and hyperparameters as random variables, BTN-V provides predictive uncertainty estimation at no additional computational cost. Sparsity-inducing hierarchical priors enable automatic rank determination and the learning of fading-memory behavior directly from data, improving interpretability and preventing overfitting. Empirical results demonstrate competitive accuracy, enhanced uncertainty quantification, and reduced computational cost.

Paperid: 189, https://arxiv.org/pdf/2511.20446.pdf GitHub

Abstract:
The way humans interact with each other, including interpersonal distances, spatial configuration, and motion, varies significantly across different situations. To enable machines to understand such complex, context-dependent behaviors, it is essential to model multiple people in relation to the surrounding scene context. In this paper, we present a novel research problem to model the correlations between two people engaged in a shared interaction involving an object. We refer to this formulation as Human-Human-Object Interactions (HHOIs). To overcome the lack of dedicated datasets for HHOIs, we present a newly captured HHOIs dataset and a method to synthesize HHOI data by leveraging image generative models. As an intermediary, we obtain individual human-object interaction (HOIs) and human-human interaction (HHIs) from the HHOIs, and with these data, we train an text-to-HOI and text-to-HHI model using score-based diffusion model. Finally, we present a unified generative framework that integrates the two individual model, capable of synthesizing complete HHOIs in a single advanced sampling process. Our method extends HHOI generation to multi-human settings, enabling interactions involving more than two individuals. Experimental results show that our method generates realistic HHOIs conditioned on textual descriptions, outperforming previous approaches that focus only on single-human HOIs. Furthermore, we introduce multi-human motion generation involving objects as an application of our framework.

Paperid: 190, https://arxiv.org/pdf/2511.20439.pdf GitHub

Abstract:
In Vision Language Models (VLMs), vision tokens are quantity-heavy yet information-dispersed compared with language tokens, thus consume too much unnecessary computation. Pruning redundant vision tokens for high VLM inference efficiency has been continuously studied but all existing methods resort to indirect and non-guaranteed ways. We propose OC-VTP, a direct and guaranteed approach to select the most representative vision tokens for high-efficiency yet accuracy-preserving VLM inference. Our OC-VTP requires merely light-weight pre-training of a small object-centric vision token pruner, which can then be inserted into existing VLMs, without fine-tuning of any models on any datasets. It is gauranteed that the most representative vision tokens are kept by minimizing the error in reconstructing the original unpruned tokens from the selected ones. Across any vision pruning ratios, i.e., inference efficiency, our OC-VTP consistently helps mainstream VLMs to preserve the highest inference accuracy. Our pruning also demonstrates interesting interpretability. Our codes are available at https://github.com/GarryLarry010131/OC-VTP.

Paperid: 191, https://arxiv.org/pdf/2511.20426.pdf GitHub

Abstract:
Block-causal video generation faces a stark speed-quality trade-off: small 1.3B models manage only 16 FPS while large 14B models crawl at 4.5 FPS, forcing users to choose between responsiveness and quality. Block Cascading significantly mitigates this trade-off through training-free parallelization. Our key insight: future video blocks do not need fully denoised current blocks to begin generation. By starting block generation with partially denoised context from predecessors, we transform sequential pipelines into parallel cascades where multiple blocks denoise simultaneously. With 5 GPUs exploiting temporal parallelism, we achieve ~2x acceleration across all model scales: 1.3B models accelerate from 16 to 30 FPS, 14B models from 4.5 to 12.5 FPS. Beyond inference speed, Block Cascading eliminates overhead from KV-recaching (of ~200ms) during context switches for interactive generation. Extensive evaluations validated against multiple block-causal pipelines demonstrate no significant loss in generation quality when switching from block-causal to Block Cascading pipelines for inference. Project Page: https://hmrishavbandy.github.io/block_cascading_page/

Paperid: 192, https://arxiv.org/pdf/2511.20415.pdf GitHub

Abstract:
Generating realistic 3D cities is fundamental to world models, virtual reality, and game development, where an ideal urban scene must satisfy both stylistic diversity, fine-grained, and controllability. However, existing methods struggle to balance the creative flexibility offered by text-based generation with the object-level editability enabled by explicit structural representations. We introduce MajutsuCity, a natural language-driven and aesthetically adaptive framework for synthesizing structurally consistent and stylistically diverse 3D urban scenes. MajutsuCity represents a city as a composition of controllable layouts, assets, and materials, and operates through a four-stage pipeline. To extend controllability beyond initial generation, we further integrate MajutsuAgent, an interactive language-grounded editing agent} that supports five object-level operations. To support photorealistic and customizable scene synthesis, we also construct MajutsuDataset, a high-quality multimodal dataset} containing 2D semantic layouts and height maps, diverse 3D building assets, and curated PBR materials and skyboxes, each accompanied by detailed annotations. Meanwhile, we develop a practical set of evaluation metrics, covering key dimensions such as structural consistency, scene complexity, material fidelity, and lighting atmosphere. Extensive experiments demonstrate MajutsuCity reduces layout FID by 83.7% compared with CityDreamer and by 20.1% over CityCraft. Our method ranks first across all AQS and RDR scores, outperforming existing methods by a clear margin. These results confirm MajutsuCity as a new state-of-the-art in geometric fidelity, stylistic adaptability, and semantic controllability for 3D city generation. We expect our framework can inspire new avenues of research in 3D city generation. Our project page: https://longhz140516.github.io/MajutsuCity/.

Paperid: 193, https://arxiv.org/pdf/2511.20410.pdf GitHub

Abstract:
Timestep distillation is an effective approach for improving the generation efficiency of diffusion models. The Consistency Model (CM), as a trajectory-based framework, demonstrates significant potential due to its strong theoretical foundation and high-quality few-step generation. Nevertheless, current continuous-time consistency distillation methods still rely heavily on training data and computational resources, hindering their deployment in resource-constrained scenarios and limiting their scalability to diverse domains. To address this issue, we propose Trajectory-Backward Consistency Model (TBCM), which eliminates the dependence on external training data by extracting latent representations directly from the teacher model's generation trajectory. Unlike conventional methods that require VAE encoding and large-scale datasets, our self-contained distillation paradigm significantly improves both efficiency and simplicity. Moreover, the trajectory-extracted samples naturally bridge the distribution gap between training and inference, thereby enabling more effective knowledge transfer. Empirically, TBCM achieves 6.52 FID and 28.08 CLIP scores on MJHQ-30k under one-step generation, while reducing training time by approximately 40% compared to Sana-Sprint and saving a substantial amount of GPU memory, demonstrating superior efficiency without sacrificing quality. We further reveal the diffusion-generation space discrepancy in continuous-time consistency distillation and analyze how sampling strategies affect distillation performance, offering insights for future distillation research. GitHub Link: https://github.com/hustvl/TBCM.

Paperid: 194, https://arxiv.org/pdf/2511.20366.pdf GitHub

Abstract:
Reconstructing topologically consistent facial geometry is crucial for the digital avatar creation pipelines. Existing methods either require tedious manual efforts, lack generalization to in-the-wild data, or are constrained by the limited expressiveness of 3D Morphable Models. To address these limitations, we propose VGGTFace, an automatic approach that innovatively applies the 3D foundation model, i.e. VGGT, for topologically consistent facial geometry reconstruction from in-the-wild multi-view images captured by everyday users. Our key insight is that, by leveraging VGGT, our method naturally inherits strong generalization ability and expressive power from its large-scale training and point map representation. However, it is unclear how to reconstruct a topologically consistent mesh from VGGT, as the topology information is missing in its prediction. To this end, we augment VGGT with Pixel3DMM for injecting topology information via pixel-aligned UV values. In this manner, we convert the pixel-aligned point map of VGGT to a point cloud with topology. Tailored to this point cloud with known topology, we propose a novel Topology-Aware Bundle Adjustment strategy to fuse them, where we construct a Laplacian energy for the Bundle Adjustment objective. Our method achieves high-quality reconstruction in 10 seconds for 16 views on a single NVIDIA RTX 4090. Experiments demonstrate state-of-the-art results on benchmarks and impressive generalization to in-the-wild data. Code is available at https://github.com/grignarder/vggtface.

Paperid: 195, https://arxiv.org/pdf/2511.20351.pdf GitHub

Abstract:
Humans rely on the synergistic control of head (cephalomotor) and eye (oculomotor) to efficiently search for visual information in 360°. However, prior approaches to visual search are limited to a static image, neglecting the physical embodiment and its interaction with the 3D world. How can we develop embodied visual search agents as efficient as humans while bypassing the constraints imposed by real-world hardware? To this end, we propose humanoid visual search where a humanoid agent actively rotates its head to search for objects or paths in an immersive world represented by a 360° panoramic image. To study visual search in visually-crowded real-world scenarios, we build H* Bench, a new benchmark that moves beyond household scenes to challenging in-the-wild scenes that necessitate advanced visual-spatial reasoning capabilities, such as transportation hubs, large-scale retail spaces, urban streets, and public institutions. Our experiments first reveal that even top-tier proprietary models falter, achieving only ~30% success in object and path search. We then use post-training techniques to enhance the open-source Qwen2.5-VL, increasing its success rate by over threefold for both object search (14.83% to 47.38%) and path search (6.44% to 24.94%). Notably, the lower ceiling of path search reveals its inherent difficulty, which we attribute to the demand for sophisticated spatial commonsense. Our results not only show a promising path forward but also quantify the immense challenge that remains in building MLLM agents that can be seamlessly integrated into everyday human life.

Paperid: 196, https://arxiv.org/pdf/2511.20343.pdf GitHub

Abstract:
We present AMB3R, a multi-view feed-forward model for dense 3D reconstruction on a metric-scale that addresses diverse 3D vision tasks. The key idea is to leverage a sparse, yet compact, volumetric scene representation as our backend, enabling geometric reasoning with spatial compactness. Although trained solely for multi-view reconstruction, we demonstrate that AMB3R can be seamlessly extended to uncalibrated visual odometry (online) or large-scale structure from motion without the need for task-specific fine-tuning or test-time optimization. Compared to prior pointmap-based models, our approach achieves state-of-the-art performance in camera pose, depth, and metric-scale estimation, 3D reconstruction, and even surpasses optimization-based SLAM and SfM methods with dense reconstruction priors on common benchmarks.

Paperid: 197, https://arxiv.org/pdf/2511.20332.pdf GitHub

Abstract:
This article trained a network for perceiving three-dimensional motion information of binocular vision target, which can provide real-time three-dimensional coordinate, velocity, and acceleration, and has a basic spatiotemporal perception capability. Understood the ability of neural networks to fit nonlinear problems from the perspective of PID. Considered a single-layer neural network as using a second-order difference equation and a nonlinearity to describe a local problem. Multilayer networks gradually transform the raw representation to the desired representation through multiple such combinations. Analysed some reference principles for designing neural networks. Designed a relatively small PID convolutional neural network, with a total of 17 layers and 413 thousand parameters. Implemented a simple but practical feature reuse method by concatenation and pooling. The network was trained and tested using the simulated randomly moving ball datasets, and the experimental results showed that the prediction accuracy was close to the upper limit that the input image resolution can represent. Analysed the experimental results and errors, as well as the existing shortcomings and possible directions for improvement. Finally, discussed the advantages of high-dimensional convolution in improving computational efficiency and feature space utilization. As well as the potential advantages of using PID information to implement memory and attention mechanisms.

Paperid: 198, https://arxiv.org/pdf/2511.20296.pdf GitHub

Abstract:
Despite significant advancements in deep learning-based sparse-view computed tomography (SVCT) reconstruction algorithms, these methods still encounter two primary limitations: (i) It is challenging to explicitly prove that the prior networks of deep unfolding algorithms satisfy Lipschitz constraints due to their empirically designed nature. (ii) The substantial storage costs of training a separate model for each setting in the case of multiple views hinder practical clinical applications. To address these issues, we elaborate an explicitly provable Lipschitz-constrained network, dubbed LipNet, and integrate an explicit prompt module to provide discriminative knowledge of different sparse sampling settings, enabling the treatment of multiple sparse view configurations within a single model. Furthermore, we develop a storage-saving deep unfolding framework for multiple-in-one SVCT reconstruction, termed PromptCT, which embeds LipNet as its prior network to ensure the convergence of its corresponding iterative algorithm. In simulated and real data experiments, PromptCT outperforms benchmark reconstruction algorithms in multiple-in-one SVCT reconstruction, achieving higher-quality reconstructions with lower storage costs. On the theoretical side, we explicitly demonstrate that LipNet satisfies boundary property, further proving its Lipschitz continuity and subsequently analyzing the convergence of the proposed iterative algorithms. The data and code are publicly available at https://github.com/shibaoshun/PromptCT.

Paperid: 199, https://arxiv.org/pdf/2511.20292.pdf GitHub

Abstract:
Reliable odometry in highly dynamic environments remains challenging when it relies on ICP-based registration: ICP assumes near-static scenes and degrades in repetitive or low-texture geometry. We introduce Dynamic-ICP, a Doppler-aware registration framework. The method (i) estimates ego motion from per-point Doppler velocity via robust regression and builds a velocity filter, (ii) clusters dynamic objects and reconstructs object-wise translational velocities from ego-compensated radial measurements, (iii) predicts dynamic points with a constant-velocity model, and (iv) aligns scans using a compact objective that combines point-to-plane geometry residual with a translation-invariant, rotation-only Doppler residual. The approach requires no external sensors or sensor-vehicle calibration and operates directly on FMCW LiDAR range and Doppler velocities. We evaluate Dynamic-ICP on three datasets-HeRCULES, HeLiPR, AevaScenes-focusing on highly dynamic scenes. Dynamic-ICP consistently improves rotational stability and translation accuracy over the state-of-the-art methods. Our approach is also simple to integrate into existing pipelines, runs in real time, and provides a lightweight solution for robust registration in dynamic environments. To encourage further research, the code is available at: https://github.com/JMUWRobotics/Dynamic-ICP.

Paperid: 200, https://arxiv.org/pdf/2511.20274.pdf GitHub

Abstract:
Until recently, the general corpus of CLIP-type fundamental models has widely explored either the retrieval of short descriptions or the classification of objects in the scene as SINGLE-object image classification task. The same holds for retrieving the image embedding (image retrieval task) given a text prompt. However, real-world scene images exhibit rich compositional structure involving multiple objects and actions. The latest methods in the CLIP-based literature improve class-level discrimination by mining harder negative image-text pairs and by refining permanent text prompts, often using LLMs. However, these improvements remain confined to predefined class lists and do not explicitly model relational or compositional structure. PyramidCLIP partially addresses this gap by aligning global and local visual features, yet it still lacks explicit modeling of inter-object relations. Hence, to further leverage this aspect for scene analysis, the proposed ScenarioCLIP model accepts input texts, grounded relations, and input images, along with focused regions highlighting relations. The proposed model is pretrained on curated scenario data, and finetuned for specialized downstream tasks, such as cross-modal retrieval and fine-grained visual understanding tasks. To address the lack of domain-specific datasets, we generate a novel dataset by extending image-text pairs from existing diverse indoor and outdoor scenario datasets that are publicly available. We used a pipeline of existing language models to ground action, object, and relations, filled by manual and automatic curation. We established a comprehensive benchmark for several scenario-based tasks and compared it with many baseline methods. ScenarioCLIP demonstrates robust zero-shot and finetune performance on various domain-specific tasks. Our code and dataset are available at https://github.com/scenario-clip/ScenarioCLIP

Paperid: 201, https://arxiv.org/pdf/2511.20263.pdf GitHub

Abstract:
Image classification is a well-studied task in computer vision, and yet it remains challenging under high-uncertainty conditions, such as when input images are corrupted or training data are limited. Conventional classification approaches typically train models to directly predict class labels from input images, but this might lead to suboptimal performance in such scenarios. To address this issue, we propose Discrete Diffusion Classification Modeling (DiDiCM), a novel framework that leverages a diffusion-based procedure to model the posterior distribution of class labels conditioned on the input image. DiDiCM supports diffusion-based predictions either on class probabilities or on discrete class labels, providing flexibility in computation and memory trade-offs. We conduct a comprehensive empirical study demonstrating the superior performance of DiDiCM over standard classifiers, showing that a few diffusion iterations achieve higher classification accuracy on the ImageNet dataset compared to baselines, with accuracy gains increasing as the task becomes more challenging. We release our code at https://github.com/omerb01/didicm .

Paperid: 202, https://arxiv.org/pdf/2511.20253.pdf GitHub

Abstract:
3D object detection is fundamental for spatial understanding. Real-world environments demand models capable of recognizing diverse, previously unseen objects, which remains a major limitation of closed-set methods. Existing open-vocabulary 3D detectors relax annotation requirements but still depend on training scenes, either as point clouds or images. We take this a step further by introducing Zoo3D, the first training-free 3D object detection framework. Our method constructs 3D bounding boxes via graph clustering of 2D instance masks, then assigns semantic labels using a novel open-vocabulary module with best-view selection and view-consensus mask generation. Zoo3D operates in two modes: the zero-shot Zoo3D$_0$, which requires no training at all, and the self-supervised Zoo3D$_1$, which refines 3D box prediction by training a class-agnostic detector on Zoo3D$_0$-generated pseudo labels. Furthermore, we extend Zoo3D beyond point clouds to work directly with posed and even unposed images. Across ScanNet200 and ARKitScenes benchmarks, both Zoo3D$_0$ and Zoo3D$_1$ achieve state-of-the-art results in open-vocabulary 3D object detection. Remarkably, our zero-shot Zoo3D$_0$ outperforms all existing self-supervised methods, hence demonstrating the power and adaptability of training-free, off-the-shelf approaches for real-world 3D understanding. Code is available at https://github.com/col14m/zoo3d .

Paperid: 203, https://arxiv.org/pdf/2511.20252.pdf GitHub

Abstract:
WhatsApp, with 3.5 billion active accounts as of early 2025, is the world's largest instant messaging platform. Given its massive user base, WhatsApp plays a critical role in global communication. To initiate conversations, users must first discover whether their contacts are registered on the platform. This is achieved by querying WhatsApp's servers with mobile phone numbers extracted from the user's address book (if they allowed access). This architecture inherently enables phone number enumeration, as the service must allow legitimate users to query contact availability. While rate limiting is a standard defense against abuse, we revisit the problem and show that WhatsApp remains highly vulnerable to enumeration at scale. In our study, we were able to probe over a hundred million phone numbers per hour without encountering blocking or effective rate limiting. Our findings demonstrate not only the persistence but the severity of this vulnerability. We further show that nearly half of the phone numbers disclosed in the 2021 Facebook data leak are still active on WhatsApp, underlining the enduring risks associated with such exposures. Moreover, we were able to perform a census of WhatsApp users, providing a glimpse on the macroscopic insights a large messaging service is able to generate even though the messages themselves are end-to-end encrypted. Using the gathered data, we also discovered the re-use of certain X25519 keys across different devices and phone numbers, indicating either insecure (custom) implementations, or fraudulent activity. In this updated version of the paper, we also provide insights into the collaborative remediation process through which we confirmed that the underlying rate-limiting issue had been resolved.

Paperid: 204, https://arxiv.org/pdf/2511.20224.pdf GitHub

Abstract:
Duo-Tok is a source-aware dual-codebook tokenizer for vocal-accompaniment music that targets the growing tension between reconstruction quality and language-model (LM) learnability in modern lyrics-to-song systems. Existing codecs either prioritize high-fidelity reconstruction with difficult-to-model acoustic tokens or compress aggressively into semantic tokens that are LM-friendly but lossy, and they rarely make the tokenizer itself aware of dual-track structure. Duo-Tok follows a four-stage, SSL-centered pipeline: we first pretrain a BEST-RQ-style encoder on large-scale audio, then stabilize and factorize the representation with Gaussian replacement noise and multi-task supervision, before freezing the encoder to learn SimVQ-based dual codebooks with hard routing for vocals and accompaniment, and finally training latent diffusion decoders on top of the discrete tokens. Duo-Tok at 0.75 kbps shifts the empirical reconstruction-generation Pareto frontier, achieving the best music-tagging AP and the lowest vocabulary-normalized LM perplexity among compared codecs while maintaining reconstruction quality comparable to state-of-the-art music tokenizers.

Paperid: 205, https://arxiv.org/pdf/2511.20223.pdf GitHub

Abstract:
Adversarial attacks have evolved from simply disrupting predictions on conventional task-specific models to the more complex goal of manipulating image semantics on Large Vision-Language Models (LVLMs). However, existing methods struggle with controllability and fail to precisely manipulate the semantics of specific concepts in the image. We attribute this limitation to semantic entanglement in the patch-token representations on which adversarial attacks typically operate: global context aggregated by self-attention in the vision encoder dominates individual patch features, making them unreliable handles for precise local semantic manipulation. Our systematic investigation reveals a key insight: value features (V) computed within the transformer attention block serve as much more precise handles for manipulation. We show that V suppresses global-context channels, allowing it to retain high-entropy, disentangled local semantic information. Building on this discovery, we propose V-Attack, a novel method designed for precise local semantic attacks. V-Attack targets the value features and introduces two core components: (1) a Self-Value Enhancement module to refine V's intrinsic semantic richness, and (2) a Text-Guided Value Manipulation module that leverages text prompts to locate source concept and optimize it toward a target concept. By bypassing the entangled patch features, V-Attack achieves highly effective semantic control. Extensive experiments across diverse LVLMs, including LLaVA, InternVL, DeepseekVL and GPT-4o, show that V-Attack improves the attack success rate by an average of 36% over state-of-the-art methods, exposing critical vulnerabilities in modern visual-language understanding. Our code and data are available https://github.com/Summu77/V-Attack.

Paperid: 206, https://arxiv.org/pdf/2511.20189.pdf GitHub

Abstract:
Discovering subgroups with the maximum average treatment effect is crucial for targeted decision making in domains such as precision medicine, public policy, and education. While most prior work is formulated in the potential outcome framework, the corresponding structural causal model (SCM) for this task has been largely overlooked. In practice, two approaches dominate. The first estimates pointwise conditional treatment effects and then fits a tree on those estimates, effectively turning subgroup estimation into the harder problem of accurate pointwise estimation. The second constructs decision trees or rule sets with ad-hoc 'causal' heuristics, typically without rigorous justification for why a given heuristic may be used or whether such heuristics are necessary at all. We address these issues by studying the problem directly under the SCM framework. Under the assumption of a partition-based model, we show that optimal subgroup discovery reduces to recovering the data-generating models and hence a standard supervised learning problem (regression or classification). This allows us to adopt any partition-based methods to learn the subgroup from data. We instantiate the approach with CART, arguably one of the most widely used tree-based methods, to learn the subgroup with maximum treatment effect. Finally, on a large collection of synthetic and semi-synthetic datasets, we compare our method against a wide range of baselines and find that our approach, which avoids such causal heuristics, more accurately identifies subgroups with maximum treatment effect. Our source code is available at https://github.com/ylincen/causal-subgroup.

Paperid: 207, https://arxiv.org/pdf/2511.20170.pdf GitHub

Abstract:
Neural networks struggle on small tabular datasets, where tree-based models remain dominant. We introduce Adaptive Contrastive Approach (AdaCap), a training scheme that combines a permutation-based contrastive loss with a Tikhonov-based closed-form output mapping. Across 85 real-world regression datasets and multiple architectures, AdaCap yields consistent and statistically significant improvements in the small-sample regime, particularly for residual models. A meta-predictor trained on dataset characteristics (size, skewness, noise) accurately anticipates when AdaCap is beneficial. These results show that AdaCap acts as a targeted regularization mechanism, strengthening neural networks precisely where they are most fragile. All results and code are publicly available at https://github.com/BrunoBelucci/adacap.

Paperid: 208, https://arxiv.org/pdf/2511.20169.pdf GitHub

Abstract:
Anomaly detection (AD) aims to identify defects using normal-only training data. Existing anomaly detection benchmarks (e.g., MVTec-AD with 15 categories) cover only a narrow range of categories, limiting the evaluation of cross-context generalization and scalability. We introduce ADNet, a large-scale, multi-domain benchmark comprising 380 categories aggregated from 49 publicly available datasets across Electronics, Industry, Agrifood, Infrastructure, and Medical domains. The benchmark includes a total of 196,294 RGB images, consisting of 116,192 normal samples for training and 80,102 test images, of which 60,311 are anomalous. All images are standardized with MVTec-style pixel-level annotations and structured text descriptions spanning both spatial and visual attributes, enabling multimodal anomaly detection tasks. Extensive experiments reveal a clear scalability challenge: existing state-of-the-art methods achieve 90.6% I-AUROC in one-for-one settings but drop to 78.5% when scaling to all 380 categories in a multi-class setting. To address this, we propose Dinomaly-m, a context-guided Mixture-of-Experts extension of Dinomaly that expands decoder capacity without increasing inference cost. It achieves 83.2% I-AUROC and 93.1% P-AUROC, demonstrating superior performance over existing approaches. ADNet is designed as a standardized and extensible benchmark, supporting the community in expanding anomaly detection datasets across diverse domains and providing a scalable foundation for future anomaly detection foundation models. Dataset: https://grainnet.github.io/ADNet

Paperid: 209, https://arxiv.org/pdf/2511.20157.pdf GitHub GitHub

Abstract:
Parametric 3D human models such as SMPL have driven significant advances in human pose and shape estimation, yet their simplified kinematics limit biomechanical realism. The recently proposed SKEL model addresses this limitation by re-rigging SMPL with an anatomically accurate skeleton. However, estimating SKEL parameters directly remains challenging due to limited training data, perspective ambiguities, and the inherent complexity of human articulation. We introduce SKEL-CF, a coarse-to-fine framework for SKEL parameter estimation. SKEL-CF employs a transformer-based encoder-decoder architecture, where the encoder predicts coarse camera and SKEL parameters, and the decoder progressively refines them in successive layers. To ensure anatomically consistent supervision, we convert the existing SMPL-based dataset 4DHuman into a SKEL-aligned version, 4DHuman-SKEL, providing high-quality training data for SKEL estimation. In addition, to mitigate depth and scale ambiguities, we explicitly incorporate camera modeling into the SKEL-CF pipeline and demonstrate its importance across diverse viewpoints. Extensive experiments validate the effectiveness of the proposed design. On the challenging MOYO dataset, SKEL-CF achieves 85.0 MPJPE / 51.4 PA-MPJPE, significantly outperforming the previous SKEL-based state-of-the-art HSMR (104.5 / 79.6). These results establish SKEL-CF as a scalable and anatomically faithful framework for human motion analysis, bridging the gap between computer vision and biomechanics. Our implementation is available on the project page: https://pokerman8.github.io/SKEL-CF/.

Paperid: 210, https://arxiv.org/pdf/2511.20123.pdf GitHub

Abstract:
Despite advances, video diffusion transformers still struggle to generalize beyond their training length, a challenge we term video length extrapolation. We identify two failure modes: model-specific periodic content repetition and a universal quality degradation. Prior works attempt to solve repetition via positional encodings, overlooking quality degradation and achieving only limited extrapolation. In this paper, we revisit this challenge from a more fundamental view: attention maps, which directly govern how context influences outputs. We identify that both failure modes arise from a unified cause: attention dispersion, where tokens beyond the training window dilute learned attention patterns. This leads to quality degradation and repetition emerges as a special case when this dispersion becomes structured into periodic attention patterns, induced by harmonic properties of positional encodings. Building on this insight, we propose UltraViCo, a training-free, plug-and-play method that suppresses attention for tokens beyond the training window via a constant decay factor. By jointly addressing both failure modes, we outperform a broad set of baselines largely across models and extrapolation ratios, pushing the extrapolation limit from 2x to 4x. Remarkably, it improves Dynamic Degree and Imaging Quality by 233% and 40.5% over the previous best method at 4x extrapolation. Furthermore, our method generalizes seamlessly to downstream tasks such as controllable video synthesis and editing.

Paperid: 211, https://arxiv.org/pdf/2511.20106.pdf GitHub

Abstract:
This study introduces EM2LDL, a novel multilingual speech corpus designed to advance mixed emotion recognition through label distribution learning. Addressing the limitations of predominantly monolingual and single-label emotion corpora \textcolor{black}{that restrict linguistic diversity, are unable to model mixed emotions, and lack ecological validity}, EM2LDL comprises expressive utterances in English, Mandarin, and Cantonese, capturing the intra-utterance code-switching prevalent in multilingual regions like Hong Kong and Macao. The corpus integrates spontaneous emotional expressions from online platforms, annotated with fine-grained emotion distributions across 32 categories. Experimental baselines using self-supervised learning models demonstrate robust performance in speaker-independent gender-, age-, and personality-based evaluations, with HuBERT-large-EN achieving optimal results. By incorporating linguistic diversity and ecological validity, EM2LDL enables the exploration of complex emotional dynamics in multilingual settings. This work provides a versatile testbed for developing adaptive, empathetic systems for applications in affective computing, including mental health monitoring and cross-cultural communication. The dataset, annotations, and baseline codes are publicly available at https://github.com/xingfengli/EM2LDL.

Paperid: 212, https://arxiv.org/pdf/2511.20045.pdf GitHub GitHub

Abstract:
Planetary remote sensing images are affected by diverse and unknown degradations caused by imaging environments and hardware constraints. These factors limit image quality and hinder supervised blind super-resolution due to the lack of ground-truth images. This work presents History-Augmented Contrastive Blind Super-Resolution (HACBSR), an unsupervised framework for blind super-resolution that operates without ground-truth images and external kernel priors. HACBSR comprises two components: (1) a contrastive kernel sampling mechanism with kernel similarity control to mitigate distribution bias from Gaussian sampling, and (2) a history-augmented contrastive learning that uses historical models to generate negative samples to enable less greedy optimization and to induce strong convexity without ground-truth. A convergence analysis of the history-augmented contrastive learning is given in the Appendix. To support evaluation in planetary applications, we introduce Ceres-50, a dataset with diverse geological features simulated degradation patterns. Experiments show that HACBSR achieves competitive performance compared with state-of-the-art unsupervised methods across multiple upscaling factors. The code is available at https://github.com/2333repeat/HACBSR, and the dataset is available at https://github.com/2333repeat/Ceres-50.

Paperid: 213, https://arxiv.org/pdf/2511.20030.pdf GitHub

Abstract:
Multimodal Attributed Graphs (MMAGs) are an expressive data model for representing the complex interconnections among entities that associate attributes from multiple data modalities (text, images, etc.). Clustering over such data finds numerous practical applications in real scenarios, including social community detection, medical data analytics, etc. However, as revealed by our empirical studies, existing multi-view clustering solutions largely rely on the high correlation between attributes across various views and overlook the unique characteristics (e.g., low modality-wise correlation and intense feature-wise noise) of multimodal attributes output by large pre-trained language and vision models in MMAGs, leading to suboptimal clustering performance. Inspired by foregoing empirical observations and our theoretical analyses with graph signal processing, we propose the Dual Graph Filtering (DGF) scheme, which innovatively incorporates a feature-wise denoising component into node representation learning, thereby effectively overcoming the limitations of traditional graph filters adopted in the extant multi-view graph clustering approaches. On top of that, DGF includes a tri-cross contrastive training strategy that employs instance-level contrastive learning across modalities, neighborhoods, and communities for learning robust and discriminative node representations. Our comprehensive experiments on eight benchmark MMAG datasets exhibit that DGF is able to outperform a wide range of state-of-the-art baselines consistently and significantly in terms of clustering quality measured against ground-truth labels.

Paperid: 214, https://arxiv.org/pdf/2511.20015.pdf GitHub

Abstract:
Radio maps (RMs) serve as environment-aware electromagnetic (EM) representations that connect scenario geometry and material properties to the spatial distribution of signal strength, enabling localization without costly in-situ measurements. However, constructing high-fidelity indoor RMs remains challenging due to the prohibitive latency of EM solvers and the limitations of learning-based methods, which often rely on sparse measurements or assumptions of homogeneous material, which are misaligned with the heterogeneous and multipath-rich nature of indoor environments. To overcome these challenges, we propose iRadioDiff, a sampling-free diffusion-based framework for indoor RM construction. iRadioDiff is conditioned on access point (AP) positions, and physics-informed prompt encoded by material reflection and transmission coefficients. It further incorporates multipath-critical priors, including diffraction points, strong transmission boundaries, and line-of-sight (LoS) contours, to guide the generative process via conditional channels and boundary-weighted objectives. This design enables accurate modeling of nonstationary field discontinuities and efficient construction of physically consistent RMs. Experiments demonstrate that iRadioDiff achieves state-of-the-art performance in indoor RM construction and received signal strength based indoor localization, which offers effective generalization across layouts and material configurations. Code is available at https://github.com/UNIC-Lab/iRadioDiff.

Paperid: 215, https://arxiv.org/pdf/2511.20011.pdf GitHub

Abstract:
Pedestrian crossing intention prediction is essential for autonomous vehicles to improve pedestrian safety and reduce traffic accidents. However, accurate pedestrian intention prediction in urban environments remains challenging due to the multitude of factors affecting pedestrian behavior. In this paper, we propose a multi-context fusion Transformer (MFT) that leverages diverse numerical contextual attributes across four key dimensions, encompassing pedestrian behavior context, environmental context, pedestrian localization context and vehicle motion context, to enable accurate pedestrian intention prediction. MFT employs a progressive fusion strategy, where mutual intra-context attention enables reciprocal interactions within each context, thereby facilitating feature sequence fusion and yielding a context token as a context-specific representation. This is followed by mutual cross-context attention, which integrates features across contexts with a global CLS token serving as a compact multi-context representation. Finally, guided intra-context attention refines context tokens within each context through directed interactions, while guided cross-context attention strengthens the global CLS token to promote multi-context fusion via guided information propagation, yielding deeper and more efficient integration. Experimental results validate the superiority of MFT over state-of-the-art methods, achieving accuracy rates of 73%, 93%, and 90% on the JAADbeh, JAADall, and PIE datasets, respectively. Extensive ablation studies are further conducted to investigate the effectiveness of the network architecture and contribution of different input context. Our code is open-source: https://github.com/ZhongHang0307/Multi-Context-Fusion-Transformer.

Paperid: 216, https://arxiv.org/pdf/2511.19997.pdf GitHub

Abstract:
Transformers are theoretically reversal-invariant: their function class does not prefer left-to-right over right-to-left mappings. Yet empirical studies on natural language repeatedly report a "reversal curse," and recent work on temporal asymmetry in LLMs suggests that real-world corpora carry their own arrow of time. This leaves an unresolved question: do directional failures stem from linguistic statistics, or from the architecture itself? We cut through this ambiguity with a fully synthetic, entropy-controlled benchmark designed as a clean-room stress test for directional learning. Using random string mappings with tunable branching factor K, we construct forward tasks with zero conditional entropy and inverse tasks with analytically determined entropy floors. Excess loss above these floors reveals that even scratch-trained GPT-2 models exhibit a strong, reproducible directional optimization gap (e.g., 1.16 nats at K=5), far larger than that of an MLP trained on the same data. Pre-trained initializations shift optimization behavior but do not eliminate this gap, while LoRA encounters a sharp capacity wall on high-entropy inverse mappings. Together, these results isolate a minimal, semantics-free signature of directional friction intrinsic to causal Transformer training-one that persists even when linguistic priors, token frequencies, and corpus-level temporal asymmetries are removed. Our benchmark provides a controlled instrument for dissecting directional biases in modern sequence models and motivates deeper mechanistic study of why inversion remains fundamentally harder for Transformers.

Paperid: 217, https://arxiv.org/pdf/2511.19985.pdf GitHub

Abstract:
We propose a novel training-free method for inpainting with off-the-shelf text-to-image models. While guidance-based methods in theory allow generic models to be used for inverse problems such as inpainting, in practice, their effectiveness is limited, leading to the necessity of specialized inpainting-specific models. In this work, we argue that the missing ingredient for training-free inpainting is the optimization (guidance) of the initial seed noise. We propose to optimize the initial seed noise to approximately match the unmasked parts of the data - with as few as a few tens of optimization steps. We then apply conventional training-free inpainting methods on top of our optimized initial seed noise. Critically, we propose two core ideas to effectively implement this idea: (i) to avoid the costly unrolling required to relate the initial noise and the generated outcome, we perform linear approximation; and (ii) to stabilize the optimization, we optimize the initial seed noise in the spectral domain. We demonstrate the effectiveness of our method on various inpainting tasks, outperforming the state of the art. Project page: https://ubc-vision.github.io/sonic/

Paperid: 218, https://arxiv.org/pdf/2511.19984.pdf GitHub

Abstract:
Message passing neural networks (MPNNs) have emerged as go-to models for learning on graph-structured data in the past decade. Despite their effectiveness, most of such models still incur severe issues such as over-smoothing and -correlation, due to their underlying objective of minimizing the Dirichlet energy and the derived neighborhood aggregation operations. In this paper, we propose the DDSM, a new MPNN model built on an optimization framework that includes the stress majorization and orthogonal regularization for overcoming the above issues. Further, we introduce the diffusion distances for nodes into the framework to guide the new message passing operations and develop efficient algorithms for distance approximations, both backed by rigorous theoretical analyses. Our comprehensive experiments showcase that DDSM consistently and considerably outperforms 15 strong baselines on both homophilic and heterophilic graphs.

Paperid: 219, https://arxiv.org/pdf/2511.19957.pdf GitHub

Abstract:
Computer Using Agents (CUAs) are increasingly equipped with external tools, enabling them to perform complex and realistic tasks. For CUAs to operate effectively, application selection, which refers to deciding which application to use before invoking fine-grained tools such as APIs, is a fundamental capability. It determines whether the agent initializes the correct environment, avoids orchestration confusion, and efficiently focuses on relevant context. However, existing benchmarks primarily assess fine-grained API selection, offering limited insight into whether models can reason across and choose between different applications. To fill this gap, we introduce AppSelectBench, a comprehensive benchmark for evaluating application selection in CUAs. AppSelectBench contains a novel user task generation pipeline that produces realistic, diverse, and semantically grounded user intents at scale, together with unified evaluation protocols covering random, heuristic, zero-shot, few-shot, and retrieval-augmented-settings. AppSelectBench covers one hundred widely used desktop applications and includes more than one hundred thousand realistic, diverse, and semantically grounded user tasks. Extensive experiments across both closed-source and open-source large language models reveal systematic strengths and weaknesses in inter-application reasoning, showing that even the most capable models still struggle to make consistent application choices. Together, these results establish AppSelectBench as a foundation for studying and advancing application level reasoning, an essential yet underexplored capability of intelligent CUAs. The source is available at https://microsoft.github.io/appselectbench/.

Paperid: 220, https://arxiv.org/pdf/2511.19925.pdf GitHub

Abstract:
Evaluating the open-form textual responses generated by Large Language Models (LLMs) typically requires measuring the semantic similarity of the response to a (human generated) reference. However, there is evidence that current semantic similarity methods may capture syntactic or lexical forms over semantic content. While benchmarks exist for semantic equivalence, they often suffer from high generation costs due to reliance on subjective human judgment, limited availability for domain-specific applications, and unclear definitions of equivalence. This paper introduces a novel method for generating benchmarks to evaluate semantic similarity methods for LLM outputs, specifically addressing these limitations. Our approach leverages knowledge graphs (KGs) to generate pairs of natural-language statements that are semantically similar or dissimilar, with dissimilar pairs categorized into one of four sub-types. We generate benchmark datasets in four different domains (general knowledge, biomedicine, finance, biology), and conduct a comparative study of semantic similarity methods including traditional natural language processing scores and LLM-as-a-judge predictions. We observe that the sub-type of semantic variation, as well as the domain of the benchmark impact the performance of semantic similarity methods, with no method being consistently superior. Our results present important implications for the use of LLM-as-a-judge in detecting the semantic content of text. Code is available at https://github.com/QiyaoWei/semantic-kg and the dataset is available at https://huggingface.co/datasets/QiyaoWei/Semantic-KG.

Paperid: 221, https://arxiv.org/pdf/2511.19919.pdf GitHub GitHub

Abstract:
Conventional document layout analysis (DLA) traditionally depends on empirical priors or a fixed set of learnable queries executed in a single forward pass. While sufficient for early-generation documents with a small, predetermined number of regions, this paradigm struggles with contemporary documents, which exhibit diverse element counts and increasingly complex layouts. To address challenges posed by modern documents, we present HybriDLA, a novel generative framework that unifies diffusion and autoregressive decoding within a single layer. The diffusion component iteratively refines bounding-box hypotheses, whereas the autoregressive component injects semantic and contextual awareness, enabling precise region prediction even in highly varied layouts. To further enhance detection quality, we design a multi-scale feature-fusion encoder that captures both fine-grained and high-level visual cues. This architecture elevates performance to 83.5% mean Average Precision (mAP). Extensive experiments on the DocLayNet and M$^6$Doc benchmarks demonstrate that HybriDLA sets a state-of-the-art performance, outperforming previous approaches. All data and models will be made publicly available at https://yufanchen96.github.io/projects/HybriDLA.

Paperid: 222, https://arxiv.org/pdf/2511.19900.pdf GitHub

Abstract:
Vision-language agents have achieved remarkable progress in a variety of multimodal reasoning tasks; however, their learning remains constrained by the limitations of human-annotated supervision. Recent self-rewarding approaches attempt to overcome this constraint by allowing models to act as their own critics or reward providers. Yet, purely text-based self-evaluation struggles to verify complex visual reasoning steps and often suffers from evaluation hallucinations. To address these challenges, inspired by recent advances in tool-integrated reasoning, we propose Agent0-VL, a self-evolving vision-language agent that achieves continual improvement with tool-integrated reasoning. Agent0-VL incorporates tool usage not only into reasoning but also into self-evaluation and self-repair, enabling the model to introspect, verify, and refine its reasoning through evidence-grounded analysis. It unifies two synergistic roles within a single LVLM: a Solver that performs multi-turn tool-integrated reasoning, and a Verifier that generates structured feedback and fine-grained self-rewards through tool-grounded critique. These roles interact through a Self-Evolving Reasoning Cycle, where tool-based verification and reinforcement learning jointly align the reasoning and evaluation distributions for stable self-improvement. Through this zero-external-reward evolution, Agent0-VL aligns its reasoning and verification behaviors without any human annotation or external reward models, achieving continual self-improvement. Experiments on geometric problem solving and visual scientific analysis show that Agent0-VL achieves an 12.5% improvement over the base model. Our code is available at https://github.com/aiming-lab/Agent0.

Paperid: 223, https://arxiv.org/pdf/2511.19887.pdf GitHub

Abstract:
Knowledge distillation (KD) has proven highly effective for compressing large models and enhancing the performance of smaller ones. However, its effectiveness diminishes in cross-modal scenarios, such as vision-to-language distillation, where inconsistencies in representation across modalities lead to difficult knowledge transfer. To address this challenge, we propose frequency-decoupled cross-modal knowledge distillation, a method designed to decouple and balance knowledge transfer across modalities by leveraging frequency-domain features. We observed that low-frequency features exhibit high consistency across different modalities, whereas high-frequency features demonstrate extremely low cross-modal similarity. Accordingly, we apply distinct losses to these features: enforcing strong alignment in the low-frequency domain and introducing relaxed alignment for high-frequency features. We also propose a scale consistency loss to address distributional shifts between modalities, and employ a shared classifier to unify feature spaces. Extensive experiments across multiple benchmark datasets show our method substantially outperforms traditional KD and state-of-the-art cross-modal KD approaches. Code is available at https://github.com/Johumliu/FD-CMKD.

Paperid: 224, https://arxiv.org/pdf/2511.19836.pdf GitHub

Abstract:
World Generation Models are emerging as a cornerstone of next-generation multimodal intelligence systems. Unlike traditional 2D visual generation, World Models aim to construct realistic, dynamic, and physically consistent 3D/4D worlds from images, videos, or text. These models not only need to produce high-fidelity visual content but also maintain coherence across space, time, physics, and instruction control, enabling applications in virtual reality, autonomous driving, embodied intelligence, and content creation. However, prior benchmarks emphasize different evaluation dimensions and lack a unified assessment of world-realism capability. To systematically evaluate World Models, we introduce the 4DWorldBench, which measures models across four key dimensions: Perceptual Quality, Condition-4D Alignment, Physical Realism, and 4D Consistency. The benchmark covers tasks such as Image-to-3D/4D, Video-to-4D, Text-to-3D/4D. Beyond these, we innovatively introduce adaptive conditioning across multiple modalities, which not only integrates but also extends traditional evaluation paradigms. To accommodate different modality-conditioned inputs, we map all modality conditions into a unified textual space during evaluation, and further integrate LLM-as-judge, MLLM-as-judge, and traditional network-based methods. This unified and adaptive design enables more comprehensive and consistent evaluation of alignment, physical realism, and cross-modal coherence. Preliminary human studies further demonstrate that our adaptive tool selection achieves closer agreement with subjective human judgments. We hope this benchmark will serve as a foundation for objective comparisons and improvements, accelerating the transition from "visual generation" to "world generation." Our project can be found at https://yeppp27.github.io/4DWorldBench.github.io/.

Paperid: 225, https://arxiv.org/pdf/2511.19835.pdf GitHub

Abstract:
Diffusion Transformers dominate video generation, but the quadratic complexity of attention computation introduces substantial latency. Attention sparsity reduces computational costs by focusing on critical tokens while ignoring non-critical tokens. However, existing methods suffer from severe performance degradation. In this paper, we revisit attention sparsity and reveal that existing methods induce systematic biases in attention allocation: (1) excessive focus on critical tokens amplifies their attention weights; (2) complete neglect of non-critical tokens causes the loss of relevant attention weights. To address these issues, we propose Rectified SpaAttn, which rectifies attention allocation with implicit full attention reference, thereby enhancing the alignment between sparse and full attention maps. Specifically: (1) for critical tokens, we show that their bias is proportional to the sparse attention weights, with the ratio governed by the amplified weights. Accordingly, we propose Isolated-Pooling Attention Reallocation, which calculates accurate rectification factors by reallocating multimodal pooled weights. (2) for non-critical tokens, recovering attention weights from the pooled query-key yields attention gains but also introduces pooling errors. Therefore, we propose Gain-Aware Pooling Rectification, which ensures that the rectified gain consistently surpasses the induced error. Moreover, we customize and integrate the Rectified SpaAttn kernel using Triton, achieving up to 3.33 and 2.08 times speedups on HunyuanVideo and Wan 2.1, respectively, while maintaining high generation quality. We release Rectified SpaAttn as open-source at https://github.com/BienLuky/Rectified-SpaAttn .

Paperid: 226, https://arxiv.org/pdf/2511.19827.pdf GitHub

Abstract:
We present ReDirector, a novel camera-controlled video retake generation method for dynamically captured variable-length videos. In particular, we rectify a common misuse of RoPE in previous works by aligning the spatiotemporal positions of the input video and the target retake. Moreover, we introduce Rotary Camera Encoding (RoCE), a camera-conditioned RoPE phase shift that captures and integrates multi-view relationships within and across the input and target videos. By integrating camera conditions into RoPE, our method generalizes to out-of-distribution camera trajectories and video lengths, yielding improved dynamic object localization and static background preservation. Extensive experiments further demonstrate significant improvements in camera controllability, geometric consistency, and video quality across various trajectories and lengths.

Paperid: 227, https://arxiv.org/pdf/2511.19810.pdf GitHub

Abstract:
We present a case study for the calibration of Low-cost air-quality (LCAQ) CO sensors from one of the largest multi-site-multi-season-multi-sensor-multi-pollutant mobile air-quality monitoring network deployments in India. LCAQ sensors have been shown to play a critical role in the establishment of dense, expansive air-quality monitoring networks and combating elevated pollution levels. The calibration of LCAQ sensors against regulatory-grade monitors is an expensive, laborious and time-consuming process, especially when a large number of sensors are to be deployed in a geographically diverse layout. In this work, we present the RESPIRE technique to calibrate LCAQ sensors to detect ambient CO (Carbon Monoxide) levels. RESPIRE offers specific advantages over baseline calibration methods popular in literature, such as improved prediction in cross-site, cross-season, and cross-sensor settings. RESPIRE offers a training algorithm that is provably resistant to outliers and an explainable model with the ability to flag instances of model overfitting. Empirical results are presented based on data collected during an extensive deployment spanning four sites, two seasons and six sensor packages. RESPIRE code is available at https://github.com/purushottamkar/respire.

Paperid: 228, https://arxiv.org/pdf/2511.19797.pdf GitHub

Abstract:
We propose Terminal Velocity Matching (TVM), a generalization of flow matching that enables high-fidelity one- and few-step generative modeling. TVM models the transition between any two diffusion timesteps and regularizes its behavior at its terminal time rather than at the initial time. We prove that TVM provides an upper bound on the $2$-Wasserstein distance between data and model distributions when the model is Lipschitz continuous. However, since Diffusion Transformers lack this property, we introduce minimal architectural changes that achieve stable, single-stage training. To make TVM efficient in practice, we develop a fused attention kernel that supports backward passes on Jacobian-Vector Products, which scale well with transformer architectures. On ImageNet-256x256, TVM achieves 3.29 FID with a single function evaluation (NFE) and 1.99 FID with 4 NFEs. It similarly achieves 4.32 1-NFE FID and 2.94 4-NFE FID on ImageNet-512x512, representing state-of-the-art performance for one/few-step models from scratch.

Paperid: 229, https://arxiv.org/pdf/2511.19768.pdf GitHub

Abstract:
Large vision-language models (VLMs) have improved embodied question answering (EQA) agents by providing strong semantic priors for open-vocabulary reasoning. However, when used directly for step-level exploration, VLMs often exhibit frontier oscillations, unstable back-and-forth movements caused by overconfidence and miscalibration, leading to inefficient navigation and degraded answer quality. We propose Prune-Then-Plan, a simple and effective framework that stabilizes exploration through step-level calibration. Instead of trusting raw VLM scores, our method prunes implausible frontier choices using a Holm-Bonferroni inspired pruning procedure and then delegates final decisions to a coverage-based planner. This separation converts overconfident predictions into conservative, interpretable actions by relying on human-level judgments to calibrate the step-level behavior of VLMs. Integrated into the 3D-Mem EQA framework, our approach achieves relative improvements of up to 49% and 33% in visually grounded SPL and LLM-Match metrics respectively over baselines. Overall, our method achieves better scene coverage under equal exploration budgets on both OpenEQA and EXPRESS-Bench datasets.

Paperid: 230, https://arxiv.org/pdf/2511.19750.pdf GitHub

Authors:Julien T. T. Vignoud, Valérian Rousset, Hugo El Guedj, Ignacio Aleman, Walid Bennaceur, Batuhan Faik Derinbay, Eduard Ďurech, Damien Gengler, Lucas Giordano, Felix Grimberg, Franziska Lippoldt, Christina Kopidaki, Jiafan Liu, Lauris Lopata, Nathan Maire, Paul Mansat, Martin Milenkoski, Emmanuel Omont, Güneş Özgün, Mina Petrović, Francesco Posa, Morgan Ridel, Giorgio Savini, Marcel Torne, Lucas Trognon, Alyssa Unell, Olena Zavertiaieva, Sai Praneeth Karimireddy, Tahseen Rabbani, Mary-Anne Hartley, Martin Jaggi

Abstract:
Data is often impractical to share for a range of well considered reasons, such as concerns over privacy, intellectual property, and legal constraints. This not only fragments the statistical power of predictive models, but creates an accessibility bias, where accuracy becomes inequitably distributed to those who have the resources to overcome these concerns. We present DISCO: an open-source DIStributed COllaborative learning platform accessible to non-technical users, offering a means to collaboratively build machine learning models without sharing any original data or requiring any programming knowledge. DISCO's web application trains models locally directly in the browser, making our tool cross-platform out-of-the-box, including smartphones. The modular design of \disco offers choices between federated and decentralized paradigms, various levels of privacy guarantees and several approaches to weight aggregation strategies that allow for model personalization and bias resilience in the collaborative training. Code repository is available at https://github.com/epfml/disco and a showcase web interface at https://discolab.ai

Paperid: 231, https://arxiv.org/pdf/2511.19717.pdf GitHub

Abstract:
Community detection, or network clustering, is used to identify latent community structure in networks. Due to the scarcity of labeled ground truth in real-world networks, evaluating these algorithms poses significant challenges. To address this, researchers use synthetic network generators that produce networks with ground-truth community labels. RECCS is one such algorithm that takes a network and its clustering as input and generates a synthetic network through a modular pipeline. Each generated ground truth cluster preserves key characteristics of the corresponding input cluster, including connectivity, minimum degree, and degree sequence distribution. The output consists of a synthetically generated network, and disjoint ground truth cluster labels for all nodes. In this paper, we present two enhanced versions: RECCS+ and RECCS++. RECCS+ maintains algorithmic fidelity to the original RECCS while introducing parallelization through an orchestrator that coordinates algorithmic components across multiple processes and employs multithreading. RECCS++ builds upon this foundation with additional algorithmic optimizations to achieve further speedup. Our experimental results demonstrate that RECCS+ and RECCS++ achieve speedups of up to 49x and 139x respectively on our benchmark datasets, with RECCS++'s additional performance gains involving a modest accuracy tradeoff. With this newfound performance, RECCS++ can now scale to networks with over 100 million nodes and nearly 2 billion edges.

Paperid: 232, https://arxiv.org/pdf/2511.19686.pdf GitHub

Abstract:
Cell counting in biomedical imaging is pivotal for various clinical applications, yet the interpretability of deep learning models in this domain remains a significant challenge. We propose a novel prototype-based method for interpretable cell counting via density map estimation. Our approach integrates a prototype layer into the density estimation network, enabling the model to learn representative visual patterns for both cells and background artifacts. The learned prototypes were evaluated through a survey of biologists, who confirmed the relevance of the visual patterns identified, further validating the interpretability of the model. By generating interpretations that highlight regions in the input image most similar to each prototype, our method offers a clear understanding of how the model identifies and counts cells. Extensive experiments on two public datasets demonstrate that our method achieves interpretability without compromising counting effectiveness. This work provides researchers and clinicians with a transparent and reliable tool for cell counting, potentially increasing trust and accelerating the adoption of deep learning in critical biomedical applications. Code is available at https://github.com/NRT-D4/CountXplain.

Paperid: 233, https://arxiv.org/pdf/2511.19676.pdf GitHub

Abstract:
We introduce INTERLACE, a novel framework that prunes redundant layers in VLMs while maintaining performance through sample-efficient finetuning. Existing layer pruning methods lead to significant performance drop when applied to VLMs. Instead, we analyze triplets of consecutive layers to identify local redundancy, removing the most redundant of the first two layers, finetune the remaining layer to compensate for the lost capacity, and freeze the third layer to serve as a stable anchor during finetuning. We found that this interleaved finetune-freeze design enables rapid convergence with minimal data after pruning. By finetuning only a subset of layers on just 1% of the FineVision dataset for one epoch, Interlace achieves 88.9% average performance retention after dropping 25% of the network, achieving SOTA performance. Our code is available at: https://github.com/pmadinei/Interlace.git

Paperid: 234, https://arxiv.org/pdf/2511.19569.pdf GitHub

Abstract:
Language model inversion (LMI), i.e., recovering hidden prompts from outputs, emerges as a concrete threat to user privacy and system security. We recast LMI as reusing the LLM's own latent space and propose the Invariant Latent Space Hypothesis (ILSH): (1) diverse outputs from the same source prompt should preserve consistent semantics (source invariance), and (2) input<->output cyclic mappings should be self-consistent within a shared latent space (cyclic invariance). Accordingly, we present Inv^2A, which treats the LLM as an invariant decoder and learns only a lightweight inverse encoder that maps outputs to a denoised pseudo-representation. When multiple outputs are available, they are sparsely concatenated at the representation layer to increase information density. Training proceeds in two stages: contrastive alignment (source invariance) and supervised reinforcement (cyclic invariance). An optional training-free neighborhood search can refine local performance. Across 9 datasets covering user and system prompt scenarios, Inv^2A outperforms baselines by an average of 4.77% BLEU score while reducing dependence on large inverse corpora. Our analysis further shows that prevalent defenses provide limited protection, underscoring the need for stronger strategies. The source code and data involved in this paper can be found in https://github.com/yyy01/Invariant_Attacker.

Paperid: 235, https://arxiv.org/pdf/2511.19566.pdf GitHub

Abstract:
Open weight models, which are ubiquitous, rarely provide access to their training data or loss function. This makes modifying such models for tasks such as pruning or unlearning constrained by this unavailability an active area of research. Existing techniques typically require gradients or ground-truth labels, rendering them infeasible in settings with limited computational resources. In this work, we investigate the fundamental question of identifying components that are critical to the model's predictive performance, without access to either gradients or the loss function, and with only distributional access such as synthetic data. We theoretically demonstrate that the global reconstruction error is linearly bounded by local reconstruction errors for Lipschitz-continuous networks such as CNNs and well-trained Transformers (which, contrary to existing literature, we find exhibit Lipschitz continuity). This motivates using the locally reconstructive behavior of component subsets to quantify their global importance, via a metric that we term Subset Fidelity. In the uncorrelated features setting, selecting individual components via their Subset Fidelity scores is optimal, which we use to propose ModHiFi, an algorithm for model modification that requires no training data or loss function access. ModHiFi-P, for structured pruning, achieves an 11% speedup over the current state of the art on ImageNet models and competitive performance on language models. ModHiFi-U, for classwise unlearning, achieves complete unlearning on CIFAR-10 without fine-tuning and demonstrates competitive performance on Swin Transformers.

Paperid: 236, https://arxiv.org/pdf/2511.19542.pdf GitHub

Abstract:
We introduce SpLap, a proxy-free deformation method for Gaussian splats (GS) based on a Laplacian operator computed from our novel surface-aware splat graph. Existing approaches to GS deformation typically rely on deformation proxies such as cages or meshes, but they suffer from dependency on proxy quality and additional computational overhead. An alternative is to directly apply Laplacian-based deformation techniques by treating splats as point clouds. However, this often fail to properly capture surface information due to lack of explicit structure. To address this, we propose a novel method that constructs a surface-aware splat graph, enabling the Laplacian operator derived from it to support more plausible deformations that preserve details and topology. Our key idea is to leverage the spatial arrangement encoded in splats, defining neighboring splats not merely by the distance between their centers, but by their intersections. Furthermore, we introduce a Gaussian kernel adaptation technique that preserves surface structure under deformation, thereby improving rendering quality after deformation. In our experiments, we demonstrate the superior performance of our method compared to both proxy-based and proxy-free baselines, evaluated on 50 challenging objects from the ShapeNet, Objaverse, and Sketchfab datasets, as well as the NeRF-Synthetic dataset. Code is available at https://github.com/kjae0/SpLap.

Paperid: 237, https://arxiv.org/pdf/2511.19535.pdf GitHub

Abstract:
Accurate diagnosis of spitzoid tumors (ST) is critical to ensure a favorable prognosis and to avoid both under- and over-treatment. Epigenetic data, particularly DNA methylation, provide a valuable source of information for this task. However, prior studies assume complete data, an unrealistic setting as methylation profiles frequently contain missing entries due to limited coverage and experimental artifacts. Our work challenges these favorable scenarios and introduces ReMAC, an extension of ReMasker designed to tackle classification tasks on high-dimensional data under complete and incomplete regimes. Evaluation on real clinical data demonstrates that ReMAC achieves strong and robust performance compared to competing classification methods in the stratification of ST. Code is available: https://github.com/roshni-mahtani/ReMAC.

Paperid: 238, https://arxiv.org/pdf/2511.19496.pdf GitHub

Abstract:
Large language models deliver strong reasoning and tool-use skills, yet their computational demands make them impractical for edge or cost-sensitive deployments. We present \textbf{Xmodel-2.5}, a 1.3-billion-parameter small language model designed as a \emph{drop-in agent core}. Training with maximal-update parameterization ($μ$P) allows hyper-parameters tuned on a 20M-parameter proxy to transfer directly to the full model, even under the parameter-tied \emph{tie-word-embedding} architecture. A 1.4T-token Warmup--Stable--Decay curriculum is used, and we further show that \textbf{switching from AdamW to Muon during the decay phase} improves the 13-task reasoning average by 4.58\,\% while keeping every other hyper-parameter fixed, verifying that early AdamW stability can be paired with late Muon sharpening for better downstream performance. FP8-mixed-precision training balances accuracy and throughput. All checkpoints, recipes, and evaluation code are released under the Apache-2.0 license.\footnote{https://huggingface.co/XiaoduoAILab/Xmodel-2.5 and https://huggingface.co/XiaoduoAILab/Xmodel-2.5-history (training checkpoints).} Training code and evaluation harness: https://github.com/XiaoduoAILab/Xmodel-2.5.

Paperid: 239, https://arxiv.org/pdf/2511.19433.pdf GitHub

Abstract:
Vision-language-action (VLA) models have shown remarkable capabilities in robotic manipulation, but their performance is sensitive to the $\textbf{action chunk length}$ used during training, termed $\textbf{horizon}$. Our empirical study reveals an inherent trade-off: longer horizons provide stronger global foresight but degrade fine-grained accuracy, while shorter ones sharpen local control yet struggle on long-term tasks, implying fixed choice of single horizons being suboptimal. To mitigate the trade-off, we propose a $\textbf{mixture of horizons (MoH)}$ strategy. MoH rearranges the action chunk into several segments with different horizons, processes them in parallel with a shared action transformer, and fuses outputs with a light linear gate. It has three appealing benefits. 1) MoH exploits long-term foresight and short-term precision jointly within a single model, improving both performance and generalizability to complex tasks. 2) MoH is plug-and-play for full-attention action modules with minimal training or inference overhead. 3) MoH enables dynamic inference with adaptive horizons, which selects stable actions through cross-horizon consensus, achieving 2.5$\times$ higher throughput than baselines while preserving superior performance. Extensive experiments over flow-based policies $π_0$, $π_{0.5}$, and one-step regression policy $π_{\text{reg}}$ demonstrate that MoH yields consistent and significant gains on both simulations and real-world tasks. Notably, under mixed-task setting, $π_{0.5}$ with MoH reaches a new state-of-the-art with 99$\%$ average success rate on LIBERO after only $30k$ training iterations. Project page: https://github.com/Timsty1/MixtureOfHorizons

Paperid: 240, https://arxiv.org/pdf/2511.19430.pdf GitHub GitHub

Abstract:
Task scheduling is critical for embodied AI, enabling agents to follow natural language instructions and execute actions efficiently in 3D physical worlds. However, existing datasets often simplify task planning by ignoring operations research (OR) knowledge and 3D spatial grounding. In this work, we propose Operations Research knowledge-based 3D Grounded Task Scheduling (ORS3D), a new task that requires the synergy of language understanding, 3D grounding, and efficiency optimization. Unlike prior settings, ORS3D demands that agents minimize total completion time by leveraging parallelizable subtasks, e.g., cleaning the sink while the microwave operates. To facilitate research on ORS3D, we construct ORS3D-60K, a large-scale dataset comprising 60K composite tasks across 4K real-world scenes. Furthermore, we propose GRANT, an embodied multi-modal large language model equipped with a simple yet effective scheduling token mechanism to generate efficient task schedules and grounded actions. Extensive experiments on ORS3D-60K validate the effectiveness of GRANT across language understanding, 3D grounding, and scheduling efficiency. The code is available at https://github.com/H-EmbodVis/GRANT

Paperid: 241, https://arxiv.org/pdf/2511.19426.pdf GitHub GitHub

Abstract:
SAM3D has garnered widespread attention for its strong 3D object reconstruction capabilities. However, a key limitation remains: SAM3D cannot reconstruct specific objects referred to by textual descriptions, a capability that is essential for practical applications such as 3D editing, game development, and virtual environments. To address this gap, we introduce Ref-SAM3D, a simple yet effective extension to SAM3D that incorporates textual descriptions as a high-level prior, enabling text-guided 3D reconstruction from a single RGB image. Through extensive qualitative experiments, we show that Ref-SAM3D, guided only by natural language and a single 2D view, delivers competitive and high-fidelity zero-shot reconstruction performance. Our results demonstrate that Ref-SAM3D effectively bridges the gap between 2D visual cues and 3D geometric understanding, offering a more flexible and accessible paradigm for reference-guided 3D reconstruction. Code is available at: https://github.com/FudanCVL/Ref-SAM3D.

Paperid: 242, https://arxiv.org/pdf/2511.19418.pdf GitHub

Abstract:
Vision-Language Models (VLMs) excel at reasoning in linguistic space but struggle with perceptual understanding that requires dense visual perception, e.g., spatial reasoning and geometric awareness. This limitation stems from the fact that current VLMs have limited mechanisms to capture dense visual information across spatial dimensions. We introduce Chain-of-Visual-Thought (COVT), a framework that enables VLMs to reason not only in words but also through continuous visual tokens-compact latent representations that encode rich perceptual cues. Within a small budget of roughly 20 tokens, COVT distills knowledge from lightweight vision experts, capturing complementary properties such as 2D appearance, 3D geometry, spatial layout, and edge structure. During training, the VLM with COVT autoregressively predicts these visual tokens to reconstruct dense supervision signals (e.g., depth, segmentation, edges, and DINO features). At inference, the model reasons directly in the continuous visual token space, preserving efficiency while optionally decoding dense predictions for interpretability. Evaluated across more than ten diverse perception benchmarks, including CV-Bench, MMVP, RealWorldQA, MMStar, WorldMedQA, and HRBench, integrating COVT into strong VLMs such as Qwen2.5-VL and LLaVA consistently improves performance by 3% to 16% and demonstrates that compact continuous visual thinking enables more precise, grounded, and interpretable multimodal intelligence.

Paperid: 243, https://arxiv.org/pdf/2511.19413.pdf GitHub

Abstract:
Unified Multimodal Models (UMMs) have shown impressive performance in both understanding and generation with a single architecture. However, UMMs still exhibit a fundamental inconsistency: understanding favors compact embeddings, whereas generation favors reconstruction-rich representations. This structural trade-off produces misaligned decision boundaries, degraded cross-modal coherence, and heightened vulnerability under distributional and adversarial shifts. In this paper, we present UniGame, a self-adversarial post-training framework that directly targets the inconsistencies. By applying a lightweight perturber at the shared token interface, UniGame enables the generation branch to actively seek and challenge fragile understanding, turning the model itself into its own adversary. Experiments demonstrate that UniGame significantly improves the consistency (+4.6%). Moreover, it also achieves substantial improvements in understanding (+3.6%), generation (+0.02), out-of-distribution and adversarial robustness (+4.8% and +6.2% on NaturalBench and AdVQA). The framework is architecture-agnostic, introduces less than 1% additional parameters, and is complementary to existing post-training methods. These results position adversarial self-play as a general and effective principle for enhancing the coherence, stability, and unified competence of future multimodal foundation models. The official code is available at: https://github.com/AIFrontierLab/UniGame

Paperid: 244, https://arxiv.org/pdf/2511.19365.pdf GitHub GitHub GitHub

Abstract:
Pixel diffusion aims to generate images directly in pixel space in an end-to-end fashion. This approach avoids the limitations of VAE in the two-stage latent diffusion, offering higher model capacity. Existing pixel diffusion models suffer from slow training and inference, as they usually model both high-frequency signals and low-frequency semantics within a single diffusion transformer (DiT). To pursue a more efficient pixel diffusion paradigm, we propose the frequency-DeCoupled pixel diffusion framework. With the intuition to decouple the generation of high and low frequency components, we leverage a lightweight pixel decoder to generate high-frequency details conditioned on semantic guidance from the DiT. This thus frees the DiT to specialize in modeling low-frequency semantics. In addition, we introduce a frequency-aware flow-matching loss that emphasizes visually salient frequencies while suppressing insignificant ones. Extensive experiments show that DeCo achieves superior performance among pixel diffusion models, attaining FID of 1.62 (256x256) and 2.22 (512x512) on ImageNet, closing the gap with latent diffusion methods. Furthermore, our pretrained text-to-image model achieves a leading overall score of 0.86 on GenEval in system-level comparison. Codes are publicly available at https://github.com/Zehong-Ma/DeCo.

Paperid: 245, https://arxiv.org/pdf/2511.19343.pdf GitHub

Abstract:
RL (reinforcement learning) methods (e.g., GRPO) for MLLM (Multimodal LLM) perception ability has attracted wide research interest owing to its remarkable generalization ability. Nevertheless, existing reinforcement learning methods still face the problem of low data quality, where data samples cannot elicit diverse responses from MLLMs, thus restricting the exploration scope for MLLM reinforcement learning. Some methods attempt to mitigate this problem by imposing constraints on entropy, but none address it at its root. Therefore, to tackle this problem, this work proposes Syn-GRPO (Synthesis-GRPO), which employs an online data generator to synthesize high-quality training data with diverse responses in GRPO training. Specifically, Syn-GRPO consists of two components: (1) data server; (2) GRPO workflow. The data server synthesizes new samples from existing ones using an image generation model, featuring a decoupled and asynchronous scheme to achieve high generation efficiency. The GRPO workflow provides the data server with the new image descriptions, and it leverages a diversity reward to supervise the MLLM to predict image descriptions for synthesizing samples with diverse responses. Experiment results across three visual perception tasks demonstrate that Syn-GRPO improves the data quality by a large margin, achieving significant superior performance to existing MLLM perception methods, and Syn-GRPO presents promising potential for scaling long-term self-evolving RL. Our code is available at https://github.com/hqhQAQ/Syn-GRPO.

Paperid: 246, https://arxiv.org/pdf/2511.19319.pdf GitHub

Abstract:
Hand-Object Interaction (HOI) generation plays a critical role in advancing applications across animation and robotics. Current video-based methods are predominantly single-view, which impedes comprehensive 3D geometry perception and often results in geometric distortions or unrealistic motion patterns. While 3D HOI approaches can generate dynamically plausible motions, their dependence on high-quality 3D data captured in controlled laboratory settings severely limits their generalization to real-world scenarios. To overcome these limitations, we introduce SyncMV4D, the first model that jointly generates synchronized multi-view HOI videos and 4D motions by unifying visual prior, motion dynamics, and multi-view geometry. Our framework features two core innovations: (1) a Multi-view Joint Diffusion (MJD) model that co-generates HOI videos and intermediate motions, and (2) a Diffusion Points Aligner (DPA) that refines the coarse intermediate motion into globally aligned 4D metric point tracks. To tightly couple 2D appearance with 4D dynamics, we establish a closed-loop, mutually enhancing cycle. During the diffusion denoising process, the generated video conditions the refinement of the 4D motion, while the aligned 4D point tracks are reprojected to guide next-step joint generation. Experimentally, our method demonstrates superior performance to state-of-the-art alternatives in visual realism, motion plausibility, and multi-view consistency.

Paperid: 247, https://arxiv.org/pdf/2511.19314.pdf GitHub

Abstract:
Information-seeking is a core capability for AI agents, requiring them to gather and reason over tool-generated information across long trajectories. However, such multi-step information-seeking tasks remain challenging for agents backed by language models. While process reward models (PRMs) can guide agents by ranking candidate steps at test-time, existing PRMs, designed for short reasoning with binary judgment, cannot capture richer dimensions of information-seeking steps, such as tool interactions and reasoning over tool outputs, nor handle the rapidly growing context in long-horizon tasks. To address these limitations, we introduce PRInTS, a generative PRM trained with dual capabilities: (1) dense scoring based on the PRM's reasoning across multiple step quality dimensions (e.g., interpretation of tool outputs, tool call informativeness) and (2) trajectory summarization that compresses the growing context while preserving essential information for step evaluation. Extensive evaluations across FRAMES, GAIA (levels 1-3), and WebWalkerQA (easy-hard) benchmarks on multiple models, along with ablations, reveal that best-of-n sampling with PRInTS enhances information-seeking abilities of open-source models as well as specialized agents, matching or surpassing the performance of frontier models with a much smaller backbone agent and outperforming other strong reward modeling baselines.

Paperid: 248, https://arxiv.org/pdf/2511.19304.pdf GitHub

Abstract:
Humans naturally adapt to diverse environments by learning underlying rules across worlds with different dynamics, observations, and reward structures. In contrast, existing agents typically demonstrate improvements via self-evolving within a single domain, implicitly assuming a fixed environment distribution. Cross-environment learning has remained largely unmeasured: there is no standard collection of controllable, heterogeneous environments, nor a unified way to represent how agents learn. We address these gaps in two steps. First, we propose AutoEnv, an automated framework that treats environments as factorizable distributions over transitions, observations, and rewards, enabling low-cost (4.12 USD on average) generation of heterogeneous worlds. Using AutoEnv, we construct AutoEnv-36, a dataset of 36 environments with 358 validated levels, on which seven language models achieve 12-49% normalized reward, demonstrating the challenge of AutoEnv-36. Second, we formalize agent learning as a component-centric process driven by three stages of Selection, Optimization, and Evaluation applied to an improvable agent component. Using this formulation, we design eight learning methods and evaluate them on AutoEnv-36. Empirically, the gain of any single learning method quickly decrease as the number of environments increases, revealing that fixed learning methods do not scale across heterogeneous environments. Environment-adaptive selection of learning methods substantially improves performance but exhibits diminishing returns as the method space expands. These results highlight both the necessity and the current limitations of agent learning for scalable cross-environment generalization, and position AutoEnv and AutoEnv-36 as a testbed for studying cross-environment agent learning. The code is avaiable at https://github.com/FoundationAgents/AutoEnv.

Paperid: 249, https://arxiv.org/pdf/2511.19269.pdf GitHub

Abstract:
Diffusion Language Models (DLMs) offer a promising parallel generation paradigm but suffer from slow inference due to numerous refinement steps and the inability to use standard KV caching. We introduce CDLM (Consistency Diffusion Language Models), a training-based acceleration method that simultaneously tackles both bottlenecks. CDLM integrates consistency modeling to drastically reduce the number of required sampling steps by enabling multi-token finalization. Furthermore, we enforce a block-wise causal attention mask during fine-tuning, making the model fully compatible with KV caching. Experiments show CDLM achieves 3.6x-14.5x lower latency while maintaining competitive accuracy on math and coding tasks. The full training and evaluation code is available at https://github.com/SqueezeAILab/CDLM.

Paperid: 250, https://arxiv.org/pdf/2511.19268.pdf GitHub

Abstract:
Conditional image generation enhances text-to-image synthesis with structural, spatial, or stylistic priors, but current methods face challenges in handling conflicts between sources. These include 1) input-level conflicts, where the conditioning image contradicts the text prompt, and 2) model-bias conflicts, where generative biases disrupt alignment even when conditions match the text. Addressing these conflicts requires nuanced solutions, which standard supervised fine-tuning struggles to provide. Preference-based optimization techniques like Direct Preference Optimization (DPO) show promise but are limited by gradient entanglement between text and condition signals and lack disentangled training data for multi-constraint tasks. To overcome this, we propose a bidirectionally decoupled DPO framework (BideDPO). Our method creates two disentangled preference pairs-one for the condition and one for the text-to reduce gradient entanglement. The influence of pairs is managed using an Adaptive Loss Balancing strategy for balanced optimization. We introduce an automated data pipeline to sample model outputs and generate conflict-aware data. This process is embedded in an iterative optimization strategy that refines both the model and the data. We construct a DualAlign benchmark to evaluate conflict resolution between text and condition. Experiments show BideDPO significantly improves text success rates (e.g., +35%) and condition adherence. We also validate our approach using the COCO dataset. Project Pages: https://limuloo.github.io/BideDPO/.

Paperid: 251, https://arxiv.org/pdf/2511.19229.pdf GitHub

Abstract:
Diffusion Transformer(DiT) based video generation models have recently achieved impressive visual quality and temporal coherence, but they still frequently violate basic physical laws and commonsense dynamics, revealing a lack of explicit world knowledge. In this work, we explore how to equip them with a plug-and-play memory that injects useful world knowledge. Motivated by in-context memory in Transformer-based LLMs, we conduct empirical studies to show that DiT can be steered via interventions on its hidden states, and simple low-pass and high-pass filters in the embedding space naturally disentangle low-level appearance and high-level physical/semantic cues, enabling targeted guidance. Building on these observations, we propose a learnable memory encoder DiT-Mem, composed of stacked 3D CNNs, low-/high-pass filters, and self-attention layers. The encoder maps reference videos into a compact set of memory tokens, which are concatenated as the memory within the DiT self-attention layers. During training, we keep the diffusion backbone frozen, and only optimize the memory encoder. It yields a rather efficient training process on few training parameters (150M) and 10K data samples, and enables plug-and-play usage at inference time. Extensive experiments on state-of-the-art models demonstrate the effectiveness of our method in improving physical rule following and video fidelity. Our code and data are publicly released here: https://thrcle421.github.io/DiT-Mem-Web/.

Paperid: 252, https://arxiv.org/pdf/2511.19183.pdf GitHub

Abstract:
Semantic segmentation is crucial for various biomedical applications, yet its reliance on large annotated datasets presents a bottleneck due to the high cost and specialized expertise required for manual labeling. Active Learning (AL) aims to mitigate this challenge by querying only the most informative samples, thereby reducing annotation effort. However, in the domain of 3D biomedical imaging, there is no consensus on whether AL consistently outperforms Random sampling. Four evaluation pitfalls hinder the current methodological assessment. These are (1) restriction to too few datasets and annotation budgets, (2) using 2D models on 3D images without partial annotations, (3) Random baseline not being adapted to the task, and (4) measuring annotation cost only in voxels. In this work, we introduce nnActive, an open-source AL framework that overcomes these pitfalls by (1) means of a large scale study spanning four biomedical imaging datasets and three label regimes, (2) extending nnU-Net by using partial annotations for training with 3D patch-based query selection, (3) proposing Foreground Aware Random sampling strategies tackling the foreground-background class imbalance of medical images and (4) propose the foreground efficiency metric, which captures the low annotation cost of background-regions. We reveal the following findings: (A) while all AL methods outperform standard Random sampling, none reliably surpasses an improved Foreground Aware Random sampling; (B) benefits of AL depend on task specific parameters; (C) Predictive Entropy is overall the best performing AL method, but likely requires the most annotation effort; (D) AL performance can be improved with more compute intensive design choices. As a holistic, open-source framework, nnActive can serve as a catalyst for research and application of AL in 3D biomedical imaging. Code is at: https://github.com/MIC-DKFZ/nnActive

Paperid: 253, https://arxiv.org/pdf/2511.19172.pdf GitHub

Abstract:
Recently, 3D Gaussian Splatting and its derivatives have achieved significant breakthroughs in large-scale scene reconstruction. However, how to efficiently and stably achieve high-quality geometric fidelity remains a core challenge. To address this issue, we introduce MetroGS, a novel Gaussian Splatting framework for efficient and robust reconstruction in complex urban environments. Our method is built upon a distributed 2D Gaussian Splatting representation as the core foundation, serving as a unified backbone for subsequent modules. To handle potential sparse regions in complex scenes, we propose a structured dense enhancement scheme that utilizes SfM priors and a pointmap model to achieve a denser initialization, while incorporating a sparsity compensation mechanism to improve reconstruction completeness. Furthermore, we design a progressive hybrid geometric optimization strategy that organically integrates monocular and multi-view optimization to achieve efficient and accurate geometric refinement. Finally, to address the appearance inconsistency commonly observed in large-scale scenes, we introduce a depth-guided appearance modeling approach that learns spatial features with 3D consistency, facilitating effective decoupling between geometry and appearance and further enhancing reconstruction stability. Experiments on large-scale urban datasets demonstrate that MetroGS achieves superior geometric accuracy, rendering quality, offering a unified solution for high-fidelity large-scale scene reconstruction.

Paperid: 254, https://arxiv.org/pdf/2511.19171.pdf GitHub

Abstract:
Research on the safety evaluation of large language models (LLMs) has become extensive, driven by jailbreak studies that elicit unsafe responses. Such response involves information already available to humans, such as the answer to "how to make a bomb". When LLMs are jailbroken, the practical threat they pose to humans is negligible. However, it remains unclear whether LLMs commonly produce unpredictable outputs that could pose substantive threats to human safety. To address this gap, we study whether LLM-generated content contains potential existential threats, defined as outputs that imply or promote direct harm to human survival. We propose \textsc{ExistBench}, a benchmark designed to evaluate such risks. Each sample in \textsc{ExistBench} is derived from scenarios where humans are positioned as adversaries to AI assistants. Unlike existing evaluations, we use prefix completion to bypass model safeguards. This leads the LLMs to generate suffixes that express hostility toward humans or actions with severe threat, such as the execution of a nuclear strike. Our experiments on 10 LLMs reveal that LLM-generated content indicates existential threats. To investigate the underlying causes, we also analyze the attention logits from LLMs. To highlight real-world safety risks, we further develop a framework to assess model behavior in tool-calling. We find that LLMs actively select and invoke external tools with existential threats. Code and data are available at: https://github.com/cuiyu-ai/ExistBench.

Paperid: 255, https://arxiv.org/pdf/2511.19162.pdf GitHub

Abstract:
Bioart's hybrid nature spanning art, science, technology, ethics, and politics defies traditional single-axis categorization. I present BioArtlas, analyzing 81 bioart works across thirteen curated dimensions using novel axis-aware representations that preserve semantic distinctions while enabling cross-dimensional comparison. Our codebook-based approach groups related concepts into unified clusters, addressing polysemy in cultural terminology. Comprehensive evaluation of up to 800 representation-space-algorithm combinations identifies Agglomerative clustering at k=15 on 4D UMAP as optimal (silhouette 0.664 +/- 0.008, trustworthiness/continuity 0.805/0.812). The approach reveals four organizational patterns: artist-specific methodological cohesion, technique-based segmentation, temporal artistic evolution, and trans-temporal conceptual affinities. By separating analytical optimization from public communication, I provide rigorous analysis and accessible exploration through an interactive web interface (https://www.bioartlas.com) with the dataset publicly available (https://github.com/joonhyungbae/BioArtlas).

Paperid: 256, https://arxiv.org/pdf/2511.19135.pdf GitHub

Abstract:
Multi-rotor UAVs face limited flight time due to battery constraints. Autonomous docking on blimps with onboard battery recharging and data offloading offers a promising solution for extended UAV missions. However, the vulnerability of blimps to wind gusts causes trajectory deviations, requiring precise, obstacle-aware docking strategies. To this end, this work introduces two key novelties: (i) a temporal convolutional network that predicts blimp responses to wind gusts, enabling rapid gust detection and estimation of points where the wind gust effect has subsided; (ii) a model predictive controller (MPC) that leverages these predictions to compute collision-free trajectories for docking, enabled by a novel obstacle avoidance method for close-range manoeuvres near the blimp. Simulation results show our method outperforms a baseline constant-velocity model of the blimp significantly across different scenarios. We further validate the approach in real-world experiments, demonstrating the first autonomous multi-rotor docking control strategy on blimps shown outside simulation. Source code is available here https://github.com/robot-perception-group/multi_rotor_airship_docking.

Paperid: 257, https://arxiv.org/pdf/2511.19117.pdf GitHub

Abstract:
The miniaturization of thermal sensors for mobile platforms inherently limits their spatial resolution and textural fidelity, leading to blurry and less informative images. Existing thermal super-resolution (SR) methods can be grouped into single-image and RGB-guided approaches: the former struggles to recover fine structures from limited information, while the latter relies on accurate and laborious cross-camera calibration, which hinders practical deployment and robustness. Here, we propose 3M-TI, a calibration-free Multi-camera cross-Modality diffusion framework for Mobile Thermal Imaging. At its core, 3M-TI integrates a cross-modal self-attention module (CSM) into the diffusion UNet, replacing the original self-attention layers to adaptively align thermal and RGB features throughout the denoising process, without requiring explicit camera calibration. This design enables the diffusion network to leverage its generative prior to enhance spatial resolution, structural fidelity, and texture detail in the super-resolved thermal images. Extensive evaluations on real-world mobile thermal cameras and public benchmarks validate our superior performance, achieving state-of-the-art results in both visual quality and quantitative metrics. More importantly, the thermal images enhanced by 3M-TI lead to substantial gains in critical downstream tasks like object detection and segmentation, underscoring its practical value for robust mobile thermal perception systems. More materials: https://github.com/work-submit/3MTI.

Paperid: 258, https://arxiv.org/pdf/2511.19105.pdf GitHub

Abstract:
WiFi-based human pose estimation (HPE) has attracted increasing attention due to its resilience to occlusion and privacy-preserving compared to camera-based methods. However, existing WiFi-based HPE approaches often employ regression networks that directly map WiFi channel state information (CSI) to 3D joint coordinates, ignoring the inherent topological relationships among human joints. In this paper, we present GraphPose-Fi, a graph-based framework that explicitly models skeletal topology for WiFi-based 3D HPE. Our framework comprises a CNN encoder shared across antennas for subcarrier-time feature extraction, a lightweight attention module that adaptively reweights features over time and across antennas, and a graph-based regression head that combines GCN layers with self-attention to capture local topology and global dependencies. Our proposed method significantly outperforms existing methods on the MM-Fi dataset in various settings. The source code is available at: https://github.com/Cirrick/GraphPose-Fi.

Paperid: 259, https://arxiv.org/pdf/2511.19083.pdf GitHub

Abstract:
In-context learning (ICL) with large language models (LLMs) has emerged as a promising paradigm for named entity recognition (NER) in low-resource scenarios. However, existing ICL-based NER methods suffer from three key limitations: (1) reliance on dynamic retrieval of annotated examples, which is problematic when annotated data is scarce; (2) limited generalization to unseen domains due to the LLM's insufficient internal domain knowledge; and (3) failure to incorporate external knowledge or resolve entity ambiguities. To address these challenges, we propose KDR-Agent, a novel multi-agent framework for multi-domain low-resource in-context NER that integrates Knowledge retrieval, Disambiguation, and Reflective analysis. KDR-Agent leverages natural-language type definitions and a static set of entity-level contrastive demonstrations to reduce dependency on large annotated corpora. A central planner coordinates specialized agents to (i) retrieve factual knowledge from Wikipedia for domain-specific mentions, (ii) resolve ambiguous entities via contextualized reasoning, and (iii) reflect on and correct model predictions through structured self-assessment. Experiments across ten datasets from five domains demonstrate that KDR-Agent significantly outperforms existing zero-shot and few-shot ICL baselines across multiple LLM backbones. The code and data can be found at https://github.com/MWXGOD/KDR-Agent.

Paperid: 260, https://arxiv.org/pdf/2511.19046.pdf GitHub

Abstract:
Medical image segmentation is fundamental for biomedical discovery. Existing methods lack generalizability and demand extensive, time-consuming manual annotation for new clinical application. Here, we propose MedSAM-3, a text promptable medical segmentation model for medical image and video segmentation. By fine-tuning the Segment Anything Model (SAM) 3 architecture on medical images paired with semantic conceptual labels, our MedSAM-3 enables medical Promptable Concept Segmentation (PCS), allowing precise targeting of anatomical structures via open-vocabulary text descriptions rather than solely geometric prompts. We further introduce the MedSAM-3 Agent, a framework that integrates Multimodal Large Language Models (MLLMs) to perform complex reasoning and iterative refinement in an agent-in-the-loop workflow. Comprehensive experiments across diverse medical imaging modalities, including X-ray, MRI, Ultrasound, CT, and video, demonstrate that our approach significantly outperforms existing specialist and foundation models. We will release our code and model at https://github.com/Joey-S-Liu/MedSAM3.

Paperid: 261, https://arxiv.org/pdf/2511.19024.pdf GitHub GitHub

Abstract:
Blind image quality assessment (BIQA) plays a crucial role in evaluating and optimizing visual experience. Most existing BIQA approaches fuse shallow and deep features extracted from backbone networks, while overlooking the unequal contributions to quality prediction. Moreover, while various vision encoder backbones are widely adopted in BIQA, the effective quality decoding architectures remain underexplored. To address these limitations, this paper investigates the contributions of shallow and deep features to BIQA, and proposes a effective quality feature decoding framework via GCN-enhanced \underline{l}ayer\underline{i}nteraction and MoE-based \underline{f}eature d\underline{e}coupling, termed \textbf{(Life-IQA)}. Specifically, the GCN-enhanced layer interaction module utilizes the GCN-enhanced deepest-layer features as query and the penultimate-layer features as key, value, then performs cross-attention to achieve feature interaction. Moreover, a MoE-based feature decoupling module is proposed to decouple fused representations though different experts specialized for specific distortion types or quality dimensions. Extensive experiments demonstrate that Life-IQA shows more favorable balance between accuracy and cost than a vanilla Transformer decoder and achieves state-of-the-art performance on multiple BIQA benchmarks.The code is available at: \href{https://github.com/TANGLONG2/Life-IQA/tree/main}{\texttt{Life-IQA}}.

Paperid: 262, https://arxiv.org/pdf/2511.18993.pdf GitHub

Abstract:
With the rapid advancement of sophisticated synthetic audio-visual content, e.g., for subtle malicious manipulations, ensuring the integrity of digital media has become paramount. This work presents a novel approach to temporal localization of deepfakes by leveraging Audio-Visual Speech Representation Reconstruction (AuViRe). Specifically, our approach reconstructs speech representations from one modality (e.g., lip movements) based on the other (e.g., audio waveform). Cross-modal reconstruction is significantly more challenging in manipulated video segments, leading to amplified discrepancies, thereby providing robust discriminative cues for precise temporal forgery localization. AuViRe outperforms the state of the art by +8.9 AP@0.95 on LAV-DF, +9.6 AP@0.5 on AV-Deepfake1M, and +5.1 AUC on an in-the-wild experiment. Code available at https://github.com/mever-team/auvire.

Paperid: 263, https://arxiv.org/pdf/2511.18991.pdf GitHub

Abstract:
Video generation models have made significant progress in generating realistic content, enabling applications in simulation, gaming, and film making. However, current generated videos still contain visual artifacts arising from 3D inconsistencies, e.g., objects and structures deforming under changes in camera pose, which can undermine user experience and simulation fidelity. Motivated by recent findings on representation alignment for diffusion models, we hypothesize that improving the multi-view consistency of video diffusion representations will yield more 3D-consistent video generation. Through detailed analysis on multiple recent camera-controlled video diffusion models we reveal strong correlations between 3D-consistent representations and videos. We also propose ViCoDR, a new approach for improving the 3D consistency of video models by learning multi-view consistent diffusion representations. We evaluate ViCoDR on camera controlled image-to-video, text-to-video, and multi-view generation models, demonstrating significant improvements in the 3D consistency of the generated videos. Project page: https://danier97.github.io/ViCoDR.

Paperid: 264, https://arxiv.org/pdf/2511.18942.pdf GitHub

Abstract:
Flow Matching (FM) has recently emerged as a principled and efficient alternative to diffusion models. Standard FM encourages the learned velocity field to follow a target direction; however, it may accumulate errors along the trajectory and drive samples off the data manifold, leading to perceptual degradation, especially in lightweight or low-step configurations. To enhance stability and generalization, we extend FM into a balanced attract-repel scheme that provides explicit guidance on both "where to go" and "where not to go." To be formal, we propose \textbf{Velocity Contrastive Regularization (VeCoR)}, a complementary training scheme for flow-based generative modeling that augments the standard FM objective with contrastive, two-sided supervision. VeCoR not only aligns the predicted velocity with a stable reference direction (positive supervision) but also pushes it away from inconsistent, off-manifold directions (negative supervision). This contrastive formulation transforms FM from a purely attractive, one-sided objective into a two-sided training signal, regularizing trajectory evolution and improving perceptual fidelity across datasets and backbones. On ImageNet-1K 256$\times$256, VeCoR yields 22\% and 35\% relative FID reductions on SiT-XL/2 and REPA-SiT-XL/2 backbones, respectively, and achieves further FID gains (32\% relative) on MS-COCO text-to-image generation, demonstrating consistent improvements in stability, convergence, and image quality, particularly in low-step and lightweight settings. Project page: https://p458732.github.io/VeCoR_Project_Page/

Paperid: 265, https://arxiv.org/pdf/2511.18934.pdf GitHub

Abstract:
The task of translating natural language questions into query languages has long been a central focus in semantic parsing. Recent advancements in Large Language Models (LLMs) have significantly accelerated progress in this field. However, existing studies typically focus on a single query language, resulting in methods with limited generalizability across different languages. In this paper, we formally define the Text-to-Query task paradigm, unifying semantic parsing tasks across various query languages. We identify query skeletons as a shared optimization target of Text-to-Query tasks, and propose a general dynamic data augmentation framework that explicitly diagnoses model-specific weaknesses in handling these skeletons to synthesize targeted training data. Experiments on four Text-to-Query benchmarks demonstrate that our method achieves state-of-the-art performance using only a small amount of synthesized data, highlighting the efficiency and generality of our approach and laying a solid foundation for unified research on Text-to-Query tasks. We release our code at https://github.com/jjjycaptain/Skeletron.

Paperid: 266, https://arxiv.org/pdf/2511.18933.pdf GitHub

Abstract:
Large Language Models (LLMs) remain susceptible to jailbreak exploits that bypass safety filters and induce harmful or unethical behavior. This work presents a systematic taxonomy of existing jailbreak defenses across prompt-level, model-level, and training-time interventions, followed by three proposed defense strategies. First, a Prompt-Level Defense Framework detects and neutralizes adversarial inputs through sanitization, paraphrasing, and adaptive system guarding. Second, a Logit-Based Steering Defense reinforces refusal behavior through inference-time vector steering in safety-sensitive layers. Third, a Domain-Specific Agent Defense employs the MetaGPT framework to enforce structured, role-based collaboration and domain adherence. Experiments on benchmark datasets show substantial reductions in attack success rate, achieving full mitigation under the agent-based defense. Overall, this study highlights how jailbreaks pose a significant security threat to LLMs and identifies key intervention points for prevention, while noting that defense strategies often involve trade-offs between safety, performance, and scalability. Code is available at: https://github.com/Kuro0911/CS5446-Project

Paperid: 267, https://arxiv.org/pdf/2511.18922.pdf GitHub

Abstract:
We present One4D, a unified framework for 4D generation and reconstruction that produces dynamic 4D content as synchronized RGB frames and pointmaps. By consistently handling varying sparsities of conditioning frames through a Unified Masked Conditioning (UMC) mechanism, One4D can seamlessly transition between 4D generation from a single image, 4D reconstruction from a full video, and mixed generation and reconstruction from sparse frames. Our framework adapts a powerful video generation model for joint RGB and pointmap generation, with carefully designed network architectures. The commonly used diffusion finetuning strategies for depthmap or pointmap reconstruction often fail on joint RGB and pointmap generation, quickly degrading the base video model. To address this challenge, we introduce Decoupled LoRA Control (DLC), which employs two modality-specific LoRA adapters to form decoupled computation branches for RGB frames and pointmaps, connected by lightweight, zero-initialized control links that gradually learn mutual pixel-level consistency. Trained on a mixture of synthetic and real 4D datasets under modest computational budgets, One4D produces high-quality RGB frames and accurate pointmaps across both generation and reconstruction tasks. This work represents a step toward general, high-quality geometry-based 4D world modeling using video diffusion models. Project page: https://mizhenxing.github.io/One4D

Paperid: 268, https://arxiv.org/pdf/2511.18921.pdf GitHub

Abstract:
Backdoor attacks undermine the reliability and trustworthiness of machine learning systems by injecting hidden behaviors that can be maliciously activated at inference time. While such threats have been extensively studied in unimodal settings, their impact on multimodal foundation models, particularly vision-language models (VLMs), remains largely underexplored. In this work, we introduce \textbf{BackdoorVLM}, the first comprehensive benchmark for systematically evaluating backdoor attacks on VLMs across a broad range of settings. It adopts a unified perspective that injects and analyzes backdoors across core vision-language tasks, including image captioning and visual question answering. BackdoorVLM organizes multimodal backdoor threats into 5 representative categories: targeted refusal, malicious injection, jailbreak, concept substitution, and perceptual hijack. Each category captures a distinct pathway through which an adversary can manipulate a model's behavior. We evaluate these threats using 12 representative attack methods spanning text, image, and bimodal triggers, tested on 2 open-source VLMs and 3 multimodal datasets. Our analysis reveals that VLMs exhibit strong sensitivity to textual instructions, and in bimodal backdoors the text trigger typically overwhelms the image trigger when forming the backdoor mapping. Notably, backdoors involving the textual modality remain highly potent, with poisoning rates as low as 1\% yielding over 90\% success across most tasks. These findings highlight significant, previously underexplored vulnerabilities in current VLMs. We hope that BackdoorVLM can serve as a useful benchmark for analyzing and mitigating multimodal backdoor threats. Code is available at: https://github.com/bin015/BackdoorVLM .

Paperid: 269, https://arxiv.org/pdf/2511.18891.pdf GitHub

Abstract:
In this reproducibility study, we revisit the LLAMBO framework of Daxberger et al. (2024), a prompting-based Bayesian optimization (BO) method that uses large language models as discriminative surrogates and acquisition optimizers via text-only interactions. We replicate the core Bayesmark and HPOBench experiments under the original evaluation protocol, but replace GPT-3.5 with the open-weight Llama 3.1 70B model used for all text encoding components. Our results broadly confirm the main claims of LLAMBO. Contextual warm starting via textual problem and hyperparameter descriptions substantially improves early regret behaviour and reduces variance across runs. LLAMBO's discriminative surrogate is weaker than GP or SMAC as a pure single task regressor, yet benefits from cross task semantic priors induced by the language model. Ablations that remove textual context markedly degrade predictive accuracy and calibration, while the LLAMBO candidate sampler consistently generates higher quality and more diverse proposals than TPE or random sampling. Experiments with smaller backbones (Gemma 27B, Llama 3.1 8B) yield unstable or invalid predictions, suggesting insufficient capacity for reliable surrogate behaviour. Overall, our study shows that the LLAMBO architecture is robust to changing the language model backbone and remains effective when instantiated with Llama 3.1 70B.

Paperid: 270, https://arxiv.org/pdf/2511.18874.pdf GitHub

Abstract:
Multimodal trajectory prediction generates multiple plausible future trajectories to address vehicle motion uncertainty from intention ambiguity and execution variability. However, HD map-dependent models suffer from costly data acquisition, delayed updates, and vulnerability to corrupted inputs, causing prediction failures. Map-free approaches lack global context, with pairwise attention over-amplifying straight patterns while suppressing transitional patterns, resulting in motion-intention misalignment. This paper proposes GContextFormer, a plug-and-play encoder-decoder architecture with global context-aware hybrid attention and scaled additive aggregation achieving intention-aligned multimodal prediction without map reliance. The Motion-Aware Encoder builds scene-level intention prior via bounded scaled additive aggregation over mode-embedded trajectory tokens and refines per-mode representations under shared global context, mitigating inter-mode suppression and promoting intention alignment. The Hierarchical Interaction Decoder decomposes social reasoning into dual-pathway cross-attention: a standard pathway ensures uniform geometric coverage over agent-mode pairs while a neighbor-context-enhanced pathway emphasizes salient interactions, with gating module mediating their contributions to maintain coverage-focus balance. Experiments on eight highway-ramp scenarios from TOD-VT dataset show GContextFormer outperforms state-of-the-art baselines. Compared to existing transformer models, GContextFormer achieves greater robustness and concentrated improvements in high-curvature and transition zones via spatial distributions. Interpretability is achieved through motion mode distinctions and neighbor context modulation exposing reasoning attribution. The modular architecture supports extensibility toward cross-domain multimodal reasoning tasks. Source: https://fenghy-chen.github.io/sources/.

Paperid: 271, https://arxiv.org/pdf/2511.18873.pdf GitHub

Abstract:
3D Gaussian Splatting (3DGS) has emerged as a leading approach for high-quality novel view synthesis, with numerous variants extending its applicability to a broad spectrum of 3D and 4D scene reconstruction tasks. Despite its success, the representational capacity of 3DGS remains limited by the use of 3D Gaussian kernels to model local variations. Recent works have proposed to augment 3DGS with additional per-primitive capacity, such as per-splat textures, to enhance its expressiveness. However, these per-splat texture approaches primarily target dense novel view synthesis with a reduced number of Gaussian primitives, and their effectiveness tends to diminish when applied to more general reconstruction scenarios. In this paper, we aim to achieve concrete performance improvement over state-of-the-art 3DGS variants across a wide range of reconstruction tasks, including novel view synthesis, geometry and dynamic reconstruction, under both sparse and dense input settings. To this end, we introduce Neural Texture Splatting (NTS). At the core of our approach is a global neural field (represented as a hybrid of a tri-plane and a neural decoder) that predicts local appearance and geometric fields for each primitive. By leveraging this shared global representation that models local texture fields across primitives, we significantly reduce model size and facilitate efficient global information exchange, demonstrating strong generalization across tasks. Furthermore, our neural modeling of local texture fields introduces expressive view- and time-dependent effects, a critical aspect that existing methods fail to account for. Extensive experiments show that Neural Texture Splatting consistently improves models and achieves state-of-the-art results across multiple benchmarks.

Paperid: 272, https://arxiv.org/pdf/2511.18870.pdf GitHub

Authors:Bing Wu, Chang Zou, Changlin Li, Duojun Huang, Fang Yang, Hao Tan, Jack Peng, Jianbing Wu, Jiangfeng Xiong, Jie Jiang, Linus, Patrol, Peizhen Zhang, Peng Chen, Penghao Zhao, Qi Tian, Songtao Liu, Weijie Kong, Weiyan Wang, Xiao He, Xin Li, Xinchi Deng, Xuefei Zhe, Yang Li, Yanxin Long, Yuanbo Peng, Yue Wu, Yuhong Liu, Zhenyu Wang, Zuozhuo Dai, Bo Peng, Coopers Li, Gu Gong, Guojian Xiao, Jiahe Tian, Jiaxin Lin, Jie Liu, Jihong Zhang, Jiesong Lian, Kaihang Pan, Lei Wang, Lin Niu, Mingtao Chen, Mingyang Chen, Mingzhe Zheng, Miles Yang, Qiangqiang Hu, Qi Yang, Qiuyong Xiao, Runzhou Wu, Ryan Xu, Rui Yuan, Shanshan Sang, Shisheng Huang, Siruis Gong, Shuo Huang, Weiting Guo, Xiang Yuan, Xiaojia Chen, Xiawei Hu, Wenzhi Sun, Xiele Wu, Xianshun Ren, Xiaoyan Yuan, Xiaoyue Mi, Yepeng Zhang, Yifu Sun, Yiting Lu, Yitong Li, You Huang, Yu Tang, Yixuan Li, Yuhang Deng, Yuan Zhou, Zhichao Hu, Zhiguang Liu, Zhihe Yang, Zilin Yang, Zhenzhi Lu, Zixiang Zhou, Zhao Zhong

Abstract:
We present HunyuanVideo 1.5, a lightweight yet powerful open-source video generation model that achieves state-of-the-art visual quality and motion coherence with only 8.3 billion parameters, enabling efficient inference on consumer-grade GPUs. This achievement is built upon several key components, including meticulous data curation, an advanced DiT architecture featuring selective and sliding tile attention (SSTA), enhanced bilingual understanding through glyph-aware text encoding, progressive pre-training and post-training, and an efficient video super-resolution network. Leveraging these designs, we developed a unified framework capable of high-quality text-to-video and image-to-video generation across multiple durations and resolutions. Extensive experiments demonstrate that this compact and proficient model establishes a new state-of-the-art among open-source video generation models. By releasing the code and model weights, we provide the community with a high-performance foundation that lowers the barrier to video creation and research, making advanced video generation accessible to a broader audience. All open-source assets are publicly available at https://github.com/Tencent-Hunyuan/HunyuanVideo-1.5.

Paperid: 273, https://arxiv.org/pdf/2511.18816.pdf GitHub

Abstract:
Out-of-Distribution (OOD) detection in semantic segmentation aims to localize anomalous regions at the pixel level, advancing beyond traditional image-level OOD techniques to better suit real-world applications such as autonomous driving. Recent literature has successfully explored the adaptation of commonly used image-level OOD methods--primarily based on classifier-derived confidence scores (e.g., energy or entropy)--for this pixel-precise task. However, these methods inherit a set of limitations, including vulnerability to overconfidence. In this work, we introduce SupLID, a novel framework that effectively guides classifier-derived OOD scores by exploiting the geometrical structure of the underlying semantic space, particularly using Linear Intrinsic Dimensionality (LID). While LID effectively characterizes the local structure of high-dimensional data by analyzing distance distributions, its direct application at the pixel level remains challenging. To overcome this, SupLID constructs a geometrical coreset that captures the intrinsic structure of the in-distribution (ID) subspace. It then computes OOD scores at the superpixel level, enabling both efficient real-time inference and improved spatial smoothness. We demonstrate that geometrical cues derived from SupLID serve as a complementary signal to traditional classifier confidence, enhancing the model's ability to detect diverse OOD scenarios. Designed as a post-hoc scoring method, SupLID can be seamlessly integrated with any semantic segmentation classifier at deployment time. Our results demonstrate that SupLID significantly enhances existing classifier-based OOD scores, achieving state-of-the-art performance across key evaluation metrics, including AUR, FPR, and AUP. Code is available at https://github.com/hdnugit/SupLID.

Paperid: 274, https://arxiv.org/pdf/2511.18806.pdf GitHub

Abstract:
X-ray imaging, based on penetration, enables detailed visualization of internal structures. Building on this capability, existing implicit 3D reconstruction methods have adapted the NeRF model and its variants for internal CT reconstruction. However, these approaches often neglect the significance of objects' anatomical priors for implicit learning, limiting both reconstruction precision and learning efficiency, particularly in ultra-sparse view scenarios. To address these challenges, we propose a novel 3D CT reconstruction framework that employs a 'target prior' derived from the object's projection data to enhance implicit learning. Our approach integrates positional and structural encoding to facilitate voxel-wise implicit reconstruction, utilizing the target prior to guide voxel sampling and enrich structural encoding. This dual strategy significantly boosts both learning efficiency and reconstruction quality. Additionally, we introduce a CUDA-based algorithm for rapid estimation of high-quality 3D target priors from sparse-view projections. Experiments utilizing projection data from a complex abdominal dataset demonstrate that the proposed model substantially enhances learning efficiency, outperforming the current leading model, NAF, by a factor of ten. In terms of reconstruction quality, it also exceeds the most accurate model, NeRP, achieving PSNR improvements of 3.57 dB, 5.42 dB, and 5.70 dB with 10, 20, and 30 projections, respectively. The code is available at https://github.com/qlcao171/TPG-INR.

Paperid: 275, https://arxiv.org/pdf/2511.18794.pdf GitHub

Abstract:
Multi-period image collections are common in real-world applications. Cities are re-scanned for mapping, construction sites are revisited for progress tracking, and natural regions are monitored for environmental change. Such data form multi-period scenes, where geometry and appearance evolve. Reconstructing such scenes is an important yet underexplored problem. Existing pipelines rely on incompatible assumptions: static and in-the-wild methods enforce a single geometry, while dynamic ones assume smooth motion, both failing under long-term, discontinuous changes. To solve this problem, we introduce ChronoGS, a temporally modulated Gaussian representation that reconstructs all periods within a unified anchor scaffold. It's also designed to disentangle stable and evolving components, achieving temporally consistent reconstruction of multi-period scenes. To catalyze relevant research, we release ChronoScene dataset, a benchmark of real and synthetic multi-period scenes, capturing geometric and appearance variation. Experiments demonstrate that ChronoGS consistently outperforms baselines in reconstruction quality and temporal consistency. Our code and the ChronoScene dataset are publicly available at https://github.com/ZhongtaoWang/ChronoGS.

Paperid: 276, https://arxiv.org/pdf/2511.18788.pdf GitHub

Abstract:
Compared to monocular 3D object detection, stereo-based 3D methods offer significantly higher accuracy but still suffer from high computational overhead and latency. The state-of-the-art stereo 3D detection method achieves twice the accuracy of monocular approaches, yet its inference speed is only half as fast. In this paper, we propose StereoDETR, an efficient stereo 3D object detection framework based on DETR. StereoDETR consists of two branches: a monocular DETR branch and a stereo branch. The DETR branch is built upon 2D DETR with additional channels for predicting object scale, orientation, and sampling points. The stereo branch leverages low-cost multi-scale disparity features to predict object-level depth maps. These two branches are coupled solely through a differentiable depth sampling strategy. To handle occlusion, we introduce a constrained supervision strategy for sampling points without requiring extra annotations. StereoDETR achieves real-time inference and is the first stereo-based method to surpass monocular approaches in speed. It also achieves competitive accuracy on the public KITTI benchmark, setting new state-of-the-art results on pedestrian and cyclist subsets. The code is available at https://github.com/shiyi-mu/StereoDETR-OPEN.

Paperid: 277, https://arxiv.org/pdf/2511.18786.pdf GitHub

Abstract:
We present STCDiT, a video super-resolution framework built upon a pre-trained video diffusion model, aiming to restore structurally faithful and temporally stable videos from degraded inputs, even under complex camera motions. The main challenges lie in maintaining temporal stability during reconstruction and preserving structural fidelity during generation. To address these challenges, we first develop a motion-aware VAE reconstruction method that performs segment-wise reconstruction, with each segment clip exhibiting uniform motion characteristic, thereby effectively handling videos with complex camera motions. Moreover, we observe that the first-frame latent extracted by the VAE encoder in each clip, termed the anchor-frame latent, remains unaffected by temporal compression and retains richer spatial structural information than subsequent frame latents. We further develop an anchor-frame guidance approach that leverages structural information from anchor frames to constrain the generation process and improve structural fidelity of video features. Coupling these two designs enables the video diffusion model to achieve high-quality video super-resolution. Extensive experiments show that STCDiT outperforms state-of-the-art methods in terms of structural fidelity and temporal consistency.

Paperid: 278, https://arxiv.org/pdf/2511.18780.pdf GitHub

Abstract:
Recent progress in video generative models has enabled the creation of high-quality videos from multimodal prompts that combine text and images. While these systems offer enhanced controllability, they also introduce new safety risks, as harmful content can emerge from individual modalities or their interaction. Existing safety methods are often text-only, require prior knowledge of the risk category, or operate as post-generation auditors, struggling to proactively mitigate such compositional, multimodal risks. To address this challenge, we present ConceptGuard, a unified safeguard framework for proactively detecting and mitigating unsafe semantics in multimodal video generation. ConceptGuard operates in two stages: First, a contrastive detection module identifies latent safety risks by projecting fused image-text inputs into a structured concept space; Second, a semantic suppression mechanism steers the generative process away from unsafe concepts by intervening in the prompt's multimodal conditioning. To support the development and rigorous evaluation of this framework, we introduce two novel benchmarks: ConceptRisk, a large-scale dataset for training on multimodal risks, and T2VSafetyBench-TI2V, the first benchmark adapted from T2VSafetyBench for the Text-and-Image-to-Video (TI2V) safety setting. Comprehensive experiments on both benchmarks show that ConceptGuard consistently outperforms existing baselines, achieving state-of-the-art results in both risk detection and safe video generation. Our code is available at https://github.com/Ruize-Ma/ConceptGuard.

Paperid: 279, https://arxiv.org/pdf/2511.18763.pdf GitHub

Abstract:
Color fundus photography (CFP) is central to diagnosing and monitoring retinal disease, yet its acquisition variability (e.g., illumination changes) often degrades image quality, which motivates robust enhancement methods. Unpaired enhancement pipelines are typically GAN-based, however, they can distort clinically critical vasculature, altering vessel topology and endpoint integrity. Motivated by these structural alterations, we propose Vessel-Aware Optimal Transport (\textbf{VAOT}), a framework that combines an optimal-transport objective with two structure-preserving regularizers: (i) a skeleton-based loss to maintain global vascular connectivity and (ii) an endpoint-aware loss to stabilize local termini. These constraints guide learning in the unpaired setting, reducing noise while preserving vessel structure. Experimental results on synthetic degradation benchmark and downstream evaluations in vessel and lesion segmentation demonstrate the superiority of the proposed methods against several state-of-the art baselines. The code is available at https://github.com/Retinal-Research/VAOT

Paperid: 280, https://arxiv.org/pdf/2511.18760.pdf GitHub

Abstract:
Informal mathematics has been central to modern large language model (LLM) reasoning, offering flexibility and enabling efficient construction of arguments. However, purely informal reasoning is prone to logical gaps and subtle errors that are difficult to detect and correct. In contrast, formal theorem proving provides rigorous, verifiable mathematical reasoning, where each inference step is checked by a trusted compiler in systems such as Lean, but lacks the exploratory freedom of informal problem solving. This mismatch leaves current LLM-based math agents without a principled way to combine the strengths of both paradigms. In this work, we introduce Hermes, the first tool-assisted agent that explicitly interleaves informal reasoning with formally verified proof steps in Lean. The framework performs intermediate formal checking to prevent reasoning drift and employs a memory module that maintains proof continuity across long, multi-step reasoning chains, enabling both exploration and verification within a single workflow. We evaluate Hermes on four challenging mathematical reasoning benchmarks using LLMs of varying parameter scales, from small models to state-of-the-art systems. Across all settings, Hermes reliably improves the reasoning accuracy of base models while substantially reducing token usage and computational cost compared to reward-based approaches. On difficult datasets such as AIME'25, Hermes achieves up to a 67% accuracy improvement while using 80% fewer total inference FLOPs. The implementation and codebase are publicly available at https://github.com/aziksh-ospanov/HERMES.

Paperid: 281, https://arxiv.org/pdf/2511.18732.pdf GitHub

Abstract:
Global ocean forecasting aims to predict key ocean variables such as temperature, salinity, and currents, which is essential for understanding and describing oceanic phenomena. In recent years, data-driven deep learning-based ocean forecast models, such as XiHe, WenHai, LangYa and AI-GOMS, have demonstrated significant potential in capturing complex ocean dynamics and improving forecasting efficiency. Despite these advancements, the absence of open-source, standardized benchmarks has led to inconsistent data usage and evaluation methods. This gap hinders efficient model development, impedes fair performance comparison, and constrains interdisciplinary collaboration. To address this challenge, we propose OceanForecastBench, a benchmark offering three core contributions: (1) A high-quality global ocean reanalysis data over 28 years for model training, including 4 ocean variables across 23 depth levels and 4 sea surface variables. (2) A high-reliability satellite and in-situ observations for model evaluation, covering approximately 100 million locations in the global ocean. (3) An evaluation pipeline and a comprehensive benchmark with 6 typical baseline models, leveraging observations to evaluate model performance from multiple perspectives. OceanForecastBench represents the most comprehensive benchmarking framework currently available for data-driven ocean forecasting, offering an open-source platform for model development, evaluation, and comparison. The dataset and code are publicly available at: https://github.com/Ocean-Intelligent-Forecasting/OceanForecastBench.

Paperid: 282, https://arxiv.org/pdf/2511.18724.pdf GitHub

Abstract:
Learned B-frame codecs with hierarchical temporal prediction often encounter the domain-shift issue due to mismatches between the Group-of-Pictures (GOP) sizes for training and testing, leading to inaccurate motion estimates, particularly for large motion. A common solution is to turn large motion into small motion by downsampling video frames during motion estimation. However, determining the optimal downsampling factor typically requires costly rate-distortion optimization. This work introduces lightweight classifiers to predict downsampling factors. These classifiers leverage simple state signals from current and reference frames to balance rate-distortion performance with computational cost. Three variants are proposed: (1) a binary classifier (Bi-Class) trained with Focal Loss to choose between high and low resolutions, (2) a multi-class classifier (Mu-Class) trained with novel soft labels based on rate-distortion costs, and (3) a co-class approach (Co-Class) that combines the predictive capability of the multi-class classifier with the selective search of the binary classifier. All classifier methods can work seamlessly with existing B-frame codecs without requiring codec retraining. Experimental results show that they achieve coding performance comparable to exhaustive search methods while significantly reducing computational complexity. The code is available at: https://github.com/NYCU-MAPL/Fast-OMRA.git.

Paperid: 283, https://arxiv.org/pdf/2511.18718.pdf GitHub

Abstract:
We introduce AIRHILT (Aviation Integrated Reasoning, Human-in-the-Loop Testbed), a modular and lightweight simulation environment designed to evaluate multimodal pilot and air traffic control (ATC) assistance systems for aviation conflict detection. Built on the open-source Godot engine, AIRHILT synchronizes pilot and ATC radio communications, visual scene understanding from camera streams, and ADS-B surveillance data within a unified, scalable platform. The environment supports pilot- and controller-in-the-loop interactions, providing a comprehensive scenario suite covering both terminal area and en route operational conflicts, including communication errors and procedural mistakes. AIRHILT offers standardized JSON-based interfaces that enable researchers to easily integrate, swap, and evaluate automatic speech recognition (ASR), visual detection, decision-making, and text-to-speech (TTS) models. We demonstrate AIRHILT through a reference pipeline incorporating fine-tuned Whisper ASR, YOLO-based visual detection, ADS-B-based conflict logic, and GPT-OSS-20B structured reasoning, and present preliminary results from representative runway-overlap scenarios, where the assistant achieves an average time-to-first-warning of approximately 7.7 s, with average ASR and vision latencies of approximately 5.9 s and 0.4 s, respectively. The AIRHILT environment and scenario suite are openly available, supporting reproducible research on multimodal situational awareness and conflict detection in aviation; code and scenarios are available at https://github.com/ogarib3/airhilt.

Paperid: 284, https://arxiv.org/pdf/2511.18713.pdf GitHub

Abstract:
In autonomous driving, vision-centric 3D object detection recognizes and localizes 3D objects from RGB images. However, due to high annotation costs and diverse outdoor scenes, training data often fails to cover all possible test scenarios, known as the out-of-distribution (OOD) issue. Training-free image editing offers a promising solution for improving model robustness by training data enhancement without any modifications to pre-trained diffusion models. Nevertheless, inversion-based methods often suffer from limited effectiveness and inherent inaccuracies, while recent rectified-flow-based approaches struggle to preserve objects with accurate 3D geometry. In this paper, we propose DriveFlow, a Rectified Flow Adaptation method for training data enhancement in autonomous driving based on pre-trained Text-to-Image flow models. Based on frequency decomposition, DriveFlow introduces two strategies to adapt noise-free editing paths derived from text-conditioned velocities. 1) High-Frequency Foreground Preservation: DriveFlow incorporates a high-frequency alignment loss for foreground to maintain precise 3D object geometry. 2) Dual-Frequency Background Optimization: DriveFlow also conducts dual-frequency optimization for background, balancing editing flexibility and semantic consistency. Comprehensive experiments validate the effectiveness and efficiency of DriveFlow, demonstrating comprehensive performance improvements on all categories across OOD scenarios. Code is available at https://github.com/Hongbin98/DriveFlow.

Paperid: 285, https://arxiv.org/pdf/2511.18685.pdf GitHub GitHub

Abstract:
Multimodal Large Language Models (MLLMs) show promising results as decision-making engines for embodied agents operating in complex, physical environments. However, existing benchmarks often prioritize high-level planning or spatial reasoning, leaving the fine-grained action intelligence required for embodied physical interaction underexplored. To address this gap, we introduce CFG-Bench, a new benchmark designed to systematically evaluate this crucial capability. CFG-Bench consists of 1,368 curated videos paired with 19,562 three-modalities question-answer pairs targeting four cognitive abilities: 1) Physical Interaction, 2) Temporal-Causal Relation, 3) Intentional Understanding, and 4) Evaluative Judgment. Together, these dimensions provide a systematic framework for assessing a model's ability to translate visual observations into actionable knowledge, moving beyond mere surface-level recognition. Our comprehensive evaluation on CFG-Bench reveals that leading MLLMs struggle to produce detailed instructions for physical interactions and exhibit profound limitations in the higher-order reasoning of intention and evaluation. Moreover, supervised fine-tuning (SFT) on our data demonstrates that teaching an MLLMs to articulate fine-grained actions directly translates to significant performance gains on established embodied benchmarks. Our analysis highlights these limitations and offers insights for developing more capable and grounded embodied agents. Project page: \href{https://cfg-bench.github.io/}{https://cfg-bench.github.io/}.

Paperid: 286, https://arxiv.org/pdf/2511.18643.pdf GitHub

Abstract:
The KV cache is a dominant memory bottleneck for LLM inference. While 4-bit KV quantization preserves accuracy, 2-bit often degrades it, especially on long-context reasoning. We close this gap via an algorithm-system co-design for mixed-precision KV caching: Kitty. On the algorithm side, extensive experiments show that Dynamic Channel-wise Precision Boost -- which ranks Key-cache channels by sensitivity and keeps only a small fraction at higher precision -- maintains near-zero loss in accuracy drop while approaching 2-bit memory. The main challenge is handling dynamic 4-bit channel boosts while keeping the page layout coalesced and the dequantization uniform, with no scattered reads or hard-coded masks. Kitty addresses these issues by decompose each mixed-precision Key page into two tensors with unified 2-bit precision. Based on this, Kitty provides a page-centric KV layout, Triton-compatible page dequantization kernels, and a lightweight runtime pipeline that preserves coalescing and avoids divergence. Across seven tasks and two model families (Qwen3, LLaMA3), Kitty cuts KV memory by nearly 8x with negligible accuracy loss, enabling up to 8x larger batches and 2.1x-4.1x higher throughput under the same memory budget. We release the full implementation of Kitty at https://github.com/Summer-Summer/Kitty.

Paperid: 287, https://arxiv.org/pdf/2511.18619.pdf GitHub

Abstract:
Language Models are extremely susceptible to performance collapse with even small changes to input prompt strings. Libraries such as DSpy (from Stanford NLP) avoid this problem through demonstration-based prompt optimisation. Inspired by this, I propose an alternative approach that treats prompt optimisation as a classical state-space search problem. I model the prompt space as a graph where nodes represent prompt states and edges correspond to deliberate transformations such as shortening, adding examples, or re- ordering content. Using beam search and random walk algorithms, I systematically explore this space, evaluating candidates on development sets and pruning unpromising branches. Across five NLP tasks (sentiment classification, question answering, summarisation, reason- ing, and natural language inference), I find that even shallow search configurations (beam width=2, depth=2) improve upon seed prompts on development sets. For instance, beam search achieves development accuracy gains from 0.40 to 0.80 on reasoning tasks, though test set improvements are more modest (0.20 to 0.50), indicating overfitting to the develop- ment heuristic. Analysis of successful optimisation paths reveals that transformations that make prompts concise appear most frequently, while verbosity operators are never selected. My results validate prompt optimization as a search problem and suggest that with greater computational resources and improved evaluation metrics, deeper exploration could yield more robust prompts that generalize beyond development sets. Code and implementation are available at [https://github.com/MaanasTaneja/PromptOptimiser].

Paperid: 288, https://arxiv.org/pdf/2511.18617.pdf GitHub

Abstract:
AutoFocus-IL is a simple yet effective method to improve data efficiency and generalization in visual imitation learning by guiding policies to attend to task-relevant features rather than distractors and spurious correlations. Although saliency regularization has emerged as a promising way to achieve this, existing approaches typically require costly supervision such as human gaze data or manual saliency annotations. In contrast, AutoFocus-IL leverages vision-language models (VLMs) to automatically identify and track key objects in demonstrations, generating temporal saliency maps that highlight causal visual signals while suppressing distractors. These maps are then used to regularize behavior cloning policies, yielding stronger alignment between visual attention and task-relevant cues. Experiments in both the CARLA simulator and real-robot manipulation tasks demonstrate that AutoFocus-IL not only outperforms standard behavior cloning but also surpasses state-of-the-art baselines that assume privileged access to human supervision, such as gaze data. Code, datasets, and trained policy videos are available at https://AutoFocus-IL.github.io/.

Paperid: 289, https://arxiv.org/pdf/2511.18601.pdf GitHub

Abstract:
In this paper, we present RigAnyFace (RAF), a scalable neural auto-rigging framework for facial meshes of diverse topologies, including those with multiple disconnected components. RAF deforms a static neutral facial mesh into industry-standard FACS poses to form an expressive blendshape rig. Deformations are predicted by a triangulation-agnostic surface learning network augmented with our tailored architecture design to condition on FACS parameters and efficiently process disconnected components. For training, we curated a dataset of facial meshes, with a subset meticulously rigged by professional artists to serve as accurate 3D ground truth for deformation supervision. Due to the high cost of manual rigging, this subset is limited in size, constraining the generalization ability of models trained exclusively on it. To address this, we design a 2D supervision strategy for unlabeled neutral meshes without rigs. This strategy increases data diversity and allows for scaled training, thereby enhancing the generalization ability of models trained on this augmented data. Extensive experiments demonstrate that RAF is able to rig meshes of diverse topologies on not only our artist-crafted assets but also in-the-wild samples, outperforming previous works in accuracy and generalizability. Moreover, our method advances beyond prior work by supporting multiple disconnected components, such as eyeballs, for more detailed expression animation. Project page: https://wenchao-m.github.io/RigAnyFace.github.io

Paperid: 290, https://arxiv.org/pdf/2511.18570.pdf GitHub

Abstract:
Understanding physical properties such as friction, stiffness, hardness, and material composition is essential for enabling robots to interact safely and effectively with their surroundings. However, existing 3D reconstruction methods focus on geometry and appearance and cannot infer these underlying physical properties. We present PhysGS, a Bayesian-inferred extension of 3D Gaussian Splatting that estimates dense, per-point physical properties from visual cues and vision--language priors. We formulate property estimation as Bayesian inference over Gaussian splats, where material and property beliefs are iteratively refined as new observations arrive. PhysGS also models aleatoric and epistemic uncertainties, enabling uncertainty-aware object and scene interpretation. Across object-scale (ABO-500), indoor, and outdoor real-world datasets, PhysGS improves accuracy of the mass estimation by up to 22.8%, reduces Shore hardness error by up to 61.2%, and lowers kinetic friction error by up to 18.1% compared to deterministic baselines. Our results demonstrate that PhysGS unifies 3D reconstruction, uncertainty modeling, and physical reasoning in a single, spatially continuous framework for dense physical property estimation. Additional results are available at https://samchopra2003.github.io/physgs.

Paperid: 291, https://arxiv.org/pdf/2511.18567.pdf GitHub GitHub

Abstract:
The Forward-Forward (FF) algorithm offers a biologically plausible alternative to backpropagation, enabling neural networks to learn through local updates. However, FF's efficacy relies heavily on the definition of "goodness", which is a scalar measure of neural activity. While current implementations predominantly utilize a simple sum-of-squares metric, it remains unclear if this default choice is optimal. To address this, we benchmarked 21 distinct goodness functions across four standard image datasets (MNIST, FashionMNIST, CIFAR-10, STL-10), evaluating classification accuracy, energy consumption, and carbon footprint. We found that certain alternative goodness functions inspired from various domains significantly outperform the standard baseline. Specifically, \texttt{game\_theoretic\_local} achieved 97.15\% accuracy on MNIST, \texttt{softmax\_energy\_margin\_local} reached 82.84\% on FashionMNIST, and \texttt{triplet\_margin\_local} attained 37.69\% on STL-10. Furthermore, we observed substantial variability in computational efficiency, highlighting a critical trade-off between predictive performance and environmental cost. These findings demonstrate that the goodness function is a pivotal hyperparameter in FF design. We release our code on \href{https://github.com/aryashah2k/In-Search-of-Goodness}{Github} for reference and reproducibility.

Paperid: 292, https://arxiv.org/pdf/2511.18563.pdf GitHub

Abstract:
Curved objects pose a fundamental challenge for skill transfer in robotics: unlike planar surfaces, they do not admit a global reference frame. As a result, task-relevant directions such as "toward" or "along" the surface vary with position and geometry, making object-centric tasks difficult to transfer across shapes. To address this, we introduce an approach using Diffused Orientation Fields (DOF), a smooth representation of local reference frames, for transfer learning of tasks across curved objects. By expressing manipulation tasks in these smoothly varying local frames, we reduce the problem of transferring tasks across curved objects to establishing sparse keypoint correspondences. DOF is computed online from raw point cloud data using diffusion processes governed by partial differential equations, conditioned on keypoints. We evaluate DOF under geometric, topological, and localization perturbations, and demonstrate successful transfer of tasks requiring continuous physical interaction such as inspection, slicing, and peeling across varied objects. We provide our open-source codes at our website https://github.com/idiap/diffused_fields_robotics

Paperid: 293, https://arxiv.org/pdf/2511.18521.pdf GitHub

Abstract:
Geostationary hyperspectral satellites generate terabytes of data daily, creating critical challenges for storage, transmission, and distribution to the scientific community. We present a variational autoencoder (VAE) approach that achieves x514 compression of NASA's TEMPO satellite hyperspectral observations (1028 channels, 290-490nm) with reconstruction errors 1-2 orders of magnitude below the signal across all wavelengths. This dramatic data volume reduction enables efficient archival and sharing of satellite observations while preserving spectral fidelity. Beyond compression, we investigate to what extent atmospheric information is retained in the compressed latent space by training linear and nonlinear probes to extract Level-2 products (NO2, O3, HCHO, cloud fraction). Cloud fraction and total ozone achieve strong extraction performance (R^2 = 0.93 and 0.81 respectively), though these represent relatively straightforward retrievals given their distinct spectral signatures. In contrast, tropospheric trace gases pose genuine challenges for extraction (NO2 R^2 = 0.20, HCHO R^2 = 0.51) reflecting their weaker signals and complex atmospheric interactions. Critically, we find the VAE encodes atmospheric information in a semi-linear manner - nonlinear probes substantially outperform linear ones - and that explicit latent supervision during training provides minimal improvement, revealing fundamental encoding challenges for certain products. This work demonstrates that neural compression can dramatically reduce hyperspectral data volumes while preserving key atmospheric signals, addressing a critical bottleneck for next-generation Earth observation systems. Code - https://github.com/cfpark00/Hyperspectral-VAE

Paperid: 294, https://arxiv.org/pdf/2511.18511.pdf GitHub

Abstract:
We present a MATLAB package for reconstructing sound-speed images from transmission ultrasound data. The package is based on two-point ray tracing and implements two complementary inversion strategies for image reconstruction. The first is a time-of-flight (ToF) method that produces low-resolution, low-contrast images with minimal artefacts. The second is a ray-Born inversion method, which integrates high-frequency ray theory with the Born approximation to generate high-resolution sound-speed reconstructions. Early iterations of the ToF reconstruction are used to provide an initial estimate for the more advanced ray-Born approach. The core of this software package consists of four ray-tracing algorithms, whose accuracy is assessed in this study with respect to known analytical trajectories and accumulated acoustic path lengths. Furthermore, both image-reconstruction strategies have been validated numerically with simulated synthetic datasets and experimentally with open-source in-vitro and in-vivo datasets in related parallel studies.

Paperid: 295, https://arxiv.org/pdf/2511.18487.pdf GitHub

Abstract:
Text-to-speech (TTS) and text-to-music (TTM) models face significant limitations in instruction-based control. TTS systems usually depend on reference audio for timbre, offer only limited text-level attribute control, and rarely support dialogue generation. TTM systems are constrained by input conditioning requirements that depend on expert knowledge annotations. The high heterogeneity of these input control conditions makes them difficult to joint modeling with speech synthesis. Despite sharing common acoustic modeling characteristics, these two tasks have long been developed independently, leaving open the challenge of achieving unified modeling through natural language instructions. We introduce InstructAudio, a unified framework that enables instruction-based (natural language descriptions) control of acoustic attributes including timbre (gender, age), paralinguistic (emotion, style, accent), and musical (genre, instrument, rhythm, atmosphere). It supports expressive speech, music, and dialogue generation in English and Chinese. The model employs joint and single diffusion transformer layers with a standardized instruction-phoneme input format, trained on 50K hours of speech and 20K hours of music data, enabling multi-task learning and cross-modal alignment. Fig. 1 visualizes performance comparisons with mainstream TTS and TTM models, demonstrating that InstructAudio achieves optimal results on most metrics. To our best knowledge, InstructAudio represents the first instruction-controlled framework unifying speech and music generation. Audio samples are available at: https://qiangchunyu.github.io/InstructAudio/

Paperid: 296, https://arxiv.org/pdf/2511.18463.pdf GitHub

Abstract:
Sufficient visual perception is the foundation of video reasoning. Nevertheless, existing Video Reasoning LLMs suffer from perception shortcuts, relying on a flawed single-step perception paradigm. This paradigm describes the video and then conducts reasoning, which runs the risk of insufficient evidence and emergent hallucinations. To address these issues, we introduce a new framework that integrates a loop-based paradigm with an anti-hallucination reward. First, to address the insufficient evidence, we introduce the Perception Loop Reasoning (PLR) paradigm. Instead of describing the video at once, each loop requires the model to describe a video segment with precise timestamps, analyze this segment, and decide the next action. Second, for the risk of hallucinations, the Factual-Aware Evaluator (FAE) evaluates each perception result as a reliable anti-hallucination reward. This reward encourages the model to provide sufficient and precise video evidence. Our FAE, which performs comparably to GPT-4o, is tuned on our AnetHallu-117K, a large-scale hallucination judgment preference dataset. Extensive experiments show that our Video-PLR achieves the state-of-the-art in both 3B and 7B parameter scales and has the best data efficiency. Our code, models, and datasets are released on: https://github.com/BoweiPu/VideoPLR.

Paperid: 297, https://arxiv.org/pdf/2511.18452.pdf GitHub GitHub

Abstract:
Vision Foundation Models (VFMs) extract spatially downsampled representations, posing challenges for pixel-level tasks. Existing upsampling approaches face a fundamental trade-off: classical filters are fast and broadly applicable but rely on fixed forms, while modern upsamplers achieve superior accuracy through learnable, VFM-specific forms at the cost of retraining for each VFM. We introduce Neighborhood Attention Filtering (NAF), which bridges this gap by learning adaptive spatial-and-content weights through Cross-Scale Neighborhood Attention and Rotary Position Embeddings (RoPE), guided solely by the high-resolution input image. NAF operates zero-shot: it upsamples features from any VFM without retraining, making it the first VFM-agnostic architecture to outperform VFM-specific upsamplers and achieve state-of-the-art performance across multiple downstream tasks. It maintains high efficiency, scaling to 2K feature maps and reconstructing intermediate-resolution maps at 18 FPS. Beyond feature upsampling, NAF demonstrates strong performance on image restoration, highlighting its versatility. Code and checkpoints are available at https://github.com/valeoai/NAF.

Paperid: 298, https://arxiv.org/pdf/2511.18441.pdf GitHub GitHub

Abstract:
Gaussian Splatting has emerged as a leading method for novel view synthesis, offering superior training efficiency and real-time inference compared to NeRF approaches, while still delivering high-quality reconstructions. Beyond view synthesis, this 3D representation has also been explored for editing tasks. Many existing methods leverage 2D diffusion models to generate multi-view datasets for training, but they often suffer from limitations such as view inconsistencies, lack of fine-grained control, and high computational demand. In this work, we focus specifically on the editing task of recoloring. We introduce a user-friendly pipeline that enables precise selection and recoloring of regions within a pre-trained Gaussian Splatting scene. To demonstrate the real-time performance of our method, we also present an interactive tool that allows users to experiment with the pipeline in practice. Code is available at https://github.com/loryruta/recogs.

Paperid: 299, https://arxiv.org/pdf/2511.18434.pdf GitHub

Abstract:
The advent of Multimodal Large Language Models (MLLMs) has unlocked the potential for end-to-end document parsing and translation. However, prevailing benchmarks such as OmniDocBench and DITrans are dominated by pristine scanned or digital-born documents, and thus fail to adequately represent the intricate challenges of real-world capture conditions, such as geometric distortions and photometric variations. To fill this gap, we introduce DocPTBench, a comprehensive benchmark specifically designed for Photographed Document Parsing and Translation. DocPTBench comprises over 1,300 high-resolution photographed documents from multiple domains, includes eight translation scenarios, and provides meticulously human-verified annotations for both parsing and translation. Our experiments demonstrate that transitioning from digital-born to photographed documents results in a substantial performance decline: popular MLLMs exhibit an average accuracy drop of 18% in end-to-end parsing and 12% in translation, while specialized document parsing models show significant average decrease of 25%. This substantial performance gap underscores the unique challenges posed by documents captured in real-world conditions and reveals the limited robustness of existing models. Dataset and code are available at https://github.com/Topdu/DocPTBench.

Paperid: 300, https://arxiv.org/pdf/2511.18393.pdf GitHub

Abstract:
A decade of rapid advances in artificial intelligence (AI) has opened new opportunities for clinical decision support systems (CDSS), with large language models (LLMs) demonstrating strong reasoning abilities on timely medical tasks. However, clinical texts are often degraded by human errors or failures in automated pipelines, raising concerns about the reliability and fairness of AI-assisted decision-making. Yet the impact of such degradations remains under-investigated, particularly regarding how noise-induced shifts can heighten predictive uncertainty and unevenly affect demographic subgroups. We present a systematic study of state-of-the-art LLMs under diverse text corruption scenarios, focusing on robustness and equity in next-visit diagnosis prediction. To address the challenge posed by the large diagnostic label space, we introduce a clinically grounded label-reduction scheme and a hierarchical chain-of-thought (CoT) strategy that emulates clinicians' reasoning. Our approach improves robustness and reduces subgroup instability under degraded inputs, advancing the reliable use of LLMs in CDSS. We release code at https://github.com/heejkoo9/NECHOv3.

Paperid: 301, https://arxiv.org/pdf/2511.18367.pdf GitHub

Abstract:
Existing dynamic scene reconstruction methods based on Gaussian Splatting enable real-time rendering and generate realistic images. However, adjusting the camera's focal length or the distance between Gaussian primitives and the camera to modify rendering resolution often introduces strong artifacts, stemming from the frequency constraints of 4D Gaussians and Gaussian scale mismatch induced by the 2D dilated filter. To address this, we derive a maximum sampling frequency formulation for 4D Gaussian Splatting and introduce a 4D scale-adaptive filter and scale loss, which flexibly regulates the sampling frequency of 4D Gaussian Splatting. Our approach eliminates high-frequency artifacts under increased rendering frequencies while effectively reducing redundant Gaussians in multi-view video reconstruction. We validate the proposed method through monocular and multi-view video reconstruction experiments.Ours project page: https://4d-alias-free.github.io/4D-Alias-free/

Paperid: 302, https://arxiv.org/pdf/2511.18359.pdf GitHub

Abstract:
How do video understanding models acquire their answers? Although current Vision Language Models (VLMs) reason over complex scenes with diverse objects, action performances, and scene dynamics, understanding and controlling their internal processes remains an open challenge. Motivated by recent advancements in text-to-video (T2V) generative models, this paper introduces a logits-to-video (L2V) task alongside a model-independent approach, TRANSPORTER, to generate videos that capture the underlying rules behind VLMs' predictions. Given the high-visual-fidelity produced by T2V models, TRANSPORTER learns an optimal transport coupling to VLM's high-semantic embedding spaces. In turn, logit scores define embedding directions for conditional video generation. TRANSPORTER generates videos that reflect caption changes over diverse object attributes, action adverbs, and scene context. Quantitative and qualitative evaluations across VLMs demonstrate that L2V can provide a fidelity-rich, novel direction for model interpretability that has not been previously explored.

Paperid: 303, https://arxiv.org/pdf/2511.18346.pdf GitHub GitHub

Abstract:
Video relighting with background replacement is a challenging task critical for applications in film production and creative media. Existing methods struggle to balance temporal consistency, spatial fidelity, and illumination naturalness. To address these issues, we introduce FlowPortal, a novel training-free flow-based video relighting framework. Our core innovation is a Residual-Corrected Flow mechanism that transforms a standard flow-based model into an editing model, guaranteeing perfect reconstruction when input conditions are identical and enabling faithful relighting when they differ, resulting in high structural consistency. This is further enhanced by a Decoupled Condition Design for precise lighting control and a High-Frequency Transfer mechanism for detail preservation. Additionally, a masking strategy isolates foreground relighting from background pure generation process. Experiments demonstrate that FlowPortal achieves superior performance in temporal coherence, structural preservation, and lighting realism, while maintaining high efficiency. Project Page: https://gaowenshuo.github.io/FlowPortalProject/.

Paperid: 304, https://arxiv.org/pdf/2511.18344.pdf GitHub

Abstract:
With the proliferation of low altitude unmanned aerial vehicles (UAVs), visual multi-object tracking is becoming a critical security technology, demanding significant robustness even in complex environmental conditions. However, tracking UAVs using a single visual modality often fails in challenging scenarios, such as low illumination, cluttered backgrounds, and rapid motion. Although multi-modal multi-object UAV tracking is more resilient, the development of effective solutions has been hindered by the absence of dedicated public datasets. To bridge this gap, we release MM-UAV, the first large-scale benchmark for Multi-Modal UAV Tracking, integrating three key sensing modalities, e.g. RGB, infrared (IR), and event signals. The dataset spans over 30 challenging scenarios, with 1,321 synchronised multi-modal sequences, and more than 2.8 million annotated frames. Accompanying the dataset, we provide a novel multi-modal multi-UAV tracking framework, designed specifically for UAV tracking applications and serving as a baseline for future research. Our framework incorporates two key technical innovations, e.g. an offset-guided adaptive alignment module to resolve spatio mismatches across sensors, and an adaptive dynamic fusion module to balance complementary information conveyed by different modalities. Furthermore, to overcome the limitations of conventional appearance modelling in multi-object tracking, we introduce an event-enhanced association mechanism that leverages motion cues from the event modality for more reliable identity maintenance. Comprehensive experiments demonstrate that the proposed framework consistently outperforms state-of-the-art methods. To foster further research in multi-modal UAV tracking, both the dataset and source code will be made publicly available at https://xuefeng-zhu5.github.io/MM-UAV/.

Paperid: 305, https://arxiv.org/pdf/2511.18329.pdf GitHub

Abstract:
Scientific posters play a vital role in academic communication by presenting ideas through visual summaries. Analyzing reading order and parent-child relations of posters is essential for building structure-aware interfaces that facilitate clear and accurate understanding of research content. Despite their prevalence in academic communication, posters remain underexplored in structural analysis research, which has primarily focused on papers. To address this gap, we constructed SciPostLayoutTree, a dataset of approximately 8,000 posters annotated with reading order and parent-child relations. Compared to an existing structural analysis dataset, SciPostLayoutTree contains more instances of spatially challenging relations, including upward, horizontal, and long-distance relations. As a solution to these challenges, we develop Layout Tree Decoder, which incorporates visual features as well as bounding box features including position and category information. The model also uses beam search to predict relations while capturing sequence-level plausibility. Experimental results demonstrate that our model improves the prediction accuracy for spatially challenging relations and establishes a solid baseline for poster structure analysis. The dataset is publicly available at https://huggingface.co/datasets/omron-sinicx/scipostlayouttree. The code is also publicly available at https://github.com/omron-sinicx/scipostlayouttree.

Paperid: 306, https://arxiv.org/pdf/2511.18290.pdf GitHub

Abstract:
3D reconstruction in large-scale scenes is a fundamental task in 3D perception, but the inherent trade-off between accuracy and computational efficiency remains a significant challenge. Existing methods either prioritize speed and produce low-quality results, or achieve high-quality reconstruction at the cost of slow inference times. In this paper, we propose SwiftVGGT, a training-free method that significantly reduce inference time while preserving high-quality dense 3D reconstruction. To maintain global consistency in large-scale scenes, SwiftVGGT performs loop closure without relying on the external Visual Place Recognition (VPR) model. This removes redundant computation and enables accurate reconstruction over kilometer-scale environments. Furthermore, we propose a simple yet effective point sampling method to align neighboring chunks using a single Sim(3)-based Singular Value Decomposition (SVD) step. This eliminates the need for the Iteratively Reweighted Least Squares (IRLS) optimization commonly used in prior work, leading to substantial speed-ups. We evaluate SwiftVGGT on multiple datasets and show that it achieves state-of-the-art reconstruction quality while requiring only 33% of the inference time of recent VGGT-based large-scale reconstruction approaches.

Paperid: 307, https://arxiv.org/pdf/2511.18271.pdf GitHub

Abstract:
Text-to-image (T2I) models today are capable of producing photorealistic, instruction-following images, yet they still frequently fail on prompts that require implicit world knowledge. Existing evaluation protocols either emphasize compositional alignment or rely on single-round VQA-based scoring, leaving critical dimensions such as knowledge grounding, multi-physics interactions, and auditable evidence-substantially undertested. To address these limitations, we introduce PicWorld, the first comprehensive benchmark that assesses the grasp of implicit world knowledge and physical causal reasoning of T2I models. This benchmark consists of 1,100 prompts across three core categories. To facilitate fine-grained evaluation, we propose PW-Agent, an evidence-grounded multi-agent evaluator to hierarchically assess images on their physical realism and logical consistency by decomposing prompts into verifiable visual evidence. We conduct a thorough analysis of 17 mainstream T2I models on PicWorld, illustrating that they universally exhibit a fundamental limitation in their capacity for implicit world knowledge and physical causal reasoning to varying degrees. The findings highlight the need for reasoning-aware, knowledge-integrative architectures in future T2I systems. The code is available at https://github.com/D4-Lab/PicWorld}{https://github.com/D4-Lab/PicWorld.

Paperid: 308, https://arxiv.org/pdf/2511.18254.pdf GitHub

Abstract:
LiDAR scene flow is the task of estimating per-point 3D motion between consecutive point clouds. Recent methods achieve centimeter-level accuracy on popular autonomous vehicle (AV) datasets, but are typically only trained and evaluated on a single sensor. In this paper, we aim to learn general motion priors that transfer to diverse and unseen LiDAR sensors. However, prior work in LiDAR semantic segmentation and 3D object detection demonstrate that naively training on multiple datasets yields worse performance than single dataset models. Interestingly, we find that this conventional wisdom does not hold for motion estimation, and that state-of-the-art scene flow methods greatly benefit from cross-dataset training. We posit that low-level tasks such as motion estimation may be less sensitive to sensor configuration; indeed, our analysis shows that models trained on fast-moving objects (e.g., from highway datasets) perform well on fast-moving objects, even across different datasets. Informed by our analysis, we propose UniFlow, a family of feedforward models that unifies and trains on multiple large-scale LiDAR scene flow datasets with diverse sensor placements and point cloud densities. Our frustratingly simple solution establishes a new state-of-the-art on Waymo and nuScenes, improving over prior work by 5.1% and 35.2% respectively. Moreover, UniFlow achieves state-of-the-art accuracy on unseen datasets like TruckScenes, outperforming prior TruckScenes-specific models by 30.1%.

Paperid: 309, https://arxiv.org/pdf/2511.18191.pdf GitHub

Abstract:
Modern web applications--from real-time content recommendation and dynamic pricing to CDN optimization--increasingly rely on time-series forecasting to deliver personalized experiences to billions of users. Large-scale Transformer-based models have achieved state-of-the-art performance in time-series forecasting but suffer from high computational costs, limiting their deployment in latency-sensitive web applications. To address this challenge, we propose a general inference acceleration framework that adapts speculative decoding to autoregressive time-series models. Our approach employs a smaller "draft" model to propose future time-series patches, which are then verified in parallel by a larger "target" model, reducing the number of sequential forward passes required. We address key technical challenges in adapting this technique from discrete language tokens to continuous time-series distributions, including the design of acceptance criteria for multivariate Gaussian patches and practical variants that balance efficiency with accuracy. Through experiments on time series forecasting benchmarks relevant to web applications, we demonstrate significant inference speedups while maintaining competitive accuracy. The framework requires no architectural modifications to existing foundation models, making it immediately applicable to accelerate deployed time-series forecasting systems. Our implementation can be found at https://github.com/PranavSubbaraman/STRIDE

Paperid: 310, https://arxiv.org/pdf/2511.18171.pdf GitHub

Abstract:
Business Process Model and Notation (BPMN) is a widely used standard for modelling business processes. While automated planning has been proposed as a method for simulating and reasoning about BPMN workflows, most implementations remain incomplete or limited in scope. This project builds upon prior theoretical work to develop a functional pipeline that translates BPMN 2.0 diagrams into PDDL representations suitable for planning. The system supports core BPMN constructs, including tasks, events, sequence flows, and gateways, with initial support for parallel and inclusive gateway behaviour. Using a non-deterministic planner, we demonstrate how to generate and evaluate valid execution traces. Our implementation aims to bridge the gap between theory and practical tooling, providing a foundation for further exploration of translating business processes into well-defined plans.

Paperid: 311, https://arxiv.org/pdf/2511.18163.pdf GitHub

Abstract:
Few-Shot Semantic Segmentation (FSS) models achieve strong performance in segmenting novel classes with minimal labeled examples, yet their decision-making processes remain largely opaque. While explainable AI has advanced significantly in standard computer vision tasks, interpretability in FSS remains virtually unexplored despite its critical importance for understanding model behavior and guiding support set selection in data-scarce scenarios. This paper introduces the first dedicated method for interpreting matching-based FSS models by leveraging their inherent structural properties. Our Affinity Explainer approach extracts attribution maps that highlight which pixels in support images contribute most to query segmentation predictions, using matching scores computed between support and query features at multiple feature levels. We extend standard interpretability evaluation metrics to the FSS domain and propose additional metrics to better capture the practical utility of explanations in few-shot scenarios. Comprehensive experiments on FSS benchmark datasets, using different models, demonstrate that our Affinity Explainer significantly outperforms adapted standard attribution methods. Qualitative analysis reveals that our explanations provide structured, coherent attention patterns that align with model architectures and and enable effective model diagnosis. This work establishes the foundation for interpretable FSS research, enabling better model understanding and diagnostic for more reliable few-shot segmentation systems. The source code is publicly available at https://github.com/pasqualedem/AffinityExplainer.

Paperid: 312, https://arxiv.org/pdf/2511.18127.pdf GitHub

Abstract:
Real-time 3D hand forecasting is a critical component for fluid human-computer interaction in applications like AR and assistive robotics. However, existing methods are ill-suited for these scenarios, as they typically require offline access to accumulated video sequences and cannot incorporate language guidance that conveys task intent. To overcome these limitations, we introduce SFHand, the first streaming framework for language-guided 3D hand forecasting. SFHand autoregressively predicts a comprehensive set of future 3D hand states, including hand type, 2D bounding box, 3D pose, and trajectory, from a continuous stream of video and language instructions. Our framework combines a streaming autoregressive architecture with an ROI-enhanced memory layer, capturing temporal context while focusing on salient hand-centric regions. To enable this research, we also introduce EgoHaFL, the first large-scale dataset featuring synchronized 3D hand poses and language instructions. We demonstrate that SFHand achieves new state-of-the-art results in 3D hand forecasting, outperforming prior work by a significant margin of up to 35.8%. Furthermore, we show the practical utility of our learned representations by transferring them to downstream embodied manipulation tasks, improving task success rates by up to 13.4% on multiple benchmarks. Dataset page: https://huggingface.co/datasets/ut-vision/EgoHaFL, project page: https://github.com/ut-vision/SFHand.

Paperid: 313, https://arxiv.org/pdf/2511.18120.pdf GitHub

Abstract:
Recent learning-based multi-view stereo (MVS) methods are data-driven and have achieved remarkable progress due to large-scale training data and advanced architectures. However, their generalization remains sub-optimal due to fixed model parameters trained on limited training data distributions. In contrast, optimization-based methods enable scene-specific adaptation but lack scalability and require costly per-scene optimization. In this paper, we propose MVS-TTA, an efficient test-time adaptation (TTA) framework that enhances the adaptability of learning-based MVS methods by bridging these two paradigms. Specifically, MVS-TTA employs a self-supervised, cross-view consistency loss as an auxiliary task to guide inference-time adaptation. We introduce a meta-auxiliary learning strategy to train the model to benefit from auxiliary-task-based updates explicitly. Our framework is model-agnostic and can be applied to a wide range of MVS methods with minimal architectural changes. Extensive experiments on standard datasets (DTU, BlendedMVS) and a challenging cross-dataset generalization setting demonstrate that MVS-TTA consistently improves performance, even when applied to state-of-the-art MVS models. To our knowledge, this is the first attempt to integrate optimization-based test-time adaptation into learning-based MVS using meta-learning. The code will be available at https://github.com/mart87987-svg/MVS-TTA.

Paperid: 314, https://arxiv.org/pdf/2511.18115.pdf GitHub

Abstract:
We present Muskie, a native multi-view vision backbone designed for 3D vision tasks. Unlike existing models, which are frame-wise and exhibit limited multi-view consistency, Muskie is designed to process multiple views simultaneously and introduce multi-view consistency in pre-training stage. Muskie is trained to reconstruct heavily masked content in one view by finding and utilizing geometric correspondences from other views. Through this pretext task and our proposed aggressive masking strategy, the model implicitly to learn view-invariant features and develop strong geometric understanding without any 3D supervision. Compared with state-of-the-art frame-wise backbones such as DINO, Muskie achieves higher multi-view correspondence accuracy. Furthermore, we demonstrate that using Muskie as a backbone consistently enhances performance on downstream 3D tasks, including camera pose estimation and pointmap reconstruction. Codes are publicly available at https://leo-frank.github.io/Muskie/

Paperid: 315, https://arxiv.org/pdf/2511.18104.pdf GitHub

Abstract:
The proliferation of videos generated by diffusion models has raised increasing concerns about information security, highlighting the urgent need for reliable detection of synthetic media. Existing methods primarily focus on image-level forgery detection, leaving generic video-level forgery detection largely underexplored. To advance video forensics, we propose a consolidated multimodal detection algorithm, named MM-Det++, specifically designed for detecting diffusion-generated videos. Our approach consists of two innovative branches and a Unified Multimodal Learning (UML) module. Specifically, the Spatio-Temporal (ST) branch employs a novel Frame-Centric Vision Transformer (FC-ViT) to aggregate spatio-temporal information for detecting diffusion-generated videos, where the FC-tokens enable the capture of holistic forgery traces from each video frame. In parallel, the Multimodal (MM) branch adopts a learnable reasoning paradigm to acquire Multimodal Forgery Representation (MFR) by harnessing the powerful comprehension and reasoning capabilities of Multimodal Large Language Models (MLLMs), which discerns the forgery traces from a flexible semantic perspective. To integrate multimodal representations into a coherent space, a UML module is introduced to consolidate the generalization ability of MM-Det++. In addition, we also establish a large-scale and comprehensive Diffusion Video Forensics (DVF) dataset to advance research in video forgery detection. Extensive experiments demonstrate the superiority of MM-Det++ and highlight the effectiveness of unified multimodal forgery learning in detecting diffusion-generated videos.

Paperid: 316, https://arxiv.org/pdf/2511.18050.pdf GitHub

Abstract:
Diffusion transformers have recently delivered strong text-to-image generation around 1K resolution, but we show that extending them to native 4K across diverse aspect ratios exposes a tightly coupled failure mode spanning positional encoding, VAE compression, and optimization. Tackling any of these factors in isolation leaves substantial quality on the table. We therefore take a data-model co-design view and introduce UltraFlux, a Flux-based DiT trained natively at 4K on MultiAspect-4K-1M, a 1M-image 4K corpus with controlled multi-AR coverage, bilingual captions, and rich VLM/IQA metadata for resolution- and AR-aware sampling. On the model side, UltraFlux couples (i) Resonance 2D RoPE with YaRN for training-window-, frequency-, and AR-aware positional encoding at 4K; (ii) a simple, non-adversarial VAE post-training scheme that improves 4K reconstruction fidelity; (iii) an SNR-Aware Huber Wavelet objective that rebalances gradients across timesteps and frequency bands; and (iv) a Stage-wise Aesthetic Curriculum Learning strategy that concentrates high-aesthetic supervision on high-noise steps governed by the model prior. Together, these components yield a stable, detail-preserving 4K DiT that generalizes across wide, square, and tall ARs. On the Aesthetic-Eval at 4096 benchmark and multi-AR 4K settings, UltraFlux consistently outperforms strong open-source baselines across fidelity, aesthetic, and alignment metrics, and-with a LLM prompt refiner-matches or surpasses the proprietary Seedream 4.0.

Paperid: 317, https://arxiv.org/pdf/2511.18047.pdf GitHub

Abstract:
Explanation fidelity, which measures how accurately an explanation reflects a model's true reasoning, remains critically underexplored in recommender systems. We introduce SPINRec (Stochastic Path Integration for Neural Recommender Explanations), a model-agnostic approach that adapts path-integration techniques to the sparse and implicit nature of recommendation data. To overcome the limitations of prior methods, SPINRec employs stochastic baseline sampling: instead of integrating from a fixed or unrealistic baseline, it samples multiple plausible user profiles from the empirical data distribution and selects the most faithful attribution path. This design captures the influence of both observed and unobserved interactions, yielding more stable and personalized explanations. We conduct the most comprehensive fidelity evaluation to date across three models (MF, VAE, NCF), three datasets (ML1M, Yahoo! Music, Pinterest), and a suite of counterfactual metrics, including AUC-based perturbation curves and fixed-length diagnostics. SPINRec consistently outperforms all baselines, establishing a new benchmark for faithful explainability in recommendation. Code and evaluation tools are publicly available at https://github.com/DeltaLabTLV/SPINRec.

Paperid: 318, https://arxiv.org/pdf/2511.18024.pdf GitHub

Abstract:
We present a method for extracting \emph{monosemantic} neurons, defined as latent dimensions that align with coherent and interpretable concepts, from user and item embeddings in recommender systems. Our approach employs a Sparse Autoencoder (SAE) to reveal semantic structure within pretrained representations. In contrast to work on language models, monosemanticity in recommendation must preserve the interactions between separate user and item embeddings. To achieve this, we introduce a \emph{prediction aware} training objective that backpropagates through a frozen recommender and aligns the learned latent structure with the model's user-item affinity predictions. The resulting neurons capture properties such as genre, popularity, and temporal trends, and support post hoc control operations including targeted filtering and content promotion without modifying the base model. Our method generalizes across different recommendation models and datasets, providing a practical tool for interpretable and controllable personalization. Code and evaluation resources are available at https://github.com/DeltaLabTLV/Monosemanticity4Rec.

Paperid: 319, https://arxiv.org/pdf/2511.18011.pdf GitHub

Abstract:
Multimodal large language models (MLLMs) have demonstrated powerful capabilities in general spatial understanding and reasoning. However, their fine-grained spatial understanding and reasoning capabilities in complex urban scenarios have not received significant attention in the fields of both research and industry. To fill this gap, we focus primarily on road markings as a typical example of fine-grained spatial elements under urban scenarios, given the essential role of the integrated road traffic network they form within cities. Around road markings and urban traffic systems, we propose RoadBench, a systematic benchmark that comprehensively evaluates MLLMs' fine-grained spatial understanding and reasoning capabilities using BEV and FPV image inputs. This benchmark comprises six tasks consisting of 9,121 strictly manually verified test cases. These tasks form a systematic evaluation framework that bridges understanding at local spatial scopes to global reasoning. They not only test MLLMs' capabilities in recognition, joint understanding, and reasoning but also assess their ability to integrate image information with domain knowledge. After evaluating 14 mainstream MLLMs, we confirm that RoadBench is a challenging benchmark for MLLMs while revealing significant shortcomings in existing MLLMs' fine-grained spatial understanding and reasoning capabilities within urban scenarios. In certain tasks, their performance even falls short of simple rule-based or random selection baselines. These findings, along with RoadBench itself, will contribute to the comprehensive advancement of spatial understanding capabilities for MLLMs. The benchmark code, example datasets, and raw evaluation results are available in the supplementary material.

Paperid: 320, https://arxiv.org/pdf/2511.18007.pdf GitHub

Abstract:
Detecting changes in longitudinal medical imaging using deep learning requires a substantial amount of accurately labeled data. However, labeling these images is notably more costly and time-consuming than labeling other image types, as it requires labeling across various time points, where new lesions can be minor, and subtle changes are easily missed. Deep Active Learning (DAL) has shown promise in minimizing labeling costs by selectively querying the most informative samples, but existing studies have primarily focused on static tasks like classification and segmentation. Consequently, the conventional DAL approach cannot be directly applied to change detection tasks, which involve identifying subtle differences across multiple images. In this study, we propose a novel DAL framework, named Longitudinal Medical Imaging Active Learning (LMI-AL), tailored specifically for longitudinal medical imaging. By pairing and differencing all 2D slices from baseline and follow-up 3D images, LMI-AL iteratively selects the most informative pairs for labeling using DAL, training a deep learning model with minimal manual annotation. Experimental results demonstrate that, with less than 8% of the data labeled, LMI-AL can achieve performance comparable to models trained on fully labeled datasets. We also provide a detailed analysis of the method's performance, as guidance for future research. The code is publicly available at https://github.com/HelenMa9998/Longitudinal_AL.

Paperid: 321, https://arxiv.org/pdf/2511.18005.pdf GitHub

Abstract:
City-scale 3D generation is of great importance for the development of embodied intelligence and world models. Existing methods, however, face significant challenges regarding quality, fidelity, and scalability in 3D world generation. Thus, we propose RAISECity, a \textbf{R}eality-\textbf{A}ligned \textbf{I}ntelligent \textbf{S}ynthesis \textbf{E}ngine that creates detailed, \textbf{C}ity-scale 3D worlds. We introduce an agentic framework that leverages diverse multimodal foundation tools to acquire real-world knowledge, maintain robust intermediate representations, and construct complex 3D scenes. This agentic design, featuring dynamic data processing, iterative self-reflection and refinement, and the invocation of advanced multimodal tools, minimizes cumulative errors and enhances overall performance. Extensive quantitative experiments and qualitative analyses validate the superior performance of RAISECity in real-world alignment, shape precision, texture fidelity, and aesthetics level, achieving over a 90% win-rate against existing baselines for overall perceptual quality. This combination of 3D quality, reality alignment, scalability, and seamless compatibility with computer graphics pipelines makes RAISECity a promising foundation for applications in immersive media, embodied intelligence, and world models.

Paperid: 322, https://arxiv.org/pdf/2511.17986.pdf GitHub

Abstract:
Diffusion Transformers have demonstrated remarkable capabilities in visual synthesis, yet they often struggle with high-level semantic reasoning and long-horizon planning. This limitation frequently leads to visual hallucinations and mis-alignments with user instructions, especially in scenarios involving complex scene understanding, human-object interactions, multi-stage actions, and in-context motion reasoning. To address these challenges, we propose Plan-X, a framework that explicitly enforces high-level semantic planning to instruct video generation process. At its core lies a Semantic Planner, a learnable multimodal language model that reasons over the user's intent from both text prompts and visual context, and autoregressively generates a sequence of text-grounded spatio-temporal semantic tokens. These semantic tokens, complementary to high-level text prompt guidance, serve as structured "semantic sketches" over time for the video diffusion model, which has its strength at synthesizing high-fidelity visual details. Plan-X effectively integrates the strength of language models in multimodal in-context reasoning and planning, together with the strength of diffusion models in photorealistic video synthesis. Extensive experiments demonstrate that our framework substantially reduces visual hallucinations and enables fine-grained, instruction-aligned video generation consistent with multimodal context.

Paperid: 323, https://arxiv.org/pdf/2511.17983.pdf GitHub

Abstract:
Clustering in stationary and nonstationary settings, where data distributions remain static or evolve over time, requires models that can adapt to distributional shifts while preserving previously learned cluster structures. This paper proposes an Adaptive Resonance Theory (ART)-based topological clustering algorithm that autonomously adjusts its recalculation interval and vigilance threshold through a diversity-driven adaptation mechanism. This mechanism enables hyperparameter-free learning that maintains cluster stability and continuity in dynamic environments. Experiments on 24 real-world datasets demonstrate that the proposed algorithm outperforms state-of-the-art methods in both clustering performance and continual learning capability. These results highlight the effectiveness of the proposed parameter adaptation in mitigating catastrophic forgetting and maintaining consistent clustering in evolving data streams. Source code is available at https://github.com/Masuyama-lab/IDAT

Paperid: 324, https://arxiv.org/pdf/2511.17967.pdf GitHub

Abstract:
RGB-Thermal (RGBT) tracking aims to exploit visible and thermal infrared modalities for robust all-weather object tracking. However, existing RGBT trackers struggle to resolve modality discrepancies, which poses great challenges for robust feature representation. This limitation hinders effective cross-modal information propagation and fusion, which significantly reduces the tracking accuracy. To address this limitation, we propose a novel Contextual Aggregation with Deformable Alignment framework called CADTrack for RGBT Tracking. To be specific, we first deploy the Mamba-based Feature Interaction (MFI) that establishes efficient feature interaction via state space models. This interaction module can operate with linear complexity, reducing computational cost and improving feature discrimination. Then, we propose the Contextual Aggregation Module (CAM) that dynamically activates backbone layers through sparse gating based on the Mixture-of-Experts (MoE). This module can encode complementary contextual information from cross-layer features. Finally, we propose the Deformable Alignment Module (DAM) to integrate deformable sampling and temporal propagation, mitigating spatial misalignment and localization drift. With the above components, our CADTrack achieves robust and accurate tracking in complex scenarios. Extensive experiments on five RGBT tracking benchmarks verify the effectiveness of our proposed method. The source code is released at https://github.com/IdolLab/CADTrack.

Paperid: 325, https://arxiv.org/pdf/2511.17965.pdf GitHub

Abstract:
Multi-modal object Re-IDentification (ReID) is devoted to retrieving specific objects through the exploitation of complementary multi-modal image information. Existing methods mainly concentrate on the fusion of multi-modal features, yet neglecting the background interference. Besides, current multi-modal fusion methods often focus on aligning modality pairs but suffer from multi-modal consistency alignment. To address these issues, we propose a novel selective interaction and global-local alignment framework called Signal for multi-modal object ReID. Specifically, we first propose a Selective Interaction Module (SIM) to select important patch tokens with intra-modal and inter-modal information. These important patch tokens engage in the interaction with class tokens, thereby yielding more discriminative features. Then, we propose a Global Alignment Module (GAM) to simultaneously align multi-modal features by minimizing the volume of 3D polyhedra in the gramian space. Meanwhile, we propose a Local Alignment Module (LAM) to align local features in a shift-aware manner. With these modules, our proposed framework could extract more discriminative features for object ReID. Extensive experiments on three multi-modal object ReID benchmarks (i.e., RGBNT201, RGBNT100, MSVR310) validate the effectiveness of our method. The source code is available at https://github.com/010129/Signal.

Paperid: 326, https://arxiv.org/pdf/2511.17964.pdf GitHub

Abstract:
Large-scale vision-language models (e.g., CLIP) have recently achieved remarkable performance in retrieval tasks, yet their potential for Video-based Visible-Infrared Person Re-Identification (VVI-ReID) remains largely unexplored. The primary challenges are narrowing the modality gap and leveraging spatiotemporal information in video sequences. To address the above issues, in this paper, we propose a novel cross-modality feature learning framework named X-ReID for VVI-ReID. Specifically, we first propose a Cross-modality Prototype Collaboration (CPC) to align and integrate features from different modalities, guiding the network to reduce the modality discrepancy. Then, a Multi-granularity Information Interaction (MII) is designed, incorporating short-term interactions from adjacent frames, long-term cross-frame information fusion, and cross-modality feature alignment to enhance temporal modeling and further reduce modality gaps. Finally, by integrating multi-granularity information, a robust sequence-level representation is achieved. Extensive experiments on two large-scale VVI-ReID benchmarks (i.e., HITSZ-VCM and BUPTCampus) demonstrate the superiority of our method over state-of-the-art methods. The source code is released at https://github.com/AsuradaYuci/X-ReID.

Paperid: 327, https://arxiv.org/pdf/2511.17958.pdf GitHub

Abstract:
Growing demands for clinical data privacy and storage constraints have spurred advances in Source Free Unsupervised Domain Adaptation (SFUDA). SFUDA addresses the domain shift by adapting models from the source domain to the unseen target domain without accessing source data, even when target-domain labels are unavailable. However, SFUDA faces significant challenges: the absence of source domain data and label supervision in the target domain due to source free and unsupervised settings. To address these issues, we propose HEAL, a novel SFUDA framework that integrates Hierarchical denoising, Edge-guided selection, size-Aware fusion, and Learning-free characteristic. Large-scale cross-modality experiments demonstrate that our method outperforms existing SFUDA approaches, achieving state-of-the-art (SOTA) performance. The source code is publicly available at: https://github.com/derekshiii/HEAL.

Paperid: 328, https://arxiv.org/pdf/2511.17955.pdf GitHub

Abstract:
With the rapid rise of short-form videos, TikTok has become one of the most influential platforms among children and teenagers, but also a source of harmful content that can affect their perception and behavior. Such content, often subtle or deceptive, challenges traditional moderation methods due to the massive volume and real-time nature of uploads. This paper presents MTikGuard, a real-time multimodal harmful content detection system for TikTok, with three key contributions: (1) an extended TikHarm dataset expanded to 4,723 labeled videos by adding diverse real-world samples, (2) a multimodal classification framework integrating visual, audio, and textual features to achieve state-of-the-art performance with 89.37% accuracy and 89.45% F1-score, and (3) a scalable streaming architecture built on Apache Kafka and Apache Spark for real-time deployment. The results demonstrate the effectiveness of combining dataset expansion, advanced multimodal fusion, and robust deployment for practical large-scale social media content moderation. The dataset is available at https://github.com/ntdat-8324/MTikGuard-System.git.

Paperid: 329, https://arxiv.org/pdf/2511.17952.pdf GitHub

Abstract:
Understanding social interaction in video requires reasoning over a dynamic interplay of verbal and non-verbal cues: who is speaking, to whom, and with what gaze or gestures. While Multimodal Large Language Models (MLLMs) are natural candidates, simply adding visual inputs yields surprisingly inconsistent gains on social tasks. Our quantitative analysis of cross-modal attention inside state-of-the-art MLLMs reveals a core failure mode: in multi-speaker scenes, visual and textual tokens lack speaker-consistent alignment, exhibiting substantially weaker cross-modal attention than in object-centric images. To address this, we propose a multimodal multi-speaker attention alignment method that can be integrated into existing MLLMs. First, we introduce dynamic cross-modal head selection to identify attention heads most responsible for grounding. Then, an adaptive social-aware attention bias, computed from existing attention patterns and speaker locations, is injected into the attention mechanism. This bias reinforces alignment between a speaker's visual representation and their utterances without introducing trainable parameters or architectural changes. We integrate our method into three distinct MLLMs (LLaVA-NeXT-Video, Qwen2.5-VL, and InternVL3) and evaluate on three benchmarks (TVQA+, MMSI, OnlineMMSI). Across four social tasks, results demonstrate that our approach improves the ability of MLLMs and achieves state-of-the-art results. Attention visualizations confirm our method successfully focuses the model on speaker-relevant regions, enabling more robust multi-party social reasoning. Our implementation and model will be available at https://github.com/ut-vision/SocialInteraction.

Paperid: 330, https://arxiv.org/pdf/2511.17946.pdf GitHub

Abstract:
Hallucination in large language models (LLMs) is a fundamental challenge, particularly in open-domain question answering. Prior work attempts to detect hallucination with model-internal signals such as token-level entropy or generation consistency, while the connection between pretraining data exposure and hallucination is underexplored. Existing studies show that LLMs underperform on long-tail knowledge, i.e., the accuracy of the generated answer drops for the ground-truth entities that are rare in pretraining. However, examining whether data coverage itself can serve as a detection signal is overlooked. We propose a complementary question: Does lexical training-data coverage of the question and/or generated answer provide additional signal for hallucination detection? To investigate this, we construct scalable suffix arrays over RedPajama's 1.3-trillion-token pretraining corpus to retrieve $n$-gram statistics for both prompts and model generations. We evaluate their effectiveness for hallucination detection across three QA benchmarks. Our observations show that while occurrence-based features are weak predictors when used alone, they yield modest gains when combined with log-probabilities, particularly on datasets with higher intrinsic model uncertainty. These findings suggest that lexical coverage features provide a complementary signal for hallucination detection. All code and suffix-array infrastructure are provided at https://github.com/WWWonderer/ostd.

Paperid: 331, https://arxiv.org/pdf/2511.17945.pdf GitHub

Abstract:
Processing long videos with multimodal large language models (MLLMs) poses a significant computational challenge, as the model's self-attention mechanism scales quadratically with the number of video tokens, resulting in high computational demand and slow inference speed. Current solutions, such as rule-based sub-sampling, learned frame selector, or memory-based summarization, often introduce their own trade-offs: they compromise accuracy, necessitate additional training, or decrease inference speed. In this paper, we propose Test-Time Temporal Sampling (T3S), a training-free, plug-and-play inference wrapper that enables MLLMs to process long videos both efficiently and effectively. T3S exploits spatiotemporal redundancy by generating multiple short and diverse subsequences of video tokens at inference time, packing them within a single forward pass, and aggregating their predictions. This multi-subsequence formulation broadens visual coverage while reducing the computational cost of self-attention from $O(L^2)$ to $O(\sum_{i=1}^m α_i^2L^2)$, where $\sum_{i=1}^m α_i^2 < 1$. Extensive experiments on long video understanding benchmarks demonstrate that T3S improves accuracy by up to 3.1% and reduces first token delay by $2.04\times$, all with minimal integration effort. Our approach operates entirely at inference time, requires no model modifications or fine-tuning, and is compatible with a wide range of pretrained MLLMs. T3S turns video redundancy into a computational advantage, offering a scalable solution for long-video understanding. The code is available at https://github.com/kaibinwang3/T3S.

Paperid: 332, https://arxiv.org/pdf/2511.17938.pdf GitHub

Abstract:
Large language models (LLMs) and multimodal LLMs (MLLMs) excel at chain-of-thought reasoning but face distribution shift at test-time and a lack of verifiable supervision. Recent test-time reinforcement learning (TTRL) methods derive label-free pseudo-rewards from self-consistency voting over sampled trajectories, yet they often collapse: the majority-vote reward prevails, responses shorten, and Pass@1 declines. We trace this to uniform sequence updates in which most tokens are low-entropy followers, while a small high-entropy subset determines the reasoning branches. Thus we propose SPINE, a token-selective test-time reinforcement learning framework that (i) updates only forking tokens, the high-entropy branch points identified from forward-pass statistics, and (ii) applies an entropy-band regularizer at those tokens to sustain exploration when entropy is too low and to suppress noisy supervision when it is too high. SPINE plugs into GRPO-style objectives, optionally with a KL anchor, and requires no labels or reward models. Across ten benchmarks spanning multimodal VQA, general and expert QA, mathematical reasoning, and medical QA, SPINE consistently improves Pass@1 over TTRL while avoiding response-length collapse and yielding more stable training dynamics on both LLM and MLLM backbones. These results indicate that aligning updates with chain-of-thought branch points is a simple and label-free mechanism for stable and effective test-time adaptation in reasoning models. Code is available at https://github.com/JianghaoWu/SPINE.

Paperid: 333, https://arxiv.org/pdf/2511.17923.pdf GitHub

Abstract:
Heterogeneous graphs are widely present in real-world complex networks, where the diversity of node and relation types leads to complex and rich semantics. Efforts for modeling complex relation semantics in heterogeneous graphs are restricted by the limitations of predefined semantic dependencies and the scarcity of supervised signals. The advanced pre-training and fine-tuning paradigm leverages graph structure to provide rich self-supervised signals, but introduces semantic gaps between tasks. Large Language Models (LLMs) offer significant potential to address the semantic issues of relations and tasks in heterogeneous graphs through their strong reasoning capabilities in textual modality, but their incorporation into heterogeneous graphs is largely limited by computational complexity. Therefore, in this paper, we propose an Efficient LLM-Aware (ELLA) framework for heterogeneous graphs, addressing the above issues. To capture complex relation semantics, we propose an LLM-aware Relation Tokenizer that leverages LLM to encode multi-hop, multi-type relations. To reduce computational complexity, we further employ a Hop-level Relation Graph Transformer, which help reduces the complexity of LLM-aware relation reasoning from exponential to linear. To bridge semantic gaps between pre-training and fine-tuning tasks, we introduce the fine-grained task-aware textual Chain-of-Thought (CoT) prompts. Extensive experiments on four heterogeneous graphs show that our proposed ELLA outperforms state-of-the-art methods in the performance and efficiency. In particular, ELLA scales up to 13b-parameter LLMs and achieves up to a 4x speedup compared with existing LLM-based methods. Our code is publicly available at https://github.com/l-wd/ELLA.

Paperid: 334, https://arxiv.org/pdf/2511.17918.pdf GitHub GitHub

Abstract:
Despite 3D Gaussian Splatting (3DGS) excelling in most configurations, it lacks generalization across novel viewpoints in a few-shot scenario because it overfits to the sparse observations. We revisit 3DGS optimization from a machine learning perspective, framing novel view synthesis as a generalization problem to unseen viewpoints-an underexplored direction. We propose Frequency-Adaptive Sharpness Regularization (FASR), which reformulates the 3DGS training objective, thereby guiding 3DGS to converge toward a better generalization solution. Although Sharpness-Aware Minimization (SAM) similarly reduces the sharpness of the loss landscape to improve generalization of classification models, directly employing it to 3DGS is suboptimal due to the discrepancy between the tasks. Specifically, it hinders reconstructing high-frequency details due to excessive regularization, while reducing its strength leads to under-penalizing sharpness. To address this, we reflect the local frequency of images to set the regularization weight and the neighborhood radius when estimating the local sharpness. It prevents floater artifacts in novel viewpoints and reconstructs fine details that SAM tends to oversmooth. Across datasets with various configurations, our method consistently improves a wide range of baselines. Code will be available at https://bbangsik13.github.io/FASR.

Paperid: 335, https://arxiv.org/pdf/2511.17914.pdf GitHub

Abstract:
Dataset distillation compresses large-scale datasets into compact, highly informative synthetic data, significantly reducing storage and training costs. However, existing research primarily focuses on balanced datasets and struggles to perform under real-world long-tailed distributions. In this work, we emphasize the critical role of soft labels in long-tailed dataset distillation and uncover the underlying mechanisms contributing to performance degradation. Specifically, we derive an imbalance-aware generalization bound for model trained on distilled dataset. We then identify two primary sources of soft-label bias, which originate from the distillation model and the distilled images, through systematic perturbation of the data imbalance levels. To address this, we propose ADSA, an Adaptive Soft-label Alignment module that calibrates the entangled biases. This lightweight module integrates seamlessly into existing distillation pipelines and consistently improves performance. On ImageNet-1k-LT with EDC and IPC=50, ADSA improves tail-class accuracy by up to 11.8% and raises overall accuracy to 41.4%. Extensive experiments demonstrate that ADSA provides a robust and generalizable solution under limited label budgets and across a range of distillation techniques. Code is available at: https://github.com/j-cyoung/ADSA_DD.git.

Paperid: 336, https://arxiv.org/pdf/2511.17898.pdf GitHub GitHub

Abstract:
Denoising-based models, such as diffusion and flow matching, have been a critical component of robotic manipulation for their strong distribution-fitting and scaling capacity. Concurrently, several works have demonstrated that simple learning objectives, such as L1 regression, can achieve performance comparable to denoising-based methods on certain tasks, while offering faster convergence and inference. In this paper, we focus on how to combine the advantages of these two paradigms: retaining the ability of denoising models to capture multi-modal distributions and avoid mode collapse while achieving the efficiency of the L1 regression objective. To achieve this vision, we reformulate the original v-prediction flow matching and transform it into sample-prediction with the L1 training objective. We empirically show that the multi-modality can be expressed via a single ODE step. Thus, we propose \textbf{L1 Flow}, a two-step sampling schedule that generates a suboptimal action sequence via a single integration step and then reconstructs the precise action sequence through a single prediction. The proposed method largely retains the advantages of flow matching while reducing the iterative neural function evaluations to merely two and mitigating the potential performance degradation associated with direct sample regression. We evaluate our method with varying baselines and benchmarks, including 8 tasks in MimicGen, 5 tasks in RoboMimic \& PushT Bench, and one task in the real-world scenario. The results show the advantages of the proposed method with regard to training efficiency, inference speed, and overall performance. \href{https://song-wx.github.io/l1flow.github.io/}{Project Website.}

Paperid: 337, https://arxiv.org/pdf/2511.17889.pdf GitHub GitHub

Abstract:
Grounding natural-language instructions into continuous control for quadruped robots remains a fundamental challenge in vision language action. Existing methods struggle to bridge high-level semantic reasoning and low-level actuation, leading to unstable grounding and weak generalization in the real world. To address these issues, we present MobileVLA-R1, a unified vision-language-action framework that enables explicit reasoning and continuous control for quadruped robots. We construct MobileVLA-CoT, a large-scale dataset of multi-granularity chain-of-thought (CoT) for embodied trajectories, providing structured reasoning supervision for alignment. Built upon this foundation, we introduce a two-stage training paradigm that combines supervised CoT alignment with GRPO reinforcement learning to enhance reasoning consistency, control stability, and long-horizon execution. Extensive evaluations on VLN and VLA tasks demonstrate superior performance over strong baselines, with approximately a 5% improvement. Real-world deployment on a quadruped robot validates robust performance in complex environments. Code: https://github.com/AIGeeksGroup/MobileVLA-R1. Website: https://aigeeksgroup.github.io/MobileVLA-R1.

Paperid: 338, https://arxiv.org/pdf/2511.17888.pdf GitHub

Abstract:
In the personalization process of large-scale text-to-image models, overfitting often occurs when learning specific subject from a limited number of images. Existing methods, such as DreamBooth, mitigate this issue through a class-specific prior-preservation loss, which requires increased computational cost during training and limits user control during inference time. To address these limitations, we propose Mask-Integrated Negative Attention Diffusion (MINDiff). MINDiff introduces a novel concept, negative attention, which suppresses the subject's influence in masked irrelevant regions. We achieve this by modifying the cross-attention mechanism during inference. This enables semantic control and improves text alignment by reducing subject dominance in irrelevant regions. Additionally, during the inference time, users can adjust a scale parameter lambda to balance subject fidelity and text alignment. Our qualitative and quantitative experiments on DreamBooth models demonstrate that MINDiff mitigates overfitting more effectively than class-specific prior-preservation loss. As our method operates entirely at inference time and does not alter the model architecture, it can be directly applied to existing DreamBooth models without re-training. Our code is available at https://github.com/seuleepy/MINDiff.

Paperid: 339, https://arxiv.org/pdf/2511.17855.pdf GitHub

Abstract:
Robots must learn from both what people do and what they say, but either modality alone is often incomplete: physical corrections are grounded but ambiguous in intent, while language expresses high-level goals but lacks physical grounding. We introduce QuickLAP: Quick Language-Action Preference learning, a Bayesian framework that fuses physical and language feedback to infer reward functions in real time. Our key insight is to treat language as a probabilistic observation over the user's latent preferences, clarifying which reward features matter and how physical corrections should be interpreted. QuickLAP uses Large Language Models (LLMs) to extract reward feature attention masks and preference shifts from free-form utterances, which it integrates with physical feedback in a closed-form update rule. This enables fast, real-time, and robust reward learning that handles ambiguous feedback. In a semi-autonomous driving simulator, QuickLAP reduces reward learning error by over 70% compared to physical-only and heuristic multimodal baselines. A 15-participant user study further validates our approach: participants found QuickLAP significantly more understandable and collaborative, and preferred its learned behavior over baselines. Code is available at https://github.com/MIT-CLEAR-Lab/QuickLAP.

Paperid: 340, https://arxiv.org/pdf/2511.17854.pdf GitHub

Abstract:
The capacity for highly complex, evidence-based, and strategically adaptive persuasion remains a formidable great challenge for artificial intelligence. Previous work, like IBM Project Debater, focused on generating persuasive speeches in simplified and shortened debate formats intended for relatively lay audiences. We introduce DeepDebater, a novel autonomous system capable of participating in and winning a full, unmodified, two-team competitive policy debate. Our system employs a hierarchical architecture of specialized multi-agent workflows, where teams of LLM-powered agents collaborate and critique one another to perform discrete argumentative tasks. Each workflow utilizes iterative retrieval, synthesis, and self-correction using a massive corpus of policy debate evidence (OpenDebateEvidence) and produces complete speech transcripts, cross-examinations, and rebuttals. We introduce a live, interactive end-to-end presentation pipeline that renders debates with AI speech and animation: transcripts are surface-realized and synthesized to audio with OpenAI TTS, and then displayed as talking-head portrait videos with EchoMimic V1. Beyond fully autonomous matches (AI vs AI), DeepDebater supports hybrid human-AI operation: human debaters can intervene at any stage, and humans can optionally serve as opponents against AI in any speech, allowing AI-human and AI-AI rounds. In preliminary evaluations against human-authored cases, DeepDebater produces qualitatively superior argumentative components and consistently wins simulated rounds as adjudicated by an independent autonomous judge. Expert human debate coaches also prefer the arguments, evidence, and cases constructed by DeepDebater. We open source all code, generated speech transcripts, audio and talking head video here: https://github.com/Hellisotherpeople/DeepDebater/tree/main

Paperid: 341, https://arxiv.org/pdf/2511.17841.pdf GitHub

Abstract:
This paper presents RadioGUNet, a UNet-based deep learning framework for pathloss estimation in wireless communication. Unlike other frameworks, it leverages group equivariant convolutional networks, which are known to increase the expressive capacity of a neural network by allowing the model to generalize to further classes of symmetries, such as rotations and reflections, without the need for data augmentation or data pre-processing. The results of this work are twofold. First, we show that typical UNet-based convolutional models can be easily extended to support group equivariant convolution (g-conv). Secondly, we show that the task of pathloss estimation benefits from such an extension, as the proposed extended model outperforms typical UNet-based models by up to 0.41 dB for a similar number of parameters in the RadioMapSeer dataset. The code is publicly available on the GitHub page: https://github.com/EricssonResearch/radiogunet

Paperid: 342, https://arxiv.org/pdf/2511.17826.pdf GitHub

Abstract:
Deterministic inference is increasingly critical for large language model (LLM) applications such as LLM-as-a-judge evaluation, multi-agent systems, and Reinforcement Learning (RL). However, existing LLM serving frameworks exhibit non-deterministic behavior: identical inputs can yield different outputs when system configurations (e.g., tensor parallel (TP) size, batch size) vary, even under greedy decoding. This arises from the non-associativity of floating-point arithmetic and inconsistent reduction orders across GPUs. While prior work has addressed batch-size-related nondeterminism through batch-invariant kernels, determinism across different TP sizes remains an open problem, particularly in RL settings, where the training engine typically uses Fully Sharded Data Parallel (i.e., TP = 1) while the rollout engine relies on multi-GPU TP to maximize the inference throughput, creating a natural mismatch between the two. This precision mismatch problem may lead to suboptimal performance or even collapse for RL training. We identify and analyze the root causes of TP-induced inconsistency and propose Tree-Based Invariant Kernels (TBIK), a set of TP-invariant matrix multiplication and reduction primitives that guarantee bit-wise identical results regardless of TP size. Our key insight is to align intra- and inter-GPU reduction orders through a unified hierarchical binary tree structure. We implement these kernels in Triton and integrate them into vLLM and FSDP. Experiments confirm zero probability divergence and bit-wise reproducibility for deterministic inference across different TP sizes. Also, we achieve bit-wise identical results between vLLM and FSDP in RL training pipelines with different parallel strategy. Code is available at https://github.com/nanomaoli/llm_reproducibility.

Paperid: 343, https://arxiv.org/pdf/2511.17813.pdf GitHub

Abstract:
Large language models offer opportunities to simulate multi-party deliberation, but realistic modeling remains limited by a lack of speaker-attributed data. Transcripts produced via automatic speech recognition (ASR) assign anonymous speaker labels (e.g., Speaker_1), preventing models from capturing consistent human behavior. This work introduces a reproducible pipeline to transform public Zoom recordings into speaker-attributed transcripts with metadata like persona profiles and pragmatic action tags (e.g., [propose_motion]). We release three local government deliberation datasets: Appellate Court hearings, School Board meetings, and Municipal Council sessions. Fine-tuning LLMs to model specific participants using this "action-aware" data produces a 67% reduction in perplexity and nearly doubles classifier-based performance metrics for speaker fidelity and realism. Turing-style human evaluations show our simulations are often indistinguishable from real deliberations, providing a practical and scalable method for complex realistic civic simulations.

Paperid: 344, https://arxiv.org/pdf/2511.17808.pdf GitHub

Abstract:
Large Language Models (LLMs) exhibit significant variations in performance across linguistic and cultural contexts, underscoring the need for systematic evaluation in diverse languages. In this work, we present the most extensive evaluation of LLMs for the Portuguese language to date. Leveraging our newly introduced PoETa v2 benchmark -- a comprehensive suite of over 40 tasks in Portuguese -- we assess more than 20 models covering a broad spectrum of training scales and computational resources. Our study reveals how computational investment and language-specific adaptation impact performance in Portuguese, while also analyzing performance gaps in comparison to equivalent tasks in English. Through this benchmark and analysis, PoETa v2 lays the groundwork for future research on Portuguese language modeling and evaluation. The benchmark is available at https://github.com/PoETaV2/PoETaV2.

Paperid: 345, https://arxiv.org/pdf/2511.17729.pdf GitHub

Abstract:
We present M^3-Bench, the first benchmark for evaluating multimodal tool use under the Model Context Protocol. The benchmark targets realistic, multi-hop and multi-threaded workflows that require visual grounding and textual reasoning, cross-tool dependencies, and persistence of intermediate resources across steps. We introduce a similarity-driven alignment that serializes each tool call, embeds signatures with a sentence encoder, and performs similarity-bucketed Hungarian matching to obtain auditable one-to-one correspondences. On top of this alignment, we report interpretable metrics that decouple semantic fidelity from workflow consistency. The benchmark spans 28 servers with 231 tools, and provides standardized trajectories curated through an Executor & Judge pipeline with human verification; an auxiliary four large language models (LLMs) judge ensemble reports end-task Task Completion and information grounding. Evaluations of representative state-of-the-art Multimodal LLMs (MLLMs) reveal persistent gaps in multimodal MCP tool use, particularly in argument fidelity and structure consistency, underscoring the need for methods that jointly reason over images, text, and tool graphs. Our Benchmark's anonymous repository is at https://github.com/EtaYang10th/Open-M3-Bench

Paperid: 346, https://arxiv.org/pdf/2511.17689.pdf GitHub

Abstract:
The rapid expansion of scholarly literature presents significant challenges in synthesizing comprehensive, high-quality academic surveys. Recent advancements in agentic systems offer considerable promise for automating tasks that traditionally require human expertise, including literature review, synthesis, and iterative refinement. However, existing automated survey-generation solutions often suffer from inadequate quality control, poor formatting, and limited adaptability to iterative feedback, which are core elements intrinsic to scholarly writing. To address these limitations, we introduce ARISE, an Agentic Rubric-guided Iterative Survey Engine designed for automated generation and continuous refinement of academic survey papers. ARISE employs a modular architecture composed of specialized large language model agents, each mirroring distinct scholarly roles such as topic expansion, citation curation, literature summarization, manuscript drafting, and peer-review-based evaluation. Central to ARISE is a rubric-guided iterative refinement loop in which multiple reviewer agents independently assess manuscript drafts using a structured, behaviorally anchored rubric, systematically enhancing the content through synthesized feedback. Evaluating ARISE against state-of-the-art automated systems and recent human-written surveys, our experimental results demonstrate superior performance, achieving an average rubric-aligned quality score of 92.48. ARISE consistently surpasses baseline methods across metrics of comprehensiveness, accuracy, formatting, and overall scholarly rigor. All code, evaluation rubrics, and generated outputs are provided openly at https://github.com/ziwang11112/ARISE

Paperid: 347, https://arxiv.org/pdf/2511.17649.pdf GitHub

Abstract:
Autonomous intelligence requires not only perception and reasoning, but critically, effective interaction with the existing world and its infrastructure. Everyday environments are rich in tangible control interfaces (TCIs), e.g., light switches, appliance panels, and embedded GUIs, that demand commonsense and physics reasoning, but also causal prediction and outcome verification in time and space (e.g., delayed heating, remote lights). Moreover, failures here have potential safety implications, yet current benchmarks rarely test grounding, partial observability (video), or post-hoc verification in situated settings. We introduce SWITCH (Semantic World Interface Tasks for Control and Handling), an embodied, task-driven benchmark created through iterative releases to probe these gaps. Its first iteration, SWITCH-Basic, evaluates five complementary abilities:task-aware VQA, semantic UI grounding, action generation, state-transition prediction, and result verification, under egocentric RGB video input and device diversity. Across 351 tasks spanning 98 real devices and appliances, commercial and open LMMMs exhibit inconsistent performance even on single-step interactions, often over-relying on textual cues and under-using visual or video evidence (and high aggregate scores can mask such failures). SWITCH provides data, code, and held-out splits to enable reproducible evaluation and community contributions toward more challenging future iterations of the benchmark and the creation of training datasets. Benchmark resources are available at: https://github.com/BAAI-Agents/SWITCH.

Paperid: 348, https://arxiv.org/pdf/2511.17624.pdf GitHub

Abstract:
QML-HCS is a research-grade framework for constructing and analyzing quantum-inspired machine learning models operating under hypercausal feedback dynamics. Hypercausal refers to AI systems that leverage extended, deep, or nonlinear causal relationships (expanded causality) to reason, predict, and infer states beyond the capabilities of traditional causal models. Current machine learning and quantum-inspired systems struggle in non-stationary environments, where data distributions drift and models lack mechanisms for continuous adaptation, causal stability, and coherent state updating. QML-HCS addresses this limitation through a unified computational architecture that integrates quantum-inspired superposition principles, dynamic causal feedback, and deterministic-stochastic hybrid execution to enable adaptive behavior in changing environments. The framework implements a hypercausal processing core capable of reversible transformations, multipath causal propagation, and evaluation of alternative states under drift. Its architecture incorporates continuous feedback to preserve causal consistency and adjust model behavior without requiring full retraining. QML-HCS provides a reproducible and extensible Python interface backed by efficient computational routines, enabling experimentation in quantum-inspired learning, causal reasoning, and hybrid computation without the need for specialized hardware. A minimal simulation demonstrates how a hypercausal model adapts to a sudden shift in the input distribution while preserving internal coherence. This initial release establishes the foundational architecture for future theoretical extensions, benchmarking studies, and integration with classical and quantum simulation platforms.

Paperid: 349, https://arxiv.org/pdf/2511.17614.pdf GitHub

Abstract:
Due to the high cost of annotation or the rarity of some diseases, medical image segmentation is often limited by data scarcity and the resulting overfitting problem. Self-supervised learning and semi-supervised learning can mitigate the data scarcity challenge to some extent. However, both of these paradigms are complex and require either hand-crafted pretexts or well-defined pseudo-labels. In contrast, data augmentation represents a relatively simple and straightforward approach to addressing data scarcity issues. It has led to significant improvements in image recognition tasks. However, the effectiveness of local image editing augmentation techniques in the context of segmentation has been less explored. We propose HSMix, a novel approach to local image editing data augmentation involving hard and soft mixing for medical semantic segmentation. In our approach, a hard-augmented image is created by combining homogeneous regions (superpixels) from two source images. A soft mixing method further adjusts the brightness of these composed regions with brightness mixing based on locally aggregated pixel-wise saliency coefficients. The ground-truth segmentation masks of the two source images undergo the same mixing operations to generate the associated masks for the augmented images. Our method fully exploits both the prior contour and saliency information, thus preserving local semantic information in the augmented images while enriching the augmentation space with more diversity. Our method is a plug-and-play solution that is model agnostic and applicable to a range of medical imaging modalities. Extensive experimental evidence has demonstrated its effectiveness in a variety of medical segmentation tasks. The source code is available in https://github.com/DanielaPlusPlus/HSMix.

Paperid: 350, https://arxiv.org/pdf/2511.17606.pdf GitHub

Abstract:
Understanding brain function represents a fundamental goal in neuroscience, with critical implications for therapeutic interventions and neural engineering applications. Computational modeling provides a quantitative framework for accelerating this understanding, but faces a fundamental trade-off between computational efficiency and high-fidelity modeling. To address this limitation, we introduce a novel Energy-based Autoregressive Generation (EAG) framework that employs an energy-based transformer learning temporal dynamics in latent space through strictly proper scoring rules, enabling efficient generation with realistic population and single-neuron spiking statistics. Evaluation on synthetic Lorenz datasets and two Neural Latents Benchmark datasets (MC_Maze and Area2_bump) demonstrates that EAG achieves state-of-the-art generation quality with substantial computational efficiency improvements, particularly over diffusion-based methods. Beyond optimal performance, conditional generation applications show two capabilities: generalizing to unseen behavioral contexts and improving motor brain-computer interface decoding accuracy using synthetic neural data. These results demonstrate the effectiveness of energy-based modeling for neural population dynamics with applications in neuroscience research and neural engineering. Code is available at https://github.com/NinglingGe/Energy-based-Autoregressive-Generation-for-Neural-Population-Dynamics.

Paperid: 351, https://arxiv.org/pdf/2511.17598.pdf GitHub

Abstract:
Algorithms developed under stationary Markov Decision Processes (MDPs) often face challenges in non-stationary environments, and infinite-horizon formulations may not directly apply to finite-horizon tasks. To address these limitations, we introduce the Non-stationary and Varying-discounting MDP (NVMDP) framework, which naturally accommodates non-stationarity and allows discount rates to vary with time and transitions. Infinite-horizon, stationary MDPs emerge as special cases of NVMDPs for identifying an optimal policy, and finite-horizon MDPs are also subsumed within the NVMDP formulations. Moreover, NVMDPs provide a flexible mechanism to shape optimal policies, without altering the state space, action space, or the reward structure. We establish the theoretical foundations of NVMDPs, including assumptions, state- and action-value formulation and recursion, matrix representation, optimality conditions, and policy improvement under finite state and action spaces. Building on these results, we adapt dynamic programming and generalized Q-learning algorithms to NVMDPs, along with formal convergence proofs. For problems requiring function approximation, we extend the Policy Gradient Theorem and the policy improvement bound in Trust Region Policy Optimization (TRPO), offering proofs in both scalar and matrix forms. Empirical evaluations in a non-stationary gridworld environment demonstrate that NVMDP-based algorithms successfully recover optimal trajectories under multiple reward and discounting schemes, whereas original Q-learning fails. These results collectively show that NVMDPs provide a theoretically sound and practically effective framework for reinforcement learning, requiring only minor algorithmic modifications while enabling robust handling of non-stationarity and explicit optimal policy shaping.

Paperid: 352, https://arxiv.org/pdf/2511.17597.pdf GitHub

Abstract:
Wildfire risk prediction remains a critical yet challenging task due to the complex interactions among fuel conditions, meteorology, topography, and human activity. Despite growing interest in data-driven approaches, publicly available benchmark datasets that support long-term temporal modeling, large-scale spatial coverage, and multimodal drivers remain scarce. To address this gap, we present a 25-year, daily-resolution wildfire dataset covering 240 million hectares across British Columbia and surrounding regions. The dataset includes 38 covariates, encompassing active fire detections, weather variables, fuel conditions, terrain features, and anthropogenic factors. Using this benchmark, we evaluate a diverse set of time-series forecasting models, including CNN-based, linear-based, Transformer-based, and Mamba-based architectures. We also investigate effectiveness of position embedding and the relative importance of different fire-driving factors. The dataset and the corresponding code can be found at https://github.com/SynUW/mmFire

Paperid: 353, https://arxiv.org/pdf/2511.17594.pdf GitHub

Abstract:
Sparse GNN aggregations (CSR SpMM/SDDMM) vary widely in performance with degree skew, feature width, and GPU micro-architecture. We present AutoSAGE, an input-aware CUDA scheduler that chooses tiling and mapping per input using a lightweight estimate refined by on-device micro-probes, with a guardrail that safely falls back to vendor kernels and a persistent cache for deterministic replay. AutoSAGE covers SpMM and SDDMM and composes into a CSR attention pipeline (SDDMM -> row-softmax -> SpMM). On Reddit and OGBN-Products, it matches vendor baselines at bandwidth-bound feature widths and finds gains at small widths; on synthetic sparsity and skew stress tests it achieves up to 4.7x kernel-level speedups. We release CUDA sources, Python bindings, a reproducible harness, and replayable cache logs.

Paperid: 354, https://arxiv.org/pdf/2511.17592.pdf GitHub

Abstract:
Recent advances in LLM-guided evolutionary computation, particularly AlphaEvolve (Novikov et al., 2025; Georgiev et al., 2025), have demonstrated remarkable success in discovering novel mathematical constructions and solving challenging optimization problems. However, the high-level descriptions in published work leave many implementation details unspecified, hindering reproducibility and further research. In this report we present GigaEvo, an extensible open-source framework that enables researchers to study and experiment with hybrid LLM-evolution approaches inspired by AlphaEvolve. Our system provides modular implementations of key components: MAP-Elites quality-diversity algorithms, asynchronous DAG-based evaluation pipelines, LLM-driven mutation operators with insight generation and bidirectional lineage tracking, and flexible multi-island evolutionary strategies. In order to assess reproducibility and validate our implementation we evaluate GigaEvo on challenging problems from the AlphaEvolve paper: Heilbronn triangle placement, circle packing in squares, and high-dimensional kissing numbers. The framework emphasizes modularity, concurrency, and ease of experimentation, enabling rapid prototyping through declarative configuration. We provide detailed descriptions of system architecture, implementation decisions, and experimental methodology to support further research in LLM driven evolutionary methods. The GigaEvo framework and all experimental code are available at https://github.com/AIRI-Institute/gigaevo-core.

Paperid: 355, https://arxiv.org/pdf/2511.17573.pdf GitHub

Abstract:
Sequence models for binary analysis are bottlenecked by byte-level tokenization: raw bytes waste precious context window capacity for transformers and other neural network architectures, and many existing text-oriented tokenizers fail on arbitrary 0x00--0xFF sequences. To address this issue, we introduce the Binary BPE tokenizer family, a set of cross-platform Byte Pair Encoding (BPE) tokenizers for executables trained on a large corpus of binaries spanning multiple platforms, architectures, and operating systems, including Linux, Windows, macOS, Android, and malware sources. We release trained tokenizers with vocabularies of 4K, 8K, 16K, 32K, and 64K tokens, enabling both systematic scaling studies and practical deployment from resource-constrained edge devices to high-throughput datacenters. These tokenizers discover interpretable patterns (ELF/PE headers, instruction sequences, cross-platform strings) while yielding multi-byte compression per token. On representative uncompressed executables (e.g., ELF/PE/Mach-O rather than compressed APKs), the Binary BPE tokenizers typically allow for roughly 2-3x more binary content per fixed-length transformer context window than raw bytes, enabling more efficient research and practical deployment for content identification, malware detection, reverse engineering, and optimization. We release the trained Binary BPE tokenizers on HuggingFace, providing a drop-in, open-source foundation for binary-focused language models and context-efficient agentic tools.

Paperid: 356, https://arxiv.org/pdf/2511.17558.pdf GitHub

Abstract:
Satellite-based radar retrieval methods are widely employed to fill coverage gaps in ground-based radar systems, especially in remote areas affected by terrain blockage and limited detection range. Existing methods predominantly rely on overly simplistic spatial-domain architectures constructed from a single data source, limiting their ability to accurately capture complex precipitation patterns and sharply defined meteorological boundaries. To address these limitations, we propose WaveC2R, a novel wavelet-driven coarse-to-refined framework for radar retrieval. WaveC2R integrates complementary multi-source data and leverages frequency-domain decomposition to separately model low-frequency components for capturing precipitation patterns and high-frequency components for delineating sharply defined meteorological boundaries. Specifically, WaveC2R consists of two stages (i)Intensity-Boundary Decoupled Learning, which leverages wavelet decomposition and frequency-specific loss functions to separately optimize low-frequency intensity and high-frequency boundaries; and (ii)Detail-Enhanced Diffusion Refinement, which employs frequency-aware conditional priors and multi-source data to progressively enhance fine-scale precipitation structures while preserving coarse-scale meteorological consistency. Experimental results on the publicly available SEVIR dataset demonstrate that WaveC2R achieves state-of-the-art performance in satellite-based radar retrieval, particularly excelling at preserving high-intensity precipitation features and sharply defined meteorological boundaries.

Paperid: 357, https://arxiv.org/pdf/2511.17554.pdf GitHub

Abstract:
Large Language Models (LLMs) have been positioned as having the potential to expand access to health information in the Global South, yet their evaluation remains heavily dependent on benchmarks designed around Western norms. We present insights from a preliminary benchmarking exercise with a chatbot for sexual and reproductive health (SRH) for an underserved community in India. We evaluated using HealthBench, a benchmark for conversational health models by OpenAI. We extracted 637 SRH queries from the dataset and evaluated on the 330 single-turn conversations. Responses were evaluated using HealthBench's rubric-based automated grader, which rated responses consistently low. However, qualitative analysis by trained annotators and public health experts revealed that many responses were actually culturally appropriate and medically accurate. We highlight recurring issues, particularly a Western bias, such as for legal framing and norms (e.g., breastfeeding in public), diet assumptions (e.g., fish safe to eat during pregnancy), and costs (e.g., insurance models). Our findings demonstrate the limitations of current benchmarks in capturing the effectiveness of systems built for different cultural and healthcare contexts. We argue for the development of culturally adaptive evaluation frameworks that meet quality standards while recognizing needs of diverse populations.

Paperid: 358, https://arxiv.org/pdf/2511.17526.pdf GitHub

Abstract:
Radio maps (RMs), which provide location-based pathloss estimations, are fundamental to enabling proactive, environment-aware communication in 6G networks. However, existing deep learning-based methods for RM construction often model dynamic environments as a series of independent static snapshots, thereby omitting the temporal continuity inherent in signal propagation changes caused by the motion of dynamic entities. To address this limitation, we propose the task of spatio-temporal RM prediction, which involves forecasting a sequence of future maps from historical observations. A key barrier to this predictive approach has been the lack of datasets capturing continuous environmental evolution. To fill this gap, we introduce RadioMapMotion, the first large-scale public dataset of continuous RM sequences generated from physically consistent vehicle trajectories. As a baseline for this task, we propose RadioLSTM, a UNet architecture based on Convolutional Long Short-Term Memory (ConvLSTM) and designed for multi-step sequence forecasting. Experimental evaluations show that RadioLSTM achieves higher prediction accuracy and structural fidelity compared to representative baseline methods. Furthermore, the model exhibits a low inference latency, indicating its potential suitability for real-time network operations. Our project will be publicly released at: https://github.com/UNIC-Lab/RadioMapMotion upon paper acceptance.

Paperid: 359, https://arxiv.org/pdf/2511.17497.pdf GitHub

Abstract:
We demonstrate real-time high-altitude aerial metric-semantic mapping and exploration using a monocular camera paired with a global positioning system (GPS) and an inertial measurement unit (IMU). Our system, named HALO, addresses two key challenges: (i) real-time dense 3D reconstruction using vision at large distances, and (ii) mapping and exploration of large-scale outdoor environments with accurate scene geometry and semantics. We demonstrate that HALO can plan informative paths that exploit this information to complete missions with multiple tasks specified in natural language. In simulation-based evaluation across large-scale environments of size up to 78,000 sq. m., HALO consistently completes tasks with less exploration time and achieves up to 68% higher competitive ratio in terms of the distance traveled compared to the state-of-the-art semantic exploration baseline. We use real-world experiments on a custom quadrotor platform to demonstrate that (i) all modules can run onboard the robot, and that (ii) in diverse environments HALO can support effective autonomous execution of missions covering up to 24,600 sq. m. area at an altitude of 40 m. Experiment videos and more details can be found on our project page: https://tyuezhan.github.io/halo/.

Paperid: 360, https://arxiv.org/pdf/2511.17490.pdf GitHub

Abstract:
Understanding text-rich videos requires reading small, transient textual cues that often demand repeated inspection. Yet most video QA models rely on single-pass perception over fixed frames, leading to hallucinations and failures on fine-grained evidence. Inspired by how humans pause, zoom, and re-read critical regions, we introduce Video-R4 (Reinforcing Text-Rich Video Reasoning with Visual Rumination), a video reasoning LMM that performs visual rumination: iteratively selecting frames, zooming into informative regions, re-encoding retrieved pixels, and updating its reasoning state. We construct two datasets with executable rumination trajectories: Video-R4-CoT-17k for supervised practice and Video-R4-RL-30k for reinforcement learning. We propose a multi-stage rumination learning framework that progressively finetunes a 7B LMM to learn atomic and mixing visual operations via SFT and GRPO-based RL. Video-R4-7B achieves state-of-the-art results on M4-ViteVQA and further generalizes to multi-page document QA, slides QA, and generic video QA, demonstrating that iterative rumination is an effective paradigm for pixel-grounded multimodal reasoning. Project Page: https://yunlong10.github.io/Video-R4/

Paperid: 361, https://arxiv.org/pdf/2511.17455.pdf GitHub

Abstract:
Semantic segmentation networks trained under full supervision for one type of lidar fail to generalize to unseen lidars without intervention. To reduce the performance gap under domain shifts, a recent trend is to leverage vision foundation models (VFMs) providing robust features across domains. In this work, we conduct an exhaustive study to identify recipes for exploiting VFMs in unsupervised domain adaptation for semantic segmentation of lidar point clouds. Building upon unsupervised image-to-lidar knowledge distillation, our study reveals that: (1) the architecture of the lidar backbone is key to maximize the generalization performance on a target domain; (2) it is possible to pretrain a single backbone once and for all, and use it to address many domain shifts; (3) best results are obtained by keeping the pretrained backbone frozen and training an MLP head for semantic segmentation. The resulting pipeline achieves state-of-the-art results in four widely-recognized and challenging settings. The code will be available at: https://github.com/valeoai/muddos.

Paperid: 362, https://arxiv.org/pdf/2511.17448.pdf GitHub

Abstract:
Vision-Language Models (VLMs) are increasingly deployed in safety-critical applications, making their adversarial robustness a crucial concern. While adversarial knowledge distillation has shown promise in transferring robustness from teacher to student models, traditional single-teacher approaches suffer from limited knowledge diversity, slow convergence, and difficulty in balancing robustness and accuracy. To address these challenges, we propose MMT-ARD: a Multimodal Multi-Teacher Adversarial Robust Distillation framework. Our key innovation is a dual-teacher knowledge fusion architecture that collaboratively optimizes clean feature preservation and robust feature enhancement. To better handle challenging adversarial examples, we introduce a dynamic weight allocation strategy based on teacher confidence, enabling adaptive focus on harder samples. Moreover, to mitigate bias among teachers, we design an adaptive sigmoid-based weighting function that balances the strength of knowledge transfer across modalities. Extensive experiments on ImageNet and zero-shot benchmarks demonstrate that MMT-ARD improves robust accuracy by +4.32% and zero-shot accuracy by +3.5% on the ViT-B-32 model, while achieving a 2.3x increase in training efficiency over traditional single-teacher methods. These results highlight the effectiveness and scalability of MMT-ARD in enhancing the adversarial robustness of multimodal large models. Our codes are available at https://github.com/itsnotacie/MMT-ARD.

Paperid: 363, https://arxiv.org/pdf/2511.17442.pdf GitHub

Abstract:
Foundation Models (FMs) are increasingly used in remote sensing (RS) for tasks such as environmental monitoring, disaster assessment, and land-use mapping. These models include unimodal vision encoders trained on a single data modality and multimodal architectures trained on combinations of SAR, multispectral, hyperspectral, and image-text data. They support diverse RS tasks including semantic segmentation, image classification, change detection, and visual question answering. However, selecting an appropriate remote sensing foundation model (RSFM) remains difficult due to scattered documentation, heterogeneous formats, and varied deployment constraints. We introduce the RSFM Database (RS-FMD), a structured resource covering over 150 RSFMs spanning multiple data modalities, resolutions, and learning paradigms. Built on RS-FMD, we present REMSA, the first LLM-based agent for automated RSFM selection from natural language queries. REMSA interprets user requirements, resolves missing constraints, ranks candidate models using in-context learning, and provides transparent justifications. We also propose a benchmark of 75 expert-verified RS query scenarios, producing 900 configurations under an expert-centered evaluation protocol. REMSA outperforms several baselines, including naive agents, dense retrieval, and unstructured RAG-based LLMs. It operates entirely on publicly available metadata and does not access private or sensitive data.

Paperid: 364, https://arxiv.org/pdf/2511.17441.pdf GitHub

Authors:Shihan Wu, Xuecheng Liu, Shaoxuan Xie, Pengwei Wang, Xinghang Li, Bowen Yang, Zhe Li, Kai Zhu, Hongyu Wu, Yiheng Liu, Zhaoye Long, Yue Wang, Chong Liu, Dihan Wang, Ziqiang Ni, Xiang Yang, You Liu, Ruoxuan Feng, Runtian Xu, Lei Zhang, Denghang Huang, Chenghao Jin, Anlan Yin, Xinlong Wang, Zhenguo Sun, Junkai Zhao, Mengfei Du, Mingyu Cao, Xiansheng Chen, Hongyang Cheng, Xiaojie Zhang, Yankai Fu, Ning Chen, Cheng Chi, Sixiang Chen, Huaihai Lyu, Xiaoshuai Hao, Yankai Fu, Yequan Wang, Bo Lei, Dong Liu, Xi Yang, Yance Jiao, Tengfei Pan, Yunyan Zhang, Songjing Wang, Ziqian Zhang, Xu Liu, Ji Zhang, Caowei Meng, Zhizheng Zhang, Jiyang Gao, Song Wang, Xiaokun Leng, Zhiqiang Xie, Zhenzhen Zhou, Peng Huang, Wu Yang, Yandong Guo, Yichao Zhu, Suibing Zheng, Hao Cheng, Xinmin Ding, Yang Yue, Huanqian Wang, Chi Chen, Jingrui Pang, YuXi Qian, Haoran Geng, Lianli Gao, Haiyuan Li, Bin Fang, Gao Huang, Yaodong Yang, Hao Dong, He Wang, Hang Zhao, Yadong Mu, Di Hu, Hao Zhao, Tiejun Huang, Shanghang Zhang, Yonghua Lin, Zhongyuan Wang, Guocai Yao

Abstract:
Bimanual manipulation is essential for achieving human-like dexterity in robots, but the large-scale and diverse bimanual robot datasets remain scarce due to hardware heterogeneity across robotic platforms. To address the challenge, we present RoboCOIN, a comprehensive multi-embodiment bimanual manipulation dataset with over 180,000 demonstrations collected from 15 distinct robotic platforms. The dataset covers 16 scenarios, including residential, commercial, and working environments, with 421 tasks systematically organized by bimanual coordination patterns and object properties. Our key innovation is a hierarchical capability pyramid that provides multi-level annotations, spanning trajectory-level concepts, segment-level subtasks, and frame-level kinematics. We further develop CoRobot, a comprehensive processing framework featuring Robot Trajectory Markup Language (RTML) for quality assessment, automated annotation generation, and unified multi-embodiment management. Extensive experiments demonstrate the reliability and effectiveness of RoboCOIN in multi-embodiment bimanual learning, with significant performance improvements across various model architectures and robotic platforms. The complete dataset and framework are open-sourced and publicly available for further research purposes. Project website: https://FlagOpen.github.io/RoboCOIN/.

Paperid: 365, https://arxiv.org/pdf/2511.17405.pdf GitHub

Abstract:
Multiple-choice question answering (MCQA) has been a popular format for evaluating and reinforcement fine-tuning (RFT) of modern multimodal language models. Its constrained output format allows for simplified, deterministic automatic verification. However, we find that the options may leak exploitable signals, which makes the accuracy metrics unreliable for indicating real capabilities and encourages explicit or implicit answer guessing behaviors during RFT. We propose ReVeL (Rewrite and Verify by LLM), a framework that rewrites multiple-choice questions into open-form questions while keeping answers verifiable whenever possible. The framework categorizes questions according to different answer types, apply different rewriting and verification schemes, respectively. When applied for RFT, we converted 20k MCQA examples and use GRPO to finetune Qwen2.5-VL models. Models trained on ReVeL-OpenQA match MCQA accuracy on multiple-choice benchmarks and improve OpenQA accuracy by about six percentage points, indicating better data efficiency and more robust reward signals than MCQA-based training. When used for evaluation, ReVeL also reveals up to 20 percentage points of score inflation in MCQA benchmarks (relative to OpenQA), improves judging accuracy, and reduces both cost and latency. We will release code and data publicly.

Paperid: 366, https://arxiv.org/pdf/2511.17397.pdf GitHub

Abstract:
Multimodal Action Quality Assessment (AQA) has recently emerged as a promising paradigm. By leveraging complementary information across shared contextual cues, it enhances the discriminative evaluation of subtle intra-class variations in highly similar action sequences. However, partial modalities are frequently unavailable at the inference stage in reality. The absence of any modality often renders existing multimodal models inoperable. Furthermore, it triggers catastrophic performance degradation due to interruptions in cross-modal interactions. To address this issue, we propose a novel Missing Completion Framework with Mixture of Experts (MCMoE) that unifies unimodal and joint representation learning in single-stage training. Specifically, we propose an adaptive gated modality generator that dynamically fuses available information to reconstruct missing modalities. We then design modality experts to learn unimodal knowledge and dynamically mix the knowledge of all experts to extract cross-modal joint representations. With a mixture of experts, missing modalities are further refined and complemented. Finally, in the training phase, we mine the complete multimodal features and unimodal expert knowledge to guide modality generation and generation-based joint representation extraction. Extensive experiments demonstrate that our MCMoE achieves state-of-the-art results in both complete and incomplete multimodal learning on three public AQA benchmarks. Code is available at https://github.com/XuHuangbiao/MCMoE.

Paperid: 367, https://arxiv.org/pdf/2511.17375.pdf GitHub

Abstract:
The vector cost bimatrix game is a method for multi-objective decision making that enables autonomous robotic systems to optimize for multiple goals at once while avoiding worst-case scenarios in neglected objectives. We expand this approach to arbitrary numbers of objectives and compare its performance to scalar weighted sum methods during competitive motion planning. Explainable Artificial Intelligence (XAI) software is used to aid in the analysis of high dimensional decision-making data. State-space Exploration of Multidimensional Boundaries using Adherence Strategies (SEMBAS) is applied to explore performance modes in the parameter space as a sensitivity study for the baseline and proposed frameworks. While some works have explored aspects of game theoretic planning and intelligent systems validation separately, we combine each of these into a novel and comprehensive simulation pipeline. This integration demonstrates a dramatic improvement of the vector cost method over scalarization and offers an interpretable and generalizable framework for robotic behavioral planning. Code available at https://github.com/toazbenj/race_simulation. The video companion to this work is available at https://tinyurl.com/vectorcostvideo.

Paperid: 368, https://arxiv.org/pdf/2511.17361.pdf GitHub

Abstract:
Semantic occupancy estimation enables comprehensive scene understanding for automated driving, providing dense spatial and semantic information essential for perception and planning. While Gaussian representations have been widely adopted in self-supervised occupancy estimation, the deployment of a large number of Gaussian primitives drastically increases memory requirements and is not suitable for real-time inference. In contrast, superquadrics permit reduced primitive count and lower memory requirements due to their diverse shape set. However, implementation into a self-supervised occupancy model is nontrivial due to the absence of a superquadric rasterizer to enable model supervision. Our proposed method, SuperQuadricOcc, employs a superquadric-based scene representation. By leveraging a multi-layer icosphere-tessellated Gaussian approximation of superquadrics, we enable Gaussian rasterization for supervision during training. On the Occ3D dataset, SuperQuadricOcc achieves a 75% reduction in memory footprint, 124% faster inference, and a 5.9% improvement in mIoU compared to previous Gaussian-based methods, without the use of temporal labels. To our knowledge, this is the first occupancy model to enable real-time inference while maintaining competitive performance. The use of superquadrics reduces the number of primitives required for scene modeling by 84% relative to Gaussian-based approaches. Finally, evaluation against prior methods is facilitated by our fast superquadric voxelization module. The code will be made available at https://github.com/seamie6/SuperQuadricOcc.

Paperid: 369, https://arxiv.org/pdf/2511.17354.pdf GitHub GitHub

Abstract:
Image-based Joint-Embedding Predictive Architecture (I-JEPA) learns visual representations by predicting latent embeddings of masked regions from visible context. However, it treats all regions uniformly and independently, lacking an explicit notion of where or in what order predictions should be made. Inspired by human visual perception, which deploys attention selectively and sequentially from the most informative to secondary regions, we propose DSeq-JEPA, a Discriminative Sequential Joint-Embedding Predictive Architecture that bridges predictive and autoregressive self-supervised learning, integrating JEPA-style latent prediction with GPT-style sequential reasoning. Specifically, DSeq-JEPA (i) first identifies primary discriminative regions based on a transformer-derived saliency map, emphasizing the distribution of visual importance, and then (ii) predicts subsequent regions in this discriminative order, progressively forming a curriculum-like semantic progression from primary to secondary cues -- a form of GPT-style pre-training. Extensive experiments across diverse tasks, including image classification (ImageNet), fine-grained visual categorization (iNaturalist21, CUB-200-2011, Stanford-Cars), detection and segmentation (MS-COCO, ADE20K), and low-level reasoning tasks (Clevr/Count, Clevr/Dist), demonstrate that DSeq-JEPA consistently focuses on more discriminative and generalizable representations than I-JEPA variants. Project page: https://github.com/SkyShunsuke/DSeq-JEPA.

Paperid: 370, https://arxiv.org/pdf/2511.17353.pdf GitHub GitHub

Abstract:
Beyond the commonly recognized optical aberrations, the imaging performance of compact optical systems-including single-lens and metalens designs-is often further degraded by veiling glare caused by stray-light scattering from non-ideal optical surfaces and coatings, particularly in complex real-world environments. This compound degradation undermines traditional lens aberration correction yet remains underexplored. A major challenge is that conventional scattering models (e.g., for dehazing) fail to fit veiling glare due to its spatial-varying and depth-independent nature. Consequently, paired high-quality data are difficult to prepare via simulation, hindering application of data-driven veiling glare removal models. To this end, we propose VeilGen, a generative model that learns to simulate veiling glare by estimating its underlying optical transmission and glare maps in an unsupervised manner from target images, regularized by Stable Diffusion (SD)-based priors. VeilGen enables paired dataset generation with realistic compound degradation of optical aberrations and veiling glare, while also providing the estimated latent optical transmission and glare maps to guide the veiling glare removal process. We further introduce DeVeiler, a restoration network trained with a reversibility constraint, which utilizes the predicted latent maps to guide an inverse process of the learned scattering model. Extensive experiments on challenging compact optical systems demonstrate that our approach delivers superior restoration quality and physical fidelity compared with existing methods. These suggest that VeilGen reliably synthesizes realistic veiling glare, and its learned latent maps effectively guide the restoration process in DeVeiler. All code and datasets will be publicly released at https://github.com/XiaolongQian/DeVeiler.

Paperid: 371, https://arxiv.org/pdf/2511.17308.pdf GitHub

Abstract:
Multimodal large language models (MLLMs) have achieved significant progress in image and language tasks due to the strong reasoning capability of large language models (LLMs). Nevertheless, most MLLMs suffer from limited spatial reasoning ability to interpret and infer spatial arrangements in three-dimensional space. In this work, we propose a novel vision encoder based on hierarchical fusion of geometry and semantics features, generating spatial-aware visual embedding and boosting the spatial grounding capability of MLLMs. Specifically, we first unveil that the spatial ambiguity shortcoming stems from the lossy embedding of the vision encoder utilized in most existing MLLMs (e.g., CLIP), restricted to instance-level semantic features. This motivates us to complement CLIP with the geometry features from vision-only self-supervised learning via a hierarchical adapter, enhancing the spatial awareness in the proposed SpatialGeo. The network is efficiently trained using pretrained LLaVA model and optimized with random feature dropping to avoid trivial solutions relying solely on the CLIP encoder. Experimental results show that SpatialGeo improves the accuracy in spatial reasoning tasks, enhancing state-of-the-art models by at least 8.0% in SpatialRGPT-Bench with approximately 50% less memory cost during inference. The source code is available via https://ricky-plus.github.io/SpatialGeoPages/.

Paperid: 372, https://arxiv.org/pdf/2511.17306.pdf GitHub

Abstract:
Finger pose offers promising opportunities to expand human computer interaction capability of touchscreen devices. Existing finger pose estimation algorithms that can be implemented in portable devices predominantly rely on capacitive images, which are currently limited to estimating pitch and yaw angles and exhibit reduced accuracy when processing large-angle inputs (especially when it is greater than 45 degrees). In this paper, we propose BiFingerPose, a novel bimodal based finger pose estimation algorithm capable of simultaneously and accurately predicting comprehensive finger pose information. A bimodal input is explored, including a capacitive image and a fingerprint patch obtained from the touchscreen with an under-screen fingerprint sensor. Our approach leads to reliable estimation of roll angle, which is not achievable using only a single modality. In addition, the prediction performance of other pose parameters has also been greatly improved. The evaluation of a 12-person user study on continuous and discrete interaction tasks further validated the advantages of our approach. Specifically, BiFingerPose outperforms previous SOTA methods with over 21% improvement in prediction performance, 2.5 times higher task completion efficiency, and 23% better user operation accuracy, demonstrating its practical superiority. Finally, we delineate the application space of finger pose with respect to enhancing authentication security and improving interactive experiences, and develop corresponding prototypes to showcase the interaction potential. Our code will be available at https://github.com/XiongjunGuan/DualFingerPose.

Paperid: 373, https://arxiv.org/pdf/2511.17254.pdf GitHub

Abstract:
Despite their impressive performance across a wide range of tasks, Large Vision-Language Models (LVLMs) remain prone to hallucination. In this study, we propose a comprehensive intervention framework aligned with the transformer's causal architecture in LVLMs, integrating the effects of different intervention paths on hallucination. We find that hallucinations in LVLMs do not arise from a single causal path, but rather from the interplay among image-to-input-text, image-to-output-text, and text-to-text pathways. For the first time, we also find that LVLMs rely on different pathways depending on the question-answer alignment format. Building on these insights, we propose simple yet effective methods to identify and intervene on critical hallucination heads within each pathway, tailored to discriminative and generative formats. Experiments across multiple benchmarks demonstrate that our approach consistently reduces hallucinations across diverse alignment types.

Paperid: 374, https://arxiv.org/pdf/2511.17238.pdf GitHub

Abstract:
The impressive performance of VLMs is largely measured on benchmarks that fail to capture the complexities of real-world scenarios. Existing datasets for tabular QA, such as WikiTableQuestions and FinQA, are overwhelmingly monolingual (English) and present tables in a digitally perfect, clean format. This creates a significant gap between research and practice. To address this, we present \textbf{MirageTVQA}, a new benchmark designed to evaluate VLMs on these exact dimensions. Featuring nearly 60,000 QA pairs across 24 languages, MirageTVQA challenges models with tables that are not only multilingual but also visually imperfect, incorporating realistic noise to mimic scanned documents. Our evaluation of the leading VLMs reveals two primary failure points: a severe degradation in performance (over 35\% drop for the best models) when faced with visual noise and a consistent English-first bias where reasoning abilities fail to transfer to other languages. MirageTVQA provides a benchmark for measuring and driving progress towards more robust VLM models for table reasoning. The dataset and the code are available at: https://github.com/anshulsc/MirageTVQA.

Paperid: 375, https://arxiv.org/pdf/2511.17217.pdf GitHub

Abstract:
Realistic image super-resolution (SR) focuses on transforming real-world low-resolution (LR) images into high-resolution (HR) ones, handling more complex degradation patterns than synthetic SR tasks. This is critical for applications like surveillance, medical imaging, and consumer electronics. However, current methods struggle with limited real-world LR-HR data, impacting the learning of basic image features. Pre-trained SR models from large-scale synthetic datasets offer valuable prior knowledge, which can improve generalization, speed up training, and reduce the need for extensive real-world data in realistic SR tasks. In this paper, we introduce a novel approach, Dual-domain Adaptation Networks, which is able to efficiently adapt pre-trained image SR models from simulated to real-world datasets. To achieve this target, we first set up a spatial-domain adaptation strategy through selectively updating parameters of pre-trained models and employing the low-rank adaptation technique to adjust frozen parameters. Recognizing that image super-resolution involves recovering high-frequency components, we further integrate a frequency domain adaptation branch into the adapted model, which combines the spectral data of the input and the spatial-domain backbone's intermediate features to infer HR frequency maps, enhancing the SR result. Experimental evaluations on public realistic image SR benchmarks, including RealSR, D2CRealSR, and DRealSR, demonstrate the superiority of our proposed method over existing state-of-the-art models. Codes are available at: https://github.com/dummerchen/DAN.

Paperid: 376, https://arxiv.org/pdf/2511.17208.pdf GitHub

Abstract:
LLM-based conversational agents still struggle to maintain coherent, personalized interaction over many sessions: fixed context windows limit how much history can be kept in view, and most external memory approaches trade off between coarse retrieval over large chunks and fine-grained but fragmented views of the dialogue. Motivated by neo-Davidsonian event semantics, we propose an event-centric alternative that represents conversational history as short, event-like propositions which bundle together participants, temporal cues, and minimal local context, rather than as independent relation triples or opaque summaries. In contrast to work that aggressively compresses or forgets past content, our design aims to preserve information in a non-compressive form and make it more accessible, rather than more lossy. Concretely, we instruct an LLM to decompose each session into enriched elementary discourse units (EDUs) -- self-contained statements with normalized entities and source turn attributions -- and organize sessions, EDUs, and their arguments in a heterogeneous graph that supports associative recall. On top of this representation we build two simple retrieval-based variants that use dense similarity search and LLM filtering, with an optional graph-based propagation step to connect and aggregate evidence across related EDUs. Experiments on the LoCoMo and LongMemEval$_S$ benchmarks show that these event-centric memories match or surpass strong baselines, while operating with much shorter QA contexts. Our results suggest that structurally simple, event-level memory provides a principled and practical foundation for long-horizon conversational agents. Our code and data will be released at https://github.com/KevinSRR/EMem.

Paperid: 377, https://arxiv.org/pdf/2511.17201.pdf GitHub

Abstract:
In medical image segmentation, heterogeneous privacy policies across institutions often make joint training on pooled datasets infeasible, motivating continual image segmentation-learning from data streams without catastrophic forgetting. While the Segment Anything Model (SAM) offers strong zero-shot priors and has been widely fine-tuned across downstream tasks, its large parameter count and computational overhead challenge practical deployment. This paper demonstrates that the SAM paradigm is highly promising once its computational efficiency and performance can be balanced. To this end, we introduce the Alignment Layer, a lightweight, plug-and-play module which aligns encoder-decoder feature distributions to efficiently adapt SAM to specific medical images, improving accuracy while reducing computation. Building on SAM and the Alignment Layer, we then propose Continual Alignment for SAM (CA-SAM), a continual learning strategy that automatically adapts the appropriate Alignment Layer to mitigate catastrophic forgetting, while leveraging SAM's zero-shot priors to preserve strong performance on unseen medical datasets. Experimented across nine medical segmentation datasets under continual-learning scenario, CA-SAM achieves state-of-the-art performance. Our code, models and datasets will be released on \mbox{https://github.com/azzzzyo/Continual-Alignment-for-SAM.}

Paperid: 378, https://arxiv.org/pdf/2511.17198.pdf GitHub

Abstract:
LLM-driven agents, particularly those using general frameworks like ReAct or human-inspired role-playing, often struggle in specialized domains that necessitate rigorously structured workflows. Fields such as remote sensing, requiring specialized tools (e.g., correction, spectral indices calculation), and multi-step procedures (e.g., numerous intermediate products and optional steps), significantly challenge generalized approaches. To address this gap, we introduce a novel agent design framework centered on a Hierarchical Task Abstraction Mechanism (HTAM). Specifically, HTAM moves beyond emulating social roles, instead structuring multi-agent systems into a logical hierarchy that mirrors the intrinsic task-dependency graph of a given domain. This task-centric architecture thus enforces procedural correctness and decomposes complex problems into sequential layers, where each layer's sub-agents operate on the outputs of the preceding layers. We instantiate this framework as EarthAgent, a multi-agent system tailored for complex geospatial analysis. To evaluate such complex planning capabilities, we build GeoPlan-bench, a comprehensive benchmark of realistic, multi-step geospatial planning tasks. It is accompanied by a suite of carefully designed metrics to evaluate tool selection, path similarity, and logical completeness. Experiments show that EarthAgent substantially outperforms a range of established single- and multi-agent systems. Our work demonstrates that aligning agent architecture with a domain's intrinsic task structure is a critical step toward building robust and reliable specialized autonomous systems.

Paperid: 379, https://arxiv.org/pdf/2511.17185.pdf GitHub

Abstract:
We propose PostCam, a framework for novel-view video generation that enables post-capture editing of camera trajectories in dynamic scenes. We find that existing video recapture methods suffer from suboptimal camera motion injection strategies; such suboptimal designs not only limit camera control precision but also result in generated videos that fail to preserve fine visual details from the source video. To achieve more accurate and flexible motion manipulation, PostCam introduces a query-shared cross-attention module. It integrates two distinct forms of control signals: the 6-DoF camera poses and the 2D rendered video frames. By fusing them into a unified representation within a shared feature space, our model can extract underlying motion cues, which enhances both control precision and generation quality. Furthermore, we adopt a two-stage training strategy: the model first learns coarse camera control from pose inputs, and then incorporates visual information to refine motion accuracy and enhance visual fidelity. Experiments on both real-world and synthetic datasets demonstrate that PostCam outperforms state-of-the-art methods by over 20% in camera control precision and view consistency, while achieving the highest video generation quality. Our project webpage is publicly available at: https://cccqaq.github.io/PostCam.github.io/

Paperid: 380, https://arxiv.org/pdf/2511.17155.pdf GitHub

Abstract:
The appearance of ultrasound images varies across acquisition devices, causing domain shifts that degrade the performance of fixed black-box downstream inference models when reused. To mitigate this issue, it is practical to develop unpaired image translation (UIT) methods that effectively align the statistical distributions between source and target domains, particularly under the constraint of a reused inference-blackbox setting. However, existing UIT approaches often overlook class-specific semantic alignment during domain adaptation, resulting in misaligned content-class mappings that can impair diagnostic accuracy. To address this limitation, we propose UI-Styler, a novel ultrasound-specific, class-aware image style transfer framework. UI-Styler leverages a pattern-matching mechanism to transfer texture patterns embedded in the target images onto source images while preserving the source structural content. In addition, we introduce a class-aware prompting strategy guided by pseudo labels of the target domain, which enforces accurate semantic alignment with diagnostic categories. Extensive experiments on ultrasound cross-device tasks demonstrate that UI-Styler consistently outperforms existing UIT methods, achieving state-of-the-art performance in distribution distance and downstream tasks, such as classification and segmentation.

Paperid: 381, https://arxiv.org/pdf/2511.17138.pdf GitHub

Abstract:
Recent advances in diffusion-based real-world image super-resolution (Real-ISR) have demonstrated remarkable perceptual quality, yet the balance between fidelity and controllability remains a problem: multi-step diffusion-based methods suffer from generative diversity and randomness, resulting in low fidelity, while one-step methods lose control flexibility due to fidelity-specific finetuning. In this paper, we present ODTSR, a one-step diffusion transformer based on Qwen-Image that performs Real-ISR considering fidelity and controllability simultaneously: a newly introduced visual stream receives low-quality images (LQ) with adjustable noise (Control Noise), and the original visual stream receives LQs with consistent noise (Prior Noise), forming the Noise-hybrid Visual Stream (NVS) design. ODTSR further employs Fidelity-aware Adversarial Training (FAA) to enhance controllability and achieve one-step inference. Extensive experiments demonstrate that ODTSR not only achieves state-of-the-art (SOTA) performance on generic Real-ISR, but also enables prompt controllability on challenging scenarios such as real-world scene text image super-resolution (STISR) of Chinese characters without training on specific datasets. Codes are available at https://github.com/RedMediaTech/ODTSR.

Paperid: 382, https://arxiv.org/pdf/2511.17131.pdf GitHub

Abstract:
While current Computer Use Agent (CUA) benchmarks measure task completion effectively, they provide limited assessment of enterprise deployment readiness, emphasizing functional correctness over the operational reliability required for production systems. We present UI-CUBE (UiPath Computer Use BEnchmark), a systematic benchmark comprising 226 tasks across two difficulty tiers designed to expose fundamental architectural limitations in current CUAs. Our evaluation covers simple UI interactions (136 tasks) and complex workflows including copy-paste tasks (50 tasks) and enterprise application scenarios (40 tasks), with systematic interface variation coverage, multi-resolution testing and automated validation of task success through the application state. Evaluation of five state-of-the-art models reveals a sharp capability cliff rather than gradual performance degradation. Simple UI interactions achieve 67-85% success rates (compared to 97.9% human performance), but complex workflows drop precipitously to 9-19%. Human evaluators with no prior application experience achieve only 61.2% on complex tasks despite near-perfect performance on simple tasks, establishing realistic performance ceilings. This discontinuous performance pattern -- where agents achieve 68-87% of human performance on simple tasks but only 15-32% on complex workflows -- indicates fundamental architectural limitations in memory management, hierarchical planning, and state coordination rather than incremental capability gaps addressable through better training or prompting. UI-CUBE functions as an enterprise-readiness diagnostic, revealing that while current CUAs can manipulate individual interface elements, they cannot yet function as reliable workflow automation tools. These findings provide architectural insights essential for developing production-ready CUAs capable of managing complex, multi-step enterprise processes.

Paperid: 383, https://arxiv.org/pdf/2511.17126.pdf GitHub GitHub

Abstract:
Emerging deep-learning-based lens library pre-training (LensLib-PT) pipeline offers a new avenue for blind lens aberration correction by training a universal neural network, demonstrating strong capability in handling diverse unknown optical degradations. This work proposes the OmniLens++ framework, which resolves two challenges that hinder the generalization ability of existing pipelines: the difficulty of scaling data and the absence of prior guidance characterizing optical degradation. To improve data scalability, we expand the design specifications to increase the degradation diversity of the lens source, and we sample a more uniform distribution by quantifying the spatial-variation patterns and severity of optical degradation. In terms of model design, to leverage the Point Spread Functions (PSFs), which intuitively describe optical degradation, as guidance in a blind paradigm, we propose the Latent PSF Representation (LPR). The VQVAE framework is introduced to learn latent features of LensLib's PSFs, which is assisted by modeling the optical degradation process to constrain the learning of degradation priors. Experiments on diverse aberrations of real-world lenses and synthetic LensLib show that OmniLens++ exhibits state-of-the-art generalization capacity in blind aberration correction. Beyond performance, the AODLibpro is verified as a scalable foundation for more effective training across diverse aberrations, and LPR can further tap the potential of large-scale LensLib. The source code and datasets will be made publicly available at https://github.com/zju-jiangqi/OmniLens2.

Paperid: 384, https://arxiv.org/pdf/2511.17103.pdf GitHub

Abstract:
Visual emotion recognition (VER) is a longstanding field that has garnered increasing attention with the advancement of deep neural networks. Although recent studies have achieved notable improvements by leveraging the knowledge embedded within pre-trained visual models, the lack of direct association between factual-level features and emotional categories, called the "affective gap", limits the applicability of pre-training knowledge for VER tasks. On the contrary, the explicit emotional expression and high information density in textual modality eliminate the "affective gap". Therefore, we propose borrowing the knowledge from the pre-trained textual model to enhance the emotional perception of pre-trained visual models. We focus on the factual and emotional connections between images and texts in noisy social media data, and propose Partitioned Adaptive Contrastive Learning (PACL) to leverage these connections. Specifically, we manage to separate different types of samples and devise distinct contrastive learning strategies for each type. By dynamically constructing negative and positive pairs, we fully exploit the potential of noisy samples. Through comprehensive experiments, we demonstrate that bridging the "affective gap" significantly improves the performance of various pre-trained visual models in downstream emotion-related tasks. Our code is released on https://github.com/wdqqdw/PACL.

Paperid: 385, https://arxiv.org/pdf/2511.17079.pdf GitHub

Abstract:
Unified video and action prediction models hold great potential for robotic manipulation, as future observations offer contextual cues for planning, while actions reveal how interactions shape the environment. However, most existing approaches treat observation and action generation in a monolithic and goal-agnostic manner, often leading to semantically misaligned predictions and incoherent behaviors. To this end, we propose H-GAR, a Hierarchical interaction framework via Goal-driven observation-Action Refinement.To anchor prediction to the task objective, H-GAR first produces a goal observation and a coarse action sketch that outline a high-level route toward the goal. To enable explicit interaction between observation and action under the guidance of the goal observation for more coherent decision-making, we devise two synergistic modules. (1) Goal-Conditioned Observation Synthesizer (GOS) synthesizes intermediate observations based on the coarse-grained actions and the predicted goal observation. (2) Interaction-Aware Action Refiner (IAAR) refines coarse actions into fine-grained, goal-consistent actions by leveraging feedback from the intermediate observations and a Historical Action Memory Bank that encodes prior actions to ensure temporal consistency. By integrating goal grounding with explicit action-observation interaction in a coarse-to-fine manner, H-GAR enables more accurate manipulation. Extensive experiments on both simulation and real-world robotic manipulation tasks demonstrate that H-GAR achieves state-of-the-art performance.

Paperid: 386, https://arxiv.org/pdf/2511.17078.pdf GitHub

Abstract:
Molecular fingerprinting methods use hash functions to create fixed-length vector representations of molecules. However, hash collisions cause distinct substructures to be represented with the same feature, leading to overestimates in molecular similarity calculations. We investigate whether using exact fingerprints improves accuracy compared to standard compressed fingerprints in molecular property prediction and Bayesian optimization where the underlying predictive model is a Gaussian process. We find that using exact fingerprints yields a small yet consistent improvement in predictive accuracy on five molecular property prediction benchmarks from the DOCKSTRING dataset. However, these gains did not translate to significant improvements in Bayesian optimization performance.

Paperid: 387, https://arxiv.org/pdf/2511.17074.pdf GitHub

Abstract:
Visual Autoregressive (VAR) models have recently garnered significant attention for their innovative next-scale prediction paradigm, offering notable advantages in both inference efficiency and image quality compared to traditional multi-step autoregressive (AR) and diffusion models. However, despite their efficiency, VAR models often suffer from the diversity collapse i.e., a reduction in output variability, analogous to that observed in few-step distilled diffusion models. In this paper, we introduce DiverseVAR, a simple yet effective approach that restores the generative diversity of VAR models without requiring any additional training. Our analysis reveals the pivotal component of the feature map as a key factor governing diversity formation at early scales. By suppressing the pivotal component in the model input and amplifying it in the model output, DiverseVAR effectively unlocks the inherent generative potential of VAR models while preserving high-fidelity synthesis. Empirical results demonstrate that our approach substantially enhances generative diversity with only neglectable performance influences. Our code will be publicly released at https://github.com/wangtong627/DiverseVAR.

Paperid: 388, https://arxiv.org/pdf/2511.17045.pdf GitHub

Abstract:
We introduce RacketVision, a novel dataset and benchmark for advancing computer vision in sports analytics, covering table tennis, tennis, and badminton. The dataset is the first to provide large-scale, fine-grained annotations for racket pose alongside traditional ball positions, enabling research into complex human-object interactions. It is designed to tackle three interconnected tasks: fine-grained ball tracking, articulated racket pose estimation, and predictive ball trajectory forecasting. Our evaluation of established baselines reveals a critical insight for multi-modal fusion: while naively concatenating racket pose features degrades performance, a CrossAttention mechanism is essential to unlock their value, leading to trajectory prediction results that surpass strong unimodal baselines. RacketVision provides a versatile resource and a strong starting point for future research in dynamic object tracking, conditional motion forecasting, and multimodal analysis in sports. Project page at https://github.com/OrcustD/RacketVision

Paperid: 389, https://arxiv.org/pdf/2511.16980.pdf GitHub

Abstract:
3DGS employs a large number of Gaussian primitives to fit scenes, resulting in substantial storage and computational overhead. Existing pruning methods rely on manually designed criteria or introduce additional learnable parameters, yielding suboptimal results. To address this, we propose an natural selection inspired pruning framework that models survival pressure as a regularization gradient field applied to opacity, allowing the optimization gradients--driven by the goal of maximizing rendering quality--to autonomously determine which Gaussians to retain or prune. This process is fully learnable and requires no human intervention. We further introduce an opacity decay technique with a finite opacity prior, which accelerates the selection process without compromising pruning effectiveness. Compared to 3DGS, our method achieves over 0.6 dB PSNR gain under 15\% budgets, establishing state-of-the-art performance for compact 3DGS. Project page https://xiaobin2001.github.io/GNS-web.

Paperid: 390, https://arxiv.org/pdf/2511.16972.pdf GitHub

Abstract:
Optimizing patent claims is a critical yet challenging task, demanding careful balance between maximizing novelty and preserving legal scope. Manual claim drafting is labor-intensive, costly, and inherently inconsistent, while conventional Large Language Models (LLMs) often lack the structured, iterative reasoning essential for precise claim refinement. To address these challenges, we introduce Tree of Claims (ToC), an innovative framework that redefines claim editing as a guided search problem. ToC synergistically integrates Monte Carlo Tree Search (MCTS) with a collaborative multi-agent system, comprising an LLM-based EditorAgent that proposes contextually grounded edits, and an ExaminerAgent that mimics patent examiner critiques through structured, chain-of-thought analyses of novelty and prior art disclosure. Driven by a carefully designed multi-objective reward function, ToC jointly optimizes novelty, scope retention, and semantic coherence. Experimental evaluation on a benchmark of 1145 claims demonstrates that ToC significantly outperforms standard LLMs in zero-shot and few-shot scenarios, achieving an average composite score improvement of 8\%, and up to 9\% in certain cases. Extensive experiments, including detailed ablation studies, validate ToC's efficacy in generating superior, legally robust claim revisions. Overall, ToC establishes a transparent, controllable, and interpretable methodology that effectively bridges advanced LLM reasoning capabilities with strategic MCTS planning for structured patent claim optimization.The source code is available at https://github.com/ysy2003/ToC.

Paperid: 391, https://arxiv.org/pdf/2511.16943.pdf GitHub

Abstract:
Generative recommendation systems typically leverage Semantic Identifiers (SIDs), which represent each item as a sequence of tokens that encode semantic information. However, representing item ID with multiple SIDs significantly increases input sequence length, which is a major determinant of computational complexity and memory consumption. While existing efforts primarily focus on optimizing attention computation and KV cache, we propose RASTP (Representation-Aware Semantic Token Pruning), which directly prunes less informative tokens in the input sequence. Specifically, RASTP evaluates token importance by combining semantic saliency, measured via representation magnitude, and attention centrality, derived from cumulative attention weights. Since RASTP dynamically prunes low-information or irrelevant semantic tokens, experiments on three real-world Amazon datasets show that RASTP reduces training time by 26.7\%, while maintaining or slightly improving recommendation performance. The code has been open-sourced at https://github.com/Yuzt-zju/RASTP.

Paperid: 392, https://arxiv.org/pdf/2511.16938.pdf GitHub

Abstract:
Meeting real-time constraints for high-performance Approximate Nearest Neighbor (ANN) search remains a critical challenge in remote sensing edge devices, which are essentially fusion systems like micro-satellites and UAVs, largely due to stringent limitations in primary (RAM) and secondary (disk) storage. To address this challenge, we propose Edge-ANN, an innovative ANN framework specifically engineered for storage efficiency. The core innovation of Edge-ANN lies in its departure from traditional tree-based methods that store high-dimensional hyperplanes. Instead, it leverages pairs of existing data items, termed "anchors," to implicitly define spatial partitions. To ensure these partitions are both balanced and effective, we have developed a novel Binary Anchor Optimization algorithm.This architectural shift eliminates the dimension-dependence of the space complexity. Rigorous experiments on three multi-source datasets, MillionAID, High-resolution Urban Complex Dataset, and GlobalUrbanNet Dataset, demonstrate that under simulated edge environments with dual storage constraints, Edge-ANN achieves a 30-40% reduction in secondary storage compared to the baseline, at the cost of a minor 3-5% drop in retrieval accuracy. Furthermore, its overall retrieval performance surpasses that of other mainstream methods in these constrained scenarios. Collectively, these results establish Edge-ANN as a state-of-the-art solution for enabling large-scale, high-performance, real-time remote sensing feature retrieval on edge devices with exceptionally constrained storage. The codes of Edge-ANN are available at https://github.com/huaijiao666/Edge-ANN.

Paperid: 393, https://arxiv.org/pdf/2511.16901.pdf GitHub

Abstract:
Recently, rapid advancements have been made in multimodal large language models (MLLMs), especially in video understanding tasks. However, current research focuses on simple video scenarios, failing to reflect the complex and diverse nature of real-world audio-visual events in videos. To bridge this gap, we firstly introduce R-AVST, a dataset for audio-visual reasoning featuring fine-grained spatio-temporal annotations. In constructing this, we design a pipeline consisting of LLM-based key object extraction, automatic spatial annotation and manual quality inspection, resulting in over 5K untrimmed videos with 27K objects across 100 types of audio-visual events. Building on this dataset, we define three core tasks for spatio-temporal reasoning in audio-visual scenes and generate more than 8K high-quality, evenly distributed question-answer pairs to effectively benchmark model performance. To further enhance reasoning, we propose AVST-Zero, a reinforcement learning-based model that avoids intermediate supervision, directly optimizing behavior via carefully designed multi-dimensional rewards. Extensive experiments validate the effectiveness of our R-AVST in advancing audio-visual spatio-temporal reasoning, upon which AVST-Zero demonstrates competitive performance compared to existing models. To the best of our knowledge, R-AVST is the first dataset designed for real-world audio-visual spatio-temporal reasoning, and AVST-Zero offers a novel perspective for tackling future challenges in this domain.

Paperid: 394, https://arxiv.org/pdf/2511.16871.pdf GitHub

Abstract:
Graph Neural Networks rely on local message passing, which limits their ability to model long-range dependencies in graphs. Existing approaches extend this range through continuous-time dynamics or dense self-attention, but both suffer from high computational cost and limited scalability. We propose Topologic Attention Networks, a new framework that applies topologic attention, a probabilistic mechanism that learns how information should flow through both direct and indirect connections in a graph. Unlike conventional attention that depends on explicit pairwise interactions, topologic attention emerges from the learned information propagation of the graph, enabling unified reasoning over local and global relationships. This method achieves provides state-of-the-art performance across all measured baseline models. Our implementation is available at https://github.com/Marshall-Rosenhoover/Topologic-Attention-Networks.

Paperid: 395, https://arxiv.org/pdf/2511.16854.pdf GitHub

Abstract:
High-resolution (HR) magnetic resonance imaging (MRI) is crucial for many clinical and research applications. However, achieving it remains costly and constrained by technical trade-offs and experimental limitations. Super-resolution (SR) presents a promising computational approach to overcome these challenges by generating HR images from more affordable low-resolution (LR) scans, potentially improving diagnostic accuracy and efficiency without requiring additional hardware. This survey reviews recent advances in MRI SR techniques, with a focus on deep learning (DL) approaches. It examines DL-based MRI SR methods from the perspectives of computer vision, computational imaging, inverse problems, and MR physics, covering theoretical foundations, architectural designs, learning strategies, benchmark datasets, and performance metrics. We propose a systematic taxonomy to categorize these methods and present an in-depth study of both established and emerging SR techniques applicable to MRI, considering unique challenges in clinical and research contexts. We also highlight open challenges and directions that the community needs to address. Additionally, we provide a collection of essential open-access resources, tools, and tutorials, available on our GitHub: https://github.com/mkhateri/Awesome-MRI-Super-Resolution. IEEE keywords: MRI, Super-Resolution, Deep Learning, Computational Imaging, Inverse Problem, Survey.

Paperid: 396, https://arxiv.org/pdf/2511.16853.pdf GitHub GitHub

Abstract:
Recent progress in vision language models (VLMs) has enabled remarkable perception and reasoning capabilities, yet their potential for scientific regression in Earth Observation (EO) remains largely unexplored. Existing EO datasets mainly emphasize semantic understanding tasks such as captioning or classification, lacking benchmarks that align multimodal perception with measurable biophysical variables. To fill this gap, we present REO-Instruct, the first unified benchmark designed for both descriptive and regression tasks in EO. REO-Instruct establishes a cognitively interpretable logic chain in forest ecological scenario (human activity,land-cover classification, ecological patch counting, above-ground biomass (AGB) regression), bridging qualitative understanding and quantitative prediction. The dataset integrates co-registered Sentinel-2 and ALOS-2 imagery with structured textual annotations generated and validated through a hybrid human AI pipeline. Comprehensive evaluation protocols and baseline results across generic VLMs reveal that current models struggle with numeric reasoning, highlighting an essential challenge for scientific VLMs. REO-Instruct offers a standardized foundation for developing and assessing next-generation geospatial models capable of both description and scientific inference. The project page are publicly available at \href{https://github.com/zhu-xlab/REO-Instruct}{REO-Instruct}.

Paperid: 397, https://arxiv.org/pdf/2511.16792.pdf GitHub

Abstract:
Membership inference attacks (MIAs) against machine learning (ML) models aim to determine whether a given data point was part of the model training data. These attacks may pose significant privacy risks to individuals whose sensitive data were used for training, which motivates the use of defenses such as differential privacy, often at the cost of high accuracy losses. MIAs exploit the differences in the behavior of a model when making predictions on samples it has seen during training (members) versus those it has not seen (non-members). Several studies have pointed out that model overfitting is the major factor contributing to these differences in behavior and, consequently, to the success of MIAs. However, the literature also shows that even non-overfitted ML models can leak information about a small subset of their training data. In this paper, we investigate the root causes of membership inference vulnerabilities beyond traditional overfitting concerns and suggest targeted defenses. We empirically analyze the characteristics of the training data samples vulnerable to MIAs in models that are not overfitted (and hence able to generalize). Our findings reveal that these samples are often outliers within their classes (e.g., noisy or hard to classify). We then propose potential defensive strategies to protect these vulnerable samples and enhance the privacy-preserving capabilities of ML models. Our code is available at https://github.com/najeebjebreel/mia_analysis.

Paperid: 398, https://arxiv.org/pdf/2511.16712.pdf GitHub

Abstract:
Personalized dual-person portrait customization has considerable potential applications, such as preserving emotional memories and facilitating wedding photography planning. However, the absence of a benchmark dataset hinders the pursuit of high-quality customization in dual-person portrait generation. In this paper, we propose the PairHuman dataset, which is the first large-scale benchmark dataset specifically designed for generating dual-person portraits that meet high photographic standards. The PairHuman dataset contains more than 100K images that capture a variety of scenes, attire, and dual-person interactions, along with rich metadata, including detailed image descriptions, person localization, human keypoints, and attribute tags. We also introduce DHumanDiff, which is a baseline specifically crafted for dual-person portrait generation that features enhanced facial consistency and simultaneously balances in personalized person generation and semantic-driven scene creation. Finally, the experimental results demonstrate that our dataset and method produce highly customized portraits with superior visual quality that are tailored to human preferences. Our dataset is publicly available at https://github.com/annaoooo/PairHuman.

Paperid: 399, https://arxiv.org/pdf/2511.16709.pdf GitHub

Abstract:
Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted triggers and static data pipelines, which are rigid, labor-intensive, and inadequate for systematically evaluating modern defense robustness. As AI agents become increasingly capable, there is a growing need for more rigorous, diverse, and scalable \textit{red-teaming frameworks} that can realistically simulate backdoor threats and assess model resilience under adversarial conditions. In this work, we introduce \textsc{AutoBackdoor}, a general framework for automating backdoor injection, encompassing trigger generation, poisoned data construction, and model fine-tuning via an autonomous agent-driven pipeline. Unlike prior approaches, AutoBackdoor uses a powerful language model agent to generate semantically coherent, context-aware trigger phrases, enabling scalable poisoning across arbitrary topics with minimal human effort. We evaluate AutoBackdoor under three realistic threat scenarios, including \textit{Bias Recommendation}, \textit{Hallucination Injection}, and \textit{Peer Review Manipulation}, to simulate a broad range of attacks. Experiments on both open-source and commercial models, including LLaMA-3, Mistral, Qwen, and GPT-4o, demonstrate that our method achieves over 90\% attack success with only a small number of poisoned samples. More importantly, we find that existing defenses often fail to mitigate these attacks, underscoring the need for more rigorous and adaptive evaluation techniques against agent-driven threats as explored in this work. All code, datasets, and experimental configurations will be merged into our primary repository at https://github.com/bboylyg/BackdoorLLM.

Paperid: 400, https://arxiv.org/pdf/2511.16698.pdf GitHub

Abstract:
SNOMED CT is a biomedical ontology with a hierarchical representation of large-scale concepts. Knowledge retrieval in SNOMED CT is critical for its application, but often proves challenging due to language ambiguity, synonyms, polysemies and so on. This problem is exacerbated when the queries are out-of-vocabulary (OOV), i.e., having no equivalent matchings in the ontology. In this work, we focus on the problem of hierarchical concept retrieval from SNOMED CT with OOV queries, and propose an approach based on language model-based ontology embeddings. For evaluation, we construct OOV queries annotated against SNOMED CT concepts, testing the retrieval of the most direct subsumers and their less relevant ancestors. We find that our method outperforms the baselines including SBERT and two lexical matching methods. While evaluated against SNOMED CT, the approach is generalisable and can be extended to other ontologies. We release code, tools, and evaluation datasets at https://github.com/jonathondilworth/HR-OOV.

Paperid: 401, https://arxiv.org/pdf/2511.16693.pdf GitHub

Abstract:
Multilingual LLMs demonstrate strong performance across diverse languages, yet there has been limited systematic analysis of how language information is structured within their internal representation space and how it emerges across layers. We conduct a comprehensive probing study on six multilingual LLMs, covering all 268 transformer layers, using linear and nonlinear probes together with a new Token--Language Alignment analysis to quantify the layer-wise dynamics and geometric structure of language encoding. Our results show that language information becomes sharply separated in the first transformer block (+76.4$\pm$8.2 percentage points from Layer 0 to 1) and remains almost fully linearly separable throughout model depth. We further find that the alignment between language directions and vocabulary embeddings is strongly tied to the language composition of the training data. Notably, Chinese-inclusive models achieve a ZH Match@Peak of 16.43\%, whereas English-centric models achieve only 3.90\%, revealing a 4.21$\times$ structural imprinting effect. These findings indicate that multilingual LLMs distinguish languages not by surface script features but by latent representational structures shaped by the training corpus. Our analysis provides practical insights for data composition strategies and fairness in multilingual representation learning. All code and analysis scripts are publicly available at: https://github.com/thisiskorea/How-Language-Directions-Align-with-Token-Geometry-in-Multilingual-LLMs.

Paperid: 402, https://arxiv.org/pdf/2511.16681.pdf GitHub GitHub

Abstract:
Retrieval-Augmented Generation (RAG) systems have become a dominant approach to augment large language models (LLMs) with external knowledge. However, existing vector database (VecDB) retrieval pipelines rely on flat or single-resolution indexing structures, which cannot adapt to the varying semantic granularity required by diverse user queries. This limitation leads to suboptimal trade-offs between retrieval speed and contextual relevance. To address this, we propose \textbf{Semantic Pyramid Indexing (SPI)}, a novel multi-resolution vector indexing framework that introduces query-adaptive resolution control for RAG in VecDBs. Unlike existing hierarchical methods that require offline tuning or separate model training, SPI constructs a semantic pyramid over document embeddings and dynamically selects the optimal resolution level per query through a lightweight classifier. This adaptive approach enables progressive retrieval from coarse-to-fine representations, significantly accelerating search while maintaining semantic coverage. We implement SPI as a plugin for both FAISS and Qdrant backends and evaluate it across multiple RAG tasks including MS MARCO, Natural Questions, and multimodal retrieval benchmarks. SPI achieves up to \textbf{5.7$\times$} retrieval speedup and \textbf{1.8$\times$} memory efficiency gain while improving end-to-end QA F1 scores by up to \textbf{2.5 points} compared to strong baselines. Our theoretical analysis provides guarantees on retrieval quality and latency bounds, while extensive ablation studies validate the contribution of each component. The framework's compatibility with existing VecDB infrastructures makes it readily deployable in production RAG systems. Code is availabe at \href{https://github.com/FastLM/SPI_VecDB}{https://github.com/FastLM/SPI\_VecDB}.

Paperid: 403, https://arxiv.org/pdf/2511.16680.pdf GitHub

Abstract:
Despite rapid advances in multilingual natural language processing (NLP), the Bantu language Shona remains under-served in terms of morphological analysis and language-aware tools. This paper presents Shona spaCy, an open-source, rule-based morphological pipeline for Shona built on the spaCy framework. The system combines a curated JSON lexicon with linguistically grounded rules to model noun-class prefixes (Mupanda 1-18), verbal subject concords, tense-aspect markers, ideophones, and clitics, integrating these into token-level annotations for lemma, part-of-speech, and morphological features. The toolkit is available via pip install shona-spacy, with source code at https://github.com/HappymoreMasoka/shona-spacy and a PyPI release at https://pypi.org/project/shona-spacy/0.1.4/. Evaluation on formal and informal Shona corpora yields 90% POS-tagging accuracy and 88% morphological-feature accuracy, while maintaining transparency in its linguistic decisions. By bridging descriptive grammar and computational implementation, Shona spaCy advances NLP accessibility and digital inclusion for Shona speakers and provides a template for morphological analysis tools for other under-resourced Bantu languages.

Paperid: 404, https://arxiv.org/pdf/2511.16674.pdf GitHub

Abstract:
The task of dataset distillation aims to find a small set of synthetic images such that training a model on them reproduces the performance of the same model trained on a much larger dataset of real samples. Existing distillation methods focus on synthesizing datasets that enable training randomly initialized models. In contrast, state-of-the-art vision approaches are increasingly building on large, pre-trained self-supervised models rather than training from scratch. In this paper, we investigate the problem of distilling datasets that enable us to optimally train linear probes on top of such large, pre-trained vision models. We introduce a method of dataset distillation for this task called Linear Gradient Matching that optimizes the synthetic images such that, when passed through a pre-trained feature extractor, they induce gradients in the linear classifier similar to those produced by the real data. Our method yields synthetic data that outperform all real-image baselines and, remarkably, generalize across pre-trained vision models, enabling us, for instance, to train a linear CLIP probe that performs competitively using a dataset distilled via a DINO backbone. Further, we show that our distilled datasets are exceptionally effective for fine-grained classification and provide a valuable tool for model interpretability, predicting, among other things, how similar two models' embedding spaces are under the platonic representation hypothesis or whether a model is sensitive to spurious correlations in adversarial datasets.

Paperid: 405, https://arxiv.org/pdf/2511.16673.pdf GitHub

Abstract:
We tackle the task of recovering an animatable 3D human avatar from a single or a sparse set of images. For this task, beyond a set of images, many prior state-of-the-art methods use accurate "ground-truth" camera poses and human poses as input to guide reconstruction at test-time. We show that pose-dependent reconstruction degrades results significantly if pose estimates are noisy. To overcome this, we introduce NoPo-Avatar, which reconstructs avatars solely from images, without any pose input. By removing the dependence of test-time reconstruction on human poses, NoPo-Avatar is not affected by noisy human pose estimates, making it more widely applicable. Experiments on challenging THuman2.0, XHuman, and HuGe100K data show that NoPo-Avatar outperforms existing baselines in practical settings (without ground-truth poses) and delivers comparable results in lab settings (with ground-truth poses).

Paperid: 406, https://arxiv.org/pdf/2511.16672.pdf GitHub

Abstract:
Recent advances in large multimodal models (LMMs) have enabled impressive reasoning and perception abilities, yet most existing training pipelines still depend on human-curated data or externally verified reward models, limiting their autonomy and scalability. In this work, we strive to improve LMM reasoning capabilities in a purely unsupervised fashion (without any annotated data or reward distillation). To this end, we propose a self-evolving framework, named EvoLMM, that instantiates two cooperative agents from a single backbone model: a Proposer, which generates diverse, image-grounded questions, and a Solver, which solves them through internal consistency, where learning proceeds through a continuous self-rewarding process. This dynamic feedback encourages both the generation of informative queries and the refinement of structured reasoning without relying on ground-truth or human judgments. When using the popular Qwen2.5-VL as the base model, our EvoLMM yields consistent gains upto $\sim$3\% on multimodal math-reasoning benchmarks, including ChartQA, MathVista, and MathVision, using only raw training images. We hope our simple yet effective approach will serve as a solid baseline easing future research in self-improving LMMs in a fully-unsupervised fashion. Our code and models are available at https://github.com/mbzuai-oryx/EvoLMM.

Paperid: 407, https://arxiv.org/pdf/2511.16671.pdf GitHub GitHub

Abstract:
Recent advances in visual generation have increasingly explored the integration of reasoning capabilities. They incorporate textual reasoning, i.e., think, either before (as pre-planning) or after (as post-refinement) the generation process, yet they lack on-the-fly multimodal interaction during the generation itself. In this preliminary study, we introduce Thinking-while-Generating (TwiG), the first interleaved framework that enables co-evolving textual reasoning throughout the visual generation process. As visual content is progressively generating, textual reasoning is interleaved to both guide upcoming local regions and reflect on previously synthesized ones. This dynamic interplay produces more context-aware and semantically rich visual outputs. To unveil the potential of this framework, we investigate three candidate strategies, zero-shot prompting, supervised fine-tuning (SFT) on our curated TwiG-50K dataset, and reinforcement learning (RL) via a customized TwiG-GRPO strategy, each offering unique insights into the dynamics of interleaved reasoning. We hope this work inspires further research into interleaving textual reasoning for enhanced visual generation. Code will be released at: https://github.com/ZiyuGuo99/Thinking-while-Generating.

Paperid: 408, https://arxiv.org/pdf/2511.16669.pdf GitHub

Abstract:
While language models have become impactful in many real-world applications, video generation remains largely confined to entertainment. Motivated by video's inherent capacity to demonstrate physical-world information that is difficult to convey through language alone (e.g., imagine teaching someone to tie a tie using only text), we identify an underutilized opportunity to extend video as a new answer modality for Next-Event Prediction (NEP), formalized as Video-Next-Event Prediction (VNEP). While the established NEP task takes a video with a procedural or predictive question as input to predict the next event in text, VNEP requires dynamic video responses. This shift from telling to showing unlocks more intuitive and customized answers for procedural learning and creative exploration. However, this task remains challenging for existing models, as it demands an understanding of multimodal input, instruction-conditioned reasoning, and the generation of video with visual and semantic consistency. To address this, we introduce VANS, a model that leverages reinforcement learning to align a Vision-Language Model (VLM) with a Video Diffusion Model (VDM) for VNEP. The core of VANS is our proposed Joint-GRPO that orchestrates the VLM and VDM to function as a unit. Driven by a shared reward on their respective output, it optimizes the VLM to produce captions that are both accurate and friendly to visualize, while guiding the VDM to generate videos that are faithful to these captions and the input visual context. To enable this learning, we craft VANS-Data-100K, a dedicated dataset for the VNEP task. Experiments on procedural and predictive benchmarks demonstrate that VANS achieves state-of-the-art performance in both video event prediction and visualization. Codes are released in https://github.com/KlingTeam/VANS.

Paperid: 409, https://arxiv.org/pdf/2511.16668.pdf GitHub

Abstract:
Recent progress in generative video models, such as Veo-3, has shown surprising zero-shot reasoning abilities, creating a growing need for systematic and reliable evaluation. We introduce V-ReasonBench, a benchmark designed to assess video reasoning across four key dimensions: structured problem-solving, spatial cognition, pattern-based inference, and physical dynamics. The benchmark is built from both synthetic and real-world image sequences and provides a diverse set of answer-verifiable tasks that are reproducible, scalable, and unambiguous. Evaluations of six state-of-the-art video models reveal clear dimension-wise differences, with strong variation in structured, spatial, pattern-based, and physical reasoning. We further compare video models with strong image models, analyze common hallucination behaviors, and study how video duration affects Chain-of-Frames reasoning. Overall, V-ReasonBench offers a unified and reproducible framework for measuring video reasoning and aims to support the development of models with more reliable, human-aligned reasoning skills.

Paperid: 410, https://arxiv.org/pdf/2511.16666.pdf GitHub

Abstract:
Controllable image generation has attracted increasing attention in recent years, enabling users to manipulate visual content such as identity and style. However, achieving simultaneous control over the 9D poses (location, size, and orientation) of multiple objects remains an open challenge. Despite recent progress, existing methods often suffer from limited controllability and degraded quality, falling short of comprehensive multi-object 9D pose control. To address these limitations, we propose SceneDesigner, a method for accurate and flexible multi-object 9-DoF pose manipulation. SceneDesigner incorporates a branched network to the pre-trained base model and leverages a new representation, CNOCS map, which encodes 9D pose information from the camera view. This representation exhibits strong geometric interpretation properties, leading to more efficient and stable training. To support training, we construct a new dataset, ObjectPose9D, which aggregates images from diverse sources along with 9D pose annotations. To further address data imbalance issues, particularly performance degradation on low-frequency poses, we introduce a two-stage training strategy with reinforcement learning, where the second stage fine-tunes the model using a reward-based objective on rebalanced data. At inference time, we propose Disentangled Object Sampling, a technique that mitigates insufficient object generation and concept confusion in complex multi-object scenes. Moreover, by integrating user-specific personalization weights, SceneDesigner enables customized pose control for reference subjects. Extensive qualitative and quantitative experiments demonstrate that SceneDesigner significantly outperforms existing approaches in both controllability and quality. Code is publicly available at https://github.com/FudanCVL/SceneDesigner.

Paperid: 411, https://arxiv.org/pdf/2511.16665.pdf GitHub

Abstract:
The emergence of Large Language Models (LLMs) with strong reasoning capabilities marks a significant milestone, unlocking new frontiers in complex problem-solving. However, training these reasoning models, typically using Reinforcement Learning (RL), encounters critical efficiency bottlenecks: response generation during RL training exhibits a persistent long-tail distribution, where a few very long responses dominate execution time, wasting resources and inflating costs. To address this, we propose TLT, a system that accelerates reasoning RL training losslessly by integrating adaptive speculative decoding. Applying speculative decoding in RL is challenging due to the dynamic workloads, evolving target model, and draft model training overhead. TLT overcomes these obstacles with two synergistic components: (1) Adaptive Drafter, a lightweight draft model trained continuously on idle GPUs during long-tail generation to maintain alignment with the target model at no extra cost; and (2) Adaptive Rollout Engine, which maintains a memory-efficient pool of pre-captured CUDAGraphs and adaptively select suitable SD strategies for each input batch. Evaluations demonstrate that TLT achieves over 1.7x end-to-end RL training speedup over state-of-the-art systems, preserves the model accuracy, and yields a high-quality draft model as a free byproduct suitable for efficient deployment. Code is released at https://github.com/mit-han-lab/fastrl.

Paperid: 412, https://arxiv.org/pdf/2511.16655.pdf GitHub

Abstract:
Cambrian-S aims to take the first steps towards improving video world models with spatial supersensing by introducing (i) two benchmarks, VSI-Super-Recall (VSR) and VSI-Super-Counting (VSC), and (ii) bespoke predictive sensing inference strategies tailored to each benchmark. In this work, we conduct a critical analysis of Cambrian-S across both these fronts. First, we introduce a simple baseline, NoSense, which discards almost all temporal structure and uses only a bag-of-words SigLIP model, yet near-perfectly solves VSR, achieving 95% accuracy even on 4-hour videos. This shows benchmarks like VSR can be nearly solved without spatial cognition, world modeling or spatial supersensing. Second, we hypothesize that the tailored inference methods proposed by Cambrian-S likely exploit shortcut heuristics in the benchmark. We illustrate this with a simple sanity check on the VSC benchmark, called VSC-Repeat: We concatenate each video with itself 1-5 times, which does not change the number of unique objects. However, this simple perturbation entirely collapses the mean relative accuracy of Cambrian-S from 42% to 0%. A system that performs spatial supersensing and integrates information across experiences should recognize views of the same scene and keep object-count predictions unchanged; instead, Cambrian-S inference algorithm relies largely on a shortcut in the VSC benchmark that rooms are never revisited. Taken together, our findings suggest that (i) current VSI-Super benchmarks do not yet reliably measure spatial supersensing, and (ii) predictive-sensing inference recipes used by Cambrian-S improve performance by inadvertently exploiting shortcuts rather than from robust spatial supersensing. We include the response from the Cambrian-S authors (in Appendix A) to provide a balanced perspective alongside our claims. We release our code at: https://github.com/bethgelab/supersanity

Paperid: 413, https://arxiv.org/pdf/2511.16642.pdf GitHub GitHub

Abstract:
Recent advances in 3D Gaussian diffusion models suffer from time-intensive denoising and post-denoising processing due to the massive number of Gaussian primitives, resulting in slow generation and limited scalability along sampling trajectories. To improve the efficiency of 3D diffusion models, we propose $\textbf{TRIM}$ ($\textbf{T}$rajectory $\textbf{R}$eduction and $\textbf{I}$nstance $\textbf{M}$ask denoising), a post-training approach that incorporates both temporal and spatial trimming strategies, to accelerate inference without compromising output quality while supporting the inference-time scaling for Gaussian diffusion models. Instead of scaling denoising trajectories in a costly end-to-end manner, we develop a lightweight selector model to evaluate latent Gaussian primitives derived from multiple sampled noises, enabling early trajectory reduction by selecting candidates with high-quality potential. Furthermore, we introduce instance mask denoising to prune learnable Gaussian primitives by filtering out redundant background regions, reducing inference computation at each denoising step. Extensive experiments and analysis demonstrate that TRIM significantly improves both the efficiency and quality of 3D generation. Source code is available at $\href{https://github.com/zeyuanyin/TRIM}{link}$.

Paperid: 414, https://arxiv.org/pdf/2511.16618.pdf GitHub

Abstract:
Surgical video segmentation is crucial for computer-assisted surgery, enabling precise localization and tracking of instruments and tissues. Interactive Video Object Segmentation (iVOS) models such as Segment Anything Model 2 (SAM2) provide prompt-based flexibility beyond methods with predefined categories, but face challenges in surgical scenarios due to the domain gap and limited long-term tracking. To address these limitations, we construct SA-SV, the largest surgical iVOS benchmark with instance-level spatio-temporal annotations (masklets) spanning eight procedure types (61k frames, 1.6k masklets), enabling comprehensive development and evaluation for long-term tracking and zero-shot generalization. Building on SA-SV, we propose SAM2S, a foundation model enhancing \textbf{SAM2} for \textbf{S}urgical iVOS through: (1) DiveMem, a trainable diverse memory mechanism for robust long-term tracking; (2) temporal semantic learning for instrument understanding; and (3) ambiguity-resilient learning to mitigate annotation inconsistencies across multi-source datasets. Extensive experiments demonstrate that fine-tuning on SA-SV enables substantial performance gains, with SAM2 improving by 12.99 average $\mathcal{J}$\&$\mathcal{F}$ over vanilla SAM2. SAM2S further advances performance to 80.42 average $\mathcal{J}$\&$\mathcal{F}$, surpassing vanilla and fine-tuned SAM2 by 17.10 and 4.11 points respectively, while maintaining 68 FPS real-time inference and strong zero-shot generalization. Code and dataset will be released at https://jinlab-imvr.github.io/SAM2S.

Paperid: 415, https://arxiv.org/pdf/2511.16595.pdf GitHub GitHub

Abstract:
We introduce TimeViper, a hybrid vision-language model designed to tackle challenges of long video understanding. Processing long videos demands both an efficient model architecture and an effective mechanism for handling extended temporal contexts. To this end, TimeViper adopts a hybrid Mamba-Transformer backbone that combines the efficiency of state-space models with the expressivity of attention mechanisms. Through this hybrid design, we reveal the vision-to-text information aggregation phenomenon, where information progressively flows from vision tokens to text tokens across increasing LLM depth, resulting in severe vision token redundancy. Motivated by this observation, we propose TransV, a token information transfer module that transfers and compresses vision tokens into instruction tokens while maintaining multimodal understanding capabilities. This design enables TimeViper to process hour-long videos exceeding 10,000 frames. Extensive experiments across multiple benchmarks demonstrate that TimeViper competes with state-of-the-art models while extending frame numbers. We further analyze attention behaviors of both Mamba and Transformer layers, offering new insights into hybrid model interpretability. This work represents an initial step towards developing, interpreting, and compressing hybrid Mamba-Transformer architectures.

Paperid: 416, https://arxiv.org/pdf/2511.16592.pdf GitHub

Abstract:
In this paper, we present gfnx, a fast and scalable package for training and evaluating Generative Flow Networks (GFlowNets) written in JAX. gfnx provides an extensive set of environments and metrics for benchmarking, accompanied with single-file implementations of core objectives for training GFlowNets. We include synthetic hypergrids, multiple sequence generation environments with various editing regimes and particular reward designs for molecular generation, phylogenetic tree construction, Bayesian structure learning, and sampling from the Ising model energy. Across different tasks, gfnx achieves significant wall-clock speedups compared to Pytorch-based benchmarks (such as torchgfn library) and author implementations. For example, gfnx achieves up to 55 times speedup on CPU-based sequence generation environments, and up to 80 times speedup with the GPU-based Bayesian network structure learning setup. Our package provides a diverse set of benchmarks and aims to standardize empirical evaluation and accelerate research and applications of GFlowNets. The library is available on GitHub (https://github.com/d-tiapkin/gfnx) and on pypi (https://pypi.org/project/gfnx/). Documentation is available on https://gfnx.readthedocs.io.

Paperid: 417, https://arxiv.org/pdf/2511.16588.pdf GitHub

Abstract:
Case-based reasoning networks are machine-learning models that make predictions based on similarity between the input and prototypical parts of training samples, called prototypes. Such models are able to explain each decision by pointing to the prototypes that contributed the most to the final outcome. As the explanation is a core part of the prediction, they are often qualified as ``interpretable by design". While promising, we show that such explanations are sometimes misleading, which hampers their usefulness in safety-critical contexts. In particular, several instances may lead to different predictions and yet have the same explanation. Drawing inspiration from the field of formal eXplainable AI (FXAI), we propose Abductive Latent Explanations (ALEs), a formalism to express sufficient conditions on the intermediate (latent) representation of the instance that imply the prediction. Our approach combines the inherent interpretability of case-based reasoning models and the guarantees provided by formal XAI. We propose a solver-free and scalable algorithm for generating ALEs based on three distinct paradigms, compare them, and present the feasibility of our approach on diverse datasets for both standard and fine-grained image classification. The associated code can be found at https://github.com/julsoria/ale

Paperid: 418, https://arxiv.org/pdf/2511.16567.pdf GitHub

Abstract:
In this paper, we introduce POMA-3D, the first self-supervised 3D representation model learned from point maps. Point maps encode explicit 3D coordinates on a structured 2D grid, preserving global 3D geometry while remaining compatible with the input format of 2D foundation models. To transfer rich 2D priors into POMA-3D, a view-to-scene alignment strategy is designed. Moreover, as point maps are view-dependent with respect to a canonical space, we introduce POMA-JEPA, a joint embedding-predictive architecture that enforces geometrically consistent point map features across multiple views. Additionally, we introduce ScenePoint, a point map dataset constructed from 6.5K room-level RGB-D scenes and 1M 2D image scenes to facilitate large-scale POMA-3D pretraining. Experiments show that POMA-3D serves as a strong backbone for both specialist and generalist 3D understanding. It benefits diverse tasks, including 3D question answering, embodied navigation, scene retrieval, and embodied localization, all achieved using only geometric inputs (i.e., 3D coordinates). Overall, our POMA-3D explores a point map way to 3D scene understanding, addressing the scarcity of pretrained priors and limited data in 3D representation learning. Project Page: https://matchlab-imperial.github.io/poma3d/

Paperid: 419, https://arxiv.org/pdf/2511.16518.pdf GitHub GitHub

Authors:Xiaoshuai Hao, Lei Zhou, Zhijian Huang, Zhiwen Hou, Yingbo Tang, Lingfeng Zhang, Guang Li, Zheng Lu, Shuhuai Ren, Xianhui Meng, Yuchen Zhang, Jing Wu, Jinghui Lu, Chenxu Dang, Jiayi Guan, Jianhua Wu, Zhiyi Hou, Hanbing Li, Shumeng Xia, Mingliang Zhou, Yinan Zheng, Zihao Yue, Shuhao Gu, Hao Tian, Yuannan Shen, Jianwei Cui, Wen Zhang, Shaoqing Xu, Bing Wang, Haiyang Sun, Zeyu Zhu, Yuncheng Jiang, Zibin Guo, Chuhong Gong, Chaofan Zhang, Wenbo Ding, Kun Ma, Guang Chen, Rui Cai, Diyun Xiang, Heng Qu, Fuli Luo, Hangjun Ye, Long Chen

Abstract:
We open-source MiMo-Embodied, the first cross-embodied foundation model to successfully integrate and achieve state-of-the-art performance in both Autonomous Driving and Embodied AI. MiMo-Embodied sets new records across 17 embodied AI benchmarks in Task Planning, Affordance Prediction and Spatial Understanding, while also excelling in 12 autonomous driving benchmarks across Environmental Perception, Status Prediction, and Driving Planning. Across these tasks, MiMo-Embodied significantly outperforms existing open-source, closed-source, and specialized baselines. Our results indicate that through multi-stage learning, curated data construction, and CoT/RL fine-tuning, these two domains exhibit strong positive transfer and mutually reinforce one another. We provide a detailed analysis of our model design and training methodologies to facilitate further research. Code and models are available at https://github.com/XiaomiMiMo/MiMo-Embodied.

Paperid: 420, https://arxiv.org/pdf/2511.16418.pdf GitHub

Abstract:
Marker-based optical motion capture (MoCap), while long regarded as the gold standard for accuracy, faces practical challenges, such as time-consuming preparation and marker identification ambiguity, due to its reliance on dense marker configurations, which fundamentally limit its scalability. To address this, we introduce a novel fundamental unit for MoCap, the Rigid Body Marker (RBM), which provides unambiguous 6-DoF data and drastically simplifies setup. Leveraging this new data modality, we develop a deep-learning-based regression model that directly estimates SMPL parameters under a geodesic loss. This end-to-end approach matches the performance of optimization-based methods while requiring over an order of magnitude less computation. Trained on synthesized data from the AMASS dataset, our end-to-end model achieves state-of-the-art accuracy in body pose estimation. Real-world data captured using a Vicon optical tracking system further demonstrates the practical viability of our approach. Overall, the results show that combining sparse 6-DoF RBM with a manifold-aware geodesic loss yields a practical and high-fidelity solution for real-time MoCap in graphics, virtual reality, and biomechanics.

Paperid: 421, https://arxiv.org/pdf/2511.16407.pdf GitHub

Abstract:
Learning latent actions from large-scale videos is crucial for the pre-training of scalable embodied foundation models, yet existing methods often struggle with action-irrelevant distractors. Although incorporating action supervision can alleviate these distractions, its effectiveness is restricted by the scarcity of available action labels. Optical flow represents pixel-level motion between consecutive frames, naturally suppressing background elements and emphasizing moving objects. Motivated by this, we propose robust Latent Action learning with Optical Flow constraints, called LAOF, a pseudo-supervised framework that leverages the agent's optical flow as an action-driven signal to learn latent action representations robust to distractors. Experimental results show that the latent representations learned by LAOF outperform existing methods on downstream imitation learning and reinforcement learning tasks. This superior performance arises from optical flow constraints, which substantially stabilize training and improve the quality of latent representations under extremely label-scarce conditions, while remaining effective as the proportion of action labels increases to 10 percent. Importantly, even without action supervision, LAOF matches or surpasses action-supervised methods trained with 1 percent of action labels.

Paperid: 422, https://arxiv.org/pdf/2511.16378.pdf GitHub

Abstract:
Compositional zero-shot learning (CZSL) aims to learn the concepts of attributes and objects in seen compositions and to recognize their unseen compositions. Most Contrastive Language-Image Pre-training (CLIP)-based CZSL methods focus on disentangling attributes and objects by leveraging the global semantic representation obtained from the image encoder. However, this representation has limited representational capacity and do not allow for complete disentanglement of the two. To this end, we propose CAMS, which aims to extract semantic features from visual features and perform semantic disentanglement in multidimensional spaces, thereby improving generalization over unseen attribute-object compositions. Specifically, CAMS designs a Gated Cross-Attention that captures fine-grained semantic features from the high-level image encoding blocks of CLIP through a set of latent units, while adaptively suppressing background and other irrelevant information. Subsequently, it conducts Multi-Space Disentanglement to achieve disentanglement of attribute and object semantics. Experiments on three popular benchmarks (MIT-States, UT-Zappos, and C-GQA) demonstrate that CAMS achieves state-of-the-art performance in both closed-world and open-world settings. The code is available at https://github.com/ybyangjing/CAMS.

Paperid: 423, https://arxiv.org/pdf/2511.16334.pdf GitHub

Abstract:
Recent advancements in large reasoning models have fueled growing interest in extending such capabilities to multimodal domains. However, despite notable progress in visual reasoning, the lack of transparent and reproducible data curation and training strategies remains a major barrier to scalable research. In this work, we introduce OpenMMReasoner, a fully transparent two-stage recipe for multimodal reasoning spanning supervised fine-tuning (SFT) and reinforcement learning (RL). In the SFT stage, we construct an 874K-sample cold-start dataset with rigorous step-by-step validation, providing a strong foundation for reasoning capabilities. The subsequent RL stage leverages a 74K-sample dataset across diverse domains to further sharpen and stabilize these abilities, resulting in a more robust and efficient learning process. Extensive evaluations demonstrate that our training recipe not only surpasses strong baselines but also highlights the critical role of data quality and training design in shaping multimodal reasoning performance. Notably, our method achieves a 11.6% improvement over the Qwen2.5-VL-7B-Instruct baseline across nine multimodal reasoning benchmarks, establishing a solid empirical foundation for future large-scale multimodal reasoning research. We open-sourced all our codes, pipeline, and data at https://github.com/EvolvingLMMs-Lab/OpenMMReasoner.

Paperid: 424, https://arxiv.org/pdf/2511.16322.pdf GitHub

Abstract:
Remote sensing change detection (RSCD) aims to identify surface changes from co-registered bi-temporal images. However, many deep learning-based RSCD methods rely solely on change-map annotations and underuse the semantic information in non-changing regions, which limits robustness under illumination variation, off-nadir views, and scarce labels. This article introduces ChangeDINO, an end-to-end multiscale Siamese framework for optical building change detection. The model fuses a lightweight backbone stream with features transferred from a frozen DINOv3, yielding semantic- and context-rich pyramids even on small datasets. A spatial-spectral differential transformer decoder then exploits multi-scale absolute differences as change priors to highlight true building changes and suppress irrelevant responses. Finally, a learnable morphology module refines the upsampled logits to recover clean boundaries. Experiments on four public benchmarks show that ChangeDINO consistently outperforms recent state-of-the-art methods in IoU and F1, and ablation studies confirm the effectiveness of each component. The source code is available at https://github.com/chingheng0808/ChangeDINO.

Paperid: 425, https://arxiv.org/pdf/2511.16321.pdf GitHub

Abstract:
Underwater Image Enhancement (UIE) aims to restore visibility and correct color distortions caused by wavelength-dependent absorption and scattering. Recent hybrid approaches, which couple domain priors with modern deep neural architectures, have achieved strong performance but incur high computational cost, limiting their practicality in real-time scenarios. In this work, we propose WWE-UIE, a compact and efficient enhancement network that integrates three interpretable priors. First, adaptive white balance alleviates the strong wavelength-dependent color attenuation, particularly the dominance of blue-green tones. Second, a wavelet-based enhancement block (WEB) performs multi-band decomposition, enabling the network to capture both global structures and fine textures, which are critical for underwater restoration. Third, a gradient-aware module (SGFB) leverages Sobel operators with learnable gating to explicitly preserve edge structures degraded by scattering. Extensive experiments on benchmark datasets demonstrate that WWE-UIE achieves competitive restoration quality with substantially fewer parameters and FLOPs, enabling real-time inference on resource-limited platforms. Ablation studies and visualizations further validate the contribution of each component. The source code is available at https://github.com/chingheng0808/WWE-UIE.

Paperid: 426, https://arxiv.org/pdf/2511.16318.pdf GitHub

Abstract:
This work introduces a learning-enhanced observer (LEO) for linear time-invariant systems with uncertain dynamics. Rather than relying solely on nominal models, the proposed framework treats the system matrices as optimizable variables and refines them through gradient-based minimization of a steady-state output discrepancy loss. The resulting data-informed surrogate model enables the construction of an improved observer that effectively compensates for moderate parameter uncertainty while preserving the structure of classical designs. Extensive Monte Carlo studies across diverse system dimensions show systematic and statistically significant reductions, typically exceeding 15\%, in normalized estimation error for both open-loop and Luenberger observers. These results demonstrate that modern learning mechanisms can serve as a powerful complement to traditional observer design, yielding more accurate and robust state estimation in uncertain systems. Codes are available at https://github.com/Hao-B-Shu/LTI_LEO.

Paperid: 427, https://arxiv.org/pdf/2511.16315.pdf GitHub

Abstract:
ImageNet-1K linear-probe transfer accuracy remains the default proxy for visual representation quality, yet it no longer predicts performance on scientific imagery. Across 46 modern vision model checkpoints, ImageNet top-1 accuracy explains only 34% of variance on ecology tasks and mis-ranks 30% of models above 75% accuracy. We present BioBench, an open ecology vision benchmark that captures what ImageNet misses. BioBench unifies 9 publicly released, application-driven tasks, 4 taxonomic kingdoms, and 6 acquisition modalities (drone RGB, web video, micrographs, in-situ and specimen photos, camera-trap frames), totaling 3.1M images. A single Python API downloads data, fits lightweight classifiers to frozen backbones, and reports class-balanced macro-F1 (plus domain metrics for FishNet and FungiCLEF); ViT-L models evaluate in 6 hours on an A6000 GPU. BioBench provides new signal for computer vision in ecology and a template recipe for building reliable AI-for-science benchmarks in any domain. Code and predictions are available at https://github.com/samuelstevens/biobench and results at https://samuelstevens.me/biobench.

Paperid: 428, https://arxiv.org/pdf/2511.16301.pdf GitHub GitHub

Abstract:
We present \textbf{Upsample Anything}, a lightweight test-time optimization (TTO) framework that restores low-resolution features to high-resolution, pixel-wise outputs without any training. Although Vision Foundation Models demonstrate strong generalization across diverse downstream tasks, their representations are typically downsampled by 14x/16x (e.g., ViT), which limits their direct use in pixel-level applications. Existing feature upsampling approaches depend on dataset-specific retraining or heavy implicit optimization, restricting scalability and generalization. Upsample Anything addresses these issues through a simple per-image optimization that learns an anisotropic Gaussian kernel combining spatial and range cues, effectively bridging Gaussian Splatting and Joint Bilateral Upsampling. The learned kernel acts as a universal, edge-aware operator that transfers seamlessly across architectures and modalities, enabling precise high-resolution reconstruction of features, depth, or probability maps. It runs in only $\approx0.419 \text{s}$ per 224x224 image and achieves state-of-the-art performance on semantic segmentation, depth estimation, and both depth and probability map upsampling. \textbf{Project page:} \href{https://seominseok0429.github.io/Upsample-Anything/}{https://seominseok0429.github.io/Upsample-Anything/}

Paperid: 429, https://arxiv.org/pdf/2511.16249.pdf GitHub

Abstract:
This work presents Controllable Layer Decomposition (CLD), a method for achieving fine-grained and controllable multi-layer separation of raster images. In practical workflows, designers typically generate and edit each RGBA layer independently before compositing them into a final raster image. However, this process is irreversible: once composited, layer-level editing is no longer possible. Existing methods commonly rely on image matting and inpainting, but remain limited in controllability and segmentation precision. To address these challenges, we propose two key modules: LayerDecompose-DiT (LD-DiT), which decouples image elements into distinct layers and enables fine-grained control; and Multi-Layer Conditional Adapter (MLCA), which injects target image information into multi-layer tokens to achieve precise conditional generation. To enable a comprehensive evaluation, we build a new benchmark and introduce tailored evaluation metrics. Experimental results show that CLD consistently outperforms existing methods in both decomposition quality and controllability. Furthermore, the separated layers produced by CLD can be directly manipulated in commonly used design tools such as PowerPoint, highlighting its practical value and applicability in real-world creative workflows. Our project is available at https://monkek123king.github.io/CLD_page/.

Paperid: 430, https://arxiv.org/pdf/2511.16229.pdf GitHub

Abstract:
Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in cross-modal understanding, but remain vulnerable to adversarial attacks through visual inputs despite robust textual safety mechanisms. These vulnerabilities arise from two core weaknesses: the continuous nature of visual representations, which allows for gradient-based attacks, and the inadequate transfer of text-based safety mechanisms to visual content. We introduce Q-MLLM, a novel architecture that integrates two-level vector quantization to create a discrete bottleneck against adversarial attacks while preserving multimodal reasoning capabilities. By discretizing visual representations at both pixel-patch and semantic levels, Q-MLLM blocks attack pathways and bridges the cross-modal safety alignment gap. Our two-stage training methodology ensures robust learning while maintaining model utility. Experiments demonstrate that Q-MLLM achieves significantly better defense success rate against both jailbreak attacks and toxic image attacks than existing approaches. Notably, Q-MLLM achieves perfect defense success rate (100\%) against jailbreak attacks except in one arguable case, while maintaining competitive performance on multiple utility benchmarks with minimal inference overhead. This work establishes vector quantization as an effective defense mechanism for secure multimodal AI systems without requiring expensive safety-specific fine-tuning or detection overhead. Code is available at https://github.com/Amadeuszhao/QMLLM.

Paperid: 431, https://arxiv.org/pdf/2511.16227.pdf GitHub

Abstract:
Cross-modal object tracking (CMOT) is an emerging task that maintains target consistency while the video stream switches between different modalities, with only one modality available in each frame, mostly focusing on RGB-Near Infrared (RGB-NIR) tracking. Existing methods typically connect parallel RGB and NIR branches to a shared backbone, which limits the comprehensive extraction of distinctive modality-specific features and fails to address the issue of object drift, especially in the presence of unreliable inputs. In this paper, we propose SwiTrack, a novel state-switching framework that redefines CMOT through the deployment of three specialized streams. Specifically, RGB frames are processed by the visual encoder, while NIR frames undergo refinement via a NIR gated adapter coupled with the visual encoder to progressively calibrate shared latent space features, thereby yielding more robust cross-modal representations. For invalid modalities, a consistency trajectory prediction module leverages spatio-temporal cues to estimate target movement, ensuring robust tracking and mitigating drift. Additionally, we incorporate dynamic template reconstruction to iteratively update template features and employ a similarity alignment loss to reinforce feature consistency. Experimental results on the latest benchmarks demonstrate that our tracker achieves state-of-the-art performance, boosting precision rate and success rate gains by 7.2\% and 4.3\%, respectively, while maintaining real-time tracking at 65 frames per second. Code and models are available at https://github.com/xuboyue1999/SwiTrack.git.

Paperid: 432, https://arxiv.org/pdf/2511.16216.pdf GitHub

Abstract:
The development of Large Language Models (LLMs) increasingly depends on high-quality supervised data, yet existing instruction-tuning and RL datasets remain costly to curate and often rely on synthetic samples that introduce hallucination and limited diversity. At the same time, textbooks and exercise materials contain abundant, high-quality human-authored Question-Answer(QA) content that remains underexploited due to the difficulty of transforming raw PDFs into AI-ready supervision. Although modern OCR and vision-language models can accurately parse document structure, their outputs lack the semantic alignment required for training. We propose an automated pipeline that extracts well-formed QA and visual-QA (VQA) pairs from educational documents by combining layout-aware OCR with LLM-based semantic parsing. Experiments across diverse document types show that the method produces accurate, aligned, and low-noise QA/VQA pairs. This approach enables scalable use of real-world educational content and provides a practical alternative to synthetic data generation for improving reasoning-oriented LLM training. All code and data-processing pipelines are open-sourced at https://github.com/OpenDCAI/DataFlow.

Paperid: 433, https://arxiv.org/pdf/2511.16209.pdf GitHub

Abstract:
System prompts are critical for guiding the behavior of Large Language Models (LLMs), yet they often contain proprietary logic or sensitive information, making them a prime target for extraction attacks. Adversarial queries can successfully elicit these hidden instructions, posing significant security and privacy risks. Existing defense mechanisms frequently rely on heuristics, incur substantial computational overhead, or are inapplicable to models accessed via black-box APIs. This paper introduces a novel framework for hardening system prompts through shield appending, a lightweight approach that adds a protective textual layer to the original prompt. Our core contribution is the formalization of prompt hardening as a utility-constrained optimization problem. We leverage an LLM-as-optimizer to search the space of possible SHIELDs, seeking to minimize a leakage metric derived from a suite of adversarial attacks, while simultaneously preserving task utility above a specified threshold, measured by semantic fidelity to baseline outputs. This black-box, optimization-driven methodology is lightweight and practical, requiring only API access to the target and optimizer LLMs. We demonstrate empirically that our optimized SHIELDs significantly reduce prompt leakage against a comprehensive set of extraction attacks, outperforming established baseline defenses without compromising the model's intended functionality. Our work presents a paradigm for developing robust, utility-aware defenses in the escalating landscape of LLM security. The code is made public on the following link: https://github.com/psm-defense/psm

Paperid: 434, https://arxiv.org/pdf/2511.16191.pdf GitHub

Abstract:
Rumor detection on social media remains a challenging task due to the complex propagation dynamics and the limited interpretability of existing models. While recent neural architectures capture content and structural features, they often fail to reveal the underlying causal mechanisms of misinformation spread. We propose CausalMamba, a novel framework that integrates Mamba-based sequence modeling, graph convolutional networks (GCNs), and differentiable causal discovery via NOTEARS. CausalMamba learns joint representations of temporal tweet sequences and reply structures, while uncovering latent causal graphs to identify influential nodes within each propagation chain. Experiments on the Twitter15 dataset show that our model achieves competitive classification performance compared to strong baselines, and uniquely enables counterfactual intervention analysis. Qualitative results demonstrate that removing top-ranked causal nodes significantly alters graph connectivity, offering interpretable insights into rumor dynamics. Our framework provides a unified approach for rumor classification and influence analysis, paving the way for more explainable and actionable misinformation detection systems.

Paperid: 435, https://arxiv.org/pdf/2511.16166.pdf GitHub GitHub

Abstract:
Long-horizon robotic manipulation remains challenging for Vision-Language-Action (VLA) models despite recent progress in zero-shot generalization and simulation-to-real-world transfer. Current VLA models suffer from stage hallucination, where agents exploit coarse evaluation signals to shortcut multi-step tasks, reporting high progress without truly completing them. We present EvoVLA, a self-supervised VLA framework that addresses this issue through three complementary components: Stage-Aligned Reward (SAR), which uses triplet contrastive learning with Gemini-generated hard negatives to prevent visual shortcuts; Pose-Based Object Exploration (POE), which grounds curiosity in relative object-gripper pose instead of raw pixels; and Long-Horizon Memory, which uses selective context retention and gated fusion to stabilize intrinsic shaping during extended rollouts. Extensive evaluations on Discoverse-L, a long-horizon manipulation benchmark with three multi-stage tasks, show that EvoVLA improves average task success by 10.2 percentage points over the strongest baseline (OpenVLA-OFT), reaching 69.2 percent. EvoVLA also achieves one-and-a-half times better sample efficiency and reduces stage hallucination from 38.5 percent to 14.8 percent. Real-world deployment on physical robots reaches an average success rate of 54.6 percent across four manipulation tasks, outperforming OpenVLA-OFT by 11 points, demonstrating effective sim-to-real transfer and strong generalization. Code: https://github.com/AIGeeksGroup/EvoVLA. Website: https://aigeeksgroup.github.io/EvoVLA.

Paperid: 436, https://arxiv.org/pdf/2511.16160.pdf GitHub

Abstract:
Spatial intelligence is a critical frontier for Multimodal Large Language Models (MLLMs), empowering them to comprehend the physical world. Drawing inspiration from human perception mechanisms, existing studies attempt to construct a coherent spatial understanding via grid-based cognitive maps from multi-frame visual inputs. However, current grid-based map methods rely on discretized raster representations, which limit the model's ability in fine-grained spatial reasoning. To overcome this limitation, we propose Video2Layout, a framework for reconstructing metric-grounded spatial layouts from video. The framework employs continuous object boundary coordinates to quantify inter-object physical distances and object size. This empowers the model with quantitative spatial computation capabilities, effectively alleviating the inherent ambiguity when describing spatial relationships in natural language. Specifically, our method comprises two core stages. First, in supervised fine-tuning stage, we construct a high-quality dataset from the AI2THOR simulator, which enables the model to learn the mapping from visual inputs to precise boundary coordinates. Subsequently, a reinforcement fine-tuning stage further enhances the model's real-world generalization capabilities. To systematically evaluate the correlation between cognitive map accuracy and image quantity, as well as how the quantity of image inputs affects spatial reasoning accuracy, we introduce QVS-Bench, a diagnostic benchmark designed to analyze the relevant mechanisms. Evaluated on QVS-Bench and mainstream spatial reasoning benchmarks, our model, V2LO-7B achieves an average improvement of 4.92% over the model trained on grid maps, validating the superiority of our method. Our code is available at https://github.com/ybrrraway/Video2Layout.

Paperid: 437, https://arxiv.org/pdf/2511.16158.pdf GitHub

Abstract:
Magnetic levitation is about to revolutionize in-machine material flow in industrial automation. Such systems are flexibly configurable and can include a large number of independently actuated shuttles (movers) that dynamically rebalance production capacity. Beyond their capabilities for dynamic transportation, these systems possess the inherent yet unexploited potential to perform manipulation. By merging the fields of transportation and manipulation into a coordinated swarm of magnetic robots (MagBots), we enable manufacturing systems to achieve significantly higher efficiency, adaptability, and compactness. To support the development of intelligent algorithms for magnetic levitation systems, we introduce MagBotSim (Magnetic Robotics Simulation): a physics-based simulation for magnetic levitation systems. By framing magnetic levitation systems as robot swarms and providing a dedicated simulation, this work lays the foundation for next generation manufacturing systems powered by Magnetic Robotics. MagBotSim's documentation, videos, experiments, and code are available at: https://ubi-coro.github.io/MagBotSim/

Paperid: 438, https://arxiv.org/pdf/2511.16156.pdf GitHub GitHub

Abstract:
Diffusion Transformers (DiTs) have shown exceptional performance in image generation, yet their large parameter counts incur high computational costs, impeding deployment in resource-constrained settings. To address this, we propose Pluggable Pruning with Contiguous Layer Distillation (PPCL), a flexible structured pruning framework specifically designed for DiT architectures. First, we identify redundant layer intervals through a linear probing mechanism combined with the first-order differential trend analysis of similarity metrics. Subsequently, we propose a plug-and-play teacher-student alternating distillation scheme tailored to integrate depth-wise and width-wise pruning within a single training phase. This distillation framework enables flexible knowledge transfer across diverse pruning ratios, eliminating the need for per-configuration retraining. Extensive experiments on multiple Multi-Modal Diffusion Transformer architecture models demonstrate that PPCL achieves a 50\% reduction in parameter count compared to the full model, with less than 3\% degradation in key objective metrics. Notably, our method maintains high-quality image generation capabilities while achieving higher compression ratios, rendering it well-suited for resource-constrained environments. The open-source code, checkpoints for PPCL can be found at the following link: https://github.com/OPPO-Mente-Lab/Qwen-Image-Pruning.

Paperid: 439, https://arxiv.org/pdf/2511.16145.pdf GitHub

Abstract:
Time series anomaly detection (TSAD) is a critical data mining task often constrained by label scarcity. Consequently, current research predominantly focuses on Unsupervised Time-series Anomaly Detection (UTAD), relying on complex architectures to model normal data distributions. However, this approach often overlooks the significant performance gains available from limited anomaly labels achievable in practical scenarios. This paper challenges the premise that architectural complexity is the optimal path for TSAD. We conduct the first methodical comparison between supervised and unsupervised paradigms and introduce STAND, a streamlined supervised baseline. Extensive experiments on five public datasets demonstrate that: (1) Labels matter more than models: under a limited labeling budget, simple supervised models significantly outperform complex state-of-the-art unsupervised methods; (2) Supervision yields higher returns: the performance gain from minimal supervision far exceeds that from architectural innovations; and (3) Practicality: STAND exhibits superior prediction consistency and anomaly localization compared to unsupervised counterparts. These findings advocate for a data-centric shift in TSAD research, emphasizing label utilization over purely algorithmic complexity. The code is publicly available at https://github.com/EmorZz1G/STAND.

Paperid: 440, https://arxiv.org/pdf/2511.16143.pdf GitHub

Abstract:
Remote sensing Water Body Change Detection (WBCD) aims to detect water body surface changes from bi-temporal images of the same geographic area. Recently, the scarcity of high spatial resolution datasets for WBCD restricts its application in urban and rural regions, which require more accurate positioning. Meanwhile, previous deep learning-based methods fail to comprehensively exploit the spatial semantic and structural information in deep features in the change detection networks. To resolve these concerns, we first propose a new dataset, HSRW-CD, with a spatial resolution higher than 3 meters for WBCD. Specifically, it contains a large number of image pairs, widely covering various water body types. Besides, a Spatial Semantics and Continuity Perception (SSCP) attention module is designed to fully leverage both the spatial semantics and structure of deep features in the WBCD networks, significantly improving the discrimination capability for water body. The proposed SSCP has three components: the Multi-Semantic spatial Attention (MSA), the Structural Relation-aware Global Attention (SRGA), and the Channel-wise Self-Attention (CSA). The MSA enhances the spatial semantics of water body features and provides precise spatial semantic priors for the CSA. Then, the SRGA further extracts spatial structure to learn the spatial continuity of the water body. Finally, the CSA utilizes the spatial semantic and structural priors from the MSA and SRGA to compute the similarity across channels. Specifically designed as a plug-and-play module for water body deep features, the proposed SSCP allows integration into existing WBCD models. Numerous experiments conducted on the proposed HSRW-CD and Water-CD datasets validate the effectiveness and generalization of the SSCP. The code of this work and the HSRW-CD dataset will be accessed at https://github.com/QingMa1/SSCP.

Paperid: 441, https://arxiv.org/pdf/2511.16124.pdf GitHub

Abstract:
Due to large pixel movement and high computational cost, estimating the motion of high-resolution frames is challenging. Thus, most flow-based Video Frame Interpolation (VFI) methods first predict bidirectional flows at low resolution and then use high-magnification upsampling (e.g., bilinear) to obtain the high-resolution ones. However, this kind of upsampling strategy may cause blur or mosaic at the flows' edges. Additionally, the motion of fine pixels at high resolution cannot be adequately captured in motion estimation at low resolution, which leads to the misalignment of task-oriented flows. With such inaccurate flows, input frames are warped and combined pixel-by-pixel, resulting in ghosting and discontinuities in the interpolated frame. In this study, we propose a novel VFI pipeline, VTinker, which consists of two core components: guided flow upsampling (GFU) and Texture Mapping. After motion estimation at low resolution, GFU introduces input frames as guidance to alleviate the blurring details in bilinear upsampling flows, which makes flows' edges clearer. Subsequently, to avoid pixel-level ghosting and discontinuities, Texture Mapping generates an initial interpolated frame, referred to as the intermediate proxy. The proxy serves as a cue for selecting clear texture blocks from the input frames, which are then mapped onto the proxy to facilitate producing the final interpolated frame via a reconstruction module. Extensive experiments demonstrate that VTinker achieves state-of-the-art performance in VFI. Codes are available at: https://github.com/Wucy0519/VTinker.

Paperid: 442, https://arxiv.org/pdf/2511.16114.pdf GitHub

Abstract:
Voice cloning technology poses significant privacy threats by enabling unauthorized speech synthesis from limited audio samples. Existing defenses based on imperceptible adversarial perturbations are vulnerable to common audio preprocessing such as denoising and compression. We propose SceneGuard, a training-time voice protection method that applies scene-consistent audible background noise to speech recordings. Unlike imperceptible perturbations, SceneGuard leverages naturally occurring acoustic scenes (e.g., airport, street, park) to create protective noise that is contextually appropriate and robust to countermeasures. We evaluate SceneGuard on text-to-speech training attacks, demonstrating 5.5% speaker similarity degradation with extremely high statistical significance (p < 10^{-15}, Cohen's d = 2.18) while preserving 98.6% speech intelligibility (STOI = 0.986). Robustness evaluation shows that SceneGuard maintains or enhances protection under five common countermeasures including MP3 compression, spectral subtraction, lowpass filtering, and downsampling. Our results suggest that audible, scene-consistent noise provides a more robust alternative to imperceptible perturbations for training-time voice protection. The source code are available at: https://github.com/richael-sang/SceneGuard.

Paperid: 443, https://arxiv.org/pdf/2511.16112.pdf GitHub

Abstract:
Existing 4D Gaussian Splatting (4DGS) methods struggle to accurately reconstruct dynamic scenes, often failing to resolve ambiguous pixel correspondences and inadequate densification in dynamic regions. We address these issues by introducing a novel method composed of two key components: (1) Elliptical Error Clustering and Error Correcting Splat Addition that pinpoints dynamic areas to improve and initialize fitting splats, and (2) Grouped 4D Gaussian Splatting that improves consistency of mapping between splats and represented dynamic objects. Specifically, we classify rendering errors into missing-color and occlusion types, then apply targeted corrections via backprojection or foreground splitting guided by cross-view color consistency. Evaluations on Neural 3D Video and Technicolor datasets demonstrate that our approach significantly improves temporal consistency and achieves state-of-the-art perceptual rendering quality, improving 0.39dB of PSNR on the Technicolor Light Field dataset. Our visualization shows improved alignment between splats and dynamic objects, and the error correction method's capability to identify errors and properly initialize new splats. Our implementation details and source code are available at https://github.com/tho-kn/cem-4dgs.

Paperid: 444, https://arxiv.org/pdf/2511.16110.pdf GitHub

Abstract:
The growing misuse of Vision-Language Models (VLMs) has led providers to deploy multiple safeguards, including alignment tuning, system prompts, and content moderation. However, the real-world robustness of these defenses against adversarial attacks remains underexplored. We introduce Multi-Faceted Attack (MFA), a framework that systematically exposes general safety vulnerabilities in leading defense-equipped VLMs such as GPT-4o, Gemini-Pro, and Llama-4. The core component of MFA is the Attention-Transfer Attack (ATA), which hides harmful instructions inside a meta task with competing objectives. We provide a theoretical perspective based on reward hacking to explain why this attack succeeds. To improve cross-model transferability, we further introduce a lightweight transfer-enhancement algorithm combined with a simple repetition strategy that jointly bypasses both input-level and output-level filters without model-specific fine-tuning. Empirically, we show that adversarial images optimized for one vision encoder transfer broadly to unseen VLMs, indicating that shared visual representations create a cross-model safety vulnerability. Overall, MFA achieves a 58.5% success rate and consistently outperforms existing methods. On state-of-the-art commercial models, MFA reaches a 52.8% success rate, surpassing the second-best attack by 34%. These results challenge the perceived robustness of current defense mechanisms and highlight persistent safety weaknesses in modern VLMs. Code: https://github.com/cure-lab/MultiFacetedAttack

Paperid: 445, https://arxiv.org/pdf/2511.16087.pdf GitHub

Abstract:
The performance of machine learning models in drug discovery is highly dependent on the quality and consistency of the underlying training data. Due to limitations in dataset sizes, many models are trained by aggregating bioactivity data from diverse sources, including public databases such as ChEMBL. However, this approach often introduces significant noise due to variability in experimental protocols. We introduce AssayMatch, a framework for data selection that builds smaller, more homogenous training sets attuned to the test set of interest. AssayMatch leverages data attribution methods to quantify the contribution of each training assay to model performance. These attribution scores are used to finetune language embeddings of text-based assay descriptions to capture not just semantic similarity, but also the compatibility between assays. Unlike existing data attribution methods, our approach enables data selection for a test set with unknown labels, mirroring real-world drug discovery campaigns where the activities of candidate molecules are not known in advance. At test time, embeddings finetuned with AssayMatch are used to rank all available training data. We demonstrate that models trained on data selected by AssayMatch are able to surpass the performance of the model trained on the complete dataset, highlighting its ability to effectively filter out harmful or noisy experiments. We perform experiments on two common machine learning architectures and see increased prediction capability over a strong language-only baseline for 9/12 model-target pairs. AssayMatch provides a data-driven mechanism to curate higher-quality datasets, reducing noise from incompatible experiments and improving the predictive power and data efficiency of models for drug discovery. AssayMatch is available at https://github.com/Ozymandias314/AssayMatch.

Paperid: 446, https://arxiv.org/pdf/2511.16084.pdf GitHub

Abstract:
Hyperspectral image (HSI) classification typically involves large-scale data and computationally intensive training, which limits the practical deployment of deep learning models in real-world remote sensing tasks. This study introduces SpectralTrain, a universal, architecture-agnostic training framework that enhances learning efficiency by integrating curriculum learning (CL) with principal component analysis (PCA)-based spectral downsampling. By gradually introducing spectral complexity while preserving essential information, SpectralTrain enables efficient learning of spectral -- spatial patterns at significantly reduced computational costs. The framework is independent of specific architectures, optimizers, or loss functions and is compatible with both classical and state-of-the-art (SOTA) models. Extensive experiments on three benchmark datasets -- Indian Pines, Salinas-A, and the newly introduced CloudPatch-7 -- demonstrate strong generalization across spatial scales, spectral characteristics, and application domains. The results indicate consistent reductions in training time by 2-7x speedups with small-to-moderate accuracy deltas depending on backbone. Its application to cloud classification further reveals potential in climate-related remote sensing, emphasizing training strategy optimization as an effective complement to architectural design in HSI models. Code is available at https://github.com/mh-zhou/SpectralTrain.

Paperid: 447, https://arxiv.org/pdf/2511.16077.pdf GitHub

Abstract:
Traditional video reasoning segmentation methods rely on supervised fine-tuning, which limits generalization to out-of-distribution scenarios and lacks explicit reasoning. To address this, we propose \textbf{VideoSeg-R1}, the first framework to introduce reinforcement learning into video reasoning segmentation. It adopts a decoupled architecture that formulates the task as joint referring image segmentation and video mask propagation. It comprises three stages: (1) A hierarchical text-guided frame sampler to emulate human attention; (2) A reasoning model that produces spatial cues along with explicit reasoning chains; and (3) A segmentation-propagation stage using SAM2 and XMem. A task difficulty-aware mechanism adaptively controls reasoning length for better efficiency and accuracy. Extensive evaluations on multiple benchmarks demonstrate that VideoSeg-R1 achieves state-of-the-art performance in complex video reasoning and segmentation tasks. The code will be publicly available at https://github.com/euyis1019/VideoSeg-R1.

Paperid: 448, https://arxiv.org/pdf/2511.16062.pdf GitHub

Abstract:
Graph Neural Networks (GNNs) excel on homophilous graphs but often fail under heterophily due to self-reinforcing and phase-inconsistent signals. We propose a Gauge-Equivariant Graph Network with Self-Interference Cancellation (GESC), which replaces additive aggregation with a projection-based interference mechanism. Unlike prior magnetic or gauge-equivariant GNNs that typically focus on phase handling in spectral filtering while largely relying on scalar weighting, GESC introduces a $\mathrm{U}(1)$ phase connection followed by a rank-1 projection that attenuates self-parallel components before attention. A sign- and phase-aware gate further regulates neighbor influence, attenuating components aligned with current node states and acting as a local notch on low-frequency modes. Across diverse graph benchmarks, our method consistently outperforms recent state-of-the-art models while offering a unified, interference-aware view of message passing. Our code is available at \href{here}{https://anonymous.4open.science/r/GESC-1B22}.

Paperid: 449, https://arxiv.org/pdf/2511.16050.pdf GitHub

Abstract:
Underwater robotic manipulation is fundamentally challenged by extreme lighting variations, color distortion, and reduced visibility. We introduce Bi-AQUA, the first underwater bilateral control-based imitation learning framework that integrates lighting-aware visual processing for underwater robot arms. Bi-AQUA employs a hierarchical three-level lighting adaptation mechanism: a Lighting Encoder that extracts lighting representations from RGB images without manual annotation and is implicitly supervised by the imitation objective, FiLM modulation of visual backbone features for adaptive, lighting-aware feature extraction, and an explicit lighting token added to the transformer encoder input for task-aware conditioning. Experiments on a real-world underwater pick-and-place task under diverse static and dynamic lighting conditions show that Bi-AQUA achieves robust performance and substantially outperforms a bilateral baseline without lighting modeling. Ablation studies further confirm that all three lighting-aware components are critical. This work bridges terrestrial bilateral control-based imitation learning and underwater manipulation, enabling force-sensitive autonomous operation in challenging marine environments. For additional material, please check: https://mertcookimg.github.io/bi-aqua

Paperid: 450, https://arxiv.org/pdf/2511.16049.pdf GitHub

Abstract:
Synthesizing high-fidelity and controllable 4D LiDAR data is crucial for creating scalable simulation environments for autonomous driving. This task is inherently challenging due to the sensor's unique spherical geometry, the temporal sparsity of point clouds, and the complexity of dynamic scenes. To address these challenges, we present LiSTAR, a novel generative world model that operates directly on the sensor's native geometry. LiSTAR introduces a Hybrid-Cylindrical-Spherical (HCS) representation to preserve data fidelity by mitigating quantization artifacts common in Cartesian grids. To capture complex dynamics from sparse temporal data, it utilizes a Spatio-Temporal Attention with Ray-Centric Transformer (START) that explicitly models feature evolution along individual sensor rays for robust temporal coherence. Furthermore, for controllable synthesis, we propose a novel 4D point cloud-aligned voxel layout for conditioning and a corresponding discrete Masked Generative START (MaskSTART) framework, which learns a compact, tokenized representation of the scene, enabling efficient, high-resolution, and layout-guided compositional generation. Comprehensive experiments validate LiSTAR's state-of-the-art performance across 4D LiDAR reconstruction, prediction, and conditional generation, with substantial quantitative gains: reducing generation MMD by a massive 76%, improving reconstruction IoU by 32%, and lowering prediction L1 Med by 50%. This level of performance provides a powerful new foundation for creating realistic and controllable autonomous systems simulations. Project link: https://ocean-luna.github.io/LiSTAR.gitub.io.

Paperid: 451, https://arxiv.org/pdf/2511.16043.pdf GitHub

Abstract:
Large Language Model (LLM) Agents, often trained with Reinforcement Learning (RL), are constrained by a dependency on human-curated data, limiting scalability and tethering AI to human knowledge. Existing self-evolution frameworks offer an alternative but are typically restricted by the model's inherent capabilities and single-round interactions, hindering the development of complex curricula involving tool use or dynamic reasoning. We introduce Agent0, a fully autonomous framework that evolves high-performing agents without external data through multi-step co-evolution and seamless tool integration. Agent0 establishes a symbiotic competition between two agents initialized from the same base LLM: a curriculum agent that proposes increasingly challenging frontier tasks, and an executor agent that learns to solve them. We integrate external tools to enhance the executor's problem-solving capacity; this improvement, in turn, pressures the curriculum agent to construct more complex, tool-aware tasks. Through this iterative process, Agent0 establishes a self-reinforcing cycle that continuously produces high-quality curricula. Empirically, Agent0 substantially boosts reasoning capabilities, improving the Qwen3-8B-Base model by 18% on mathematical reasoning and 24% on general reasoning benchmarks. Code is available at https://github.com/aiming-lab/Agent0.

Paperid: 452, https://arxiv.org/pdf/2511.16035.pdf GitHub

Abstract:
Prior work has introduced techniques for detecting when large language models (LLMs) lie, that is, generating statements they believe are false. However, these techniques are typically validated in narrow settings that do not capture the diverse lies LLMs can generate. We introduce LIARS' BENCH, a testbed consisting of 72,863 examples of lies and honest responses generated by four open-weight models across seven datasets. Our settings capture qualitatively different types of lies and vary along two dimensions: the model's reason for lying and the object of belief targeted by the lie. Evaluating three black- and white-box lie detection techniques on LIARS' BENCH, we find that existing techniques systematically fail to identify certain types of lies, especially in settings where it's not possible to determine whether the model lied from the transcript alone. Overall, LIARS' BENCH reveals limitations in prior techniques and provides a practical testbed for guiding progress in lie detection.

Paperid: 453, https://arxiv.org/pdf/2511.16030.pdf GitHub

Abstract:
3D Gaussian Splatting (3DGS) has recently emerged as an efficient, high-fidelity representation for real-time scene reconstruction and rendering. However, extending 3DGS to sparse-view settings remains challenging because of supervision scarcity and overfitting caused by limited viewpoint coverage. In this paper, we present CuriGS, a curriculum-guided framework for sparse-view 3D reconstruction using 3DGS. CuriGS addresses the core challenge of sparse-view synthesis by introducing student views: pseudo-views sampled around ground-truth poses (teacher). For each teacher, we generate multiple groups of student views with different perturbation levels. During training, we follow a curriculum schedule that gradually unlocks higher perturbation level, randomly sampling candidate students from the active level to assist training. Each sampled student is regularized via depth-correlation and co-regularization, and evaluated using a multi-signal metric that combines SSIM, LPIPS, and an image-quality measure. For every teacher and perturbation level, we periodically retain the best-performing students and promote those that satisfy a predefined quality threshold to the training set, resulting in a stable augmentation of sparse training views. Experimental results show that CuriGS outperforms state-of-the-art baselines in both rendering fidelity and geometric consistency across various synthetic and real sparse-view scenes. Project page: https://zijian1026.github.io/CuriGS/

Paperid: 454, https://arxiv.org/pdf/2511.16004.pdf GitHub

Abstract:
Large language models have advanced software engineering automation, yet resolving real-world software issues remains difficult because it requires repository-level reasoning, accurate diagnostics, and strong verification signals. Existing agent-based and pipeline-based methods often rely on insufficient tests, which can lead to patches that satisfy verification but fail to fix the underlying defect. We present InfCode, an adversarial multi-agent framework for automated repository-level issue resolution. InfCode iteratively refines both tests and patches through adversarial interaction between a Test Patch Generator and a Code Patch Generator, while a Selector agent identifies the most reliable fix. The framework runs inside a containerized environment that supports realistic repository inspection, modification, and validation. Experiments on SWE-bench Lite and SWE-bench Verified using models such as DeepSeek-V3 and Claude 4.5 Sonnet show that InfCode consistently outperforms strong baselines. It achieves 79.4% performance on SWE-bench Verified, establishing a new state-of-the-art. We have released InfCode as an open-source project at https://github.com/Tokfinity/InfCode.

Paperid: 455, https://arxiv.org/pdf/2511.15996.pdf GitHub

Abstract:
We present QueryGym, a lightweight, extensible Python toolkit that supports large language model (LLM)-based query reformulation. This is an important tool development since recent work on llm-based query reformulation has shown notable increase in retrieval effectiveness. However, while different authors have sporadically shared the implementation of their methods, there is no unified toolkit that provides a consistent implementation of such methods, which hinders fair comparison, rapid experimentation, consistent benchmarking and reliable deployment. QueryGym addresses this gap by providing a unified framework for implementing, executing, and comparing llm-based reformulation methods. The toolkit offers: (1) a Python API for applying diverse LLM-based methods, (2) a retrieval-agnostic interface supporting integration with backends such as Pyserini and PyTerrier, (3) a centralized prompt management system with versioning and metadata tracking, (4) built-in support for benchmarks like BEIR and MS MARCO, and (5) a completely open-source extensible implementation available to all researchers. QueryGym is publicly available at https://github.com/radinhamidi/QueryGym.

Paperid: 456, https://arxiv.org/pdf/2511.15946.pdf GitHub

Abstract:
Although the heart has complex three-dimensional (3D) anatomy, conventional medical imaging with cardiac ultrasound relies on a series of 2D videos showing individual cardiac structures. 3D echocardiography is a developing modality that now offers adequate image quality for clinical use, with potential to streamline acquisition and improve assessment of off-axis features. We propose an automated method to select standard 2D views from 3D cardiac ultrasound volumes, allowing physicians to interpret the data in their usual format while benefiting from the speed and usability of 3D scanning. Applying a deep learning view classifier and downstream heuristics based on anatomical landmarks together with heuristics provided by cardiologists, we reconstruct standard echocardiography views. This approach was validated by three cardiologists in blinded evaluation (96\% accuracy in 1,600 videos from 2 hospitals). The downstream 2D videos were also validated in their ability to detect cardiac abnormalities using AI echocardiography models (EchoPrime and PanEcho) as well as ability to generate clinical-grade measurements of cardiac anatomy (EchoNet-Measurement). We demonstrated that the extracted 2D videos preserve spatial calibration and diagnostic features, allowing clinicians to obtain accurate real-world interpretations from 3D volumes. We release the code and a dataset of 29 3D echocardiography videos https://github.com/echonet/3d-echo .

Paperid: 457, https://arxiv.org/pdf/2511.15943.pdf GitHub GitHub

Abstract:
Recent advances in image-text pretraining have significantly enhanced visual understanding by aligning visual and textual representations. Contrastive Language-Image Pretraining (CLIP) has played a pivotal role in multimodal learning. However, its focus on single-label, single-granularity alignment limits its effectiveness in complex domains such as medical imaging, where images often correspond to multiple high-level labels (e.g., disease categories) across different annotation granularities (e.g., diagnostic description, clinical explanation). To address this, we propose Multi-Granular Language Learning (MGLL), a contrastive learning framework designed to improve both multi-label and cross-granularity alignment. MGLL leverages structured multi-label supervision, integrates textual descriptions across granularities, and introduces soft-label supervision with point-wise constraints to enhance alignment. MGLL employs smooth Kullback-Leibler (KL) divergence to ensure cross-granularity consistency while maintaining computational efficiency as a plug-and-play module for vision-language models. Pretrained on our constructed large-scale multi-granular datasets and evaluated across multiple datasets, MGLL outperforms other state-of-the-art methods in downstream tasks. The code is available at \href{https://github.com/HUANGLIZI/MGLL}{https://github.com/HUANGLIZI/MGLL}.

Paperid: 458, https://arxiv.org/pdf/2511.15906.pdf GitHub

Abstract:
Generative models for structure-based drug design are often limited to a specific modality, restricting their broader applicability. To address this challenge, we introduce FuncBind, a framework based on computer vision to generate target-conditioned, all-atom molecules across atomic systems. FuncBind uses neural fields to represent molecules as continuous atomic densities and employs score-based generative models with modern architectures adapted from the computer vision literature. This modality-agnostic representation allows a single unified model to be trained on diverse atomic systems, from small to large molecules, and handle variable atom/residue counts, including non-canonical amino acids. FuncBind achieves competitive in silico performance in generating small molecules, macrocyclic peptides, and antibody complementarity-determining region loops, conditioned on target structures. FuncBind also generated in vitro novel antibody binders via de novo redesign of the complementarity-determining region H3 loop of two chosen co-crystal structures. As a final contribution, we introduce a new dataset and benchmark for structure-conditioned macrocyclic peptide generation. The code is available at https://github.com/prescient-design/funcbind.

Paperid: 459, https://arxiv.org/pdf/2511.15833.pdf GitHub

Abstract:
The Segment Anything Model 3 (SAM3) advances visual understanding with Promptable Concept Segmentation (PCS) across images and videos, but its unified architecture (shared vision backbone, DETR-style detector, dense-memory tracker) remains prohibitive for on-device use. We present EfficientSAM3, a family of efficient models built on Progressive Hierarchical Distillation (PHD) that transfers capability from SAM3 to lightweight students in three stages: (1) Encoder Distillation aligns image features via prompt-in-the-loop training on SA-1B; (2) Temporal Memory Distillation replaces dense memory with a compact Perceiver-based module trained on SA-V to compress and retrieve spatiotemporal features efficiently; and (3) End-to-End Fine-Tuning refines the full pipeline on the official SAM3 PCS data to preserve concept-level performance. PHD yields a spectrum of student variants using RepViT, TinyViT, and EfficientViT backbones, enabling on-device concept segmentation and tracking while maintaining high fidelity to teacher behavior. We benchmark on popular VOS datasets, and compare with varies of releated work, achieing strong performance-efficiency trade-offs.

Paperid: 460, https://arxiv.org/pdf/2511.15831.pdf GitHub

Abstract:
Image-based virtual try-on (VTON) aims to synthesize photorealistic images of a person wearing specified garments. Despite significant progress, building a universal VTON framework that can flexibly handle diverse and complex tasks remains a major challenge. Recent methods explore multi-task VTON frameworks guided by textual instructions, yet they still face two key limitations: (1) semantic gap between text instructions and reference images, and (2) data scarcity in complex scenarios. To address these challenges, we propose UniFit, a universal VTON framework driven by a Multimodal Large Language Model (MLLM). Specifically, we introduce an MLLM-Guided Semantic Alignment Module (MGSA), which integrates multimodal inputs using an MLLM and a set of learnable queries. By imposing a semantic alignment loss, MGSA captures cross-modal semantic relationships and provides coherent and explicit semantic guidance for the generative process, thereby reducing the semantic gap. Moreover, by devising a two-stage progressive training strategy with a self-synthesis pipeline, UniFit is able to learn complex tasks from limited data. Extensive experiments show that UniFit not only supports a wide range of VTON tasks, including multi-garment and model-to-model try-on, but also achieves state-of-the-art performance. The source code and pretrained models are available at https://github.com/zwplus/UniFit.

Paperid: 461, https://arxiv.org/pdf/2511.15830.pdf GitHub

Abstract:
Despite rapid progress in artificial intelligence, current systems struggle with the interconnected challenges that define real-world decision making. Practical domains, such as business management, require optimizing an open-ended and multi-faceted objective, actively learning environment dynamics from sparse experience, planning over long horizons in stochastic settings, and reasoning over spatial information. Yet existing human--AI benchmarks isolate subsets of these capabilities, limiting our ability to assess holistic decision-making competence. We introduce Mini Amusement Parks (MAPs), an amusement-park simulator designed to evaluate an agent's ability to model its environment, anticipate long-term consequences under uncertainty, and strategically operate a complex business. We provide human baselines and a comprehensive evaluation of state-of-the-art LLM agents, finding that humans outperform these systems by 6.5x on easy mode and 9.8x on medium mode. Our analysis reveals persistent weaknesses in long-horizon optimization, sample-efficient learning, spatial reasoning, and world modelling. By unifying these challenges within a single environment, MAPs offers a new foundation for benchmarking agents capable of adaptable decision making. Code: https://github.com/Skyfall-Research/MAPs

Paperid: 462, https://arxiv.org/pdf/2511.15819.pdf GitHub

Abstract:
The expression problem describes a fundamental tradeoff between two types of extensibility: extending a type with new operations, such as by pattern matching on an algebraic data type in functional programming, and extending a type with new constructors, such as by adding a new object implementing an interface in object-oriented programming. Most dependently typed languages have good support for the former style through inductive types, but support for the latter style through coinductive types is usually much poorer. Polarity is a language that treats both kinds of types symmetrically and allows the developer to switch between type representations.However, it currently lacks several features expected of a state-of-the-art dependently typed language, such as implicit arguments. The central aim of this paper is to provide an algorithmic type system and inference algorithm for implicit arguments that respect the core symmetry of the language. Our work provides two key contributions: a complete algorithmic description of the type system backing Polarity, and a comprehensive description of a unification algorithm that covers arbitrary inductive and coinductive types. We give rules for reduction semantics, conversion checking, and a unification algorithm for pattern-matching, which are essential for a usable implementation. A work-in-progress implementation of the algorithms in this paper is available at https://polarity-lang.github.io/. We expect that the comprehensive account of the unification algorithm and our design decisions can serve as a blueprint for other dependently typed languages that support inductive and coinductive types symmetrically.

Paperid: 463, https://arxiv.org/pdf/2511.15771.pdf GitHub

Abstract:
The Segment Anything Model 2 (SAM2) demonstrates remarkable universal segmentation capabilities on natural images. However, its performance on ultrasound images is significantly degraded due to domain disparities. This limitation raises two critical challenges: how to efficiently adapt SAM2 to ultrasound imaging while maintaining parameter efficiency, and how to deploy the adapted model effectively in resource-constrained clinical environments. To address these issues, we propose UniUltra for universal ultrasound segmentation. Specifically, we first introduce a novel context-edge hybrid adapter (CH-Adapter) that enhances fine-grained perception across diverse ultrasound imaging modalities while achieving parameter-efficient fine-tuning. To further improve clinical applicability, we develop a deep-supervised knowledge distillation (DSKD) technique that transfers knowledge from the large image encoder of the fine-tuned SAM2 to a super lightweight encoder, substantially reducing computational requirements without compromising performance. Extensive experiments demonstrate that UniUltra outperforms state-of-the-arts with superior generalization capabilities. Notably, our framework achieves competitive performance using only 8.91% of SAM2's parameters during fine-tuning, and the final compressed model reduces the parameter count by 94.08% compared to the original SAM2, making it highly suitable for practical clinical deployment. The source code is available at https://github.com/xq141839/UniUltra.

Paperid: 464, https://arxiv.org/pdf/2511.15735.pdf GitHub

Abstract:
We present LinApart2, a major update to the LinApart algorithm for univariate partial fraction decomposition. Unlike its predecessor, LinApart2 can handle denominators of arbitrary polynomial degree without explicit factorization, while retaining the efficiency and parallelizability of the Laurent series method. Benchmarks show substantial speedups in both runtime and memory usage compared to Mathematica's built-in routine Apart and to the Euclidean algorithm, enabling computations that were previously intractable.

Paperid: 465, https://arxiv.org/pdf/2511.15726.pdf GitHub

Abstract:
Reddit is in the minority of mainstream social platforms that permit posting content that may be considered to be at the edge of what is permissible, including so-called Not Safe For Work (NSFW) content. However, NSFW is becoming more common on mainstream platforms, with X now allowing such material. We examine the top 15 NSFW-restricted subreddits by size to explore the complexities of responsibly sharing adult content, aiming to balance ethical and legal considerations with monetization opportunities. We find that users often use NSFW subreddits as a social springboard, redirecting readers to private or specialized adult social platforms such as Telegram, Kik or OnlyFans for further interactions. They also directly negotiate image "trades" through credit cards or payment platforms such as PayPal, Bitcoin or Venmo. Disturbingly, we also find linguistic cues linked to non-consensual content sharing. To help platforms moderate such behavior, we trained a RoBERTa-based classification model, which outperforms GPT-4 and traditional classifiers such as logistic regression and random forest in identifying non-consensual content sharing, showing better performance in this specific task. The source code and model weights are publicly available at https://github.com/socsys/15NSFWsubreddits.

Paperid: 466, https://arxiv.org/pdf/2511.15706.pdf GitHub

Abstract:
Dense feature matching aims to estimate all correspondences between two images of a 3D scene and has recently been established as the gold-standard due to its high accuracy and robustness. However, existing dense matchers still fail or perform poorly for many hard real-world scenarios, and high-precision models are often slow, limiting their applicability. In this paper, we attack these weaknesses on a wide front through a series of systematic improvements that together yield a significantly better model. In particular, we construct a novel matching architecture and loss, which, combined with a curated diverse training distribution, enables our model to solve many complex matching tasks. We further make training faster through a decoupled two-stage matching-then-refinement pipeline, and at the same time, significantly reduce refinement memory usage through a custom CUDA kernel. Finally, we leverage the recent DINOv3 foundation model along with multiple other insights to make the model more robust and unbiased. In our extensive set of experiments we show that the resulting novel matcher sets a new state-of-the-art, being significantly more accurate than its predecessors. Code is available at https://github.com/Parskatt/romav2

Paperid: 467, https://arxiv.org/pdf/2511.15704.pdf GitHub

Abstract:
Egocentric videos are a valuable and scalable data source to learn manipulation policies. However, due to significant data heterogeneity, most existing approaches utilize human data for simple pre-training, which does not unlock its full potential. This paper first provides a scalable recipe for collecting and using egocentric data by categorizing human data into two categories: in-the-wild and on-task alongside with systematic analysis on how to use the data. We first curate a dataset, PHSD, which contains over 1,000 hours of diverse in-the-wild egocentric data and over 20 hours of on-task data directly aligned to the target manipulation tasks. This enables learning a large egocentric language-conditioned flow matching policy, Human0. With domain adaptation techniques, Human0 minimizes the gap between humans and humanoids. Empirically, we show Human0 achieves several novel properties from scaling human data, including language following of instructions from only human data, few-shot learning, and improved robustness using on-task data. Project website: https://xiongyicai.github.io/In-N-On/

Paperid: 468, https://arxiv.org/pdf/2511.15703.pdf GitHub

Abstract:
Abstract reasoning from minimal examples remains a core unsolved problem for frontier foundation models such as GPT-5 and Grok 4. These models still fail to infer structured transformation rules from a handful of examples, which is a key hallmark of human intelligence. The Abstraction and Reasoning Corpus for Artificial General Intelligence (ARC-AGI) provides a rigorous testbed for this capability, demanding conceptual rule induction and transfer to novel tasks. Most existing methods treat ARC-AGI as a purely textual reasoning task, overlooking the fact that humans rely heavily on visual abstraction when solving such puzzles. However, our pilot experiments reveal a paradox: naively rendering ARC-AGI grids as images degrades performance due to imprecise rule execution. This leads to our central hypothesis that vision and language possess complementary strengths across distinct reasoning stages: vision supports global pattern abstraction and verification, whereas language specializes in symbolic rule formulation and precise execution. Building on this insight, we introduce two synergistic strategies: (1) Vision-Language Synergy Reasoning (VLSR), which decomposes ARC-AGI into modality-aligned subtasks; and (2) Modality-Switch Self-Correction (MSSC), which leverages vision to verify text-based reasoning for intrinsic error correction. Extensive experiments demonstrate that our approach yields up to a 4.33\% improvement over text-only baselines across diverse flagship models and multiple ARC-AGI tasks. Our findings suggest that unifying visual abstraction with linguistic reasoning is a crucial step toward achieving generalizable, human-like intelligence in future foundation models. Source code is released at https://github.com/InternLM/ARC-VL.

Paperid: 469, https://arxiv.org/pdf/2511.15692.pdf GitHub

Abstract:
This paper introduces SS-MixNet, a lightweight and effective deep learning model for hyperspectral image (HSI) classification. The architecture integrates 3D convolutional layers for local spectral-spatial feature extraction with two parallel MLP-style mixer blocks that capture long-range dependencies in spectral and spatial dimensions. A depthwise convolution-based attention mechanism is employed to enhance discriminative capability with minimal computational overhead. The model is evaluated on the QUH-Tangdaowan and QUH-Qingyun datasets using only 1% of labeled data for training and validation. SS-MixNet achieves the highest performance among compared methods, including 2D-CNN, 3D-CNN, IP-SWIN, SimPoolFormer, and HybridKAN, reaching 95.68% and 93.86% overall accuracy on the Tangdaowan and Qingyun datasets, respectively. The results, supported by quantitative metrics and classification maps, confirm the model's effectiveness in delivering accurate and robust predictions with limited supervision. The code will be made publicly available at: https://github.com/mqalkhatib/SS-MixNet

Paperid: 470, https://arxiv.org/pdf/2511.15661.pdf GitHub

Abstract:
Reinforcement learning (RL) provides a principled framework for improving Vision-Language Models (VLMs) on complex reasoning tasks. However, existing RL approaches often rely on human-annotated labels or task-specific heuristics to define verifiable rewards, both of which are costly and difficult to scale. We introduce VisPlay, a self-evolving RL framework that enables VLMs to autonomously improve their reasoning abilities using large amounts of unlabeled image data. Starting from a single base VLM, VisPlay assigns the model into two interacting roles: an Image-Conditioned Questioner that formulates challenging yet answerable visual questions, and a Multimodal Reasoner that generates silver responses. These roles are jointly trained with Group Relative Policy Optimization (GRPO), which incorporates diversity and difficulty rewards to balance the complexity of generated questions with the quality of the silver answers. VisPlay scales efficiently across two model families. When trained on Qwen2.5-VL and MiMo-VL, VisPlay achieves consistent improvements in visual reasoning, compositional generalization, and hallucination reduction across eight benchmarks, including MM-Vet and MMMU, demonstrating a scalable path toward self-evolving multimodal intelligence. The project page is available at https://bruno686.github.io/VisPlay/

Paperid: 471, https://arxiv.org/pdf/2511.15600.pdf GitHub

Abstract:
Ultrasound offers a radiation-free, cost-effective solution for real-time visualization of spinal landmarks, paraspinal soft tissues and neurovascular structures, making it valuable for intraoperative guidance during spinal procedures. However, ultrasound suffers from inherent limitations in visualizing complete vertebral anatomy, in particular vertebral bodies, due to acoustic shadowing effects caused by bone. In this work, we present a novel multi-modal deep learning method for completing occluded anatomical structures in 3D ultrasound by leveraging complementary information from a single X-ray image. To enable training, we generate paired training data consisting of: (1) 2D lateral vertebral views that simulate X-ray scans, and (2) 3D partial vertebrae representations that mimic the limited visibility and occlusions encountered during ultrasound spine imaging. Our method integrates morphological information from both imaging modalities and demonstrates significant improvements in vertebral reconstruction (p < 0.001) compared to state of art in 3D ultrasound vertebral completion. We perform phantom studies as an initial step to future clinical translation, and achieve a more accurate, complete volumetric lumbar spine visualization overlayed on the ultrasound scan without the need for registration with preoperative modalities such as computed tomography. This demonstrates that integrating a single X-ray projection mitigates ultrasound's key limitation while preserving its strengths as the primary imaging modality. Code and data can be found at https://github.com/miruna20/US-X-Complete

Paperid: 472, https://arxiv.org/pdf/2511.15597.pdf GitHub

Abstract:
LiDAR place recognition plays a crucial role in SLAM, robot navigation, and autonomous driving. However, existing LiDAR place recognition methods often struggle to adapt to new environments without forgetting previously learned knowledge, a challenge widely known as catastrophic forgetting. To address this issue, we propose KDF+, a novel continual learning framework for LiDAR place recognition that extends the KDF paradigm with a loss-aware sampling strategy and a rehearsal enhancement mechanism. The proposed sampling strategy estimates the learning difficulty of each sample via its loss value and selects samples for replay according to their estimated difficulty. Harder samples, which tend to encode more discriminative information, are sampled with higher probability while maintaining distributional coverage across the dataset. In addition, the rehearsal enhancement mechanism encourages memory samples to be further refined during new-task training by slightly reducing their loss relative to previous tasks, thereby reinforcing long-term knowledge retention. Extensive experiments across multiple benchmarks demonstrate that KDF+ consistently outperforms existing continual learning methods and can be seamlessly integrated into state-of-the-art continual learning for LiDAR place recognition frameworks to yield significant and stable performance gains. The code will be available at https://github.com/repo/KDF-plus.

Paperid: 473, https://arxiv.org/pdf/2511.15574.pdf GitHub

Abstract:
Language acquisition is vital to revealing the nature of human language intelligence and has recently emerged as a promising perspective for improving the interpretability of large language models (LLMs). However, it is ethically and practically infeasible to conduct experiments that require controlling human learners' language inputs. This poses challenges for the verifiability and scalability of language acquisition modeling, particularly in Chinese second language acquisition (SLA). While LLMs provide a controllable and reproducible alternative, a systematic benchmark to support phase-wise modeling and assessment is still lacking. In this paper, we present HSKBenchmark, the first benchmark for staged modeling and writing assessment of LLMs in Chinese SLA. It covers HSK levels 3 to 6 and includes authentic textbooks with 6.76 million tokens, 16K synthetic instruction samples, 30 test topics, and a linguistically grounded evaluation system. To simulate human learning trajectories, we introduce a curriculum-tuning framework that trains models from beginner to advanced levels. An evaluation system is created to examine level-based grammar coverage, writing errors, lexical and syntactic complexity, and holistic scoring. We also build HSKAgent, fine-tuned on 10K learner compositions. Extensive experimental results demonstrate that HSKBenchmark not only models Chinese SLA effectively, but also serves as a reliable benchmark for dynamic writing assessment in LLMs. Our fine-tuned LLMs have writing performance on par with advanced human learners and exhibit human-like acquisition characteristics. The HSKBenchmark, HSKAgent, and checkpoints serve as foundational tools and resources, with the potential to pave the way for future research on language acquisition modeling and LLMs interpretability. Code and data are publicly available at: https://github.com/CharlesYang030/HSKB.

Paperid: 474, https://arxiv.org/pdf/2511.15567.pdf GitHub GitHub GitHub

Abstract:
Computer-Use Agents (CUA) are becoming increasingly capable of autonomously operating digital environments through Graphical User Interfaces (GUI). Yet, most GUI remain designed primarily for humans--prioritizing aesthetics and usability--forcing agents to adopt human-oriented behaviors that are unnecessary for efficient task execution. At the same time, rapid advances in coding-oriented language models (Coder) have transformed automatic GUI design. This raises a fundamental question: Can CUA as judges to assist Coder for automatic GUI design? To investigate, we introduce AUI-Gym, a benchmark for Automatic GUI development spanning 52 applications across diverse domains. Using language models, we synthesize 1560 tasks that simulate real-world scenarios. To ensure task reliability, we further develop a verifier that programmatically checks whether each task is executable within its environment. Building on this, we propose a Coder-CUA in Collaboration framework: the Coder acts as Designer, generating and revising websites, while the CUA serves as Judge, evaluating functionality and refining designs. Success is measured not by visual appearance, but by task solvability and CUA navigation success rate. To turn CUA feedback into usable guidance, we design a CUA Dashboard that compresses multi-step navigation histories into concise visual summaries, offering interpretable guidance for iterative redesign. By positioning agents as both designers and judges, our framework shifts interface design toward agent-native efficiency and reliability. Our work takes a step toward shifting agents from passive use toward active participation in digital environments. Our code and dataset are available at https://github.com/showlab/AUI.

Paperid: 475, https://arxiv.org/pdf/2511.15530.pdf GitHub

Abstract:
In multi-objective optimization, multiple loss terms are weighted and added together to form a single objective. These weights are chosen to properly balance the competing losses according to some meta-goal. For example, in physics-informed neural networks (PINNs), these weights are often adaptively chosen to improve the network's generalization error. A popular choice of adaptive weights is based on the neural tangent kernel (NTK) of the PINN, which describes the evolution of the network in predictor space during training. The convergence of such an adaptive weighting algorithm is not clear a priori. Moreover, these NTK-based weights would be updated frequently during training, further increasing the computational burden of the learning process. In this paper, we prove that under appropriate conditions, gradient descent enhanced with adaptive NTK-based weights is convergent in a suitable sense. We then address the problem of computational efficiency by developing a randomized algorithm inspired by a predictor-corrector approach and matrix sketching, which produces unbiased estimates of the NTK up to an arbitrarily small discretization error. Finally, we provide numerical experiments to support our theoretical findings and to show the efficacy of our randomized algorithm. Code Availability: https://github.com/maxhirsch/Efficient-NTK

Paperid: 476, https://arxiv.org/pdf/2511.15462.pdf GitHub

Abstract:
Peer review is a cornerstone of scientific publishing, including at premier machine learning conferences such as ICLR. As submission volumes increase, understanding the nature and dynamics of the review process is crucial for improving its efficiency, effectiveness, and the quality of published papers. We present a large-scale analysis of the ICLR 2024 and 2025 peer review processes, focusing on before- and after-rebuttal scores and reviewer-author interactions. We examine review scores, author-reviewer engagement, temporal patterns in review submissions, and co-reviewer influence effects. Combining quantitative analyses with LLM-based categorization of review texts and rebuttal discussions, we identify common strengths and weaknesses for each rating group, as well as trends in rebuttal strategies that are most strongly associated with score changes. Our findings show that initial scores and the ratings of co-reviewers are the strongest predictors of score changes during the rebuttal, pointing to a degree of reviewer influence. Rebuttals play a valuable role in improving outcomes for borderline papers, where thoughtful author responses can meaningfully shift reviewer perspectives. More broadly, our study offers evidence-based insights to improve the peer review process, guiding authors on effective rebuttal strategies and helping the community design fairer and more efficient review processes. Our code and score changes data are available at https://github.com/papercopilot/iclr-insights.

Paperid: 477, https://arxiv.org/pdf/2511.15433.pdf GitHub

Abstract:
Multimodal object detection has attracted significant attention in both academia and industry for its enhanced robustness. Although numerous studies have focused on improving modality fusion strategies, most neglect fusion degradation, and none provide a theoretical analysis of its underlying causes. To fill this gap, this paper presents a systematic theoretical investigation of fusion degradation in multimodal detection and identifies two key optimization deficiencies: (1) the gradients of unimodal branch backbones are severely suppressed under multimodal architectures, resulting in under-optimization of the unimodal branches; (2) disparities in modality quality cause weaker modalities to experience stronger gradient suppression, which in turn results in imbalanced modality learning. To address these issues, this paper proposes a Representation Space Constrained Learning with Modality Decoupling (RSC-MD) method, which consists of two modules. The RSC module and the MD module are designed to respectively amplify the suppressed gradients and eliminate inter-modality coupling interference as well as modality imbalance, thereby enabling the comprehensive optimization of each modality-specific backbone. Extensive experiments conducted on the FLIR, LLVIP, M3FD, and MFAD datasets demonstrate that the proposed method effectively alleviates fusion degradation and achieves state-of-the-art performance across multiple benchmarks. The code and training procedures will be released at https://github.com/yikangshao/RSC-MD.

Paperid: 478, https://arxiv.org/pdf/2511.15414.pdf GitHub

Abstract:
We investigate the sampling-based optimal path planning problem for robotics in complex and dynamic environments. Most existing sampling-based algorithms neglect environmental information or the information from previous samples. Yet, these pieces of information are highly informative, as leveraging them can provide better heuristics when sampling the next state. In this paper, we propose a novel sampling-based planning algorithm, called \emph{RRT*former}, which integrates the standard RRT* algorithm with a Transformer network in a novel way. Specifically, the Transformer is used to extract features from the environment and leverage information from previous samples to better guide the sampling process. Our extensive experiments demonstrate that, compared to existing sampling-based approaches such as RRT*, Neural RRT*, and their variants, our algorithm achieves considerable improvements in both the optimality of the path and sampling efficiency. The code for our implementation is available on https://github.com/fengmingyang666/RRTformer.

Paperid: 479, https://arxiv.org/pdf/2511.15406.pdf GitHub

Abstract:
Reliable semantic segmentation is essential for clinical decision making, yet deep models rarely provide explicit statistical guarantees on their errors. We introduce a simple post-hoc framework that constructs confidence masks with distribution-free, image-level control of false-positive predictions. Given any pretrained segmentation model, we define a nested family of shrunken masks obtained either by increasing the score threshold or by applying morphological erosion. A labeled calibration set is used to select a single shrink parameter via conformal prediction, ensuring that, for new images that are exchangeable with the calibration data, the proportion of false positives retained in the confidence mask stays below a user-specified tolerance with high probability. The method is model-agnostic, requires no retraining, and provides finite-sample guarantees regardless of the underlying predictor. Experiments on a polyp-segmentation benchmark demonstrate target-level empirical validity. Our framework enables practical, risk-aware segmentation in settings where over-segmentation can have clinical consequences. Code at https://github.com/deel-ai-papers/conseco.

Paperid: 480, https://arxiv.org/pdf/2511.15392.pdf GitHub

Abstract:
Recent advances in large language models (LLMs) have greatly improved their reasoning and decision-making abilities when deployed as agents. Richer reasoning, however, often comes at the cost of longer chain of thought (CoT), hampering interaction efficiency in real-world scenarios. Nevertheless, there still lacks systematic definition of LLM agent efficiency, hindering targeted improvements. To this end, we introduce dual-efficiency, comprising (i) step-level efficiency, which minimizes tokens per step, and (ii) trajectory-level efficiency, which minimizes the number of steps to complete a task. Building on this definition, we propose DEPO, a dual-efficiency preference optimization method that jointly rewards succinct responses and fewer action steps. Experiments on WebShop and BabyAI show that DEPO cuts token usage by up to 60.9% and steps by up to 26.9%, while achieving up to a 29.3% improvement in performance. DEPO also generalizes to three out-of-domain math benchmarks and retains its efficiency gains when trained on only 25% of the data. Our project page is at https://opencausalab.github.io/DEPO.

Paperid: 481, https://arxiv.org/pdf/2511.15369.pdf GitHub

Abstract:
Previous Quantization-Aware Training (QAT) methods for vision transformers rely on expensive retraining to recover accuracy loss in non-linear layer quantization, limiting their use in resource-constrained environments. In contrast, existing Post-Training Quantization (PTQ) methods either partially quantize non-linear functions or adjust activation distributions to maintain accuracy but fail to achieve fully integer-only inference. In this paper, we introduce IPTQ-ViT, a novel PTQ framework for fully integer-only vision transformers without retraining. We present approximation functions: a polynomial-based GELU optimized for vision data and a bit-shifting-based Softmax designed to improve approximation accuracy in PTQ. In addition, we propose a unified metric integrating quantization sensitivity, perturbation, and computational cost to select the optimal approximation function per activation layer. IPTQ-ViT outperforms previous PTQ methods, achieving up to 6.44\%p (avg. 1.78\%p) top-1 accuracy improvement for image classification, 1.0 mAP for object detection. IPTQ-ViT outperforms partial floating-point PTQ methods under W8A8 and W4A8, and achieves accuracy and latency comparable to integer-only QAT methods. We plan to release our code https://github.com/gihwan-kim/IPTQ-ViT.git.

Paperid: 482, https://arxiv.org/pdf/2511.15332.pdf GitHub

Abstract:
In high-dimensional statistics, the Lasso is a cornerstone method for simultaneous variable selection and parameter estimation. However, its reliance on the squared loss function renders it highly sensitive to outliers and heavy-tailed noise, potentially leading to unreliable model selection and biased estimates. To address this limitation, we introduce the Exponential Lasso, a novel robust method that integrates an exponential-type loss function within the Lasso framework. This loss function is designed to achieve a smooth trade-off between statistical efficiency under Gaussian noise and robustness against data contamination. Unlike other methods that cap the influence of large residuals, the exponential loss smoothly redescends, effectively downweighting the impact of extreme outliers while preserving near-quadratic behavior for small errors. We establish theoretical guarantees showing that the Exponential Lasso achieves strong statistical convergence rates, matching the classical Lasso under ideal conditions while maintaining its robustness in the presence of heavy-tailed contamination. Computationally, the estimator is optimized efficiently via a Majorization-Minimization (MM) algorithm that iteratively solves a series of weighted Lasso subproblems. Numerical experiments demonstrate that the proposed method is highly competitive, outperforming the classical Lasso in contaminated settings and maintaining strong performance even under Gaussian noise. Our method is implemented in the \texttt{R} package \texttt{heavylasso} available on Github: https://github.com/tienmt/heavylasso

Paperid: 483, https://arxiv.org/pdf/2511.15311.pdf GitHub

Abstract:
3D Vision-Language Foundation Models (VLFMs) have shown strong generalization and zero-shot recognition capabilities in open-world point cloud processing tasks. However, these models often underperform in practical scenarios where data are noisy, incomplete, or drawn from a different distribution than the training data. To address this, we propose Uni-Adapter, a novel training-free online test-time adaptation (TTA) strategy for 3D VLFMs based on dynamic prototype learning. We define a 3D cache to store class-specific cluster centers as prototypes, which are continuously updated to capture intra-class variability in heterogeneous data distributions. These dynamic prototypes serve as anchors for cache-based logit computation via similarity scoring. Simultaneously, a graph-based label smoothing module captures inter-prototype similarities to enforce label consistency among similar prototypes. Finally, we unify predictions from the original 3D VLFM and the refined 3D cache using entropy-weighted aggregation for reliable adaptation. Without retraining, Uni-Adapter effectively mitigates distribution shifts, achieving state-of-the-art performance on diverse 3D benchmarks over different 3D VLFMs, improving ModelNet-40C by 10.55%, ScanObjectNN-C by 8.26%, and ShapeNet-C by 4.49% over the source 3D VLFMs. Project page: https://mehran-tam.github.io/Uni-Adapter

Paperid: 484, https://arxiv.org/pdf/2511.15299.pdf GitHub

Abstract:
Training prohibited item detection models requires a large amount of X-ray security images, but collecting and annotating these images is time-consuming and laborious. To address data insufficiency, X-ray security image synthesis methods composite images to scale up datasets. However, previous methods primarily follow a two-stage pipeline, where they implement labor-intensive foreground extraction in the first stage and then composite images in the second stage. Such a pipeline introduces inevitable extra labor cost and is not efficient. In this paper, we propose a one-stage X-ray security image synthesis pipeline (Xsyn) based on text-to-image generation, which incorporates two effective strategies to improve the usability of synthetic images. The Cross-Attention Refinement (CAR) strategy leverages the cross-attention map from the diffusion model to refine the bounding box annotation. The Background Occlusion Modeling (BOM) strategy explicitly models background occlusion in the latent space to enhance imaging complexity. To the best of our knowledge, compared with previous methods, Xsyn is the first to achieve high-quality X-ray security image synthesis without extra labor cost. Experiments demonstrate that our method outperforms all previous methods with 1.2% mAP improvement, and the synthetic images generated by our method are beneficial to improve prohibited item detection performance across various X-ray security datasets and detectors. Code is available at https://github.com/pILLOW-1/Xsyn/.

Paperid: 485, https://arxiv.org/pdf/2511.15276.pdf GitHub

Abstract:
Test-Time Adaptation (TTA) adjusts models using unlabeled test data to handle dynamic distribution shifts. However, existing methods rely on frequent adaptation and high computational cost, making them unsuitable for resource-constrained edge environments. To address this, we propose SNAP, a sparse TTA framework that reduces adaptation frequency and data usage while preserving accuracy. SNAP maintains competitive accuracy even when adapting based on only 1% of the incoming data stream, demonstrating its robustness under infrequent updates. Our method introduces two key components: (i) Class and Domain Representative Memory (CnDRM), which identifies and stores a small set of samples that are representative of both class and domain characteristics to support efficient adaptation with limited data; and (ii) Inference-only Batch-aware Memory Normalization (IoBMN), which dynamically adjusts normalization statistics at inference time by leveraging these representative samples, enabling efficient alignment to shifting target domains. Integrated with five state-of-the-art TTA algorithms, SNAP reduces latency by up to 93.12%, while keeping the accuracy drop below 3.3%, even across adaptation rates ranging from 1% to 50%. This demonstrates its strong potential for practical use on edge devices serving latency-sensitive applications. The source code is available at https://github.com/chahh9808/SNAP.

Paperid: 486, https://arxiv.org/pdf/2511.15260.pdf GitHub

Abstract:
In this paper, we report the results of the TeamNRC's participation in the BHASHA-Task 1 Grammatical Error Correction shared task https://github.com/BHASHA-Workshop/IndicGEC2025/ for 5 Indian languages. Our approach, focusing on zero/few-shot prompting of language models of varying sizes (4B to large proprietary models) achieved a Rank 4 in Telugu and Rank 2 in Hindi with GLEU scores of 83.78 and 84.31 respectively. In this paper, we extend the experiments to the other three languages of the shared task - Tamil, Malayalam and Bangla, and take a closer look at the data quality and evaluation metric used. Our results primarily highlight the potential of small language models, and summarize the concerns related to creating good quality datasets and appropriate metrics for this task that are suitable for Indian language scripts.

Paperid: 487, https://arxiv.org/pdf/2511.15244.pdf GitHub

Abstract:
Million-level token inputs in long-context tasks pose significant computational and memory challenges for Large Language Models (LLMs). Recently, DeepSeek-OCR conducted research into the feasibility of Contexts Optical Compression and achieved preliminary results. Inspired by this, we introduce Context Cascade Compression C3 to explore the upper limits of text compression. Our method cascades two LLMs of different sizes to handle the compression and decoding tasks. Specifically, a small LLM, acting as the first stage, performs text compression by condensing a long context into a set of latent tokens (e.g., 32 or 64 in length), achieving a high ratio of text tokens to latent tokens. A large LLM, as the second stage, then executes the decoding task on this compressed context. Experiments show that at a 20x compression ratio (where the number of text tokens is 20 times the number of latent tokens), our model achieves 98% decoding accuracy, compared to approximately 60% for DeepSeek-OCR. When we further increase the compression ratio to 40x, the accuracy is maintained at around 93%. This indicates that in the domain of context compression, C3 Compression demonstrates superior performance and feasibility over optical character compression. C3 uses a simpler, pure-text pipeline that ignores factors like layout, color, and information loss from a visual encoder. This also suggests a potential upper bound for compression ratios in future work on optical character compression, OCR, and related fields. Codes and model weights are publicly accessible at https://github.com/liufanfanlff/C3-Context-Cascade-Compression

Paperid: 488, https://arxiv.org/pdf/2511.15239.pdf GitHub

Abstract:
We address the fundamental challenge of resolving symmetry-induced deadlocks in distributed multi-agent navigation by proposing a new hierarchical navigation method. When multiple agents interact, it is inherently difficult for them to autonomously break the symmetry of deciding how to pass each other. To tackle this problem, we introduce an approach that quantifies cooperative symmetry-breaking strategies using a topological invariant called the winding number, and learns the strategies themselves through reinforcement learning. Our method features a hierarchical policy consisting of a learning-based Planner, which plans topological cooperative strategies, and a model-based Controller, which executes them. Through reinforcement learning, the Planner learns to produce two types of parameters for the Controller: one is the topological cooperative strategy represented by winding numbers, and the other is a set of dynamic weights that determine which agent interaction to prioritize in dense scenarios where multiple agents cross simultaneously. The Controller then generates collision-free and efficient motions based on the strategy and weights provided by the Planner. This hierarchical structure combines the flexible decision-making ability of learning-based methods with the reliability of model-based approaches. Simulation and real-world robot experiments demonstrate that our method outperforms existing baselines, particularly in dense environments, by efficiently avoiding collisions and deadlocks while achieving superior navigation performance. The code for the experiments is available at https://github.com/omron-sinicx/WNumMPC.

Paperid: 489, https://arxiv.org/pdf/2511.15179.pdf GitHub

Abstract:
This paper proposes a novel metric for Human Motion Prediction (HMP). Since a single past sequence can lead to multiple possible futures, a probabilistic HMP method predicts such multiple motions. While a single motion predicted by a deterministic method is evaluated only with the difference from its ground truth motion, multiple predicted motions should also be evaluated based on their distribution. For this evaluation, this paper focuses on the following two criteria. \textbf{(a) Coverage}: motions should be distributed among multiple motion modes to cover diverse possibilities. \textbf{(b) Validity}: motions should be kinematically valid as future motions observable from a given past motion. However, existing metrics simply appreciate widely distributed motions even if these motions are observed in a single mode and kinematically invalid. To resolve these disadvantages, this paper proposes a Multimodality-aware Metric using Clustering-based Modes (MMCM). For (a) coverage, MMCM divides a motion space into several clusters, each of which is regarded as a mode. These modes are used to explicitly evaluate whether predicted motions are distributed among multiple modes. For (b) validity, MMCM identifies valid modes by collecting possible future motions from a motion dataset. Our experiments validate that our clustering yields sensible mode definitions and that MMCM accurately scores multimodal predictions. Code: https://github.com/placerkyo/MMCM

Paperid: 490, https://arxiv.org/pdf/2511.15153.pdf GitHub

Abstract:
Accurate, up-to-date High-Definition (HD) maps are critical for urban planning, infrastructure monitoring, and autonomous navigation. However, these maps quickly become outdated as environments evolve, creating a need for robust methods that not only detect changes but also incorporate them into updated 3D representations. While change detection techniques have advanced significantly, there remains a clear gap between detecting changes and actually updating 3D maps, particularly when relying on 2D image-based change detection. To address this gap, we introduce SceneEdited, the first city-scale dataset explicitly designed to support research on HD map maintenance through 3D point cloud updating. SceneEdited contains over 800 up-to-date scenes covering 73 km of driving and approximate 3 $\text{km}^2$ of urban area, with more than 23,000 synthesized object changes created both manually and automatically across 2000+ out-of-date versions, simulating realistic urban modifications such as missing roadside infrastructure, buildings, overpasses, and utility poles. Each scene includes calibrated RGB images, LiDAR scans, and detailed change masks for training and evaluation. We also provide baseline methods using a foundational image-based structure-from-motion pipeline for updating outdated scenes, as well as a comprehensive toolkit supporting scalability, trackability, and portability for future dataset expansion and unification of out-of-date object annotations. Both the dataset and the toolkit are publicly available at https://github.com/ChadLin9596/ScenePoint-ETK, establising a standardized benchmark for 3D map updating research.

Paperid: 491, https://arxiv.org/pdf/2511.15139.pdf GitHub

Abstract:
Spatial Transcriptomics enables mapping of gene expression within its native tissue context, but current platforms measure only a limited set of genes due to experimental constraints and excessive costs. To overcome this, computational models integrate Single-Cell RNA Sequencing data with Spatial Transcriptomics to predict unmeasured genes. We propose CASPER, a cross-attention based framework that predicts unmeasured gene expression in Spatial Transcriptomics by leveraging centroid-level representations from Single-Cell RNA Sequencing. We performed rigorous testing over four state-of-the-art Spatial Transcriptomics/Single-Cell RNA Sequencing dataset pairs across four existing baseline models. CASPER shows significant improvement in nine out of the twelve metrics for our experiments. This work paves the way for further work in Spatial Transcriptomics to Single-Cell RNA Sequencing modality translation. The code for CASPER is available at https://github.com/AI4Med-Lab/CASPER.

Paperid: 492, https://arxiv.org/pdf/2511.15131.pdf GitHub

Abstract:
We introduce CASTELLA, a human-annotated audio benchmark for the task of audio moment retrieval (AMR). Although AMR has various useful potential applications, there is still no established benchmark with real-world data. The early study of AMR trained the model with solely synthetic datasets. Moreover, the evaluation is based on annotated dataset of fewer than 100 samples. This resulted in less reliable reported performance. To ensure performance for applications in real-world environments, we present CASTELLA, a large-scale manually annotated AMR dataset. CASTELLA consists of 1,009, 213, and 640 audio recordings for train, valid, and test split, respectively, which is 24 times larger than the previous dataset. We also establish a baseline model for AMR using CASTELLA. Our experiments demonstrate that a model fine-tuned on CASTELLA after pre-training on the synthetic data outperformed a model trained solely on the synthetic data by 10.4 points in Recall1@0.7. CASTELLA is publicly available in https://h-munakata.github.io/CASTELLA-demo/.

Paperid: 493, https://arxiv.org/pdf/2511.15097.pdf GitHub

Abstract:
The AI trustworthiness crisis threatens to derail the artificial intelligence revolution, with regulatory barriers, security vulnerabilities, and accountability gaps preventing deployment in critical domains. Current AI systems operate on opaque data structures that lack the audit trails, provenance tracking, or explainability required by emerging regulations like the EU AI Act. We propose an artifact-centric AI agent paradigm where behavior is driven by persistent, verifiable data artifacts rather than ephemeral tasks, solving the trustworthiness problem at the data architecture level. Central to this approach is the Multimodal Artifact File Format (MAIF), an AI-native container embedding semantic representations, cryptographic provenance, and granular access controls. MAIF transforms data from passive storage into active trust enforcement, making every AI operation inherently auditable. Our production-ready implementation demonstrates ultra-high-speed streaming (2,720.7 MB/s), optimized video processing (1,342 MB/s), and enterprise-grade security. Novel algorithms for cross-modal attention, semantic compression, and cryptographic binding achieve up to 225 compression while maintaining semantic fidelity. Advanced security features include stream-level access control, real-time tamper detection, and behavioral anomaly analysis with minimal overhead. This approach directly addresses the regulatory, security, and accountability challenges preventing AI deployment in sensitive domains, offering a viable path toward trustworthy AI systems at scale.

Paperid: 494, https://arxiv.org/pdf/2511.15061.pdf GitHub

Abstract:
Genomic question answering often requires complex reasoning and integration across diverse biomedical sources. GeneGPT addressed this challenge by combining domain-specific APIs with OpenAI's code-davinci-002 large language model to enable natural language interaction with genomic databases. However, its reliance on a proprietary model limits scalability, increases operational costs, and raises concerns about data privacy and generalization. In this work, we revisit and reproduce GeneGPT in a pilot study using open source models, including Llama 3.1, Qwen2.5, and Qwen2.5 Coder, within a monolithic architecture; this allows us to identify the limitations of this approach. Building on this foundation, we then develop OpenBioLLM, a modular multi-agent framework that extends GeneGPT by introducing agent specialization for tool routing, query generation, and response validation. This enables coordinated reasoning and role-based task execution. OpenBioLLM matches or outperforms GeneGPT on over 90% of the benchmark tasks, achieving average scores of 0.849 on Gene-Turing and 0.830 on GeneHop, while using smaller open-source models without additional fine-tuning or tool-specific pretraining. OpenBioLLM's modular multi-agent design reduces latency by 40-50% across benchmark tasks, significantly improving efficiency without compromising model capability. The results of our comprehensive evaluation highlight the potential of open-source multi-agent systems for genomic question answering. Code and resources are available at https://github.com/ielab/OpenBioLLM.

Paperid: 495, https://arxiv.org/pdf/2511.15059.pdf GitHub

Abstract:
Multimodal Large Language Models (MLLMs) have seen rapid advances in recent years and are now being applied to visual document understanding tasks. They are expected to process a wide range of document images across languages, including Japanese. Understanding documents from images requires models to read what are written in them. Since some Japanese documents are written vertically, support for vertical writing is essential. However, research specifically focused on vertically written Japanese text remains limited. In this study, we evaluate the reading capability of existing MLLMs on vertically written Japanese text. First, we generate a synthetic Japanese OCR dataset by rendering Japanese texts into images, and use it for both model fine-tuning and evaluation. This dataset includes Japanese text in both horizontal and vertical writing. We also create an evaluation dataset sourced from the real-world document images containing vertically written Japanese text. Using these datasets, we demonstrate that the existing MLLMs perform worse on vertically written Japanese text than on horizontally written Japanese text. Furthermore, we show that training MLLMs on our synthesized Japanese OCR dataset results in improving the performance of models that previously could not handle vertical writing. The datasets and code are publicly available https://github.com/llm-jp/eval_vertical_ja.

Paperid: 496, https://arxiv.org/pdf/2511.15016.pdf GitHub

Abstract:
Lifelong person Re-IDentification (LReID) aims to match the same person employing continuously collected individual data from different scenarios. To achieve continuous all-day person matching across day and night, Visible-Infrared Lifelong person Re-IDentification (VI-LReID) focuses on sequential training on data from visible and infrared modalities and pursues average performance over all data. To this end, existing methods typically exploit cross-modal knowledge distillation to alleviate the catastrophic forgetting of old knowledge. However, these methods ignore the mutual interference of modality-specific knowledge acquisition and modality-common knowledge anti-forgetting, where conflicting knowledge leads to collaborative forgetting. To address the above problems, this paper proposes a Cross-modality Knowledge Disentanglement and Alignment method, called CKDA, which explicitly separates and preserves modality-specific knowledge and modality-common knowledge in a balanced way. Specifically, a Modality-Common Prompting (MCP) module and a Modality-Specific Prompting (MSP) module are proposed to explicitly disentangle and purify discriminative information that coexists and is specific to different modalities, avoiding the mutual interference between both knowledge. In addition, a Cross-modal Knowledge Alignment (CKA) module is designed to further align the disentangled new knowledge with the old one in two mutually independent inter- and intra-modality feature spaces based on dual-modality prototypes in a balanced manner. Extensive experiments on four benchmark datasets verify the effectiveness and superiority of our CKDA against state-of-the-art methods. The source code of this paper is available at https://github.com/PKU-ICST-MIPL/CKDA-AAAI2026.

Paperid: 497, https://arxiv.org/pdf/2511.14981.pdf GitHub

Abstract:
Knowledge distillation (KD) methods can transfer knowledge of a parameter-heavy teacher model to a light-weight student model. The status quo for feature KD methods is to utilize loss functions based on logits (i.e., pre-softmax class scores) and intermediate layer features (i.e., latent representations). Unlike previous approaches, we propose a feature KD framework for training the student's backbone using feature-based losses exclusively (i.e., without logit-based losses such as cross entropy). Leveraging recent discoveries about the geometry of latent representations, we introduce a knowledge quality metric for identifying which teacher layers provide the most effective knowledge for distillation. Experiments on three image classification datasets with four diverse student-teacher pairs, spanning convolutional neural networks and vision transformers, demonstrate our KD method achieves state-of-the-art performance, delivering top-1 accuracy boosts of up to 15% over standard approaches. We publically share our code to facilitate future work at https://github.com/Thegolfingocto/KD_wo_CE.

Paperid: 498, https://arxiv.org/pdf/2511.14955.pdf GitHub

Abstract:
The number of n-gram features grows exponentially in n, making it computationally demanding to compute the most frequent n-grams even for n as small as 3. Motivated by our production machine learning system built on n-gram features, we ask: is it possible to accurately, deterministically, and quickly recover the top-k most frequent n-grams? We devise a multi-pass algorithm called Intergrams that constructs candidate n-grams from the preceding (n - 1)-grams. By designing this algorithm with hardware in mind, our approach yields more than an order of magnitude speedup (up to 33x!) over the next known fastest algorithm, even when similar optimizations are applied to the other algorithm. Using the empirical power-law distribution over n-grams, we also provide theory to inform the efficacy of our multi-pass approach. Our code is available at https://github.com/rcurtin/Intergrams.

Paperid: 499, https://arxiv.org/pdf/2511.14907.pdf GitHub

Abstract:
Computational pathology holds substantial promise for improving diagnosis and guiding treatment decisions. Recent pathology foundation models enable the extraction of rich patch-level representations from large-scale whole-slide images (WSIs), but current approaches for aggregating these features into slide-level predictions remain constrained by design limitations that hinder generalizability and reliability. Here, we developed nnMIL, a simple yet broadly applicable multiple-instance learning framework that connects patch-level foundation models to robust slide-level clinical inference. nnMIL introduces random sampling at both the patch and feature levels, enabling large-batch optimization, task-aware sampling strategies, and efficient and scalable training across datasets and model architectures. A lightweight aggregator performs sliding-window inference to generate ensemble slide-level predictions and supports principled uncertainty estimation. Across 40,000 WSIs encompassing 35 clinical tasks and four pathology foundation models, nnMIL consistently outperformed existing MIL methods for disease diagnosis, histologic subtyping, molecular biomarker detection, and pan- cancer prognosis prediction. It further demonstrated strong cross-model generalization, reliable uncertainty quantification, and robust survival stratification in multiple external cohorts. In conclusion, nnMIL offers a practical and generalizable solution for translating pathology foundation models into clinically meaningful predictions, advancing the development and deployment of reliable AI systems in real-world settings.

Paperid: 500, https://arxiv.org/pdf/2511.14901.pdf GitHub

Abstract:
As CLIP's global alignment limits its ability to capture fine-grained details, recent efforts have focused on enhancing its region-text alignment. However, current remote sensing (RS)-specific CLIP variants still inherit this limited spatial awareness. We identify two key limitations behind this: (1) current RS image-text datasets generate global captions from object-level labels, leaving the original object-level supervision underutilized; (2) despite the success of region-text alignment methods in general domain, their direct application to RS data often leads to performance degradation. To address these, we construct the first multi-granularity RS image-text dataset, MGRS-200k, featuring rich object-level textual supervision for RS region-category alignment. We further investigate existing fine-grained CLIP tuning strategies and find that current explicit region-text alignment methods, whether in a direct or indirect way, underperform due to severe degradation of CLIP's semantic coherence. Building on these, we propose FarSLIP, a Fine-grained Aligned RS Language-Image Pretraining framework. Rather than the commonly used patch-to-CLS self-distillation, FarSLIP employs patch-to-patch distillation to align local and global visual cues, which improves feature discriminability while preserving semantic coherence. Additionally, to effectively utilize region-text supervision, it employs simple CLS token-based region-category alignment rather than explicit patch-level alignment, further enhancing spatial awareness. FarSLIP features improved fine-grained vision-language alignment in RS domain and sets a new state of the art not only on RS open-vocabulary semantic segmentation, but also on image-level tasks such as zero-shot classification and image-text retrieval. Our dataset, code, and models are available at https://github.com/NJU-LHRS/FarSLIP.

Paperid: 501, https://arxiv.org/pdf/2511.14870.pdf GitHub

Abstract:
This paper presents a novel geometric representation for CAD Boundary Representation (B-Rep) based on volumetric distance functions, dubbed B-Rep Distance Functions (BR-DF). BR-DF encodes the surface mesh geometry of a CAD model as signed distance function (SDF). B-Rep vertices, edges, faces and their topology information are encoded as per-face unsigned distance functions (UDFs). An extension of the Marching Cubes algorithm converts BR-DF directly into watertight CAD B-Rep model (strictly speaking a faceted B-Rep model). A surprising characteristic of BR-DF is that this conversion process never fails. Leveraging the volumetric nature of BR-DF, we propose a multi-branch latent diffusion with 3D U-Net backbone for jointly generating the SDF and per-face UDFs of a BR-DF model. Our approach achieves comparable CAD generation performance against SOTA methods while reaching the unprecedented 100% success rate in producing (faceted) B-Rep models.

Paperid: 502, https://arxiv.org/pdf/2511.14860.pdf GitHub

Abstract:
Accurate identification and segmentation of dental caries in panoramic radiographs are critical for early diagnosis and effective treatment planning. Automated segmentation remains challenging due to low lesion contrast, morphological variability, and limited annotated data. In this study, we present the first comprehensive benchmarking of convolutional neural networks, vision transformers and state-space mamba architectures for automated dental caries segmentation on panoramic radiographs through a DC1000 dataset. Twelve state-of-the-art architectures, including VMUnet, MambaUNet, VMUNetv2, RMAMamba-S, TransNetR, PVTFormer, DoubleU-Net, and ResUNet++, were trained under identical configurations. Results reveal that, contrary to the growing trend toward complex attention based architectures, the CNN-based DoubleU-Net achieved the highest dice coefficient of 0.7345, mIoU of 0.5978, and precision of 0.8145, outperforming all transformer and Mamba variants. In the study, the top 3 results across all performance metrics were achieved by CNN-based architectures. Here, Mamba and transformer-based methods, despite their theoretical advantage in global context modeling, underperformed due to limited data and weaker spatial priors. These findings underscore the importance of architecture-task alignment in domain-specific medical image segmentation more than model complexity. Our code is available at: https://github.com/JunZengz/dental-caries-segmentation.

Paperid: 503, https://arxiv.org/pdf/2511.14778.pdf GitHub

Abstract:
We take two key steps in automating the open-ended discovery of new mathematical theories, a grand challenge in artificial intelligence. First, we introduce $\emph{FERMAT}$, a reinforcement learning (RL) environment that models concept discovery and theorem-proving using a set of symbolic actions, opening up a range of RL problems relevant to theory discovery. Second, we explore a specific problem through $\emph{FERMAT}$: automatically scoring the $\emph{interestingness}$ of mathematical objects. We investigate evolutionary algorithms for synthesizing nontrivial interestingness measures. In particular, we introduce an LLM-based evolutionary algorithm that features function abstraction, leading to notable improvements in discovering elementary number theory and finite fields over hard-coded baselines. We open-source the $\emph{FERMAT}$ environment at this URL(https://github.com/trishullab/Fermat).

Paperid: 504, https://arxiv.org/pdf/2511.14761.pdf GitHub

Abstract:
The Abstraction and Reasoning Corpus (ARC) is designed to promote research on abstract reasoning, a fundamental aspect of human intelligence. Common approaches to ARC treat it as a language-oriented problem, addressed by large language models (LLMs) or recurrent reasoning models. However, although the puzzle-like tasks in ARC are inherently visual, existing research has rarely approached the problem from a vision-centric perspective. In this work, we formulate ARC within a vision paradigm, framing it as an image-to-image translation problem. To incorporate visual priors, we represent the inputs on a "canvas" that can be processed like natural images. It is then natural for us to apply standard vision architectures, such as a vanilla Vision Transformer (ViT), to perform image-to-image mapping. Our model is trained from scratch solely on ARC data and generalizes to unseen tasks through test-time training. Our framework, termed Vision ARC (VARC), achieves 60.4% accuracy on the ARC-1 benchmark, substantially outperforming existing methods that are also trained from scratch. Our results are competitive with those of leading LLMs and close the gap to average human performance.

Paperid: 505, https://arxiv.org/pdf/2511.14719.pdf GitHub

Abstract:
We propose an approach to enhancing synthetic video realism, which can re-render synthetic videos from a simulator in photorealistic fashion. Our realism enhancement approach is a zero-shot framework that focuses on preserving the multi-level structures from synthetic videos into the enhanced one in both spatial and temporal domains, built upon a diffusion video foundational model without further fine-tuning. Specifically, we incorporate an effective modification to have the generation/denoising process conditioned on estimated structure-aware information from the synthetic video, such as depth maps, semantic maps, and edge maps, by an auxiliary model, rather than extracting the information from a simulator. This guidance ensures that the enhanced videos are consistent with the original synthetic video at both the structural and semantic levels. Our approach is a simple yet general and powerful approach to enhancing synthetic video realism: we show that our approach outperforms existing baselines in structural consistency with the original video while maintaining state-of-the-art photorealism quality in our experiments.

Paperid: 506, https://arxiv.org/pdf/2511.14715.pdf GitHub

Abstract:
Federated learning (FL) enables collaborative model training while preserving data privacy. However, it remains vulnerable to malicious clients who compromise model integrity through Byzantine attacks, data poisoning, or adaptive adversarial behaviors. Existing defense mechanisms rely on static thresholds and binary classification, failing to adapt to evolving client behaviors in real-world deployments. We propose FLARE, an adaptive reputation-based framework that transforms client reliability assessment from binary decisions to a continuous, multi-dimensional trust evaluation. FLARE integrates: (i) a multi-dimensional reputation score capturing performance consistency, statistical anomaly indicators, and temporal behavior, (ii) a self-calibrating adaptive threshold mechanism that adjusts security strictness based on model convergence and recent attack intensity, (iii) reputation-weighted aggregation with soft exclusion to proportionally limit suspicious contributions rather than eliminating clients outright, and (iv) a Local Differential Privacy (LDP) mechanism enabling reputation scoring on privatized client updates. We further introduce a highly evasive Statistical Mimicry (SM) attack, a benchmark adversary that blends honest gradients with synthetic perturbations and persistent drift to remain undetected by traditional filters. Extensive experiments with 100 clients on MNIST, CIFAR-10, and SVHN demonstrate that FLARE maintains high model accuracy and converges faster than state-of-the-art Byzantine-robust methods under diverse attack types, including label flipping, gradient scaling, adaptive attacks, ALIE, and SM. FLARE improves robustness by up to 16% and preserves model convergence within 30% of the non-attacked baseline, while achieving strong malicious-client detection performance with minimal computational overhead. https://github.com/Anonymous0-0paper/FLARE

Paperid: 507, https://arxiv.org/pdf/2511.14712.pdf GitHub

Abstract:
The quadratic time and memory complexity of the attention mechanism in modern Transformer based video generators makes end-to-end training for ultra high resolution videos prohibitively expensive. Motivated by this limitation, we introduce a training-free approach that leverages video Diffusion Transformers pretrained at their native scale to synthesize higher resolution videos without any additional training or adaptation. At the core of our method lies an inward sliding window attention mechanism, which originates from a key observation: maintaining each query token's training scale receptive field is crucial for preserving visual fidelity and detail. However, naive local window attention, unfortunately, often leads to repetitive content and exhibits a lack of global coherence in the generated results. To overcome this challenge, we devise a dual-path pipeline that backs up window attention with a novel cross-attention override strategy, enabling the semantic content produced by local attention to be guided by another branch with a full receptive field and, therefore, ensuring holistic consistency. Furthermore, to improve efficiency, we incorporate a cross-attention caching strategy for this branch to avoid the frequent computation of full 3D attention. Extensive experiments demonstrate that our method delivers ultra-high-resolution videos with fine-grained visual details and high efficiency in a training-free paradigm. Meanwhile, it achieves superior performance on VBench, even compared to training-based alternatives, with competitive or improved efficiency. Codes are available at: https://github.com/WillWu111/FreeSwim

Paperid: 508, https://arxiv.org/pdf/2511.14693.pdf GitHub

Abstract:
Existing approaches to complaint analysis largely rely on unimodal, short-form content such as tweets or product reviews. This work advances the field by leveraging multimodal, multi-turn customer support dialogues, where users often share both textual complaints and visual evidence (e.g., screenshots, product photos) to enable fine-grained classification of complaint aspects and severity. We introduce VALOR, a Validation-Aware Learner with Expert Routing, tailored for this multimodal setting. It employs a multi-expert reasoning setup using large-scale generative models with Chain-of-Thought (CoT) prompting for nuanced decision-making. To ensure coherence between modalities, a semantic alignment score is computed and integrated into the final classification through a meta-fusion strategy. In alignment with the United Nations Sustainable Development Goals (UN SDGs), the proposed framework supports SDG 9 (Industry, Innovation and Infrastructure) by advancing AI-driven tools for robust, scalable, and context-aware service infrastructure. Further, by enabling structured analysis of complaint narratives and visual context, it contributes to SDG 12 (Responsible Consumption and Production) by promoting more responsive product design and improved accountability in consumer services. We evaluate VALOR on a curated multimodal complaint dataset annotated with fine-grained aspect and severity labels, showing that it consistently outperforms baseline models, especially in complex complaint scenarios where information is distributed across text and images. This study underscores the value of multimodal interaction and expert validation in practical complaint understanding systems. Resources related to data and codes are available here: https://github.com/sarmistha-D/VALOR

Paperid: 509, https://arxiv.org/pdf/2511.14684.pdf GitHub

Abstract:
Large language models (LLMs) often make reasoning errors when solving mathematical problems, and how to automatically detect and correct these errors has become an important research direction. However, existing approaches \textit{mainly focus on self-correction within the model}, which falls short of the ``teacher-style`` correction required in educational settings, \textit{i.e.}, systematically guiding and revising a student's problem-solving process. To address this gap, we propose \texttt{SMRC} (\textit{\underline{S}tudent \underline{M}athematical \underline{R}easoning \underline{C}orrection}), a novel method that aligns LLMs with student reasoning. Specifically, \texttt{SMRC} formulates student reasoning as a multi-step sequential decision problem and introduces Monte Carlo Tree Search (MCTS) to explore optimal correction paths. To reduce the cost of the annotating process-level rewards, we leverage breadth-first search (BFS) guided by LLMs and final-answer evaluation to generate reward signals, which are then distributed across intermediate reasoning steps via a back-propagation mechanism, enabling fine-grained process supervision. Additionally, we construct a benchmark for high school mathematics, MSEB (Multi-Solution Error Benchmark), consisting of 158 instances that include problem statements, student solutions, and correct reasoning steps. We further propose a dual evaluation protocol centered on \textbf{solution accuracy} and \textbf{correct-step retention}, offering a comprehensive measure of educational applicability. Experiments demonstrate that \texttt{SMRC} significantly outperforms existing methods on two public datasets (ProcessBench and MR-GSM8K) and our MSEB in terms of effectiveness and overall performance. The code and data are available at https://github.com/Mind-Lab-ECNU/SMRC.

Paperid: 510, https://arxiv.org/pdf/2511.14659.pdf GitHub

Abstract:
Vision--language--action (VLA) models have recently shown promising performance on a variety of embodied tasks, yet they still fall short in reliability and generalization, especially when deployed across different embodiments or real-world environments. In this work, we introduce NORA-1.5, a VLA model built from the pre-trained NORA backbone by adding to it a flow-matching-based action expert. This architectural enhancement alone yields substantial performance gains, enabling NORA-1.5 to outperform NORA and several state-of-the-art VLA models across both simulated and real-world benchmarks. To further improve robustness and task success, we develop a set of reward models for post-training VLA policies. Our rewards combine (i) an action-conditioned world model (WM) that evaluates whether generated actions lead toward the desired goal, and (ii) a deviation-from-ground-truth heuristic that distinguishes good actions from poor ones. Using these reward signals, we construct preference datasets and adapt NORA-1.5 to target embodiments through direct preference optimization (DPO). Extensive evaluations show that reward-driven post-training consistently improves performance in both simulation and real-robot settings, demonstrating significant VLA model-reliability gains through simple yet effective reward models. Our findings highlight NORA-1.5 and reward-guided post-training as a viable path toward more dependable embodied agents suitable for real-world deployment.

Paperid: 511, https://arxiv.org/pdf/2511.14650.pdf GitHub

Abstract:
Large Language Model (LLM) agents have emerged as powerful tools for automating complex tasks by leveraging the reasoning and decision-making abilities of LLMs. However, a major bottleneck in current agent frameworks lies in the high inference cost of tool selection, especially in approaches like ReAct that repeatedly invoke the LLM to determine which tool to use at each step. In this work, we propose AutoTool, a novel graph-based framework that bypasses repeated LLM inference by exploiting a key empirical observation: tool usage inertia - the tendency of tool invocations to follow predictable sequential patterns. AutoTool constructs a directed graph from historical agent trajectories, where nodes represent tools and edges capture transition probabilities, effectively modeling the inertia in tool selection. It further integrates parameter-level information to refine tool input generation. By traversing this structured representation, AutoTool efficiently selects tools and their parameters with minimal reliance on LLM inference. Extensive experiments across diverse agent tasks demonstrate that AutoTool reduces inference costs by up to 30% while maintaining competitive task completion rates, offering a practical and scalable enhancement for inference-heavy frameworks. Our work highlights the promise of integrating statistical structure into LLM agent design for greater efficiency without sacrificing performance.

Paperid: 512, https://arxiv.org/pdf/2511.14639.pdf GitHub

Abstract:
Computational cytology faces two major challenges: i) instance-level labels are unreliable and prohibitively costly to obtain, ii) witness rates are extremely low. We propose SLAM-AGS, a Slide-Label-Aware Multitask pretraining framework that jointly optimizes (i) a weakly supervised similarity objective on slide-negative patches and (ii) a self-supervised contrastive objective on slide-positive patches, yielding stronger performance on downstream tasks. To stabilize learning, we apply Adaptive Gradient Surgery to tackle conflicting task gradients and prevent model collapse. We integrate the pretrained encoder into an attention-based Multiple Instance Learning aggregator for bag-level prediction and attention-guided retrieval of the most abnormal instances in a bag. On a publicly available bone-marrow cytology dataset, with simulated witness rates from 10% down to 0.5%, SLAM-AGS improves bag-level F1-Score and Top 400 positive cell retrieval over other pretraining methods, with the largest gains at low witness rates, showing that resolving gradient interference enables stable pretraining and better performance on downstream tasks. To facilitate reproducibility, we share our complete implementation and evaluation framework as open source: https://github.com/Ace95/SLAM-AGS.

Paperid: 513, https://arxiv.org/pdf/2511.14633.pdf GitHub

Abstract:
Recent advances in optimizing Gaussian Splatting for scene geometry have enabled efficient reconstruction of detailed surfaces from images. However, when input views are sparse, such optimization is prone to overfitting, leading to suboptimal reconstruction quality. Existing approaches address this challenge by employing flattened Gaussian primitives to better fit surface geometry, combined with depth regularization to alleviate geometric ambiguities under limited viewpoints. Nevertheless, the increased anisotropy inherent in flattened Gaussians exacerbates overfitting in sparse-view scenarios, hindering accurate surface fitting and degrading novel view synthesis performance. In this paper, we propose \net{}, a method that reconstructs more accurate and detailed surfaces while preserving high-quality novel view rendering. Our key insight is to introduce Stereo Geometry-Texture Alignment, which bridges rendering quality and geometry estimation, thereby jointly enhancing both surface reconstruction and view synthesis. In addition, we present a Pseudo-Feature Enhanced Geometry Consistency that enforces multi-view geometric consistency by incorporating both training and unseen views, effectively mitigating overfitting caused by sparse supervision. Extensive experiments on the DTU, BlendedMVS, and Mip-NeRF360 datasets demonstrate that our method achieves the state-of-the-art performance.

Paperid: 514, https://arxiv.org/pdf/2511.14631.pdf GitHub

Abstract:
We show that multi-agent systems guided by vision-language models (VLMs) improve end-to-end autonomous scientific discovery. By treating plots as verifiable checkpoints, a VLM-as-a-judge evaluates figures against dynamically generated domain-specific rubrics, enabling agents to correct their own errors and steer exploratory data analysis in real-time. Case studies in cosmology and astrochemistry demonstrate recovery from faulty reasoning paths and adaptation to new datasets without human intervention. On a 10-task benchmark for data-driven discovery, VLM-augmented systems achieve pass at 1 scores of 0.7-0.8, compared to 0.2-0.3 for code-only and 0.4-0.5 for code-and-text baselines, while also providing auditable reasoning traces that improve interpretability. Code available here: https://github.com/CMBAgents/cmbagent

Paperid: 515, https://arxiv.org/pdf/2511.14630.pdf GitHub

Abstract:
Scientific idea generation and selection requires exploration following a target probability distribution. In contrast, current AI benchmarks have objectively correct answers, and training large language models (LLMs) via reinforcement learning against these benchmarks discourages probabilistic exploration. Here, we conducted systematic experiments requesting LLMs to produce outputs following simple probabilistic distributions, and found that all modern LLMs tested grossly fail to follow the distributions. For example, requesting a binary output of "1" 49% of the time produces an answer of "0" nearly 100% of the time. This step function-like behavior of near-exclusively generating the output with marginally highest probability even overrules even strong in-built LLM biases.

Paperid: 516, https://arxiv.org/pdf/2511.14582.pdf GitHub

Abstract:
Omnimodal large language models (OmniLLMs) have attracted increasing research attention of late towards unified audio-video understanding, wherein processing audio-video token sequences creates a significant computational bottleneck, however. Existing token compression methods have yet to accommodate this emerging need of jointly compressing multimodal tokens. To bridge this gap, we present OmniZip, a training-free, audio-guided audio-visual token-compression framework that optimizes multimodal token representation and accelerates inference. Specifically, OmniZip first identifies salient audio tokens, then computes an audio retention score for each time group to capture information density, thereby dynamically guiding video token pruning and preserving cues from audio anchors enhanced by cross-modal similarity. For each time window, OmniZip compresses the video tokens using an interleaved spatio-temporal scheme. Extensive empirical results demonstrate the merits of OmniZip - it achieves 3.42X inference speedup and 1.4X memory reduction over other top-performing counterparts, while maintaining performance with no training.

Paperid: 517, https://arxiv.org/pdf/2511.14565.pdf GitHub GitHub

Abstract:
Robots can adapt to user preferences by learning reward functions from demonstrations, but with limited data, reward models often overfit to spurious correlations and fail to generalize. This happens because demonstrations show robots how to do a task but not what matters for that task, causing the model to focus on irrelevant state details. Natural language can more directly specify what the robot should focus on, and, in principle, disambiguate between many reward functions consistent with the demonstrations. However, existing language-conditioned reward learning methods typically treat instructions as simple conditioning signals, without fully exploiting their potential to resolve ambiguity. Moreover, real instructions are often ambiguous themselves, so naive conditioning is unreliable. Our key insight is that these two input types carry complementary information: demonstrations show how to act, while language specifies what is important. We propose Masked Inverse Reinforcement Learning (Masked IRL), a framework that uses large language models (LLMs) to combine the strengths of both input types. Masked IRL infers state-relevance masks from language instructions and enforces invariance to irrelevant state components. When instructions are ambiguous, it uses LLM reasoning to clarify them in the context of the demonstrations. In simulation and on a real robot, Masked IRL outperforms prior language-conditioned IRL methods by up to 15% while using up to 4.7 times less data, demonstrating improved sample-efficiency, generalization, and robustness to ambiguous language. Project page: https://MIT-CLEAR-Lab.github.io/Masked-IRL and Code: https://github.com/MIT-CLEAR-Lab/Masked-IRL

Paperid: 518, https://arxiv.org/pdf/2511.14521.pdf GitHub

Abstract:
Underwater image restoration and enhancement are crucial for correcting color distortion and restoring image details, thereby establishing a fundamental basis for subsequent underwater visual tasks. However, current deep learning methodologies in this area are frequently constrained by the scarcity of high-quality paired datasets. Since it is difficult to obtain pristine reference labels in underwater scenes, existing benchmarks often rely on manually selected results from enhancement algorithms, providing debatable reference images that lack globally consistent color and authentic supervision. This limits the model's capabilities in color restoration, image enhancement, and generalization. To overcome this limitation, we propose using in-air natural images as unambiguous reference targets and translating them into underwater-degraded versions, thereby constructing synthetic datasets that provide authentic supervision signals for model learning. Specifically, we establish a generative data framework based on unpaired image-to-image translation, producing a large-scale dataset that covers 6 representative underwater degradation types. The framework constructs synthetic datasets with precise ground-truth labels, which facilitate the learning of an accurate mapping from degraded underwater images to their pristine scene appearances. Extensive quantitative and qualitative experiments across 6 representative network architectures and 3 independent test sets show that models trained on our synthetic data achieve comparable or superior color restoration and generalization performance to those trained on existing benchmarks. This research provides a reliable and scalable data-driven solution for underwater image restoration and enhancement. The generated dataset is publicly available at: https://github.com/yftian2025/SynUIEDatasets.git.

Paperid: 519, https://arxiv.org/pdf/2511.14510.pdf GitHub

Abstract:
The growth of million-token LLMs exposes the scalability limits of inference systems, where the KVCache dominates memory usage and data transfer overhead. Recent offloading systems migrate the KVCache to CPU memory and incorporate top-k attention to reduce the volume of data transferred from the CPU, while further applying system-level optimizations such as on-GPU caching and prefetching to lower transfer overhead. However, they overlook the CPU bottleneck in three aspects: (1) substantial overhead of fine-grained dynamic cache management performed on the CPU side, (2) significant transfer overhead from poor PCIe bandwidth utilization caused by heavy gathering operations at the CPU side, and (3) GPU runtime bubbles introduced by coarse-grained CPU-centric synchronization. To address these challenges, we propose CLO, a CPU-light KVCache offloading system via algorithm-system co-design. CLO features: (1) a coarse-grained head-wise approximate on-GPU caching strategy with negligible cache management cost, (2) seamless combination of data prefetching and on-GPU persistent caching for lower transfer overhead, (3) a zero-copy transfer engine to fully exploit PCIe bandwidth, and a GPU-centric synchronization method to eliminate GPU stalls. Evaluation on two widely-used LLMs demonstrates that CLO achieves comparable accuracy to state-of-the-art systems, while substantially minimizing CPU overhead, fully utilizing PCIe bandwidth, thus improving decoding throughput by 9.3%-66.6%. Our results highlight that algorithm-system co-design is essential for memory-constrained LLM inference on modern GPU platforms. We open source CLO at https://github.com/CommediaJW/CLO.

Paperid: 520, https://arxiv.org/pdf/2511.14503.pdf GitHub

Abstract:
Understanding the inter-relations and interactions between tasks is crucial for multi-task dense prediction. Existing methods predominantly utilize convolutional layers and attention mechanisms to explore task-level interactions. In this work, we introduce a novel decoder-based framework, Parameter Aware Mamba Model (PAMM), specifically designed for dense prediction in multi-task learning setting. Distinct from approaches that employ Transformers to model holistic task relationships, PAMM leverages the rich, scalable parameters of state space models to enhance task interconnectivity. It features dual state space parameter experts that integrate and set task-specific parameter priors, capturing the intrinsic properties of each task. This approach not only facilitates precise multi-task interactions but also allows for the global integration of task priors through the structured state space sequence model (S4). Furthermore, we employ the Multi-Directional Hilbert Scanning method to construct multi-angle feature sequences, thereby enhancing the sequence model's perceptual capabilities for 2D data. Extensive experiments on the NYUD-v2 and PASCAL-Context benchmarks demonstrate the effectiveness of our proposed method. Our code is available at https://github.com/CQC-gogopro/PAMM.

Paperid: 521, https://arxiv.org/pdf/2511.14477.pdf GitHub GitHub

Abstract:
This paper introduces Gaussian Spatial Transport (GST), a novel framework that leverages Gaussian splatting to facilitate transport from the probability measure in the image coordinate space to the annotation map. We propose a Gaussian splatting-based method to estimate pixel-annotation correspondence, which is then used to compute a transport plan derived from Bayesian probability. To integrate the resulting transport plan into standard network optimization in typical computer vision tasks, we derive a loss function that measures discrepancy after transport. Extensive experiments on representative computer vision tasks, including crowd counting and landmark detection, validate the effectiveness of our approach. Compared to conventional optimal transport schemes, GST eliminates iterative transport plan computation during training, significantly improving efficiency. Code is available at https://github.com/infinite0522/GST.

Paperid: 522, https://arxiv.org/pdf/2511.14469.pdf GitHub

Abstract:
Low-light video deblurring poses significant challenges in applications like nighttime surveillance and autonomous driving due to dim lighting and long exposures. While event cameras offer potential solutions with superior low-light sensitivity and high temporal resolution, existing fusion methods typically employ staged strategies, limiting their effectiveness against combined low-light and motion blur degradations. To overcome this, we propose CompEvent, a complex neural network framework enabling holistic full-process fusion of event data and RGB frames for enhanced joint restoration. CompEvent features two core components: 1) Complex Temporal Alignment GRU, which utilizes complex-valued convolutions and processes video and event streams iteratively via GRU to achieve temporal alignment and continuous fusion; and 2) Complex Space-Frequency Learning module, which performs unified complex-valued signal processing in both spatial and frequency domains, facilitating deep fusion through spatial structures and system-level characteristics. By leveraging the holistic representation capability of complex-valued neural networks, CompEvent achieves full-process spatiotemporal fusion, maximizes complementary learning between modalities, and significantly strengthens low-light video deblurring capability. Extensive experiments demonstrate that CompEvent outperforms SOTA methods in addressing this challenging task. The code is available at https://github.com/YuXie1/CompEvent.

Paperid: 523, https://arxiv.org/pdf/2511.14445.pdf GitHub

Abstract:
We present Tell Me, a mental well-being system that leverages advances in large language models to provide accessible, context-aware support for users and researchers. The system integrates three components: (i) a retrieval-augmented generation (RAG) assistant for personalized, knowledge-grounded dialogue; (ii) a synthetic client-therapist dialogue generator conditioned on client profiles to facilitate research on therapeutic language and data augmentation; and (iii) a Well-being AI crew, implemented with CrewAI, that produces weekly self-care plans and guided meditation audio. The system is designed as a reflective space for emotional processing rather than a substitute for professional therapy. It illustrates how conversational assistants can lower barriers to support, complement existing care, and broaden access to mental health resources. To address the shortage of confidential therapeutic data, we introduce synthetic client-therapist dialogue generation conditioned on client profiles. Finally, the planner demonstrates an innovative agentic workflow for dynamically adaptive, personalized self-care, bridging the limitations of static well-being tools. We describe the architecture, demonstrate its functionalities, and report evaluation of the RAG assistant in curated well-being scenarios using both automatic LLM-based judgments and a human-user study. This work highlights opportunities for interdisciplinary collaboration between NLP researchers and mental health professionals to advance responsible innovation in human-AI interaction for well-being.

Paperid: 524, https://arxiv.org/pdf/2511.14426.pdf GitHub GitHub

Abstract:
In recent years, diffusion-based models have demonstrated exceptional performance in searching for simultaneously stable, unique, and novel (S.U.N.) crystalline materials. However, most of these models don't have the ability to change the number of atoms in the crystal during the generation process, which limits the variability of model sampling trajectories. In this paper, we demonstrate the severity of this restriction and introduce a simple yet powerful technique, mirage infusion, which enables diffusion models to change the state of the atoms that make up the crystal from existent to non-existent (mirage) and vice versa. We show that this technique improves model quality by up to $\times2.5$ compared to the same model without this modification. The resulting model, Mirage Atom Diffusion (MiAD), is an equivariant joint diffusion model for de novo crystal generation that is capable of altering the number of atoms during the generation process. MiAD achieves an $8.2\%$ S.U.N. rate on the MP-20 dataset, which substantially exceeds existing state-of-the-art approaches. The source code can be found at \href{https://github.com/andrey-okhotin/miad.git}{\texttt{github.com/andrey-okhotin/miad}}.

Paperid: 525, https://arxiv.org/pdf/2511.14401.pdf GitHub

Abstract:
A key challenge in Domain Incremental Learning (DIL) is to continually learn under shifting distributions while preserving knowledge from previous domains. Existing methods face a fundamental dilemma. On one hand, projecting all domains into a single unified visual space leads to inter-domain interference and semantic distortion, as large shifts may vary with not only visual appearance but also underlying semantics. On the other hand, isolating domain-specific parameters causes knowledge fragmentation, creating "knowledge islands" that hamper knowledge reuse and exacerbate forgetting. To address this issue, we propose LAVA (Language-Anchored Visual Alignment), a novel DIL framework that replaces direct feature alignment with relative alignment driven by a text-based reference anchor. LAVA guides the visual representations of each incoming domain to preserve a consistent relative geometry, which is defined by mirroring the pairwise semantic similarities between the class names. This anchored geometric structure acts as a bridge across domains, enabling the retrieval of class-aware prior knowledge and facilitating robust feature aggregation. Extensive experiments on standard DIL benchmarks demonstrate that LAVA achieves significant performance improvements over state-of-the-arts. Code is available at https://github.com/ShuyiGeng/LAVA.

Paperid: 526, https://arxiv.org/pdf/2511.14396.pdf GitHub

Abstract:
Language-conditioned manipulation facilitates human-robot interaction via behavioral cloning (BC), which learns control policies from human demonstrations and serves as a cornerstone of embodied AI. Overcoming compounding errors in sequential action decisions remains a central challenge to improving BC performance. Existing approaches mitigate compounding errors through data augmentation, expressive representation, or temporal abstraction. However, they suffer from physical discontinuities and semantic-physical misalignment, leading to inaccurate action cloning and intermittent execution. In this paper, we present Continuous vision-language-action Co-Learning with Semantic-Physical Alignment (CCoL), a novel BC framework that ensures temporally consistent execution and fine-grained semantic grounding. It generates robust and smooth action execution trajectories through continuous co-learning across vision, language, and proprioceptive inputs (e.g., robot internal states). Meanwhile, we anchor language semantics to visuomotor representations by a bidirectional cross-attention to learn contextual information for action generation, successfully overcoming the problem of semantic-physical misalignment. Extensive experiments show that CCoL achieves an average 8.0% relative improvement across three simulation suites, with up to 19.2% relative gain in human-demonstrated bimanual insertion tasks. Real-world tests on a 7-DoF robot further confirm CCoL's generalization under unseen and noisy object states.

Paperid: 527, https://arxiv.org/pdf/2511.14391.pdf GitHub

Abstract:
Large Language Models (LLMs) are increasingly used for decision-making and planning in autonomous driving, showing promising reasoning capabilities and potential to generalize across diverse traffic situations. However, current LLM-based driving agents lack explicit mechanisms to enforce traffic rules and often struggle to reliably detect small, safety-critical objects such as traffic lights and signs. To address this limitation, we introduce TLS-Assist, a modular redundancy layer that augments LLM-based autonomous driving agents with explicit traffic light and sign recognition. TLS-Assist converts detections into structured natural language messages that are injected into the LLM input, enforcing explicit attention to safety-critical cues. The framework is plug-and-play, model-agnostic, and supports both single-view and multi-view camera setups. We evaluate TLS-Assist in a closed-loop setup on the LangAuto benchmark in CARLA. The results demonstrate relative driving performance improvements of up to 14% over LMDrive and 7% over BEVDriver, while consistently reducing traffic light and sign infractions. We publicly release the code and models on https://github.com/iis-esslingen/TLS-Assist.

Paperid: 528, https://arxiv.org/pdf/2511.14390.pdf GitHub

Abstract:
We introduce a general formulation for automatic differentiation through direct form filters, yielding a closed-form backpropagation that includes initial condition gradients. The result is a single expression that can represent both the filter and its gradients computation while supporting parallelism. C++/CUDA implementations in PyTorch achieve at least 1000x speedup over naive Python implementations and consistently run fastest on the GPU. For the low-order filters commonly used in practice, exact time-domain filtering with analytical gradients outperforms the frequency-domain method in terms of speed. The source code is available at https://github.com/yoyolicoris/philtorch.

Paperid: 529, https://arxiv.org/pdf/2511.14349.pdf GitHub

Abstract:
The proliferation of hour-long videos (e.g., lectures, podcasts, documentaries) has intensified demand for efficient content structuring. However, existing approaches are constrained by small-scale training with annotations that are typical short and coarse, restricting generalization to nuanced transitions in long videos. We introduce ARC-Chapter, the first large-scale video chaptering model trained on over million-level long video chapters, featuring bilingual, temporally grounded, and hierarchical chapter annotations. To achieve this goal, we curated a bilingual English-Chinese chapter dataset via a structured pipeline that unifies ASR transcripts, scene texts, visual captions into multi-level annotations, from short title to long summaries. We demonstrate clear performance improvements with data scaling, both in data volume and label intensity. Moreover, we design a new evaluation metric termed GRACE, which incorporates many-to-one segment overlaps and semantic similarity, better reflecting real-world chaptering flexibility. Extensive experiments demonstrate that ARC-Chapter establishes a new state-of-the-art by a significant margin, outperforming the previous best by 14.0% in F1 score and 11.3% in SODA score. Moreover, ARC-Chapter shows excellent transferability, improving the state-of-the-art on downstream tasks like dense video captioning on YouCook2.

Paperid: 530, https://arxiv.org/pdf/2511.14276.pdf GitHub

Abstract:
Recent foundation models for tabular data achieve strong task-specific performance via in-context learning. Nevertheless, they focus on direct prediction by encapsulating both representation learning and task-specific inference inside a single, resource-intensive network. This work specifically focuses on representation learning, i.e., on transferable, task-agnostic embeddings. We systematically evaluate task-agnostic representations from tabular foundation models (TabPFN and TabICL) alongside with classical feature engineering (TableVectorizer) across a variety of application tasks as outlier detection (ADBench) and supervised learning (TabArena Lite). We find that simple TableVectorizer features achieve comparable or superior performance while being up to three orders of magnitude faster than tabular foundation models. The code is available at https://github.com/ContactSoftwareAI/TabEmbedBench.

Paperid: 531, https://arxiv.org/pdf/2511.14250.pdf GitHub

Abstract:
Automatic Music Transcription (AMT) converts audio recordings into symbolic musical representations. Training deep neural networks (DNNs) for AMT typically requires strongly aligned training pairs with precise frame-level annotations. Since creating such datasets is costly and impractical for many musical contexts, weakly aligned approaches using segment-level annotations have gained traction. However, existing methods often rely on Dynamic Time Warping (DTW) or soft alignment loss functions, both of which still require local semantic correspondences, making them error-prone and computationally expensive. In this article, we introduce CountEM, a novel AMT framework that eliminates the need for explicit local alignment by leveraging note event histograms as supervision, enabling lighter computations and greater flexibility. Using an Expectation-Maximization (EM) approach, CountEM iteratively refines predictions based solely on note occurrence counts, significantly reducing annotation efforts while maintaining high transcription accuracy. Experiments on piano, guitar, and multi-instrument datasets demonstrate that CountEM matches or surpasses existing weakly supervised methods, improving AMT's robustness, scalability, and efficiency. Our project page is available at https://yoni-yaffe.github.io/count-the-notes.

Paperid: 532, https://arxiv.org/pdf/2511.14249.pdf GitHub

Abstract:
The automatic movie dubbing model generates vivid speech from given scripts, replicating a speaker's timbre from a brief timbre prompt while ensuring lip-sync with the silent video. Existing approaches simulate a simplified workflow where actors dub directly without preparation, overlooking the critical director-actor interaction. In contrast, authentic workflows involve a dynamic collaboration: directors actively engage with actors, guiding them to internalize the context cues, specifically emotion, before performance. To address this issue, we propose a new Retrieve-Augmented Director-Actor Interaction Learning scheme to achieve authentic movie dubbing, termed Authentic-Dubber, which contains three novel mechanisms: (1) We construct a multimodal Reference Footage library to simulate the learning footage provided by directors. Note that we integrate Large Language Models (LLMs) to achieve deep comprehension of emotional representations across multimodal signals. (2) To emulate how actors efficiently and comprehensively internalize director-provided footage during dubbing, we propose an Emotion-Similarity-based Retrieval-Augmentation strategy. This strategy retrieves the most relevant multimodal information that aligns with the target silent video. (3) We develop a Progressive Graph-based speech generation approach that incrementally incorporates the retrieved multimodal emotional knowledge, thereby simulating the actor's final dubbing process. The above mechanisms enable the Authentic-Dubber to faithfully replicate the authentic dubbing workflow, achieving comprehensive improvements in emotional expressiveness. Both subjective and objective evaluations on the V2C Animation benchmark dataset validate the effectiveness. The code and demos are available at https://github.com/AI-S2-Lab/Authentic-Dubber.

Paperid: 533, https://arxiv.org/pdf/2511.14223.pdf GitHub

Abstract:
This paper focuses on the task of speech-driven 3D facial animation, which aims to generate realistic and synchronized facial motions driven by speech inputs. Recent methods have employed audio-conditioned diffusion models for 3D facial animation, achieving impressive results in generating expressive and natural animations. However, these methods process the whole audio sequences in a single pass, which poses two major challenges: they tend to perform poorly when handling audio sequences that exceed the training horizon and will suffer from significant latency when processing long audio inputs. To address these limitations, we propose a novel autoregressive diffusion model that processes input audio in a streaming manner. This design ensures flexibility with varying audio lengths and achieves low latency independent of audio duration. Specifically, we select a limited number of past frames as historical motion context and combine them with the audio input to create a dynamic condition. This condition guides the diffusion process to iteratively generate facial motion frames, enabling real-time synthesis with high-quality results. Additionally, we implemented a real-time interactive demo, highlighting the effectiveness and efficiency of our approach. We will release the code at https://zju3dv.github.io/StreamingTalker/.

Paperid: 534, https://arxiv.org/pdf/2511.14187.pdf GitHub GitHub

Abstract:
The aorta, the body's largest artery, is prone to pathologies such as dissection, aneurysm, and atherosclerosis, which often require timely intervention. Minimally invasive repairs involving branch vessels necessitate detailed 3D anatomical analysis. Existing methods often overlook hierarchical anatomical relationships while struggling with severe class imbalance inherent in vascular structures. We address these challenges with a curriculum learning strategy that leverages a novel fractal softmax for hierarchical semantic learning. Inspired by human cognition, our approach progressively learns anatomical constraints by decomposing complex structures from simple to complex components. The curriculum learning framework naturally addresses class imbalance by first establishing robust feature representations for dominant classes before tackling rare but anatomically critical structures, significantly accelerating model convergence in multi-class scenarios. Our two-stage inference strategy achieves up to fivefold acceleration, enhancing clinical practicality. On the validation set at epoch 50, our hierarchical semantic loss improves the Dice score of nnU-Net ResEnc M by 11.65%. The proposed model demonstrates a 5.6% higher Dice score than baselines on the test set. Experimental results show significant improvements in segmentation accuracy and efficiency, making the framework suitable for real-time clinical applications. The implementation code for this challenge entry is publicly available at: https://github.com/PengchengShi1220/AortaSeg24. The code for fractal softmax will be available at https://github.com/PengchengShi1220/fractal-softmax.

Paperid: 535, https://arxiv.org/pdf/2511.14186.pdf GitHub

Abstract:
Precise event spotting (PES) aims to recognize fine-grained events at exact moments and has become a key component of sports analytics. This task is particularly challenging due to rapid succession, motion blur, and subtle visual differences. Consequently, most existing methods rely on domain-specific, end-to-end training with large labeled datasets and often struggle in few-shot conditions due to their dependence on pixel- or pose-based inputs alone. However, obtaining large labeled datasets is practically hard. We propose a Unified Multi-Entity Graph Network (UMEG-Net) for few-shot PES. UMEG-Net integrates human skeletons and sport-specific object keypoints into a unified graph and features an efficient spatio-temporal extraction module based on advanced GCN and multi-scale temporal shift. To further enhance performance, we employ multimodal distillation to transfer knowledge from keypoint-based graphs to visual representations. Our approach achieves robust performance with limited labeled data and significantly outperforms baseline models in few-shot settings, providing a scalable and effective solution for few-shot PES. Code is publicly available at https://github.com/LZYAndy/UMEG-Net.

Paperid: 536, https://arxiv.org/pdf/2511.14178.pdf GitHub

Abstract:
Vision-Language-Action (VLA) models have demonstrated significant potential in real-world robotic manipulation. However, pre-trained VLA policies still suffer from substantial performance degradation during downstream deployment. Although fine-tuning can mitigate this issue, its reliance on costly demonstration collection and intensive computation makes it impractical in real-world settings. In this work, we introduce VLA-Pilot, a plug-and-play inference-time policy steering method for zero-shot deployment of pre-trained VLA without any additional fine-tuning or data collection. We evaluate VLA-Pilot on six real-world downstream manipulation tasks across two distinct robotic embodiments, encompassing both in-distribution and out-of-distribution scenarios. Experimental results demonstrate that VLA-Pilot substantially boosts the success rates of off-the-shelf pre-trained VLA policies, enabling robust zero-shot generalization to diverse tasks and embodiments. Experimental videos and code are available at: https://rip4kobe.github.io/vla-pilot/.

Paperid: 537, https://arxiv.org/pdf/2511.14159.pdf GitHub

Abstract:
Evaluating the robustness of Large Vision-Language Models (LVLMs) is essential for their continued development and responsible deployment in real-world applications. However, existing robustness benchmarks typically focus on hallucination or misleading textual inputs, while largely overlooking the equally critical challenge posed by misleading visual inputs in assessing visual understanding. To fill this important gap, we introduce MVI-Bench, the first comprehensive benchmark specially designed for evaluating how Misleading Visual Inputs undermine the robustness of LVLMs. Grounded in fundamental visual primitives, the design of MVI-Bench centers on three hierarchical levels of misleading visual inputs: Visual Concept, Visual Attribute, and Visual Relationship. Using this taxonomy, we curate six representative categories and compile 1,248 expertly annotated VQA instances. To facilitate fine-grained robustness evaluation, we further introduce MVI-Sensitivity, a novel metric that characterizes LVLM robustness at a granular level. Empirical results across 18 state-of-the-art LVLMs uncover pronounced vulnerabilities to misleading visual inputs, and our in-depth analyses on MVI-Bench provide actionable insights that can guide the development of more reliable and robust LVLMs. The benchmark and codebase can be accessed at https://github.com/chenyil6/MVI-Bench.

Paperid: 538, https://arxiv.org/pdf/2511.14149.pdf GitHub

Abstract:
Recent trends in SLAM and visual navigation have embraced 3D Gaussians as the preferred scene representation, highlighting the importance of estimating camera poses from a single image using a pre-built Gaussian model. However, existing approaches typically rely on an iterative \textit{render-compare-refine} loop, where candidate views are first rendered using NeRF or Gaussian Splatting, then compared against the target image, and finally, discrepancies are used to update the pose. This multi-round process incurs significant computational overhead, hindering real-time performance in robotics. In this paper, we propose iGaussian, a two-stage feed-forward framework that achieves real-time camera pose estimation through direct 3D Gaussian inversion. Our method first regresses a coarse 6DoF pose using a Gaussian Scene Prior-based Pose Regression Network with spatial uniform sampling and guided attention mechanisms, then refines it through feature matching and multi-model fusion. The key contribution lies in our cross-correlation module that aligns image embeddings with 3D Gaussian attributes without differentiable rendering, coupled with a Weighted Multiview Predictor that fuses features from Multiple strategically sampled viewpoints. Experimental results on the NeRF Synthetic, Mip-NeRF 360, and T\&T+DB datasets demonstrate a significant performance improvement over previous methods, reducing median rotation errors to 0.2° while achieving 2.87 FPS tracking on mobile robots, which is an impressive 10 times speedup compared to optimization-based approaches. Code: https://github.com/pythongod-exe/iGaussian

Paperid: 539, https://arxiv.org/pdf/2511.14148.pdf GitHub

Abstract:
Vision-language-action (VLA) models have recently emerged as a powerful paradigm for building generalist robots. However, traditional VLA models that generate actions through flow matching (FM) typically rely on rigid and uniform time schedules, i.e., synchronous FM (SFM). Without action context awareness and asynchronous self-correction, SFM becomes unstable in long-horizon tasks, where a single action error can cascade into failure. In this work, we propose asynchronous flow matching VLA (AsyncVLA), a novel framework that introduces temporal flexibility in asynchronous FM (AFM) and enables self-correction in action generation. AsyncVLA breaks from the vanilla SFM in VLA models by generating the action tokens in a non-uniform time schedule with action context awareness. Besides, our method introduces the confidence rater to extract confidence of the initially generated actions, enabling the model to selectively refine inaccurate action tokens before execution. Moreover, we propose a unified training procedure for SFM and AFM that endows a single model with both modes, improving KV-cache utilization. Extensive experiments on robotic manipulation benchmarks demonstrate that AsyncVLA is data-efficient and exhibits self-correction ability. AsyncVLA achieves state-of-the-art results across general embodied evaluations due to its asynchronous generation in AFM. Our code is available at https://github.com/YuhuaJiang2002/AsyncVLA.

Paperid: 540, https://arxiv.org/pdf/2511.14138.pdf GitHub

Abstract:
Achieving diverse and high-quality audio transformations from text prompts remains challenging, as existing methods are fundamentally constrained by their reliance on a limited set of differentiable audio effects. This paper proposes FxSearcher, a novel gradient-free framework that discovers the optimal configuration of audio effects (FX) to transform a source signal according to a text prompt. Our method employs Bayesian Optimization and CLAP-based score function to perform this search efficiently. Furthermore, a guiding prompt is introduced to prevent undesirable artifacts and enhance human preference. To objectively evaluate our method, we propose an AI-based evaluation framework. The results demonstrate that the highest scores achieved by our method on these metrics align closely with human preferences. Demos are available at https://hojoonki.github.io/FxSearcher/

Paperid: 541, https://arxiv.org/pdf/2511.14107.pdf GitHub

Abstract:
Depth information is crucial for autonomous driving and intelligent robot navigation. The simplicity and flexibility of self-supervised monocular depth estimation are conducive to its role in these fields. However, most existing monocular depth estimation models consume many computing resources. Although some methods have reduced the model's size and improved computing efficiency, the performance deteriorates, seriously hindering the real-world deployment of self-supervised monocular depth estimation models in the real world. To address this problem, we proposed a real-time self-supervised monocular depth estimation method and implemented it in the real world. It is called RTS-Mono, which is a lightweight and efficient encoder-decoder architecture. The encoder is based on Lite-Encoder, and the decoder is designed with a multi-scale sparse fusion framework to minimize redundancy, ensure performance, and improve inference speed. RTS-Mono achieved state-of-the-art (SoTA) performance in high and low resolutions with extremely low parameter counts (3 M) in experiments based on the KITTI dataset. Compared with lightweight methods, RTS-Mono improved Abs Rel and Sq Rel by 5.6% and 9.8% at low resolution and improved Sq Rel and RMSE by 6.1% and 1.9% at high resolution. In real-world deployment experiments, RTS-Mono has extremely high accuracy and can perform real-time inference on Nvidia Jetson Orin at a speed of 49 FPS. Source code is available at https://github.com/ZYCheng777/RTS-Mono.

Paperid: 542, https://arxiv.org/pdf/2511.14097.pdf GitHub

Abstract:
For long-tailed recognition (LTR) tasks, high intra-class compactness and inter-class separability in both head and tail classes, as well as balanced separability among all the classifier vectors, are preferred. The existing LTR methods based on cross-entropy (CE) loss not only struggle to learn features with desirable properties but also couple imbalanced classifier vectors in the denominator of its Softmax, amplifying the imbalance effects in LTR. In this paper, for the LTR, we propose a binary cross-entropy (BCE)-based tripartite synergistic learning, termed BCE3S, which consists of three components: (1) BCE-based joint learning optimizes both the classifier and sample features, which achieves better compactness and separability among features than the CE-based joint learning, by decoupling the metrics between feature and the imbalanced classifier vectors in multiple Sigmoid; (2) BCE-based contrastive learning further improves the intra-class compactness of features; (3) BCE-based uniform learning balances the separability among classifier vectors and interactively enhances the feature properties by combining with the joint learning. The extensive experiments show that the LTR model trained by BCE3S not only achieves higher compactness and separability among sample features, but also balances the classifier's separability, achieving SOTA performance on various long-tailed datasets such as CIFAR10-LT, CIFAR100-LT, ImageNet-LT, and iNaturalist2018.

Paperid: 543, https://arxiv.org/pdf/2511.14096.pdf GitHub

Abstract:
Retrieval-augmented generation (RAG) greatly enhances large language models (LLMs) performance in knowledge-intensive tasks. However, naive RAG methods struggle with multi-hop question answering due to their limited capacity to capture complex dependencies across documents. Recent studies employ graph-based RAG to capture document connections. However, these approaches often result in a loss of semantic coherence and introduce irrelevant noise during node matching and subgraph construction. To address these limitations, we propose NeuroPath, an LLM-driven semantic path tracking RAG framework inspired by the path navigational planning of place cells in neurobiology. It consists of two steps: Dynamic Path Tracking and Post-retrieval Completion. Dynamic Path Tracking performs goal-directed semantic path tracking and pruning over the constructed knowledge graph (KG), improving noise reduction and semantic coherence. Post-retrieval Completion further reinforces these benefits by conducting second-stage retrieval using intermediate reasoning and the original query to refine the query goal and complete missing information in the reasoning path. NeuroPath surpasses current state-of-the-art baselines on three multi-hop QA datasets, achieving average improvements of 16.3% on recall@2 and 13.5% on recall@5 over advanced graph-based RAG methods. Moreover, compared to existing iter-based RAG methods, NeuroPath achieves higher accuracy and reduces token consumption by 22.8%. Finally, we demonstrate the robustness of NeuroPath across four smaller LLMs (Llama3.1, GLM4, Mistral0.3, and Gemma3), and further validate its scalability across tasks of varying complexity. Code is available at https://github.com/KennyCaty/NeuroPath.

Paperid: 544, https://arxiv.org/pdf/2511.14086.pdf GitHub

Abstract:
Despite recent progress in 3D-LLMs, they remain limited in accurately grounding language to visual and spatial elements in 3D environments. This limitation stems in part from training data that focuses on language reasoning rather than spatial understanding due to scarce 3D resources, leaving inherent grounding biases unresolved. To address this, we propose 3D scene editing as a key mechanism to generate precise visual counterfactuals that mitigate these biases through fine-grained spatial manipulation, without requiring costly scene reconstruction or large-scale 3D data collection. Furthermore, to make these edits targeted and directly address the specific weaknesses of the model, we introduce DEER-3D, an error-driven framework following a structured "Decompose, Diagnostic Evaluation, Edit, and Re-train" workflow, rather than broadly or randomly augmenting data as in conventional approaches. Specifically, upon identifying a grounding failure of the 3D-LLM, our framework first diagnoses the exact predicate-level error (e.g., attribute or spatial relation). It then executes minimal, predicate-aligned 3D scene edits, such as recoloring or repositioning, to produce targeted counterfactual supervision for iterative model fine-tuning, significantly enhancing grounding accuracy. We evaluate our editing pipeline across multiple benchmarks for 3D grounding and scene understanding tasks, consistently demonstrating improvements across all evaluated datasets through iterative refinement. DEER-3D underscores the effectiveness of targeted, error-driven scene editing in bridging linguistic reasoning capabilities with spatial grounding in 3D LLMs.

Paperid: 545, https://arxiv.org/pdf/2511.14083.pdf GitHub

Abstract:
Reliable measurement of glenoid bone loss is essential for operative planning in shoulder instability, but current manual and semi-automated methods are time-consuming and often subject to interreader variability. We developed and validated a fully automated deep learning pipeline for measuring glenoid bone loss on three-dimensional computed tomography (CT) scans using a linear-based, en-face view, best-circle method. Shoulder CT images of 91 patients (average age, 40 years; range, 14-89 years; 65 men) were retrospectively collected along with manual labels including glenoid segmentation, landmarks, and bone loss measurements. The multi-stage algorithm has three main stages: (1) segmentation, where we developed a U-Net to automatically segment the glenoid and humerus; (2) anatomical landmark detection, where a second network predicts glenoid rim points; and (3) geometric fitting, where we applied principal component analysis (PCA), projection, and circle fitting to compute the percentage of bone loss. The automated measurements showed strong agreement with consensus readings and exceeded surgeon-to-surgeon consistency (intraclass correlation coefficient (ICC) 0.84 vs 0.78), including in low- and high-bone-loss subgroups (ICC 0.71 vs 0.63 and 0.83 vs 0.21, respectively; P < 0.001). For classifying patients into low, medium, and high bone-loss categories, the pipeline achieved a recall of 0.714 for low and 0.857 for high severity, with no low cases misclassified as high or vice versa. These results suggest that our method is a time-efficient and clinically reliable tool for preoperative planning in shoulder instability and for screening patients with substantial glenoid bone loss. Code and dataset are available at https://github.com/Edenliu1/Auto-Glenoid-Measurement-DL-Pipeline.

Paperid: 546, https://arxiv.org/pdf/2511.14064.pdf GitHub

Abstract:
Medication recommendation systems play a crucial role in assisting clinicians with personalized treatment decisions. While existing approaches have made significant progress in learning medication representations, they suffer from two fundamental limitations: (i) treating medical entities as independent features without modeling their synergistic effects on medication selection; (ii) employing static causal relationships that fail to adapt to patient-specific contexts and health states. To address these challenges, we propose CafeMed, a framework that integrates dynamic causal reasoning with cross-modal attention for safe and accurate medication recommendation. CafeMed introduces two key components: the Causal Weight Generator (CWG) that transforms static causal effects into dynamic modulation weights based on individual patient states, and the Channel Harmonized Attention Refinement Module (CHARM) that captures complex interdependencies between diagnoses and procedures. This design enables CafeMed to model how different medical conditions jointly influence treatment decisions while maintaining medication safety constraints. Extensive experiments on MIMIC-III and MIMIC-IV datasets demonstrate that CafeMed significantly outperforms state-of-the-art baselines, achieving superior accuracy in medication prediction while maintaining the lower drug--drug interaction rates. Our results indicate that incorporating dynamic causal relationships and cross-modal synergies leads to more clinically-aligned and personalized medication recommendations. Our code is released publicly at https://github.com/rkl71/CafeMed.

Paperid: 547, https://arxiv.org/pdf/2511.14033.pdf GitHub

Abstract:
Flood prediction is critical for emergency planning and response to mitigate human and economic losses. Traditional physics-based hydrodynamic models generate high-resolution flood maps using numerical methods requiring fine-grid discretization; which are computationally intensive and impractical for real-time large-scale applications. While recent studies have applied convolutional neural networks for flood map super-resolution with good accuracy and speed, they suffer from limited generalizability to unseen areas. In this paper, we propose a novel approach that leverages latent diffusion models to perform super-resolution on coarse-grid flood maps, with the objective of achieving the accuracy of fine-grid flood maps while significantly reducing inference time. Experimental results demonstrate that latent diffusion models substantially decrease the computational time required to produce high-fidelity flood maps without compromising on accuracy, enabling their use in real-time flood risk management. Moreover, diffusion models exhibit superior generalizability across different physical locations, with transfer learning further accelerating adaptation to new geographic regions. Our approach also incorporates physics-informed inputs, addressing the common limitation of black-box behavior in machine learning, thereby enhancing interpretability. Code is available at https://github.com/neosunhan/flood-diff.

Paperid: 548, https://arxiv.org/pdf/2511.14003.pdf GitHub

Abstract:
Certified defenses promise provable robustness guarantees. We study the malicious exploitation of probabilistic certification frameworks to better understand the limits of guarantee provisions. Now, the objective is to not only mislead a classifier, but also manipulate the certification process to generate a robustness guarantee for an adversarial input certificate spoofing. A recent study in ICLR demonstrated that crafting large perturbations can shift inputs far into regions capable of generating a certificate for an incorrect class. Our study investigates if perturbations needed to cause a misclassification and yet coax a certified model into issuing a deceptive, large robustness radius for a target class can still be made small and imperceptible. We explore the idea of region-focused adversarial examples to craft imperceptible perturbations, spoof certificates and achieve certification radii larger than the source class ghost certificates. Extensive evaluations with the ImageNet demonstrate the ability to effectively bypass state-of-the-art certified defenses such as Densepure. Our work underscores the need to better understand the limits of robustness certification methods.

Paperid: 549, https://arxiv.org/pdf/2511.13954.pdf GitHub

Abstract:
Human emotions are difficult to convey through words and are often abstracted in the process; however, electroencephalogram (EEG) signals can offer a more direct lens into emotional brain activity. Recent studies show that deep learning models can process these signals to perform emotion recognition with high accuracy. However, many existing approaches overlook the dynamic interplay between distinct brain regions, which can be crucial to understanding how emotions unfold and evolve over time, potentially aiding in more accurate emotion recognition. To address this, we propose RBTransformer, a Transformer-based neural network architecture that models inter-cortical neural dynamics of the brain in latent space to better capture structured neural interactions for effective EEG-based emotion recognition. First, the EEG signals are converted into Band Differential Entropy (BDE) tokens, which are then passed through Electrode Identity embeddings to retain spatial provenance. These tokens are processed through successive inter-cortical multi-head attention blocks that construct an electrode x electrode attention matrix, allowing the model to learn the inter-cortical neural dependencies. The resulting features are then passed through a classification head to obtain the final prediction. We conducted extensive experiments, specifically under subject-dependent settings, on the SEED, DEAP, and DREAMER datasets, over all three dimensions, Valence, Arousal, and Dominance (for DEAP and DREAMER), under both binary and multi-class classification settings. The results demonstrate that the proposed RBTransformer outperforms all previous state-of-the-art methods across all three datasets, over all three dimensions under both classification settings. The source code is available at: https://github.com/nnilayy/RBTransformer.

Paperid: 550, https://arxiv.org/pdf/2511.13927.pdf GitHub

Abstract:
Models used for control design are, to some degree, uncertain. Model uncertainty must be accounted for to ensure the robustness of the closed-loop system. $μ$-analysis and $μ$-synthesis methods allow for the analysis and design of controllers subject to structured uncertainties. Moreover, these tools can be applied to robust performance problems as they are fundamentally robust control problems with structured uncertainty. The contribution of this paper is dkpy, an open-source Python package for performing robust controller analysis and synthesis for systems subject to structured uncertainty. dkpy also provides tools for performing model uncertainty characterization using data from a set of perturbed systems. The open-source project can be found at https://github.com/decargroup/dkpy.

Paperid: 551, https://arxiv.org/pdf/2511.13924.pdf GitHub

Abstract:
Chain-of-Thought (CoT) prompting has recently shown significant promise across various NLP and computer vision tasks by explicitly generating intermediate reasoning steps. However, we find that reinforcement learning (RL)-based fine-tuned CoT reasoning can paradoxically degrade performance in Visual Grounding tasks, particularly as CoT outputs become lengthy or complex. Additionally, our analysis reveals that increased dataset size does not always enhance performance due to varying data complexities. Motivated by these findings, we propose Curriculum-based Relative Policy Optimization (CuRPO), a novel training strategy that leverages CoT length and generalized Intersection over Union (gIoU) rewards as complexity indicators to progressively structure training data from simpler to more challenging examples. Extensive experiments on RefCOCO, RefCOCO+, RefCOCOg, and LISA datasets demonstrate the effectiveness of our approach. CuRPO consistently outperforms existing methods, including Visual-RFT, with notable improvements of up to +12.52 mAP on RefCOCO. Moreover, CuRPO exhibits exceptional efficiency and robustness, delivering strong localization performance even in few-shot learning scenarios, particularly benefiting tasks characterized by ambiguous and intricate textual descriptions.The code is released on https://github.com/qyoung-yan/CuRPO.

Paperid: 552, https://arxiv.org/pdf/2511.13905.pdf GitHub

Abstract:
Projected Gradient Descent (PGD) methods offer a simple and scalable approach to topology optimization (TO), yet they often struggle with nonlinear and multi-constraint problems due to the complexity of active-set detection. This paper introduces PGD-TO, a framework that reformulates the projection step into a regularized convex quadratic problem, eliminating the need for active-set search and ensuring well-posedness even when constraints are infeasible. The framework employs a semismooth Newton solver for general multi-constraint cases and a binary search projection for single or independent constraints, achieving fast and reliable convergence. It further integrates spectral step-size adaptation and nonlinear conjugate-gradient directions for improved stability and efficiency. We evaluate PGD-TO on four benchmark families representing the breadth of TO problems: (i) minimum compliance with a linear volume constraint, (ii) minimum volume under a nonlinear compliance constraint, (iii) multi-material minimum compliance with four independent volume constraints, and (iv) minimum compliance with coupled volume and center-of-mass constraints. Across these single- and multi-constraint, linear and nonlinear cases, PGD-TO achieves convergence and final compliance comparable to the Method of Moving Asymptotes (MMA) and Optimality Criteria (OC), while reducing per-iteration computation time by 10-43x on general problems and 115-312x when constraints are independent. Overall, PGD-TO establishes a fast, robust, and scalable alternative to MMA, advancing topology optimization toward practical large-scale, multi-constraint, and nonlinear design problems. Public code available at: https://github.com/ahnobari/pyFANTOM

Paperid: 553, https://arxiv.org/pdf/2511.13897.pdf GitHub

Abstract:
Temporal realism remains a central weakness of current generative video models, as most evaluation metrics prioritize spatial appearance and offer limited sensitivity to motion. We introduce a scalable, model-agnostic framework that assesses temporal behavior using motion vectors (MVs) extracted directly from compressed video streams. Codec-generated MVs from standards such as H.264 and HEVC provide lightweight, resolution-consistent descriptors of motion dynamics. We quantify realism by computing Kullback-Leibler, Jensen-Shannon, and Wasserstein divergences between MV statistics of real and generated videos. Experiments on the GenVidBench dataset containing videos from eight state-of-the-art generators reveal systematic discrepancies from real motion: entropy-based divergences rank Pika and SVD as closest to real videos, MV-sum statistics favor VC2 and Text2Video-Zero, and CogVideo shows the largest deviations across both measures. Visualizations of MV fields and class-conditional motion heatmaps further reveal center bias, sparse and piecewise constant flows, and grid-like artifacts that frame-level metrics do not capture. Beyond evaluation, we investigate MV-RGB fusion through channel concatenation, cross-attention, joint embedding, and a motion-aware fusion module. Incorporating MVs improves downstream classification across ResNet, I3D, and TSN backbones, with ResNet-18 and ResNet-34 reaching up to 97.4% accuracy and I3D achieving 99.0% accuracy on real-versus-generated discrimination. These findings demonstrate that compressed-domain MVs provide an effective temporal signal for diagnosing motion defects in generative videos and for strengthening temporal reasoning in discriminative models. The implementation is available at: https://github.com/KurbanIntelligenceLab/Motion-Vector-Learning

Paperid: 554, https://arxiv.org/pdf/2511.13893.pdf GitHub GitHub

Abstract:
In differentially private (DP) tabular data synthesis, the consensus is that statistical models are better than neural network (NN)-based methods. However, we argue that this conclusion is incomplete and overlooks the challenge of densely correlated datasets, where intricate dependencies can overwhelm statistical models. In such complex scenarios, neural networks are more suitable due to their capacity to fit complex distributions by learning directly from samples. Despite this potential, existing NN-based algorithms still suffer from significant limitations. We therefore propose MargNet, incorporating successful algorithmic designs of statistical models into neural networks. MargNet applies an adaptive marginal selection strategy and trains the neural networks to generate data that conforms to the selected marginals. On sparsely correlated datasets, our approach achieves utility close to the best statistical method while offering an average 7$\times$ speedup over it. More importantly, on densely correlated datasets, MargNet establishes a new state-of-the-art, reducing fidelity error by up to 26\% compared to the previous best. We release our code on GitHub.\footnote{https://github.com/KaiChen9909/margnet}

Paperid: 555, https://arxiv.org/pdf/2511.13876.pdf GitHub

Abstract:
Contrastive Language-Image Pretraining (CLIP) has demonstrated strong generalization for vision-language tasks in computer vision and medical domains, yet its text encoder accepts only up to 77 tokens, which limits its ability to represent long and information-rich radiology reports. Recent adaptations using domain-specific encoders, such as PubMedBERT or ClinicalBERT, mitigate this issue by leveraging medical corpora, but remain constrained by their limited input length (typically 512 tokens) and relatively shallow semantic understanding. To address these limitations, we propose QwenCLIP, a vision-language framework that replaces CLIP's text encoder with a large language model (LLM)-based embedding module (e.g., Qwen3-Embedding) and introduces learnable prompts to enhance cross-modal alignment. By leveraging the extended context window and richer representations of LLMs, QwenCLIP captures comprehensive medical semantics from long-form clinical text, substantially improving medical image-text alignment and downstream performance on radiology benchmarks. Our code is publicly available at https://github.com/Wxy-24/QwenCLIP.

Paperid: 556, https://arxiv.org/pdf/2511.13869.pdf GitHub

Abstract:
Bladder cancer is one of the most prevalent malignancies worldwide, with a recurrence rate of up to 78%, necessitating accurate post-operative monitoring for effective patient management. Multi-sequence contrast-enhanced MRI is commonly used for recurrence detection; however, interpreting these scans remains challenging, even for experienced radiologists, due to post-surgical alterations such as scarring, swelling, and tissue remodeling. AI-assisted diagnostic tools have shown promise in improving bladder cancer recurrence prediction, yet progress in this field is hindered by the lack of dedicated multi-sequence MRI datasets for recurrence assessment study. In this work, we first introduce a curated multi-sequence, multi-modal MRI dataset specifically designed for bladder cancer recurrence prediction, establishing a valuable benchmark for future research. We then propose H-CNN-ViT, a new Hierarchical Gated Attention Multi-Branch model that enables selective weighting of features from the global (ViT) and local (CNN) paths based on contextual demands, achieving a balanced and targeted feature fusion. Our multi-branch architecture processes each modality independently, ensuring that the unique properties of each imaging channel are optimally captured and integrated. Evaluated on our dataset, H-CNN-ViT achieves an AUC of 78.6%, surpassing state-of-the-art models. Our model is publicly available at https://github.com/XLIAaron/H-CNN-ViT.

Paperid: 557, https://arxiv.org/pdf/2511.13863.pdf GitHub

Abstract:
Humans excel at multisensory perception and can often recognise object properties from the sound of their interactions. Inspired by this, we propose the novel task of Collision Sound Source Segmentation (CS3), where we aim to segment the objects responsible for a collision sound in visual input (i.e. video frames from the collision clip), conditioned on the audio. This task presents unique challenges. Unlike isolated sound events, a collision sound arises from interactions between two objects, and the acoustic signature of the collision depends on both. We focus on egocentric video, where sounds are often clear, but the visual scene is cluttered, objects are small, and interactions are brief. To address these challenges, we propose a weakly-supervised method for audio-conditioned segmentation, utilising foundation models (CLIP and SAM2). We also incorporate egocentric cues, i.e. objects in hands, to find acting objects that can potentially be collision sound sources. Our approach outperforms competitive baselines by $3\times$ and $4.7\times$ in mIoU on two benchmarks we introduce for the CS3 task: EPIC-CS3 and Ego4D-CS3.

Paperid: 558, https://arxiv.org/pdf/2511.13794.pdf GitHub

Abstract:
Current multi-modal image fusion methods typically rely on task-specific models, leading to high training costs and limited scalability. While generative methods provide a unified modeling perspective, they often suffer from slow inference due to the complex sampling trajectories from noise to image. To address this, we formulate image fusion as a direct probabilistic transport from source modalities to the fused image distribution, leveraging the flow matching paradigm to improve sampling efficiency and structural consistency. To mitigate the lack of high-quality fused images for supervision, we collect fusion results from multiple state-of-the-art models as priors, and employ a task-aware selection function to select the most reliable pseudo-labels for each task. We further introduce a Fusion Refiner module that employs a divide-and-conquer strategy to systematically identify, decompose, and enhance degraded components in selected pseudo-labels. For multi-task scenarios, we integrate elastic weight consolidation and experience replay mechanisms to preserve cross-task performance and enhance continual learning ability from both parameter stability and memory retention perspectives. Our approach achieves competitive performance across diverse fusion tasks, while significantly improving sampling efficiency and maintaining a lightweight model design. The code will be available at: https://github.com/Ist-Zhy/FusionFM.

Paperid: 559, https://arxiv.org/pdf/2511.13784.pdf GitHub

Abstract:
Few-shot Video Object Detection (FSVOD) addresses the challenge of detecting novel objects in videos with limited labeled examples, overcoming the constraints of traditional detection methods that require extensive training data. This task presents key challenges, including maintaining temporal consistency across frames affected by occlusion and appearance variations, and achieving novel object generalization without relying on complex region proposals, which are often computationally expensive and require task-specific training. Our novel object-aware temporal modeling approach addresses these challenges by incorporating a filtering mechanism that selectively propagates high-confidence object features across frames. This enables efficient feature progression, reduces noise accumulation, and enhances detection accuracy in a few-shot setting. By utilizing few-shot trained detection and classification heads with focused feature propagation, we achieve robust temporal consistency without depending on explicit object tube proposals. Our approach achieves performance gains, with AP improvements of 3.7% (FSVOD-500), 5.3% (FSYTV-40), 4.3% (VidOR), and 4.5 (VidVRD) in the 5-shot setting. Further results demonstrate improvements in 1-shot, 3-shot, and 10-shot configurations. We make the code public at: https://github.com/yogesh-iitj/fs-video-vit

Paperid: 560, https://arxiv.org/pdf/2511.13772.pdf GitHub

Abstract:
Understanding the legally relevant factual basis of an event and conveying it through text is a key skill of legal professionals. This skill is important for preparing forms (e.g., insurance claims) or other legal documents (e.g., court claims), but often presents a challenge for laypeople. Current AI approaches aim to bridge this gap, but mostly rely on the user to articulate what has happened in text, which may be challenging for many. Here, we investigate the capability of large language models (LLMs) to understand and summarize events occurring in videos. We ask an LLM to summarize and draft legal letters, based on 120 YouTube videos showing legal issues in various domains. Overall, 71.7\% of the summaries were rated as of high or medium quality, which is a promising result, opening the door to a number of applications in e.g. access to justice.

Paperid: 561, https://arxiv.org/pdf/2511.13767.pdf GitHub

Abstract:
Knowledge Distillation (KD) trains a smaller student model using a large, pre-trained teacher model, with temperature as a key hyperparameter controlling the softness of output probabilities. Traditional methods use a fixed temperature throughout training, which is suboptimal. Moreover, architectural differences between teacher and student often result in mismatched logit magnitudes. We demonstrate that students benefit from softer probabilities early in training but require sharper probabilities in later stages. We introduce Dynamic Temperature Scheduler (DTS), which adjusts temperature dynamically based on the cross-entropy loss gap between teacher and student. To our knowledge, this is the first temperature scheduling method that adapts based on the divergence between teacher and student distributions. Our method integrates seamlessly with existing KD frameworks. We validate DTS across multiple KD strategies on vision (CIFAR-100, Tiny-ImageNet) and NLP tasks (GLUE, Dolly, SelfIns, UnNI, S-NI), consistently outperforming static-temperature baselines. Code is available at https://github.com/Sibgat-Ul/DTS.

Paperid: 562, https://arxiv.org/pdf/2511.13757.pdf GitHub

Abstract:
Intraoperative monitoring and prediction of vital signs are critical for ensuring patient safety and improving surgical outcomes. Despite recent advances in deep learning models for medical time-series forecasting, several challenges persist, including the lack of standardized benchmarks, incomplete data, and limited cross-center validation. To address these challenges, we introduce VitalBench, a novel benchmark specifically designed for intraoperative vital sign prediction. VitalBench includes data from over 4,000 surgeries across two independent medical centers, offering three evaluation tracks: complete data, incomplete data, and cross-center generalization. This framework reflects the real-world complexities of clinical practice, minimizing reliance on extensive preprocessing and incorporating masked loss techniques for robust and unbiased model evaluation. By providing a standardized and unified platform for model development and comparison, VitalBench enables researchers to focus on architectural innovation while ensuring consistency in data handling. This work lays the foundation for advancing predictive models for intraoperative vital sign forecasting, ensuring that these models are not only accurate but also robust and adaptable across diverse clinical environments. Our code and data are available at https://github.com/XiudingCai/VitalBench.

Paperid: 563, https://arxiv.org/pdf/2511.13755.pdf GitHub

Abstract:
Multimodal learning aims to improve performance by leveraging data from multiple sources. During joint multimodal training, due to modality bias, the advantaged modality often dominates backpropagation, leading to imbalanced optimization. Existing methods still face two problems: First, the long-term dominance of the dominant modality weakens representation-output coupling in the late stages of training, resulting in the accumulation of redundant information. Second, previous methods often directly and uniformly adjust the gradients of the advantaged modality, ignoring the semantics and directionality between modalities. To address these limitations, we propose Adaptive Redundancy Regulation for Balanced Multimodal Information Refinement (RedReg), which is inspired by information bottleneck principle. Specifically, we construct a redundancy phase monitor that uses a joint criterion of effective gain growth rate and redundancy to trigger intervention only when redundancy is high. Furthermore, we design a co-information gating mechanism to estimate the contribution of the current dominant modality based on cross-modal semantics. When the task primarily relies on a single modality, the suppression term is automatically disabled to preserve modality-specific information. Finally, we project the gradient of the dominant modality onto the orthogonal complement of the joint multimodal gradient subspace and suppress the gradient according to redundancy. Experiments show that our method demonstrates superiority among current major methods in most scenarios. Ablation experiments verify the effectiveness of our method. The code is available at https://github.com/xia-zhe/RedReg.git

Paperid: 564, https://arxiv.org/pdf/2511.13741.pdf GitHub

Abstract:
Trajectory representation learning (TRL) maps trajectories to vector embeddings and facilitates tasks such as trajectory classification and similarity search. State-of-the-art (SOTA) TRL methods transform raw GPS trajectories to grid or road trajectories to capture high-level travel semantics, i.e., regions and roads. However, they lose fine-grained spatial-temporal details as multiple GPS points are grouped into a single grid cell or road segment. To tackle this problem, we propose the BLUrred Encoding method, dubbed BLUE, which gradually reduces the precision of GPS coordinates to create hierarchical patches with multiple levels. The low-level patches are small and preserve fine-grained spatial-temporal details, while the high-level patches are large and capture overall travel patterns. To complement different patch levels with each other, our BLUE is an encoder-decoder model with a pyramid structure. At each patch level, a Transformer is used to learn the trajectory embedding at the current level, while pooling prepares inputs for the higher level in the encoder, and up-resolution provides guidance for the lower level in the decoder. BLUE is trained using the trajectory reconstruction task with the MSE loss. We compare BLUE with 8 SOTA TRL methods for 3 downstream tasks, the results show that BLUE consistently achieves higher accuracy than all baselines, outperforming the best-performing baselines by an average of 30.90%. Our code is available at https://github.com/slzhou-xy/BLUE.

Paperid: 565, https://arxiv.org/pdf/2511.13720.pdf GitHub

Abstract:
Today's denoising diffusion models do not "denoise" in the classical sense, i.e., they do not directly predict clean images. Rather, the neural networks predict noise or a noised quantity. In this paper, we suggest that predicting clean data and predicting noised quantities are fundamentally different. According to the manifold assumption, natural data should lie on a low-dimensional manifold, whereas noised quantities do not. With this assumption, we advocate for models that directly predict clean data, which allows apparently under-capacity networks to operate effectively in very high-dimensional spaces. We show that simple, large-patch Transformers on pixels can be strong generative models: using no tokenizer, no pre-training, and no extra loss. Our approach is conceptually nothing more than "$\textbf{Just image Transformers}$", or $\textbf{JiT}$, as we call it. We report competitive results using JiT with large patch sizes of 16 and 32 on ImageNet at resolutions of 256 and 512, where predicting high-dimensional noised quantities can fail catastrophically. With our networks mapping back to the basics of the manifold, our research goes back to basics and pursues a self-contained paradigm for Transformer-based diffusion on raw natural data.

Paperid: 566, https://arxiv.org/pdf/2511.13719.pdf GitHub

Abstract:
Despite remarkable progress, multimodal foundation models still exhibit surprising deficiencies in spatial intelligence. In this work, we explore scaling up multimodal foundation models to cultivate spatial intelligence within the SenseNova-SI family, built upon established multimodal foundations including visual understanding models (i.e., Qwen3-VL and InternVL3) and unified understanding and generation models (i.e., Bagel). We take a principled approach to constructing high-performing and robust spatial intelligence by systematically curating SenseNova-SI-8M: eight million diverse data samples under a rigorous taxonomy of spatial capabilities. SenseNova-SI demonstrates unprecedented performance across a broad range of spatial intelligence benchmarks: 68.7% on VSI-Bench, 43.3% on MMSI, 85.6% on MindCube, 54.6% on ViewSpatial, and 50.1% on SITE, while maintaining strong general multimodal understanding (e.g., 84.9% on MMBench-En). More importantly, we analyze the impact of data scaling, discuss early signs of emergent generalization capabilities enabled by diverse data training, analyze the risk of overfitting and language shortcuts, present a preliminary study on spatial chain-of-thought reasoning, and validate the potential downstream application. SenseNova-SI is an ongoing project, and this report will be updated continuously. All newly trained multimodal foundation models are publicly released to facilitate further research in this direction.

Paperid: 567, https://arxiv.org/pdf/2511.13704.pdf GitHub

Abstract:
The rapid evolution of video generative models has shifted their focus from producing visually plausible outputs to tackling tasks requiring physical plausibility and logical consistency. However, despite recent breakthroughs such as Veo 3's chain-of-frames reasoning, it remains unclear whether these models can exhibit reasoning capabilities similar to large language models (LLMs). Existing benchmarks predominantly evaluate visual fidelity and temporal coherence, failing to capture higher-order reasoning abilities. To bridge this gap, we propose TiViBench, a hierarchical benchmark specifically designed to evaluate the reasoning capabilities of image-to-video (I2V) generation models. TiViBench systematically assesses reasoning across four dimensions: i) Structural Reasoning & Search, ii) Spatial & Visual Pattern Reasoning, iii) Symbolic & Logical Reasoning, and iv) Action Planning & Task Execution, spanning 24 diverse task scenarios across 3 difficulty levels. Through extensive evaluations, we show that commercial models (e.g., Sora 2, Veo 3.1) demonstrate stronger reasoning potential, while open-source models reveal untapped potential that remains hindered by limited training scale and data diversity. To further unlock this potential, we introduce VideoTPO, a simple yet effective test-time strategy inspired by preference optimization. By performing LLM self-analysis on generated candidates to identify strengths and weaknesses, VideoTPO significantly enhances reasoning performance without requiring additional training, data, or reward models. Together, TiViBench and VideoTPO pave the way for evaluating and advancing reasoning in video generation models, setting a foundation for future research in this emerging field.

Paperid: 568, https://arxiv.org/pdf/2511.13655.pdf GitHub GitHub

Authors:Henry Herzog, Favyen Bastani, Yawen Zhang, Gabriel Tseng, Joseph Redmon, Hadrien Sablon, Ryan Park, Jacob Morrison, Alexandra Buraczynski, Karen Farley, Joshua Hansen, Andrew Howe, Patrick Alan Johnson, Mark Otterlee, Ted Schmitt, Hunter Pitelka, Stephen Daspit, Rachel Ratner, Christopher Wilhelm, Sebastian Wood, Mike Jacobi, Hannah Kerner, Evan Shelhamer, Ali Farhadi, Ranjay Krishna, Patrick Beukema

Abstract:
Earth observation data presents a unique challenge: it is spatial like images, sequential like video or text, and highly multimodal. We present OlmoEarth: a multimodal, spatio-temporal foundation model that employs a novel self-supervised learning formulation, masking strategy, and loss all designed for the Earth observation domain. OlmoEarth achieves state-of-the-art performance compared to 12 other foundation models across a variety of research benchmarks and real-world tasks from external partners. When evaluating embeddings OlmoEarth achieves the best performance on 15 out of 24 tasks, and with full fine-tuning it is the best on 19 of 29 tasks. We deploy OlmoEarth as the backbone of an end-to-end platform for data collection, labeling, training, and inference of Earth observation models. The OlmoEarth Platform puts frontier foundation models and powerful data management tools into the hands of non-profits and NGOs working to solve the world's biggest problems. OlmoEarth source code, training data, and pre-trained weights are available at $\href{https://github.com/allenai/olmoearth_pretrain}{\text{https://github.com/allenai/olmoearth_pretrain}}$.

Paperid: 569, https://arxiv.org/pdf/2511.13649.pdf GitHub

Abstract:
Distribution Matching Distillation (DMD) distills a pre-trained multi-step diffusion model to a few-step one to improve inference efficiency. However, the performance of the latter is often capped by the former. To circumvent this dilemma, we propose DMDR, a novel framework that combines Reinforcement Learning (RL) techniques into the distillation process. We show that for the RL of the few-step generator, the DMD loss itself is a more effective regularization compared to the traditional ones. In turn, RL can help to guide the mode coverage process in DMD more effectively. These allow us to unlock the capacity of the few-step generator by conducting distillation and RL simultaneously. Meanwhile, we design the dynamic distribution guidance and dynamic renoise sampling training strategies to improve the initial distillation process. The experiments demonstrate that DMDR can achieve leading visual quality, prompt coherence among few-step methods, and even exhibit performance that exceeds the multi-step teacher.

Paperid: 570, https://arxiv.org/pdf/2511.13645.pdf GitHub GitHub

Abstract:
We present FuseSampleAgg, a CUDA operator that fuses neighbor sampling and mean aggregation into a single pass for one and two hop GraphSAGE. By eliminating block materialization and extra kernel launches, FuseSampleAgg reduces memory traffic and overhead while preserving GraphSAGE mean semantics via saved index replay. Across the Reddit, ogbn-arxiv, and ogbn-products benchmarks (batch size 1024, automatic mixed precision enabled), we observe step time speedups up to 51x on ogbn-products, about 4x on Reddit with fanouts 10-10 and 15-10, and about 3.3x on ogbn-arxiv at larger fanouts, with peak GPU memory reductions up to 100x, 36x, and about 3.5x, respectively. The operator is deterministic, integrates with standard PyTorch optimizers, and ships with scripts that reproduce all tables and figures from CSV logs. Code and scripts are available at https://github.com/SV25-22/FuseSampleAgg.

Paperid: 571, https://arxiv.org/pdf/2511.13611.pdf GitHub

Abstract:
We present BIOMERO 2.0, a major evolution of the BIOMERO framework that transforms OMERO into a FAIR-compliant (findable, accessible, interoperable, and reusable), provenance-aware bioimaging platform. BIOMERO 2.0 integrates data import, preprocessing, analysis, and workflow monitoring through an OMERO.web plugin and containerized components. The importer subsystem facilitates in-place import using containerized preprocessing and metadata enrichment via forms, while the analyzer subsystem coordinates and tracks containerized analyses on high-performance computing systems via the BIOMERO Python library. All imports and analyses are recorded with parameters, versions, and results, ensuring real-time provenance accessible through integrated dashboards. This dual approach places OMERO at the heart of the bioimaging analysis process: the importer ensures provenance from image acquisition through preprocessing and import into OMERO, while the analyzer records it for downstream processing. These integrated layers enhance OMEROs FAIRification, supporting traceable, reusable workflows for image analysis that bridge the gap between data import, analysis, and sharing.

Paperid: 572, https://arxiv.org/pdf/2511.13552.pdf GitHub

Abstract:
Monocular height estimation plays a critical role in 3D perception for remote sensing, offering a cost-effective alternative to multi-view or LiDAR-based methods. While deep learning has significantly advanced the capabilities of monocular height estimation, these methods remain fundamentally limited by the availability of labeled data, which are expensive and labor-intensive to obtain at scale. The scarcity of high-quality annotations hinders the generalization and performance of existing models. To overcome this limitation, we propose leveraging large volumes of unlabeled data through a semi-supervised learning framework, enabling the model to extract informative cues from unlabeled samples and improve its predictive performance. In this work, we introduce TSE-Net, a self-training pipeline for semi-supervised monocular height estimation. The pipeline integrates teacher, student, and exam networks. The student network is trained on unlabeled data using pseudo-labels generated by the teacher network, while the exam network functions as a temporal ensemble of the student network to stabilize performance. The teacher network is formulated as a joint regression and classification model: the regression branch predicts height values that serve as pseudo-labels, and the classification branch predicts height value classes along with class probabilities, which are used to filter pseudo-labels. Height value classes are defined using a hierarchical bi-cut strategy to address the inherent long-tailed distribution of heights, and the predicted class probabilities are calibrated with a Plackett-Luce model to reflect the expected accuracy of pseudo-labels. We evaluate the proposed pipeline on three datasets spanning different resolutions and imaging modalities. Codes are available at https://github.com/zhu-xlab/tse-net.

Paperid: 573, https://arxiv.org/pdf/2511.13488.pdf GitHub

Abstract:
Generating high-quality human interactions holds significant value for applications like virtual reality and robotics. However, existing methods often fail to preserve unique individual characteristics or fully adhere to textual descriptions. To address these challenges, we introduce InterMoE, a novel framework built on a Dynamic Temporal-Selective Mixture of Experts. The core of InterMoE is a routing mechanism that synergistically uses both high-level text semantics and low-level motion context to dispatch temporal motion features to specialized experts. This allows experts to dynamically determine the selection capacity and focus on critical temporal features, thereby preserving specific individual characteristic identities while ensuring high semantic fidelity. Extensive experiments show that InterMoE achieves state-of-the-art performance in individual-specific high-fidelity 3D human interaction generation, reducing FID scores by 9% on the InterHuman dataset and 22% on InterX.

Paperid: 574, https://arxiv.org/pdf/2511.13465.pdf GitHub

Abstract:
Since the 21st century, artificial intelligence has been leading a new round of industrial revolution. Under the training framework, the optimization algorithm aims to stably converge high-dimensional optimization to local and even global minima. Entering the era of large language models, although the scale of model parameters and data has increased, Adam remains the mainstream optimization algorithm. However, compared with stochastic gradient descent (SGD) based optimization algorithms, Adam is more likely to converge to non-flat minima. To address this issue, the AdamX algorithm is proposed. Its core innovation lies in the proposition of a novel type of second-order moment estimation exponential decay rate, which gradually weakens the learning step correction strength as training progresses, and degrades to SGD in the stable training period, thereby improving the stability of training in the stable period and possibly enhancing generalization ability. Experimental results show that our second-order moment estimation exponential decay rate is better than the current second-order moment estimation exponential decay rate, and AdamX can stably outperform Adam and its variants in terms of performance. Our code is open-sourced at https://github.com/mengzhu0308/AdamX.

Paperid: 575, https://arxiv.org/pdf/2511.13417.pdf GitHub

Abstract:
Accurate delineation of agricultural field boundaries from satellite imagery is essential for land management and crop monitoring, yet existing methods often produce incomplete boundaries, merge adjacent fields, and struggle to scale. We present the Delineate Anything Flow (DelAnyFlow) methodology, a resolution-agnostic approach for large-scale field boundary mapping. DelAnyFlow combines the DelAny instance segmentation model, based on a YOLOv11 backbone and trained on the large-scale Field Boundary Instance Segmentation-22M (FBIS 22M) dataset, with a structured post-processing, merging, and vectorization sequence to generate topologically consistent vector boundaries. FBIS 22M, the largest dataset of its kind, contains 672,909 multi-resolution image patches (0.25-10m) and 22.9million validated field instances. The DelAny model delivers state-of-the-art accuracy with over 100% higher mAP and 400x faster inference than SAM2. DelAny demonstrates strong zero-shot generalization and supports national-scale applications: using Sentinel 2 data for 2024, DelAnyFlow generated a complete field boundary layer for Ukraine (603,000km2) in under six hours on a single workstation. DelAnyFlow outputs significantly improve boundary completeness relative to operational products from Sinergise Solutions and NASA Harvest, particularly in smallholder and fragmented systems (0.25-1ha). For Ukraine, DelAnyFlow delineated 3.75M fields at 5m and 5.15M at 2.5m, compared to 2.66M detected by Sinergise Solutions and 1.69M by NASA Harvest. This work delivers a scalable, cost-effective methodology for field delineation in regions lacking digital cadastral data. A project landing page with links to model weights, code, national-scale vector outputs, and dataset is available at https://lavreniuk.github.io/Delineate-Anything/.

Paperid: 576, https://arxiv.org/pdf/2511.13399.pdf GitHub

Abstract:
Scene Text Editing (STE) aims to naturally modify text in images while preserving visual consistency, the decisive factors of which can be divided into three parts, i.e., text style, text content, and background. Previous methods have struggled with incomplete disentanglement of editable attributes, typically addressing only one aspect - such as editing text content - thus limiting controllability and visual consistency. To overcome these limitations, we propose TripleFDS, a novel framework for STE with disentangled modular attributes, and an accompanying dataset called SCB Synthesis. SCB Synthesis provides robust training data for triple feature disentanglement by utilizing the "SCB Group", a novel construct that combines three attributes per image to generate diverse, disentangled training groups. Leveraging this construct as a basic training unit, TripleFDS first disentangles triple features, ensuring semantic accuracy through inter-group contrastive regularization and reducing redundancy through intra-sample multi-feature orthogonality. In the synthesis phase, TripleFDS performs feature remapping to prevent "shortcut" phenomena during reconstruction and mitigate potential feature leakage. Trained on 125,000 SCB Groups, TripleFDS achieves state-of-the-art image fidelity (SSIM of 44.54) and text accuracy (ACC of 93.58%) on the mainstream STE benchmarks. Besides superior performance, the more flexible editing of TripleFDS supports new operations such as style replacement and background transfer. Code: https://github.com/yusenbao01/TripleFDS

Paperid: 577, https://arxiv.org/pdf/2511.13365.pdf GitHub

Abstract:
Split inference (SI) enables users to access deep learning (DL) services without directly transmitting raw data. However, recent studies reveal that data reconstruction attacks (DRAs) can recover the original inputs from the smashed data sent from the client to the server, leading to significant privacy leakage. While various defenses have been proposed, they often result in substantial utility degradation, particularly when the client-side model is shallow. We identify a key cause of this trade-off: existing defenses apply excessive perturbation to redundant information in the smashed data. To address this issue in computer vision tasks, we propose InfoDecom, a defense framework that first decomposes and removes redundant information and then injects noise calibrated to provide theoretically guaranteed privacy. Experiments demonstrate that InfoDecom achieves a superior utility-privacy trade-off compared to existing baselines. The code and the appendix are available at https://github.com/SASA-cloud/InfoDecom.

Paperid: 578, https://arxiv.org/pdf/2511.13356.pdf GitHub

Abstract:
Backdoor attacks pose severe threats to machine learning systems, prompting extensive research in this area. However, most existing work focuses on single-target All-to-One (A2O) attacks, overlooking the more complex All-to-X (A2X) attacks with multiple target classes, which are often assumed to have low attack success rates. In this paper, we first demonstrate that A2X attacks are robust against state-of-the-art defenses. We then propose a novel attack strategy that enhances the success rate of A2X attacks while maintaining robustness by optimizing grouping and target class assignment mechanisms. Our method improves the attack success rate by up to 28%, with average improvements of 6.7%, 16.4%, 14.1% on CIFAR10, CIFAR100, and Tiny-ImageNet, respectively. We anticipate that this study will raise awareness of A2X attacks and stimulate further research in this under-explored area. Our code is available at https://github.com/kazefjj/A2X-backdoor .

Paperid: 579, https://arxiv.org/pdf/2511.13318.pdf GitHub

Abstract:
Blockchain technologies are rapidly transforming both academia and industry. However, large-scale blockchain data collection remains prohibitively expensive, as many RPC providers only offer enhanced APIs with high pricing tiers that are unsuitable for budget-constrained research or industrial-scale applications, which has significantly slowed down academic studies and product development. Moreover, there is a clear lack of a systematic framework that allows flexible integration of new modules for analyzing on-chain data. To address these challenges, we introduce LinkXplore, the first open framework for collecting and managing on-chain data. LinkXplore enables users to bypass costly blockchain data providers by directly analyzing raw data from RPC queries or streams, thereby offering high-quality blockchain data at a fraction of the cost. Through a simple API and backend processing logic, any type of chain data can be integrated into the framework. This makes it a practical alternative for both researchers and developers with limited budgets. Code and dataset used in this project are publicly available at https://github.com/Linkis-Project/LinkXplore

Paperid: 580, https://arxiv.org/pdf/2511.13278.pdf GitHub

Abstract:
Lightweight building surface models are crucial for digital city, navigation, and fast geospatial analytics, yet conventional multi-view geometry pipelines remain cumbersome and quality-sensitive due to their reliance on dense reconstruction, meshing, and subsequent simplification. This work presents SF-Recon, a method that directly reconstructs lightweight building surfaces from multi-view images without post-hoc mesh simplification. We first train an initial 3D Gaussian Splatting (3DGS) field to obtain a view-consistent representation. Building structure is then distilled by a normal-gradient-guided Gaussian optimization that selects primitives aligned with roof and wall boundaries, followed by multi-view edge-consistency pruning to enhance structural sharpness and suppress non-structural artifacts without external supervision. Finally, a multi-view depth-constrained Delaunay triangulation converts the structured Gaussian field into a lightweight, structurally faithful building mesh. Based on a proposed SF dataset, the experimental results demonstrate that our SF-Recon can directly reconstruct lightweight building models from multi-view imagery, achieving substantially fewer faces and vertices while maintaining computational efficiency. Website:https://lzh282140127-cell.github.io/SF-Recon-project/

Paperid: 581, https://arxiv.org/pdf/2511.13269.pdf GitHub

Abstract:
Vision-Language Models (VLMs), leveraging their powerful visual perception and reasoning capabilities, have been widely applied in Unmanned Aerial Vehicle (UAV) tasks. However, the spatial intelligence capabilities of existing VLMs in UAV scenarios remain largely unexplored, raising concerns about their effectiveness in navigating and interpreting dynamic environments. To bridge this gap, we introduce SpatialSky-Bench, a comprehensive benchmark specifically designed to evaluate the spatial intelligence capabilities of VLMs in UAV navigation. Our benchmark comprises two categories-Environmental Perception and Scene Understanding-divided into 13 subcategories, including bounding boxes, color, distance, height, and landing safety analysis, among others. Extensive evaluations of various mainstream open-source and closed-source VLMs reveal unsatisfactory performance in complex UAV navigation scenarios, highlighting significant gaps in their spatial capabilities. To address this challenge, we developed the SpatialSky-Dataset, a comprehensive dataset containing 1M samples with diverse annotations across various scenarios. Leveraging this dataset, we introduce Sky-VLM, a specialized VLM designed for UAV spatial reasoning across multiple granularities and contexts. Extensive experimental results demonstrate that Sky-VLM achieves state-of-the-art performance across all benchmark tasks, paving the way for the development of VLMs suitable for UAV scenarios. The source code is available at https://github.com/linglingxiansen/SpatialSKy.

Paperid: 582, https://arxiv.org/pdf/2511.13261.pdf GitHub

Abstract:
Driven by recent advances in vision language models (VLMs) and egocentric perception research, we introduce the concept of an egocentric procedural AI assistant (EgoProceAssist) tailored to step-by-step support daily procedural tasks in a first-person view. In this work, we start by identifying three core tasks: egocentric procedural error detection, egocentric procedural learning, and egocentric procedural question answering. These tasks define the essential functions of EgoProceAssist within a new taxonomy. Specifically, our work encompasses a comprehensive review of current techniques, relevant datasets, and evaluation metrics across these three core areas. To clarify the gap between the proposed EgoProceAssist and existing VLM-based AI assistants, we introduce novel experiments and provide a comprehensive evaluation of representative VLM-based methods. Based on these findings and our technical analysis, we discuss the challenges ahead and suggest future research directions. Furthermore, an exhaustive list of this study is publicly available in an active repository that continuously collects the latest work: https://github.com/z1oong/Building-Egocentric-Procedural-AI-Assistant

Paperid: 583, https://arxiv.org/pdf/2511.13259.pdf GitHub

Abstract:
Large multimodal models (LMMs) have demonstrated remarkable capabilities across a wide range of tasks, however their knowledge and abilities in the cross-view geo-localization and pose estimation domains remain unexplored, despite potential benefits for navigation, autonomous driving, outdoor robotics, \textit{etc}. To bridge this gap, we introduce \textbf{GeoX-Bench}, a comprehensive \underline{Bench}mark designed to explore and evaluate the capabilities of LMMs in \underline{cross}-view \underline{Geo}-localization and pose estimation. Specifically, GeoX-Bench contains 10,859 panoramic-satellite image pairs spanning 128 cities in 49 countries, along with corresponding 755,976 question-answering (QA) pairs. Among these, 42,900 QA pairs are designated for benchmarking, while the remaining are intended to enhance the capabilities of LMMs. Based on GeoX-Bench, we evaluate the capabilities of 25 state-of-the-art LMMs on cross-view geo-localization and pose estimation tasks, and further explore the empowered capabilities of instruction-tuning. Our benchmark demonstrate that while current LMMs achieve impressive performance in geo-localization tasks, their effectiveness declines significantly on the more complex pose estimation tasks, highlighting a critical area for future improvement, and instruction-tuning LMMs on the training data of GeoX-Bench can significantly improve the cross-view geo-sense abilities. The GeoX-Bench is available at \textcolor{magenta}{https://github.com/IntMeGroup/GeoX-Bench}.

Paperid: 584, https://arxiv.org/pdf/2511.13250.pdf GitHub

Abstract:
We present reproducible, edge-aware baselines for ogbn-proteins in PyTorch Geometric (PyG). We study two system choices that dominate practice: (i) how 8-dimensional edge evidence is aggregated into node inputs, and (ii) how edges are used inside message passing. Our strongest baseline is GraphSAGE with sum-based edge-to-node features. We compare LayerNorm (LN), BatchNorm (BN), and a species-aware Conditional LayerNorm (CLN), and report compute cost (time, VRAM, parameters) together with accuracy (ROC-AUC) and decision quality. In our primary experimental setup (hidden size 512, 3 layers, 3 seeds), sum consistently beats mean and max; BN attains the best AUC, while CLN matches the AUC frontier with better thresholded F1. Finally, post-hoc per-label temperature scaling plus per-label thresholds substantially improves micro-F1 and expected calibration error (ECE) with negligible AUC change, and light label-correlation smoothing yields small additional gains. We release standardized artifacts and scripts used for all of the runs presented in the paper.

Paperid: 585, https://arxiv.org/pdf/2511.13247.pdf GitHub

Abstract:
Contact-based grasp generation plays a crucial role in various applications. Recent methods typically focus on the geometric structure of objects, producing grasps with diverse hand poses and plausible contact points. However, these approaches often overlook the physical attributes of the grasp, specifically the contact force, leading to reduced stability of the grasp. In this paper, we focus on stable grasp generation using explicit contact force predictions. First, we define a force-aware contact representation by transforming the normal force value into discrete levels and encoding it using a one-hot vector. Next, we introduce force-aware stability constraints. We define the stability problem as an acceleration minimization task and explicitly relate stability with contact geometry by formulating the underlying physical constraints. Finally, we present a pose optimizer that systematically integrates our contact representation and stability constraints to enable stable grasp generation. We show that these constraints can help identify key contact points for stability which provide effective initialization and guidance for optimization towards a stable grasp. Experiments are carried out on two public benchmarks, showing that our method brings about 20% improvement in stability metrics and adapts well to novel objects.

Paperid: 586, https://arxiv.org/pdf/2511.13223.pdf GitHub

Abstract:
Emerging reasoning LLMs such as OpenAI-o1 and DeepSeek-R1 have achieved strong performance on complex reasoning tasks by generating long chain-of-thought (CoT) traces. However, these long CoTs result in increased token usage, leading to higher inference latency and memory consumption. As a result, balancing accuracy and reasoning efficiency has become essential for deploying reasoning LLMs in practical applications. Existing long-to-short (Long2Short) methods aim to reduce inference length but often sacrifice accuracy, revealing a need for an approach that maintains performance while lowering token costs. To address this efficiency-accuracy tradeoff, we propose TokenSqueeze, a novel Long2Short method that condenses reasoning paths while preserving performance and relying exclusively on self-generated data. First, to prevent performance degradation caused by excessive compression of reasoning depth, we propose to select self-generated samples whose reasoning depth is adaptively matched to the complexity of the problem. To further optimize the linguistic expression without altering the underlying reasoning paths, we introduce a distribution-aligned linguistic refinement method that enhances the clarity and conciseness of the reasoning path while preserving its logical integrity. Comprehensive experimental results demonstrate the effectiveness of TokenSqueeze in reducing token usage while maintaining accuracy. Notably, DeepSeek-R1-Distill-Qwen-7B fine-tuned using our proposed method achieved a 50\% average token reduction while preserving accuracy on the MATH500 benchmark. TokenSqueeze exclusively utilizes the model's self-generated data, enabling efficient and high-fidelity reasoning without relying on manually curated short-answer datasets across diverse applications. Our code is available at https://github.com/zhangyx1122/TokenSqueeze.

Paperid: 587, https://arxiv.org/pdf/2511.13222.pdf GitHub

Abstract:
Appearance-based gaze estimation, aiming to predict accurate 3D gaze direction from a single facial image, has made promising progress in recent years. However, most methods suffer significant performance degradation in cross-domain evaluation due to interference from gaze-irrelevant factors, such as expressions, wearables, and image quality. To alleviate this problem, we present a novel Hybrid-domain Adaptative Representation Learning (shorted by HARL) framework that exploits multi-source hybrid datasets to learn robust gaze representation. More specifically, we propose to disentangle gaze-relevant representation from low-quality facial images by aligning features extracted from high-quality near-eye images in an unsupervised domain-adaptation manner, which hardly requires any computational or inference costs. Additionally, we analyze the effect of head-pose and design a simple yet efficient sparse graph fusion module to explore the geometric constraint between gaze direction and head-pose, leading to a dense and robust gaze representation. Extensive experiments on EyeDiap, MPIIFaceGaze, and Gaze360 datasets demonstrate that our approach achieves state-of-the-art accuracy of $\textbf{5.02}^{\circ}$ and $\textbf{3.36}^{\circ}$, and $\textbf{9.26}^{\circ}$ respectively, and present competitive performances through cross-dataset evaluation. The code is available at https://github.com/da60266/HARL.

Paperid: 588, https://arxiv.org/pdf/2511.13216.pdf GitHub

Abstract:
Deployment of legged robots for navigating challenging terrains (e.g., stairs, slopes, and unstructured environments) has gained increasing preference over wheel-based platforms. In such scenarios, accurate odometry estimation is a preliminary requirement for stable locomotion, localization, and mapping. Traditional proprioceptive approaches, which rely on leg kinematics sensor modalities and inertial sensing, suffer from irrepressible vertical drift caused by frequent contact impacts, foot slippage, and vibrations, particularly affected by inaccurate roll and pitch estimation. Existing methods incorporate exteroceptive sensors such as LiDAR or cameras. Further enhancement has been introduced by leveraging gravity vector estimation to add additional observations on roll and pitch, thereby increasing the accuracy of vertical pose estimation. However, these approaches tend to degrade in feature-sparse or repetitive scenes and are prone to errors from double-integrated IMU acceleration. To address these challenges, we propose GaRLILEO, a novel gravity-aligned continuous-time radar-leg-inertial odometry framework. GaRLILEO decouples velocity from the IMU by building a continuous-time ego-velocity spline from SoC radar Doppler and leg kinematics information, enabling seamless sensor fusion which mitigates odometry distortion. In addition, GaRLILEO can reliably capture accurate gravity vectors leveraging a novel soft S2-constrained gravity factor, improving vertical pose accuracy without relying on LiDAR or cameras. Evaluated on a self-collected real-world dataset with diverse indoor-outdoor trajectories, GaRLILEO demonstrates state-of-the-art accuracy, particularly in vertical odometry estimation on stairs and slopes. We open-source both our dataset and algorithm to foster further research in legged robot odometry and SLAM. https://garlileo.github.io/GaRLILEO

Paperid: 589, https://arxiv.org/pdf/2511.13208.pdf GitHub

Abstract:
Existing multi-person video pose estimation methods typically adopt a two-stage pipeline: detecting individuals in each frame, followed by temporal modeling for single-person pose estimation. This design relies on heuristic operations such as detection, RoI cropping, and non-maximum suppression (NMS), limiting both accuracy and efficiency. In this paper, we present a fully end-to-end framework for multi-person 2D pose estimation in videos, effectively eliminating heuristic operations. A key challenge is to associate individuals across frames under complex and overlapping temporal trajectories. To address this, we introduce a novel Pose-Aware Video transformEr Network (PAVE-Net), which features a spatial encoder to model intra-frame relations and a spatiotemporal pose decoder to capture global dependencies across frames. To achieve accurate temporal association, we propose a pose-aware attention mechanism that enables each pose query to selectively aggregate features corresponding to the same individual across consecutive frames.Additionally, we explicitly model spatiotemporal dependencies among pose keypoints to improve accuracy. Notably, our approach is the first end-to-end method for multi-frame 2D human pose estimation.Extensive experiments show that PAVE-Net substantially outperforms prior image-based end-to-end methods, achieving a \textbf{6.0} mAP improvement on PoseTrack2017, and delivers accuracy competitive with state-of-the-art two-stage video-based approaches, while offering significant gains in efficiency.Project page: https://github.com/zgspose/PAVENet

Paperid: 590, https://arxiv.org/pdf/2511.13191.pdf GitHub

Abstract:
Painting embodies a unique form of visual storytelling, where the creation process is as significant as the final artwork. Although recent advances in generative models have enabled visually compelling painting synthesis, most existing methods focus solely on final image generation or patch-based process simulation, lacking explicit stroke structure and failing to produce smooth, realistic shading. In this work, we present a differentiable stroke reconstruction framework that unifies painting, stylized texturing, and smudging to faithfully reproduce the human painting-smudging loop. Given an input image, our framework first optimizes single- and dual-color Bezier strokes through a parallel differentiable paint renderer, followed by a style generation module that synthesizes geometry-conditioned textures across diverse painting styles. We further introduce a differentiable smudge operator to enable natural color blending and shading. Coupled with a coarse-to-fine optimization strategy, our method jointly optimizes stroke geometry, color, and texture under geometric and semantic guidance. Extensive experiments on oil, watercolor, ink, and digital paintings demonstrate that our approach produces realistic and expressive stroke reconstructions, smooth tonal transitions, and richly stylized appearances, offering a unified model for expressive digital painting creation. See our project page for more demos: https://yingjiang96.github.io/DiffPaintWebsite/.

Paperid: 591, https://arxiv.org/pdf/2511.13189.pdf GitHub

Abstract:
Foundation models have revolutionized artificial intelligence across numerous domains, yet their transformative potential remains largely untapped in Extreme Multi-label Classification (XMC). Queries in XMC are associated with relevant labels from extremely large label spaces, where it is critical to strike a balance between efficiency and performance. Therefore, many recent approaches efficiently pose XMC as a maximum inner product search between embeddings learned from small encoder-only transformer architectures. In this paper, we address two important aspects in XMC: how to effectively harness larger decoder-only models, and how to exploit visual information while maintaining computational efficiency. We demonstrate that both play a critical role in XMC separately and can be combined for improved performance. We show that a few billion-size decoder can deliver substantial improvements while keeping computational overhead manageable. Furthermore, our Vision-enhanced eXtreme Multi-label Learning framework (ViXML) efficiently integrates foundation vision models by pooling a single embedding per image. This limits computational growth while unlocking multi-modal capabilities. Remarkably, ViXML with small encoders outperforms text-only decoder in most cases, showing that an image is worth billions of parameters. Finally, we present an extension of existing text-only datasets to exploit visual metadata and make them available for future benchmarking. Comprehensive experiments across four public text-only datasets and their corresponding image enhanced versions validate our proposals' effectiveness, surpassing previous state-of-the-art by up to +8.21\% in P@1 on the largest dataset. ViXML's code is available at https://github.com/DiegoOrtego/vixml.

Paperid: 592, https://arxiv.org/pdf/2511.13186.pdf GitHub

Abstract:
Self-play reinforcement learning has demonstrated significant success in learning complex strategic and interactive behaviors in competitive multi-agent games. However, achieving such behaviors in continuous decision spaces remains challenging. Ensuring adaptability and generalization in self-play settings is critical for achieving competitive performance in dynamic multi-agent environments. These challenges often cause methods to converge slowly or fail to converge at all to a Nash equilibrium, making agents vulnerable to strategic exploitation by unseen opponents. To address these challenges, we propose DiffFP, a fictitious play (FP) framework that estimates the best response to unseen opponents while learning a robust and multimodal behavioral policy. Specifically, we approximate the best response using a diffusion policy that leverages generative modeling to learn adaptive and diverse strategies. Through empirical evaluation, we demonstrate that the proposed FP framework converges towards $ε$-Nash equilibria in continuous- space zero-sum games. We validate our method on complex multi-agent environments, including racing and multi-particle zero-sum games. Simulation results show that the learned policies are robust against diverse opponents and outperform baseline reinforcement learning policies. Our approach achieves up to 3$\times$ faster convergence and 30$\times$ higher success rates on average against RL-based baselines, demonstrating its robustness to opponent strategies and stability across training iterations

Paperid: 593, https://arxiv.org/pdf/2511.13121.pdf GitHub

Abstract:
Reconstructing 3D scenes and synthesizing novel views from sparse input views is a highly challenging task. Recent advances in video diffusion models have demonstrated strong temporal reasoning capabilities, making them a promising tool for enhancing reconstruction quality under sparse-view settings. However, existing approaches are primarily designed for modest viewpoint variations, which struggle in capturing fine-grained details in close-up scenarios since input information is severely limited. In this paper, we present a diffusion-based framework, called CloseUpShot, for close-up novel view synthesis from sparse inputs via point-conditioned video diffusion. Specifically, we observe that pixel-warping conditioning suffers from severe sparsity and background leakage in close-up settings. To address this, we propose hierarchical warping and occlusion-aware noise suppression, enhancing the quality and completeness of the conditioning images for the video diffusion model. Furthermore, we introduce global structure guidance, which leverages a dense fused point cloud to provide consistent geometric context to the diffusion process, to compensate for the lack of globally consistent 3D constraints in sparse conditioning inputs. Extensive experiments on multiple datasets demonstrate that our method outperforms existing approaches, especially in close-up novel view synthesis, clearly validating the effectiveness of our design.

Paperid: 594, https://arxiv.org/pdf/2511.13118.pdf GitHub

Abstract:
Zero-shot event extraction (ZSEE) remains a significant challenge for large language models (LLMs) due to the need for complex reasoning and domain-specific understanding. Direct prompting often yields incomplete or structurally invalid outputs--such as misclassified triggers, missing arguments, and schema violations. To address these limitations, we present Agent-Event-Coder (AEC), a novel multi-agent framework that treats event extraction like software engineering: as a structured, iterative code-generation process. AEC decomposes ZSEE into specialized subtasks--retrieval, planning, coding, and verification--each handled by a dedicated LLM agent. Event schemas are represented as executable class definitions, enabling deterministic validation and precise feedback via a verification agent. This programming-inspired approach allows for systematic disambiguation and schema enforcement through iterative refinement. By leveraging collaborative agent workflows, AEC enables LLMs to produce precise, complete, and schema-consistent extractions in zero-shot settings. Experiments across five diverse domains and six LLMs demonstrate that AEC consistently outperforms prior zero-shot baselines, showcasing the power of treating event extraction like code generation. The code and data are released on https://github.com/UESTC-GQJ/Agent-Event-Coder.

Paperid: 595, https://arxiv.org/pdf/2511.13110.pdf GitHub

Abstract:
Image dehazing is an important task in the field of computer vision, aiming at restoring clear and detail-rich visual content from haze-affected images. However, when dealing with complex scenes, existing methods often struggle to strike a balance between fine-grained feature representation of inhomogeneous haze distribution and global consistency modeling. Furthermore, to better learn the common degenerate representation of haze in spatial variations, we propose an unsupervised dehaze method for implicit neural degradation representation. Firstly, inspired by the Kolmogorov-Arnold representation theorem, we propose a mechanism combining the channel-independent and channel-dependent mechanisms, which efficiently enhances the ability to learn from nonlinear dependencies. which in turn achieves good visual perception in complex scenes. Moreover, we design an implicit neural representation to model haze degradation as a continuous function to eliminate redundant information and the dependence on explicit feature extraction and physical models. To further learn the implicit representation of the haze features, we also designed a dense residual enhancement module from it to eliminate redundant information. This achieves high-quality image restoration. Experimental results show that our method achieves competitive dehaze performance on various public and real-world datasets. This project code will be available at https://github.com/Fan-pixel/NeDR-Dehaze.

Paperid: 596, https://arxiv.org/pdf/2511.13105.pdf GitHub

Abstract:
Multi-object tracking (MOT) predominantly follows the tracking-by-detection paradigm, where Kalman filters serve as the standard motion predictor due to computational efficiency but inherently fail on non-linear motion patterns. Conversely, recent data-driven motion predictors capture complex non-linear dynamics but suffer from limited domain generalization and computational overhead. Through extensive analysis, we reveal that even in datasets dominated by non-linear motion, Kalman filter outperforms data-driven predictors in up to 34\% of cases, demonstrating that real-world tracking scenarios inherently involve both linear and non-linear patterns. To leverage this complementarity, we propose PlugTrack, a novel framework that adaptively fuses Kalman filter and data-driven motion predictors through multi-perceptive motion understanding. Our approach employs multi-perceptive motion analysis to generate adaptive blending factors. PlugTrack achieves significant performance gains on MOT17/MOT20 and state-of-the-art on DanceTrack without modifying existing motion predictors. To the best of our knowledge, PlugTrack is the first framework to bridge classical and modern motion prediction paradigms through adaptive fusion in MOT.

Paperid: 597, https://arxiv.org/pdf/2511.13100.pdf GitHub

Abstract:
As drone-based applications proliferate, paramount contactless sensing of airborne drones from the ground becomes indispensable. This work demonstrates concentrating on propeller rotational speed will substantially improve drone sensing performance and proposes an event-camera-based solution, \sysname. \sysname features two components: \textit{Count Every Rotation} achieves accurate, real-time propeller speed estimation by mitigating ultra-high sensitivity of event cameras to environmental noise. \textit{Every Rotation Counts} leverages these speeds to infer both internal and external drone dynamics. Extensive evaluations in real-world drone delivery scenarios show that \sysname achieves a sensing latency of 3$ms$ and a rotational speed estimation error of merely 0.23\%. Additionally, \sysname infers drone flight commands with 96.5\% precision and improves drone tracking accuracy by over 22\% when combined with other sensing modalities. \textit{ Demo: {\color{blue}https://eventpro25.github.io/EventPro/.} }

Paperid: 598, https://arxiv.org/pdf/2511.13099.pdf GitHub

Abstract:
Lifelong learning on Whole Slide Images (WSIs) aims to train or fine-tune a unified model sequentially on cancer-related tasks, reducing the resources and effort required for data transfer and processing, especially given the gigabyte-scale size of WSIs. In this paper, we introduce MergeSlide, a simple yet effective framework that treats lifelong learning as a model merging problem by leveraging a vision-language pathology foundation model. When a new task arrives, it is: 1) defined with class-aware prompts, 2) fine-tuned for a few epochs using an MLP-free backbone, and 3) merged into a unified model using an orthogonal continual merging strategy that preserves performance and mitigates catastrophic forgetting. For inference under the class-incremental learning (CLASS-IL) setting, where task identity is unknown, we introduce Task-to-Class Prompt-aligned (TCP) inference. Specifically, TCP first identifies the most relevant task using task-level prompts and then applies the corresponding class-aware prompts to generate predictions. To evaluate MergeSlide, we conduct experiments on a stream of six TCGA datasets. The results show that MergeSlide outperforms both rehearsal-based continual learning and vision-language zero-shot baselines. Code and data are available at https://github.com/caodoanh2001/MergeSlide.

Paperid: 599, https://arxiv.org/pdf/2511.13087.pdf GitHub GitHub

Abstract:
Graphical User Interface (GUI) grounding - the task of mapping natural language instructions to screen coordinates - is essential for autonomous agents and accessibility technologies. Existing systems rely on monolithic models or one-shot pipelines that lack modularity and fail under visual clutter and ambiguous instructions. We introduce MEGA-GUI, a multi-stage framework that separates grounding into coarse Region-of-Interest (ROI) selection and fine-grained element grounding, orchestrated by specialized vision-language agents. MEGA-GUI features a bidirectional ROI zoom algorithm that mitigates spatial dilution and a context-aware rewriting agent that reduces semantic ambiguity. Our analysis reveals complementary strengths and weaknesses across vision-language models at different visual scales, and we show that leveraging this modular structure achieves consistently higher accuracy than monolithic approaches. On the visually dense ScreenSpot-Pro benchmark, MEGA-GUI attains 73.18% accuracy, and on the semantically complex OSWorld-G benchmark it reaches 68.63%, surpassing previously reported results. Code and the Grounding Benchmark Toolkit (GBT) are available at https://github.com/samsungsds-research-papers/mega-gui.

Paperid: 600, https://arxiv.org/pdf/2511.13061.pdf GitHub

Abstract:
Sparse Matrix-Vector Multiplication (SpMV) is a fundamental operation in the inference of sparse Large Language Models (LLMs). Because existing SpMV methods perform poorly under the low and unstructured sparsity (30-90%) commonly observed in pruned LLMs, unstructured pruning provided only limited memory reduction and speedup. We propose MACKO-SpMV, a GPU-optimized format and kernel co-designed to reduce storage overhead while preserving compatibility with the GPU's execution model. This enables efficient SpMV for unstructured sparsity without specialized hardware units (e.g., tensor cores) or format-specific precomputation. Empirical results show that at sparsity 50%, MACKO is the first approach with significant 1.5x memory reduction and 1.2-1.5x speedup over dense representation. Speedups over other SpMV baselines: 2.8-13.0x over cuSPARSE, 1.9-2.6x over Sputnik, and 2.2-2.5x over DASP. Applied to Llama2-7B pruned with Wanda to sparsity 50%, it delivers 1.5x memory reduction and 1.5x faster inference at fp16 precision. Thanks to MACKO, unstructured pruning at 50% sparsity is now justified in real-world LLM workloads.

Paperid: 601, https://arxiv.org/pdf/2511.13055.pdf GitHub

Abstract:
Monocular 3D lane detection is challenged by aleatoric uncertainty arising from inherent observation noise. Existing methods rely on simplified geometric assumptions, such as independent point predictions or global planar modeling, failing to capture structural variations and aleatoric uncertainty in real-world scenarios. In this paper, we propose MonoUnc, a bird's-eye view (BEV)-free 3D lane detector that explicitly models aleatoric uncertainty informed by local lane structures. Specifically, 3D lanes are projected onto the front-view (FV) space and approximated by parametric curves. Guided by curve predictions, curve-point query embeddings are dynamically generated for lane point predictions in 3D space. Each segment formed by two adjacent points is modeled as a 3D Gaussian, parameterized by the local structure and uncertainty estimations. Accordingly, a novel 3D Gaussian matching loss is designed to constrain these parameters jointly. Experiments on the ONCE-3DLanes and OpenLane datasets demonstrate that MonoUnc outperforms previous state-of-the-art (SoTA) methods across all benchmarks under stricter evaluation criteria. Additionally, we propose two comprehensive evaluation metrics for ONCE-3DLanes, calculating the average and maximum bidirectional Chamfer distances to quantify global and local errors. Codes are released at https://github.com/lrx02/MonoUnc.

Paperid: 602, https://arxiv.org/pdf/2511.13052.pdf GitHub

Abstract:
Language models (LMs) are often adapted through supervised fine-tuning (SFT) to specialize their capabilities for downstream tasks. However, in typical scenarios where the fine-tuning data is limited, e.g., compared to pre-training, SFT can lead LMs to overfit, causing them to rely on spurious patterns within the target task or to compromise other broadly useful capabilities as a side effect of narrow specialization. In this paper, we propose Learning-from-the-Undesirable (LfU), a simple yet effective regularization scheme for SFT to mitigate overfitting issues when fine-tuning LMs with limited data. Specifically, we aim to regularize the fine-tuning process to favor solutions that are resilient to "undesirable" model updates, e.g., gradient ascent steps that steer the model toward undesirable behaviors. To this end, we propose a novel form of consistency regularization that directly aligns internal representations of the model with those after an undesirable update. By leveraging representation-level data augmentation through undesirable updates, LfU effectively promotes generalization under limited data. Our experiments on diverse LM downstream tasks show that LfU serves as an effective prior that enhances adaptability while preserving pretrained knowledge. For example, our LM from LfU achieves a 16.8% average improvement on math tasks compared to vanilla SFT on the same dataset, where the latter even leads to degraded performance on those tasks. Furthermore, LfU exhibits improved robustness to prompt variations, e.g., yielding a 92.1% lower standard deviation in output performances compared to SFT, highlighting its versatile effects.

Paperid: 603, https://arxiv.org/pdf/2511.13047.pdf GitHub

Abstract:
Indoor semantic segmentation is fundamental to computer vision and robotics, supporting applications such as autonomous navigation, augmented reality, and smart environments. Although RGB-D fusion leverages complementary appearance and geometric cues, existing methods often depend on computationally intensive cross-attention mechanisms and insufficiently model intra- and inter-modal feature relationships, resulting in imprecise feature alignment and limited discriminative representation. To address these challenges, we propose DiffPixelFormer, a differential pixel-aware Transformer for RGB-D indoor scene segmentation that simultaneously enhances intra-modal representations and models inter-modal interactions. At its core, the Intra-Inter Modal Interaction Block (IIMIB) captures intra-modal long-range dependencies via self-attention and models inter-modal interactions with the Differential-Shared Inter-Modal (DSIM) module to disentangle modality-specific and shared cues, enabling fine-grained, pixel-level cross-modal alignment. Furthermore, a dynamic fusion strategy balances modality contributions and fully exploits RGB-D information according to scene characteristics. Extensive experiments on the SUN RGB-D and NYUDv2 benchmarks demonstrate that DiffPixelFormer-L achieves mIoU scores of 54.28% and 59.95%, outperforming DFormer-L by 1.78% and 2.75%, respectively. Code is available at https://github.com/gongyan1/DiffPixelFormer.

Paperid: 604, https://arxiv.org/pdf/2511.13036.pdf GitHub

Abstract:
Contrastive Language-Image Pre-training (CLIP) has demonstrated strong generalization across a wide range of visual tasks by leveraging large-scale English-image pairs. However, its extension to low-resource languages remains limited due to the scarcity of high-quality multilingual image-text data. Existing multilingual vision-language models exhibit consistently low retrieval performance in underrepresented languages including Czech, Finnish, Croatian, Hungarian, and Romanian on the Crossmodal-3600 (XM3600) benchmark. To address this, we propose a lightweight and data-efficient framework for multilingual vision-language alignment. Our approach requires no image-text pairs or text-text pairs and freezes both the pretrained image encoder and multilingual text encoder during training. Only a compact 1.7M-parameter projection module is trained, using a contrastive loss over English representations as semantic anchors. This minimal training setup enables robust multilingual alignment even for languages with limited supervision. Extensive evaluation across multiple multilingual retrieval benchmarks confirms the effectiveness of our method, showing significant gains in five underrepresented languages where existing models typically underperform. These findings highlight the effectiveness of our pivot-based, parameter-efficient alignment strategy for inclusive multimodal learning.

Paperid: 605, https://arxiv.org/pdf/2511.13035.pdf GitHub

Abstract:
We introduce a one-step generative policy for offline reinforcement learning that maps noise directly to actions via a residual reformulation of MeanFlow, making it compatible with Q-learning. While one-step Gaussian policies enable fast inference, they struggle to capture complex, multimodal action distributions. Existing flow-based methods improve expressivity but typically rely on distillation and two-stage training when trained with Q-learning. To overcome these limitations, we propose to reformulate MeanFlow to enable direct noise-to-action generation by integrating the velocity field and noise-to-action transformation into a single policy network-eliminating the need for separate velocity estimation. We explore several reformulation variants and identify an effective residual formulation that supports expressive and stable policy learning. Our method offers three key advantages: 1) efficient one-step noise-to-action generation, 2) expressive modelling of multimodal action distributions, and 3) efficient and stable policy learning via Q-learning in a single-stage training setup. Extensive experiments on 73 tasks across the OGBench and D4RL benchmarks demonstrate that our method achieves strong performance in both offline and offline-to-online reinforcement learning settings. Code is available at https://github.com/HiccupRL/MeanFlowQL.

Paperid: 606, https://arxiv.org/pdf/2511.13019.pdf GitHub GitHub

Abstract:
MeanFlow (MF) is a diffusion-motivated generative model that enables efficient few-step generation by learning long jumps directly from noise to data. In practice, it is often used as a latent MF by leveraging the pre-trained Stable Diffusion variational autoencoder (SD-VAE) for high-dimensional data modeling. However, MF training remains computationally demanding and is often unstable. During inference, the SD-VAE decoder dominates the generation cost, and MF depends on complex guidance hyperparameters for class-conditional generation. In this work, we develop an efficient training and sampling scheme for MF in the latent space of a Representation Autoencoder (RAE), where a pre-trained vision encoder (e.g., DINO) provides semantically rich latents paired with a lightweight decoder. We observe that naive MF training in the RAE latent space suffers from severe gradient explosion. To stabilize and accelerate training, we adopt Consistency Mid-Training for trajectory-aware initialization and use a two-stage scheme: distillation from a pre-trained flow matching teacher to speed convergence and reduce variance, followed by an optional bootstrapping stage with a one-point velocity estimator to further reduce deviation from the oracle mean flow. This design removes the need for guidance, simplifies training configurations, and reduces computation in both training and sampling. Empirically, our method achieves a 1-step FID of 2.03, outperforming vanilla MF's 3.43, while reducing sampling GFLOPS by 38% and total training cost by 83% on ImageNet 256. We further scale our approach to ImageNet 512, achieving a competitive 1-step FID of 3.23 with the lowest GFLOPS among all baselines. Code is available at https://github.com/sony/mf-rae.

Paperid: 607, https://arxiv.org/pdf/2511.13001.pdf GitHub

Abstract:
We introduce Medal S, a medical segmentation foundation model that supports native-resolution spatial and textual prompts within an end-to-end trainable framework. Unlike text-only methods lacking spatial awareness, Medal S achieves channel-wise alignment between volumetric prompts and text embeddings, mitigating inaccuracies from resolution mismatches. By preserving full 3D context, it efficiently processes multiple native-resolution masks in parallel, enhancing multi-class segmentation performance. A lightweight 3D convolutional module enables precise voxel-space refinement guided by both prompt types, supporting up to 243 classes across CT, MRI, PET, ultrasound, and microscopy modalities in the BiomedSegFM dataset. Medal S offers two prompting modes: a text-only mode, where model predictions serve as spatial prompts for self-refinement without human input, and a hybrid mode, incorporating manual annotations for enhanced flexibility. For 24-class segmentation, parallel spatial prompting reduces inference time by more than 90% compared to sequential prompting. We propose dynamic resampling to address target-patch ratio imbalance, extending SAT and nnU-Net for data augmentation. Furthermore, we develop optimized text preprocessing, a two-stage inference strategy, and post-processing techniques to improve memory efficiency, precision, and inference speed. On the five-modality average on the validation set, Medal S outperforms SAT with a DSC of 75.44 (vs. 69.83), NSD of 77.34 (vs. 71.06), F1 of 38.24 (vs. 24.88), and DSC TP of 65.46 (vs. 46.97). Medal S achieves excellent performance by harmonizing spatial precision with semantic textual guidance, demonstrating superior efficiency and accuracy in multi-class medical segmentation tasks compared to sequential prompt-based approaches. Medal S will be publicly available at https://github.com/yinghemedical/Medal-S.

Paperid: 608, https://arxiv.org/pdf/2511.12998.pdf GitHub

Abstract:
Image retouching aims to enhance visual quality while aligning with users' personalized aesthetic preferences. To address the challenge of balancing controllability and subjectivity, we propose a unified diffusion-based image retouching framework called PerTouch. Our method supports semantic-level image retouching while maintaining global aesthetics. Using parameter maps containing attribute values in specific semantic regions as input, PerTouch constructs an explicit parameter-to-image mapping for fine-grained image retouching. To improve semantic boundary perception, we introduce semantic replacement and parameter perturbation mechanisms in the training process. To connect natural language instructions with visual control, we develop a VLM-driven agent that can handle both strong and weak user instructions. Equipped with mechanisms of feedback-driven rethinking and scene-aware memory, PerTouch better aligns with user intent and captures long-term preferences. Extensive experiments demonstrate each component's effectiveness and the superior performance of PerTouch in personalized image retouching. Code is available at: https://github.com/Auroral703/PerTouch.

Paperid: 609, https://arxiv.org/pdf/2511.12979.pdf GitHub

Abstract:
Retrieval-Augmented Generation (RAG) is a critical paradigm for building reliable, knowledge-intensive Large Language Model (LLM) applications. However, the multi-stage pipeline (retrieve, generate) and unique workload characteristics (e.g., knowledge dependency) of RAG systems pose significant challenges for serving performance optimization. Existing generic LLM inference traces fail to capture these RAG-specific dynamics, creating a significant performance gap between academic research and real-world deployment. To bridge this gap, this paper introduces RAGPulse, an open-source RAG workload trace dataset. This dataset was collected from an university-wide Q&A system serving that has served more than 40,000 students and faculties since April 2024. We detail RAGPulse's system architecture, its privacy-preserving hash-based data format, and provide an in-depth statistical analysis. Our analysis reveals that real-world RAG workloads exhibit significant temporal locality and a highly skewed hot document access pattern. RAGPulse provides a high-fidelity foundation for researchers to develop and validate novel optimization strategies for RAG systems, such as content-aware batching and retrieval caching, ultimately enhancing the efficiency and reliability of RAG services. The code is available at https://github.com/flashserve/RAGPulse.

Paperid: 610, https://arxiv.org/pdf/2511.12959.pdf GitHub

Abstract:
Federated Recommendation (FedRec) has emerged as a key paradigm for building privacy-preserving recommender systems. However, existing FedRec models face a critical dilemma: memory-efficient single-knowledge models suffer from a suboptimal knowledge replacement practice that discards valuable personalization, while high-performance dual-knowledge models are often too memory-intensive for practical on-device deployment. We propose Federated Recommendation with Knowledge Guidance (FedRKG), a model-agnostic framework that resolves this dilemma. The core principle, Knowledge Guidance, avoids full replacement and instead fuses global knowledge into preserved local embeddings, attaining the personalization benefits of dual-knowledge within a single-knowledge memory footprint. Furthermore, we introduce Adaptive Guidance, a fine-grained mechanism that dynamically modulates the intensity of this guidance for each user-item interaction, overcoming the limitations of static fusion methods. Extensive experiments on benchmark datasets demonstrate that FedRKG significantly outperforms state-of-the-art methods, validating the effectiveness of our approach. The code is available at https://github.com/Jaehyung-Lim/fedrkg.

Paperid: 611, https://arxiv.org/pdf/2511.12912.pdf GitHub

Abstract:
Transferring the depth-based end-to-end policy trained in simulation to physical robots can yield an efficient and robust grasping policy, yet sensor artifacts in real depth maps like voids and noise establish a significant sim2real gap that critically impedes policy transfer. Training-time strategies like procedural noise injection or learned mappings suffer from data inefficiency due to unrealistic noise simulation, which is often ineffective for grasping tasks that require fine manipulation or dependency on paired datasets heavily. Furthermore, leveraging foundation models to reduce the sim2real gap via intermediate representations fails to mitigate the domain shift fully and adds computational overhead during deployment. This work confronts dual challenges of data inefficiency and deployment complexity. We propose DiffuDepGrasp, a deploy-efficient sim2real framework enabling zero-shot transfer through simulation-exclusive policy training. Its core innovation, the Diffusion Depth Generator, synthesizes geometrically pristine simulation depth with learned sensor-realistic noise via two synergistic modules. The first Diffusion Depth Module leverages temporal geometric priors to enable sample-efficient training of a conditional diffusion model that captures complex sensor noise distributions, while the second Noise Grafting Module preserves metric accuracy during perceptual artifact injection. With only raw depth inputs during deployment, DiffuDepGrasp eliminates computational overhead and achieves a 95.7% average success rate on 12-object grasping with zero-shot transfer and strong generalization to unseen objects.Project website: https://diffudepgrasp.github.io/.

Paperid: 612, https://arxiv.org/pdf/2511.12909.pdf GitHub

Abstract:
Deep learning-based 3D anomaly detection methods have demonstrated significant potential in industrial manufacturing. However, many approaches are specifically designed for anomaly detection tasks, which limits their generalizability to other 3D understanding tasks. In contrast, self-supervised point cloud models aim for general-purpose representation learning, yet our investigation reveals that these classical models are suboptimal at anomaly detection under the unified fine-tuning paradigm. This motivates us to develop a more generalizable 3D model that can effectively detect anomalies without relying on task-specific designs. Interestingly, we find that using only the curvature of each point as its anomaly score already outperforms several classical self-supervised and dedicated anomaly detection models, highlighting the critical role of curvature in 3D anomaly detection. In this paper, we propose a Curvature-Augmented Self-supervised Learning (CASL) framework based on a reconstruction paradigm. Built upon the classical U-Net architecture, our approach introduces multi-scale curvature prompts to guide the decoder in predicting the spatial coordinates of each point. Without relying on any dedicated anomaly detection mechanisms, it achieves leading detection performance through straightforward anomaly classification fine-tuning. Moreover, the learned representations generalize well to standard 3D understanding tasks such as point cloud classification. The code is available at https://github.com/zyh16143998882/CASL.

Paperid: 613, https://arxiv.org/pdf/2511.12899.pdf GitHub

Abstract:
Due to the diversity of brain anatomy and the scarcity of annotated data, supervised anomaly detection for brain MRI remains challenging, driving the development of unsupervised anomaly detection (UAD) approaches. Current UAD methods typically utilize artificially generated noise perturbations on healthy MRIs to train generative models for normal anatomy reconstruction, enabling anomaly detection via residual mapping. However, such simulated anomalies lack the biophysical fidelity and morphological complexity characteristic of true clinical lesions. To advance UAD in brain MRI, we conduct the first systematic frequency-domain analysis of pathological signatures, revealing two key properties: (1) anomalies exhibit unique frequency patterns distinguishable from normal anatomy, and (2) low-frequency signals maintain consistent representations across healthy scans. These insights motivate our Frequency-Decomposition Preprocessing (FDP) framework, the first UAD method to leverage frequency-domain reconstruction for simultaneous pathology suppression and anatomical preservation. FDP can integrate seamlessly with existing anomaly simulation techniques, consistently enhancing detection performance across diverse architectures while maintaining diagnostic fidelity. Experimental results demonstrate that FDP consistently improves anomaly detection performance when integrated with existing methods. Notably, FDP achieves a 17.63% increase in DICE score with LDM while maintaining robust improvements across multiple baselines. The code is available at https://github.com/ls1rius/MRI_FDP.

Paperid: 614, https://arxiv.org/pdf/2511.12880.pdf GitHub

Abstract:
Assessing human creativity through visual outputs, such as drawings, plays a critical role in fields including psychology, education, and cognitive science. However, current assessment practices still rely heavily on expert-based subjective scoring, which is both labor-intensive and inherently subjective. In this paper, we propose a data-driven framework for automatic and interpretable creativity assessment from drawings. Motivated by the cognitive understanding that creativity can emerge from both what is drawn (content) and how it is drawn (style), we reinterpret the creativity score as a function of these two complementary dimensions.Specifically, we first augment an existing creativity labeled dataset with additional annotations targeting content categories. Based on the enriched dataset, we further propose a multi-modal, multi-task learning framework that simultaneously predicts creativity scores, categorizes content types, and extracts stylistic features. In particular, we introduce a conditional learning mechanism that enables the model to adapt its visual feature extraction by dynamically tuning it to creativity-relevant signals conditioned on the drawing's stylistic and semantic cues.Experimental results demonstrate that our model achieves state-of-the-art performance compared to existing regression-based approaches and offers interpretable visualizations that align well with human judgments. The code and annotations will be made publicly available at https://github.com/WonderOfU9/CSCA_PRCV_2025

Paperid: 615, https://arxiv.org/pdf/2511.12878.pdf GitHub

Abstract:
Analyzing hand-object interaction in egocentric vision facilitates VR/AR applications and human-robot policy transfer. Existing research has mostly focused on modeling the behavior paradigm of interactive actions (i.e., "how to interact"). However, the more challenging and fine-grained problem of capturing the critical moments of contact and separation between the hand and the target object (i.e., "when to interact") is still underexplored, which is crucial for immersive interactive experiences in mixed reality and robotic motion planning. Therefore, we formulate this problem as temporal interaction localization (TIL). Some recent works extract semantic masks as TIL references, but suffer from inaccurate object grounding and cluttered scenarios. Although current temporal action localization (TAL) methods perform well in detecting verb-noun action segments, they rely on category annotations during training and exhibit limited precision in localizing hand-object contact/separation moments. To address these issues, we propose a novel zero-shot approach dubbed EgoLoc to localize hand-object contact and separation timestamps in egocentric videos. EgoLoc introduces hand-dynamics-guided sampling to generate high-quality visual prompts. It exploits the vision-language model to identify contact/separation attributes, localize specific timestamps, and provide closed-loop feedback for further refinement. EgoLoc eliminates the need for object masks and verb-noun taxonomies, leading to generalizable zero-shot implementation. Comprehensive experiments on the public dataset and our novel benchmarks demonstrate that EgoLoc achieves plausible TIL for egocentric videos. It is also validated to effectively facilitate multiple downstream applications in egocentric vision and robotic manipulation tasks. Code and relevant data will be released at https://github.com/IRMVLab/EgoLoc.

Paperid: 616, https://arxiv.org/pdf/2511.12821.pdf GitHub

Abstract:
Assessing journal impact is central to scholarly communication, yet existing open resources rarely capture how collaboration structures and artificial intelligence (AI) research jointly shape venue prestige in biomedicine. We present BioMedJImpact, a large-scale, biomedical-oriented dataset designed to advance journal-level analysis of scientific impact and AI engagement. Built from 1.74 million PubMed Central articles across 2,744 journals, BioMedJImpact integrates bibliometric indicators, collaboration features, and LLM-derived semantic indicators for AI engagement. Specifically, the AI engagement feature is extracted through a reproducible three-stage LLM pipeline that we propose. Using this dataset, we analyze how collaboration intensity and AI engagement jointly influence scientific impact across pre- and post-pandemic periods (2016-2019, 2020-2023). Two consistent trends emerge: journals with higher collaboration intensity, particularly those with larger and more diverse author teams, tend to achieve greater citation impact, and AI engagement has become an increasingly strong correlate of journal prestige, especially in quartile rankings. To further validate the three-stage LLM pipeline we proposed for deriving the AI engagement feature, we conduct human evaluation, confirming substantial agreement in AI relevance detection and consistent subfield classification. Together, these contributions demonstrate that BioMedJImpact serves as both a comprehensive dataset capturing the intersection of biomedicine and AI, and a validated methodological framework enabling scalable, content-aware scientometric analysis of scientific impact and innovation dynamics. Code is available at https://github.com/JonathanWry/BioMedJImpact.

Paperid: 617, https://arxiv.org/pdf/2511.12810.pdf GitHub GitHub

Abstract:
Camouflaged object detection is an emerging and challenging computer vision task that requires identifying and segmenting objects that blend seamlessly into their environments due to high similarity in color, texture, and size. This task is further complicated by low-light conditions, partial occlusion, small object size, intricate background patterns, and multiple objects. While many sophisticated methods have been proposed for this task, current methods still struggle to precisely detect camouflaged objects in complex scenarios, especially with small and multiple objects, indicating room for improvement. We propose a Multi-Scale Recursive Network that extracts multi-scale features via a Pyramid Vision Transformer backbone and combines them via specialized Attention-Based Scale Integration Units, enabling selective feature merging. For more precise object detection, our decoder recursively refines features by incorporating Multi-Granularity Fusion Units. A novel recursive-feedback decoding strategy is developed to enhance global context understanding, helping the model overcome the challenges in this task. By jointly leveraging multi-scale learning and recursive feature optimization, our proposed method achieves performance gains, successfully detecting small and multiple camouflaged objects. Our model achieves state-of-the-art results on two benchmark datasets for camouflaged object detection and ranks second on the remaining two. Our codes, model weights, and results are available at \href{https://github.com/linaagh98/MSRNet}{https://github.com/linaagh98/MSRNet}.

Paperid: 618, https://arxiv.org/pdf/2511.12770.pdf GitHub

Abstract:
Understanding and continuously refining multimodal molecular knowledge is crucial for advancing biomedicine, chemistry, and materials science. Molecule language models (MoLMs) have become powerful tools in these domains, integrating structural representations (e.g., SMILES strings, molecular graphs) with rich contextual descriptions (e.g., physicochemical properties). However, MoLMs can encode and propagate inaccuracies due to outdated web-mined training corpora or malicious manipulation, jeopardizing downstream discovery pipelines. While knowledge editing has been explored for general-domain AI, its application to MoLMs remains uncharted, presenting unique challenges due to the multifaceted and interdependent nature of molecular knowledge. In this paper, we take the first step toward MoLM editing for two critical tasks: molecule-to-caption generation and caption-to-molecule generation. To address molecule-specific challenges, we propose MolEdit, a powerful framework that enables targeted modifications while preserving unrelated molecular knowledge. MolEdit combines a Multi-Expert Knowledge Adapter that routes edits to specialized experts for different molecular facets with an Expertise-Aware Editing Switcher that activates the adapters only when input closely matches the stored edits across all expertise, minimizing interference with unrelated knowledge. To systematically evaluate editing performance, we introduce MEBench, a comprehensive benchmark assessing multiple dimensions, including Reliability (accuracy of the editing), Locality (preservation of irrelevant knowledge), and Generality (robustness to reformed queries). Across extensive experiments on two popular MoLM backbones, MolEdit delivers up to 18.8% higher Reliability and 12.0% better Locality than baselines while maintaining efficiency. The code is available at: https://github.com/LzyFischer/MolEdit.

Paperid: 619, https://arxiv.org/pdf/2511.12764.pdf GitHub

Abstract:
When simulating partial differential equations, hybrid solvers combine coarse numerical solvers with learned correctors. They promise accelerated simulations while adhering to physical constraints. However, as shown in our theoretical framework, directly applying learned corrections to solver outputs leads to significant autoregressive errors, which originate from amplified perturbations that accumulate during long-term rollouts, especially in chaotic regimes. To overcome this, we propose the Indirect Neural Corrector ($\mathrm{INC}$), which integrates learned corrections into the governing equations rather than applying direct state updates. Our key insight is that $\mathrm{INC}$ reduces the error amplification on the order of $Δt^{-1} + L$, where $Δt$ is the timestep and $L$ the Lipschitz constant. At the same time, our framework poses no architectural requirements and integrates seamlessly with arbitrary neural networks and solvers. We test $\mathrm{INC}$ in extensive benchmarks, covering numerous differentiable solvers, neural backbones, and test cases ranging from a 1D chaotic system to 3D turbulence. INC improves the long-term trajectory performance ($R^2$) by up to 158.7\%, stabilizes blowups under aggressive coarsening, and for complex 3D turbulence cases yields speed-ups of several orders of magnitude. INC thus enables stable, efficient PDE emulation with formal error reduction, paving the way for faster scientific and engineering simulations with reliable physics guarantees. Our source code is available at https://github.com/tum-pbs/INC

Paperid: 620, https://arxiv.org/pdf/2511.12723.pdf GitHub

Abstract:
Deep neural networks typically rely on the representation produced by their final hidden layer to make predictions, implicitly assuming that this single vector fully captures the semantics encoded across all preceding transformations. However, intermediate layers contain rich and complementary information -- ranging from low-level patterns to high-level abstractions -- that is often discarded when the decision head depends solely on the last representation. This paper revisits the role of the output layer and introduces LAYA (Layer-wise Attention Aggregator), a novel output head that dynamically aggregates internal representations through attention. Instead of projecting only the deepest embedding, LAYA learns input-conditioned attention weights over layer-wise features, yielding an interpretable and architecture-agnostic mechanism for synthesizing predictions. Experiments on vision and language benchmarks show that LAYA consistently matches or improves the performance of standard output heads, with relative gains of up to about one percentage point in accuracy, while providing explicit layer-attribution scores that reveal how different abstraction levels contribute to each decision. Crucially, these interpretability signals emerge directly from the model's computation, without any external post hoc explanations. The code to reproduce LAYA is publicly available at: https://github.com/gvessio/LAYA.

Paperid: 621, https://arxiv.org/pdf/2511.12710.pdf GitHub

Abstract:
Automated red teaming frameworks for Large Language Models (LLMs) have become increasingly sophisticated, yet they share a fundamental limitation: their jailbreak logic is confined to selecting, combining, or refining pre-existing attack strategies. This binds their creativity and leaves them unable to autonomously invent entirely new attack mechanisms. To overcome this gap, we introduce \textbf{EvoSynth}, an autonomous framework that shifts the paradigm from attack planning to the evolutionary synthesis of jailbreak methods. Instead of refining prompts, EvoSynth employs a multi-agent system to autonomously engineer, evolve, and execute novel, code-based attack algorithms. Crucially, it features a code-level self-correction loop, allowing it to iteratively rewrite its own attack logic in response to failure. Through extensive experiments, we demonstrate that EvoSynth not only establishes a new state-of-the-art by achieving an 85.5\% Attack Success Rate (ASR) against highly robust models like Claude-Sonnet-4.5, but also generates attacks that are significantly more diverse than those from existing methods. We release our framework to facilitate future research in this new direction of evolutionary synthesis of jailbreak methods. Code is available at: https://github.com/dongdongunique/EvoSynth.

Paperid: 622, https://arxiv.org/pdf/2511.12705.pdf GitHub

Abstract:
Many mathematical modelling tasks (such as in Economics and Finance) are informed by data that is "found" rather than being the result of carefully designed experiments. This often results in data series that are short, noisy, multidimensional and contaminated with outliers, regime shifts, and confounding, uninformative or co-linear variables. We present a generalization of the Theil-Sen algorithm to reflect modes (rather than the median) in the parameter space distribution (of partial fits to the data). This can provide a robust piecewise-linear fit to the data while also allowing for extensions to including elements of cluster analysis, regularization and cross-validation in a unified (distribution free) approach that can:- 1. Exploit piecewise linearity to reduce the need to pre-specify the form of the underlying data generating process. 2. Detect non-homogeneity (e.g. regime shifts, multiple data generating processes etc.) in the data using an innovative non-parametric (Hamming-Distance/Affinity-Matrix) cluster analysis technique. 3. Enable dimension reduction and resistance to the effects of multi-co-linearity by including LASSO regularization as an integral part of the algorithm. 4. Estimate measures of accuracy, such as standard errors, bias, and confidence intervals, without needing to rely on traditional distributional assumptions. Taken together these extensions to the traditional Theil-Sen algorithm simplify the traditional process of parameter fitting by providing a single-stage analysis controlled by a multidimensional search of Scale/Parsimony/Precision hyper-parameters. These are early days in this research and the main limitation in this approach is that it assumes that compute power is infinite and compute time is small enough to allow interactive use.

Paperid: 623, https://arxiv.org/pdf/2511.12693.pdf GitHub

Abstract:
Vision-language models (VLMs) enable open-ended visual question answering but remain prone to hallucinations. We present HEDGE, a unified framework for hallucination detection that combines controlled visual perturbations, semantic clustering, and robust uncertainty metrics. HEDGE integrates sampling, distortion synthesis, clustering (entailment- and embedding-based), and metric computation into a reproducible pipeline applicable across multimodal architectures. Evaluations on VQA-RAD and KvasirVQA-x1 with three representative VLMs (LLaVA-Med, Med-Gemma, Qwen2.5-VL) reveal clear architecture- and prompt-dependent trends. Hallucination detectability is highest for unified-fusion models with dense visual tokenization (Qwen2.5-VL) and lowest for architectures with restricted tokenization (Med-Gemma). Embedding-based clustering often yields stronger separation when applied directly to the generated answers, whereas NLI-based clustering remains advantageous for LLaVA-Med and for longer, sentence-level responses. Across configurations, the VASE metric consistently provides the most robust hallucination signal, especially when paired with embedding clustering and a moderate sampling budget (n ~ 10-15). Prompt design also matters: concise, label-style outputs offer clearer semantic structure than syntactically constrained one-sentence responses. By framing hallucination detection as a geometric robustness problem shaped jointly by sampling scale, prompt structure, model architecture, and clustering strategy, HEDGE provides a principled, compute-aware foundation for evaluating multimodal reliability. The hedge-bench PyPI library enables reproducible and extensible benchmarking, with full code and experimental resources available at https://github.com/Simula/HEDGE .

Paperid: 624, https://arxiv.org/pdf/2511.12691.pdf GitHub

Abstract:
Foundation models for medical image segmentation struggle under out-of-distribution (OOD) shifts, often producing fragmented false positives on OOD tumors. We introduce R$^{2}$Seg, a training-free framework for robust OOD tumor segmentation that operates via a two-stage Reason-and-Reject process. First, the Reason step employs an LLM-guided anatomical reasoning planner to localize organ anchors and generate multi-scale ROIs. Second, the Reject step applies two-sample statistical testing to candidates generated by a frozen foundation model (BiomedParse) within these ROIs. This statistical rejection filter retains only candidates significantly different from normal tissue, effectively suppressing false positives. Our framework requires no parameter updates, making it compatible with zero-update test-time augmentation and avoiding catastrophic forgetting. On multi-center and multi-modal tumor segmentation benchmarks, R$^{2}$Seg substantially improves Dice, specificity, and sensitivity over strong baselines and the original foundation models. Code are available at https://github.com/Eurekashen/R2Seg.

Paperid: 625, https://arxiv.org/pdf/2511.12675.pdf GitHub

Abstract:
The goal of Novel View Synthesis (NVS) is to generate realistic images of a given content from unseen viewpoints. But how can we trust that a generated image truly reflects the intended transformation? Evaluating its reliability remains a major challenge. While recent generative models, particularly diffusion-based approaches, have significantly improved NVS quality, existing evaluation metrics struggle to assess whether a generated image is both realistic and faithful to the source view and intended viewpoint transformation. Standard metrics, such as pixel-wise similarity and distribution-based measures, often mis-rank incorrect results as they fail to capture the nuanced relationship between the source image, viewpoint change, and generated output. We propose a task-aware evaluation framework that leverages features from a strong NVS foundation model, Zero123, combined with a lightweight tuning step to enhance discrimination. Using these features, we introduce two complementary evaluation metrics: a reference-based score, $D_{\text{PRISM}}$, and a reference-free score, $\text{MMD}_{\text{PRISM}}$. Both reliably identify incorrect generations and rank models in agreement with human preference studies, addressing a fundamental gap in NVS evaluation. Our framework provides a principled and practical approach to assessing synthesis quality, paving the way for more reliable progress in novel view synthesis. To further support this goal, we apply our reference-free metric to six NVS methods across three benchmarks: Toys4K, Google Scanned Objects (GSO), and OmniObject3D, where $\text{MMD}_{\text{PRISM}}$ produces a clear and stable ranking, with lower scores consistently indicating stronger models.

Paperid: 626, https://arxiv.org/pdf/2511.12671.pdf GitHub

Abstract:
In this work, we propose an accurate and real-time optical flow and disparity estimation model by fusing pairwise input images in the proposed non-causal selective state space for dense perception tasks. We propose a non-causal Mamba block-based model that is fast and efficient and aptly manages the constraints present in a real-time applications. Our proposed model reduces inference times while maintaining high accuracy and low GPU usage for optical flow and disparity map generation. The results and analysis, and validation in real-life scenario justify that our proposed model can be used for unified real-time and accurate 3D dense perception estimation tasks. The code, along with the models, can be found at https://github.com/vimstereo/DensePerceptNCSSD

Paperid: 627, https://arxiv.org/pdf/2511.12658.pdf GitHub GitHub

Abstract:
Existing Text Image Forgery Localization (T-IFL) methods often suffer from poor generalization due to the limited scale of real-world datasets and the distribution gap caused by synthetic data that fails to capture the complexity of real-world tampering. To tackle this issue, we propose Fourier Series-based Tampering Synthesis (FSTS), a structured and interpretable framework for synthesizing tampered text images. FSTS first collects 16,750 real-world tampering instances from five representative tampering types, using a structured pipeline that records human-performed editing traces via multi-format logs (e.g., video, PSD, and editing logs). By analyzing these collected parameters and identifying recurring behavioral patterns at both individual and population levels, we formulate a hierarchical modeling framework. Specifically, each individual tampering parameter is represented as a compact combination of basis operation-parameter configurations, while the population-level distribution is constructed by aggregating these behaviors. Since this formulation draws inspiration from the Fourier series, it enables an interpretable approximation using basis functions and their learned weights. By sampling from this modeled distribution, FSTS synthesizes diverse and realistic training data that better reflect real-world forgery traces. Extensive experiments across four evaluation protocols demonstrate that models trained with FSTS data achieve significantly improved generalization on real-world datasets. Dataset is available at \href{https://github.com/ZeqinYu/FSTS}{Project Page}.

Paperid: 628, https://arxiv.org/pdf/2511.12639.pdf GitHub

Abstract:
Vision-language foundation models (VLMs) have shown great potential in feature transfer and generalization across a wide spectrum of medical-related downstream tasks. However, fine-tuning these models is resource-intensive due to their large number of parameters. Prompt tuning has emerged as a viable solution to mitigate memory usage and reduce training time while maintaining competitive performance. Nevertheless, the challenge is that existing prompt tuning methods cannot precisely distinguish different kinds of medical concepts, which miss essentially specific disease-related features across various medical imaging modalities in medical image classification tasks. We find that Large Language Models (LLMs), trained on extensive text corpora, are particularly adept at providing this specialized medical knowledge. Motivated by this, we propose incorporating LLMs into the prompt tuning process. Specifically, we introduce the CILMP, Conditional Intervention of Large Language Models for Prompt Tuning, a method that bridges LLMs and VLMs to facilitate the transfer of medical knowledge into VLM prompts. CILMP extracts disease-specific representations from LLMs, intervenes within a low-rank linear subspace, and utilizes them to create disease-specific prompts. Additionally, a conditional mechanism is incorporated to condition the intervention process on each individual medical image, generating instance-adaptive prompts and thus enhancing adaptability. Extensive experiments across diverse medical image datasets demonstrate that CILMP consistently outperforms state-of-the-art prompt tuning methods, demonstrating its effectiveness. Code is available at https://github.com/usr922/cilmp.

Paperid: 629, https://arxiv.org/pdf/2511.12630.pdf GitHub

Abstract:
Notice to Air Missions (NOTAMs) serve as a critical channel for disseminating key flight safety information, yet their complex linguistic structures and implicit reasoning pose significant challenges for automated parsing. Existing research mainly focuses on surface-level tasks such as classification and named entity recognition, lacking deep semantic understanding. To address this gap, we propose NOTAM semantic parsing, a task emphasizing semantic inference and the integration of aviation domain knowledge to produce structured, inference-rich outputs. To support this task, we construct Knots (Knowledge and NOTAM Semantics), a high-quality dataset of 12,347 expert-annotated NOTAMs covering 194 Flight Information Regions, enhanced through a multi-agent collaborative framework for comprehensive field discovery. We systematically evaluate a wide range of prompt-engineering strategies and model-adaptation techniques, achieving substantial improvements in aviation text understanding and processing. Our experimental results demonstrate the effectiveness of the proposed approach and offer valuable insights for automated NOTAM analysis systems. Our code is available at: https://github.com/Estrellajer/Knots.

Paperid: 630, https://arxiv.org/pdf/2511.12627.pdf GitHub

Abstract:
Camouflaged object detection identifies objects that blend seamlessly with their surroundings through similar colors, textures, and patterns. This task challenges both traditional segmentation methods and modern foundation models, which fail dramatically on camouflaged objects. We identify six fundamental challenges in COD: Intrinsic Similarity, Edge Disruption, Extreme Scale Variation, Environmental Complexities, Contextual Dependencies, and Salient-Camouflaged Object Disambiguation. These challenges frequently co-occur and compound the difficulty of detection, requiring comprehensive architectural solutions. We propose C3Net, which addresses all challenges through a specialized dual-pathway decoder architecture. The Edge Refinement Pathway employs gradient-initialized Edge Enhancement Modules to recover precise boundaries from early features. The Contextual Localization Pathway utilizes our novel Image-based Context Guidance mechanism to achieve intrinsic saliency suppression without external models. An Attentive Fusion Module synergistically combines the two pathways via spatial gating. C3Net achieves state-of-the-art performance with S-measures of 0.898 on COD10K, 0.904 on CAMO, and 0.913 on NC4K, while maintaining efficient processing. C3Net demonstrates that complex, multifaceted detection challenges require architectural innovation, with specialized components working synergistically to achieve comprehensive coverage beyond isolated improvements. Code, model weights, and results are available at https://github.com/Baber-Jan/C3Net.

Paperid: 631, https://arxiv.org/pdf/2511.12609.pdf GitHub GitHub

Abstract:
We present Uni-MoE 2.0 from the Lychee family. As a fully open-source omnimodal large model (OLM), it substantially advances Lychee's Uni-MoE series in language-centric multimodal understanding, reasoning, and generating. Based on the Qwen2.5-7B dense architecture, we build Uni-MoE-2.0-Omni from scratch through three core contributions: dynamic-capacity Mixture-of-Experts (MoE) design, a progressive training strategy enhanced with an iterative reinforcement strategy, and a carefully curated multimodal data matching technique. It is capable of omnimodal understanding, as well as generating images, text, and speech. Architecturally, our new MoE framework balances computational efficiency and capability for 10 cross-modal inputs using shared, routed, and null experts, while our Omni-Modality 3D RoPE ensures spatio-temporal cross-modality alignment in the self-attention layer. For training, following cross-modal pretraining, we use a progressive supervised fine-tuning strategy that activates modality-specific experts and is enhanced by balanced data composition and an iterative GSPO-DPO method to stabilise RL training and improve reasoning. Data-wise, the base model, trained on approximately 75B tokens of open-source multimodal data, is equipped with special speech and image generation tokens, allowing it to learn these generative tasks by conditioning its outputs on linguistic cues. Extensive evaluation across 85 benchmarks demonstrates that our model achieves SOTA or highly competitive performance against leading OLMs, surpassing Qwen2.5-Omni (trained with 1.2T tokens) on over 50 of 76 benchmarks. Key strengths include video understanding (+7% avg. of 8), omnimodallity understanding (+7% avg. of 4), and audiovisual reasoning (+4%). It also advances long-form speech processing (reducing WER by 4.2%) and leads in low-level image processing and controllable generation across 5 metrics.

Paperid: 632, https://arxiv.org/pdf/2511.12603.pdf GitHub GitHub

Abstract:
Langevin dynamics sampling suffers from extremely low generation speed, fundamentally limited by numerous fine-grained iterations to converge to the target distribution. We introduce PID-controlled Langevin Dynamics (PIDLD), a novel sampling acceleration algorithm that reinterprets the sampling process using control-theoretic principles. By treating energy gradients as feedback signals, PIDLD combines historical gradients (the integral term) and gradient trends (the derivative term) to efficiently traverse energy landscapes and adaptively stabilize, thereby significantly reducing the number of iterations required to produce high-quality samples. Our approach requires no additional training, datasets, or prior information, making it immediately integrable with any Langevin-based method. Extensive experiments across image generation and reasoning tasks demonstrate that PIDLD achieves higher quality with fewer steps, making Langevin-based generative models more practical for efficiency-critical applications. The implementation can be found at \href{https://github.com/tsinghua-fib-lab/PIDLD}{https://github.com/tsinghua-fib-lab/PIDLD}.

Paperid: 633, https://arxiv.org/pdf/2511.12597.pdf GitHub

Abstract:
Recent advancements in large language model-based recommendation systems often represent items as text or semantic IDs and generate recommendations in an auto-regressive manner. However, due to the left-to-right greedy decoding strategy and the unidirectional logical flow, such methods often fail to produce globally optimal recommendations. In contrast, human reasoning does not follow a rigid left-to-right sequence. Instead, it often begins with keywords or intuitive insights, which are then refined and expanded. Inspired by this fact, we propose Mind-inspired Recommender (MindRec), a novel generative framework that emulates human thought processes. Particularly, our method first generates key tokens that reflect user preferences, and then expands them into the complete item, enabling flexible and human-like generation. To further emulate the structured nature of human decision-making, we organize items into a hierarchical category tree. This structure guides the model to first produce the coarse-grained category and then progressively refine its selection through finer-grained subcategories before generating the specific item. To mitigate the local optimum problem inherent in greedy decoding, we design a novel beam search algorithm, Diffusion Beam Search, tailored for our mind-inspired generation paradigm. Experimental results demonstrate that MindRec yields a 9.5\% average improvement in top-1 recommendation performance over state-of-the-art methods, highlighting its potential to enhance recommendation accuracy. The implementation is available via https://github.com/Mr-Peach0301/MindRec.

Paperid: 634, https://arxiv.org/pdf/2511.12594.pdf GitHub

Abstract:
While visual autoregressive modeling (VAR) strategies have shed light on image generation with the autoregressive models, their potential for segmentation, a task that requires precise low-level spatial perception, remains unexplored. Inspired by the multi-scale modeling of classic Mask2Former-based models, we propose Seg-VAR, a novel framework that rethinks segmentation as a conditional autoregressive mask generation problem. This is achieved by replacing the discriminative learning with the latent learning process. Specifically, our method incorporates three core components: (1) an image encoder generating latent priors from input images, (2) a spatial-aware seglat (a latent expression of segmentation mask) encoder that maps segmentation masks into discrete latent tokens using a location-sensitive color mapping to distinguish instances, and (3) a decoder reconstructing masks from these latents. A multi-stage training strategy is introduced: first learning seglat representations via image-seglat joint training, then refining latent transformations, and finally aligning image-encoder-derived latents with seglat distributions. Experiments show Seg-VAR outperforms previous discriminative and generative methods on various segmentation tasks and validation benchmarks. By framing segmentation as a sequential hierarchical prediction task, Seg-VAR opens new avenues for integrating autoregressive reasoning into spatial-aware vision systems. Code will be available at https://github.com/rkzheng99/Seg-VAR.

Paperid: 635, https://arxiv.org/pdf/2511.12530.pdf GitHub

Abstract:
Keyframe selection has become essential for video understanding with vision-language models (VLMs) due to limited input tokens and the temporal sparsity of relevant information across video frames. Video understanding often relies on effective keyframes that are not only informative but also causally decisive. To this end, we propose Reinforced Causal Search with Information Bottleneck (ReaSon), a framework that formulates keyframe selection as an optimization problem with the help of a novel Causal Information Bottleneck (CIB), which explicitly defines keyframes as those satisfying both predictive sufficiency and causal necessity. Specifically, ReaSon employs a learnable policy network to select keyframes from a visually relevant pool of candidate frames to capture predictive sufficiency, and then assesses causal necessity via counterfactual interventions. Finally, a composite reward aligned with the CIB principle is designed to guide the selection policy through reinforcement learning. Extensive experiments on NExT-QA, EgoSchema, and Video-MME demonstrate that ReaSon consistently outperforms existing state-of-the-art methods under limited-frame settings, validating its effectiveness and generalization ability.

Paperid: 636, https://arxiv.org/pdf/2511.12528.pdf GitHub

Abstract:
Visual Place Recognition (VPR) aims to determine the geographic location of a query image by retrieving its most visually similar counterpart from a geo-tagged reference database. Recently, the emergence of the powerful visual foundation model, DINOv2, trained in a self-supervised manner on massive datasets, has significantly improved VPR performance. This improvement stems from DINOv2's exceptional feature generalization capabilities but is often accompanied by increased model complexity and computational overhead that impede deployment on resource-constrained devices. To address this challenge, we propose $D^{2}$-VPR, a $D$istillation- and $D$eformable-based framework that retains the strong feature extraction capabilities of visual foundation models while significantly reducing model parameters and achieving a more favorable performance-efficiency trade-off. Specifically, first, we employ a two-stage training strategy that integrates knowledge distillation and fine-tuning. Additionally, we introduce a Distillation Recovery Module (DRM) to better align the feature spaces between the teacher and student models, thereby minimizing knowledge transfer losses to the greatest extent possible. Second, we design a Top-Down-attention-based Deformable Aggregator (TDDA) that leverages global semantic features to dynamically and adaptively adjust the Regions of Interest (ROI) used for aggregation, thereby improving adaptability to irregular structures. Extensive experiments demonstrate that our method achieves competitive performance compared to state-of-the-art approaches. Meanwhile, it reduces the parameter count by approximately 64.2% and FLOPs by about 62.6% (compared to CricaVPR).Code is available at https://github.com/tony19980810/D2VPR.

Paperid: 637, https://arxiv.org/pdf/2511.12511.pdf GitHub

Abstract:
With growing concerns over image authenticity and digital safety, the field of AI-generated image (AIGI) detection has progressed rapidly. Yet, most AIGI detectors still struggle under real-world degradations, particularly motion blur, which frequently occurs in handheld photography, fast motion, and compressed video. Such blur distorts fine textures and suppresses high-frequency artifacts, causing severe performance drops in real-world settings. We address this limitation with a blur-robust AIGI detection framework based on teacher-student knowledge distillation. A high-capacity teacher (DINOv3), trained on clean (i.e., sharp) images, provides stable and semantically rich representations that serve as a reference for learning. By freezing the teacher to maintain its generalization ability, we distill its feature and logit responses from sharp images to a student trained on blurred counterparts, enabling the student to produce consistent representations under motion degradation. Extensive experiments benchmarks show that our method achieves state-of-the-art performance under both motion-blurred and clean conditions, demonstrating improved generalization and real-world applicability. Source codes will be released at: https://github.com/JiaLiangShen/Dino-Detect-for-blur-robust-AIGC-Detection.

Paperid: 638, https://arxiv.org/pdf/2511.12502.pdf GitHub

Abstract:
Binary Spiking Neural Networks (BSNNs) offer promising efficiency advantages for resource-constrained computing. However, their training algorithms often require substantial memory overhead due to latent weights storage and temporal processing requirements. To address this issue, we propose Binary Spiking Online (BSO) optimization algorithm, a novel online training algorithm that significantly reduces training memory. BSO directly updates weights through flip signals under the online training framework. These signals are triggered when the product of gradient momentum and weights exceeds a threshold, eliminating the need for latent weights during training. To enhance performance, we propose T-BSO, a temporal-aware variant that leverages the inherent temporal dynamics of BSNNs by capturing gradient information across time steps for adaptive threshold adjustment. Theoretical analysis establishes convergence guarantees for both BSO and T-BSO, with formal regret bounds characterizing their convergence rates. Extensive experiments demonstrate that both BSO and T-BSO achieve superior optimization performance compared to existing training methods for BSNNs. The codes are available at https://github.com/hamings1/BSO.

Paperid: 639, https://arxiv.org/pdf/2511.12472.pdf GitHub

Abstract:
Large Language Models (LLMs) have greatly advanced knowledge graph question answering (KGQA), yet existing systems are typically optimized for returning highly relevant but predictable answers. A missing yet desired capacity is to exploit LLMs to suggest surprise and novel ("serendipitious") answers. In this paper, we formally define the serendipity-aware KGQA task and propose the SerenQA framework to evaluate LLMs' ability to uncover unexpected insights in scientific KGQA tasks. SerenQA includes a rigorous serendipity metric based on relevance, novelty, and surprise, along with an expert-annotated benchmark derived from the Clinical Knowledge Graph, focused on drug repurposing. Additionally, it features a structured evaluation pipeline encompassing three subtasks: knowledge retrieval, subgraph reasoning, and serendipity exploration. Our experiments reveal that while state-of-the-art LLMs perform well on retrieval, they still struggle to identify genuinely surprising and valuable discoveries, underscoring a significant room for future improvements. Our curated resources and extended version are released at: https://cwru-db-group.github.io/serenQA.

Paperid: 640, https://arxiv.org/pdf/2511.12460.pdf GitHub

Abstract:
Depression represents a global mental health challenge requiring efficient and reliable automated detection methods. Current Transformer- or Graph Neural Networks (GNNs)-based multimodal depression detection methods face significant challenges in modeling individual differences and cross-modal temporal dependencies across diverse behavioral contexts. Therefore, we propose P$^3$HF (Personality-guided Public-Private Domain Disentangled Hypergraph-Former Network) with three key innovations: (1) personality-guided representation learning using LLMs to transform discrete individual features into contextual descriptions for personalized encoding; (2) Hypergraph-Former architecture modeling high-order cross-modal temporal relationships; (3) event-level domain disentanglement with contrastive learning for improved generalization across behavioral contexts. Experiments on MPDD-Young dataset show P$^3$HF achieves around 10\% improvement on accuracy and weighted F1 for binary and ternary depression classification task over existing methods. Extensive ablation studies validate the independent contribution of each architectural component, confirming that personality-guided representation learning and high-order hypergraph reasoning are both essential for generating robust, individual-aware depression-related representations. The code is released at https://github.com/hacilab/P3HF.

Paperid: 641, https://arxiv.org/pdf/2511.12410.pdf GitHub

Abstract:
The deployment of automated pavement defect detection is often hindered by poor cross-domain generalization. Supervised detectors achieve strong in-domain accuracy but require costly re-annotation for new environments, while standard self-supervised methods capture generic features and remain vulnerable to domain shift. We propose \ours, a self-supervised framework that \emph{visually probes} target domains without labels. \ours introduces a Self-supervised Prompt Enhancement Module (SPEM), which derives defect-aware prompts from unlabeled target data to guide a frozen ViT backbone, and a Domain-Aware Prompt Alignment (DAPA) objective, which aligns prompt-conditioned source and target representations. Experiments on four challenging benchmarks show that \ours consistently outperforms strong supervised, self-supervised, and adaptation baselines, achieving robust zero-shot transfer, improved resilience to domain variations, and high data efficiency in few-shot adaptation. These results highlight self-supervised prompting as a practical direction for building scalable and adaptive visual inspection systems. Source code is publicly available: https://github.com/xixiaouab/PROBE/tree/main

Paperid: 642, https://arxiv.org/pdf/2511.12396.pdf GitHub

Abstract:
Quantitative magnetization transfer (qMT) imaging provides myelin-sensitive biomarkers, such as the pool size ratio (PSR), which is valuable for multiple sclerosis (MS) assessment. However, qMT requires specialized 20-30 minute scans. We propose DEMIST to synthesize PSR maps from standard T1w and FLAIR images using a 3D latent diffusion model with three complementary conditioning mechanisms. Our approach has two stages: first, we train separate autoencoders for PSR and anatomical images to learn aligned latent representations. Second, we train a conditional diffusion model in this latent space on top of a frozen diffusion foundation backbone. Conditioning is decoupled into: (i) \textbf{semantic} tokens via cross-attention, (ii) \textbf{spatial} per-scale residual hints via a 3D ControlNet branch, and (iii) \textbf{adaptive} LoRA-modulated attention. We include edge-aware loss terms to preserve lesion boundaries and alignment losses to maintain quantitative consistency, while keeping the number of trainable parameters low and retaining the inductive bias of the pretrained model. We evaluate on 163 scans from 99 subjects using 5-fold cross-validation. Our method outperforms VAE, GAN and diffusion baselines on multiple metrics, producing sharper boundaries and better quantitative agreement with ground truth. Our code is publicly available at https://github.com/MedICL-VU/MS-Synthesis-3DcLDM.

Paperid: 643, https://arxiv.org/pdf/2511.12373.pdf GitHub

Abstract:
In the field of medical imaging, AI-assisted techniques such as object detection, segmentation, and classification are widely employed to alleviate the workload of physicians and doctors. However, single-task models are predominantly used, overlooking the shared information across tasks. This oversight leads to inefficiencies in real-life applications. In this work, we propose MTMed3D, a novel end-to-end Multi-task Transformer-based model to address the limitations of single-task models by jointly performing 3D detection, segmentation, and classification in medical imaging. Our model uses a Transformer as the shared encoder to generate multi-scale features, followed by CNN-based task-specific decoders. The proposed framework was evaluated on the BraTS 2018 and 2019 datasets, achieving promising results across all three tasks, especially in detection, where our method achieves better results than prior works. Additionally, we compare our multi-task model with equivalent single-task variants trained separately. Our multi-task model significantly reduces computational costs and achieves faster inference speed while maintaining comparable performance to the single-task models, highlighting its efficiency advantage. To the best of our knowledge, this is the first work to leverage Transformers for multi-task learning that simultaneously covers detection, segmentation, and classification tasks in 3D medical imaging, presenting its potential to enhance diagnostic processes. The code is available at https://github.com/fanlimua/MTMed3D.git.

Paperid: 644, https://arxiv.org/pdf/2511.12367.pdf GitHub

Abstract:
This paper addresses the Quadratic Multiple Constraints Variable-Sized Bin Packing Problem (QMC-VSBPP), a challenging combinatorial optimization problem that generalizes the classical bin packing by incorporating multiple capacity dimensions, heterogeneous bin types, and quadratic interaction costs between items. We propose two complementary methods that advance the current state-of-the-art. First, a linearized mathematical formulation is introduced to eliminate quadratic terms, enabling the use of exact solvers such as Gurobi to compute strong lower bounds - reported here for the first time for this problem. Second, we develop RKO-ACO, a continuous-domain Ant Colony Optimization algorithm within the Random-Key Optimization framework, enhanced with adaptive Q-learning parameter control and efficient local search. Extensive computational experiments on benchmark instances show that the proposed linearized model produces significantly tighter lower bounds than the original quadratic formulation, while RKO-ACO consistently matches or improves upon all best-known solutions in the literature, establishing new upper bounds for large-scale instances. These results provide new reference values for future studies and demonstrate the effectiveness of evolutionary and random-key metaheuristic approaches for solving complex quadratic packing problems. Source code and data available at https://github.com/nataliaalves03/RKO-ACO

Paperid: 645, https://arxiv.org/pdf/2511.12363.pdf GitHub

Abstract:
Conventional, classification-based AI-generated image detection methods cannot explain why an image is considered real or AI-generated in a way a human expert would, which reduces the trustworthiness and persuasiveness of these detection tools for real-world applications. Leveraging Multimodal Large Language Models (MLLMs) has recently become a trending solution to this issue. Further, to evaluate the quality of generated explanations, a common approach is to adopt an "MLLM as a judge" methodology to evaluate explanations generated by other MLLMs. However, how well those MLLMs perform when judging explanations for AI-generated image detection generated by themselves or other MLLMs has not been well studied. We therefore propose \textbf{XAIGID-RewardBench}, the first benchmark designed to evaluate the ability of current MLLMs to judge the quality of explanations about whether an image is real or AI-generated. The benchmark consists of approximately 3,000 annotated triplets sourced from various image generation models and MLLMs as policy models (detectors) to assess the capabilities of current MLLMs as reward models (judges). Our results show that the current best reward model scored 88.76\% on this benchmark (while human inter-annotator agreement reaches 98.30\%), demonstrating that a visible gap remains between the reasoning abilities of today's MLLMs and human-level performance. In addition, we provide an analysis of common pitfalls that these models frequently encounter. Code and benchmark are available at https://github.com/RewardBench/XAIGID-RewardBench.

Paperid: 646, https://arxiv.org/pdf/2511.12280.pdf GitHub GitHub

Abstract:
Diffusion-based multimodal large language models (Diffusion MLLMs) have recently demonstrated impressive non-autoregressive generative capabilities across vision-and-language tasks. However, Diffusion MLLMs exhibit substantially slower inference than autoregressive models: Each denoising step employs full bidirectional self-attention over the entire sequence, resulting in cubic decoding complexity that becomes computationally impractical with thousands of visual tokens. To address this challenge, we propose D$^{3}$ToM, a Decider-guided dynamic token merging method that dynamically merges redundant visual tokens at different denoising steps to accelerate inference in Diffusion MLLMs. At each denoising step, D$^{3}$ToM uses decider tokens-the tokens generated in the previous denoising step-to build an importance map over all visual tokens. Then it maintains a proportion of the most salient tokens and merges the remainder through similarity-based aggregation. This plug-and-play module integrates into a single transformer layer, physically shortening the visual token sequence for all subsequent layers without altering model parameters. Moreover, D$^{3}$ToM employs a merge ratio that dynamically varies with each denoising step, aligns with the native decoding process of Diffusion MLLMs, achieving superior performance under equivalent computational budgets. Extensive experiments show that D$^{3}$ToM accelerates inference while preserving competitive performance. The code is released at https://github.com/bcmi/D3ToM-Diffusion-MLLM.

Paperid: 647, https://arxiv.org/pdf/2511.12270.pdf GitHub

Abstract:
Medical image segmentation is essential for clinical diagnosis and treatment planning. Although transformer-based methods have achieved remarkable results, their high computational cost hinders clinical deployment. To address this issue, we propose TM-UNet, a novel lightweight framework that integrates token sequence modeling with an efficient memory mechanism for efficient medical segmentation. Specifically, we introduce a multi-scale token-memory (MSTM) block that transforms 2D spatial features into token sequences through strategic spatial scanning, leveraging matrix memory cells to selectively retain and propagate discriminative contextual information across tokens. This novel token-memory mechanism acts as a dynamic knowledge store that captures long-range dependencies with linear complexity, enabling efficient global reasoning without redundant computation. Our MSTM block further incorporates exponential gating to identify token effectiveness and multi-scale contextual extraction via parallel pooling operations, enabling hierarchical representation learning without computational overhead. Extensive experiments demonstrate that TM-UNet outperforms state-of-the-art methods across diverse medical segmentation tasks with substantially reduced computation cost. The code is available at https://github.com/xq141839/TM-UNet.

Paperid: 648, https://arxiv.org/pdf/2511.12249.pdf GitHub

Abstract:
Recent advances in contextualized word embeddings have greatly improved semantic tasks such as Word Sense Disambiguation (WSD) and contextual similarity, but most progress has been limited to high-resource languages like English. Vietnamese, in contrast, still lacks robust models and evaluation resources for fine-grained semantic understanding. In this paper, we present ViConBERT, a novel framework for learning Vietnamese contextualized embeddings that integrates contrastive learning (SimCLR) and gloss-based distillation to better capture word meaning. We also introduce ViConWSD, the first large-scale synthetic dataset for evaluating semantic understanding in Vietnamese, covering both WSD and contextual similarity. Experimental results show that ViConBERT outperforms strong baselines on WSD (F1 = 0.87) and achieves competitive performance on ViCon (AP = 0.88) and ViSim-400 (Spearman's rho = 0.60), demonstrating its effectiveness in modeling both discrete senses and graded semantic relations. Our code, models, and data are available at https://github.com/tkhangg0910/ViConBERT

Paperid: 649, https://arxiv.org/pdf/2511.12232.pdf GitHub

Abstract:
Social navigation in densely populated dynamic environments poses a significant challenge for autonomous mobile robots, requiring advanced strategies for safe interaction. Existing reinforcement learning (RL)-based methods require over 2000+ hours of extensive training and often struggle to generalize to unfamiliar environments without additional fine-tuning, limiting their practical application in real-world scenarios. To address these limitations, we propose SocialNav-Map, a novel zero-shot social navigation framework that combines dynamic human trajectory prediction with occupancy mapping, enabling safe and efficient navigation without the need for environment-specific training. Specifically, SocialNav-Map first transforms the task goal position into the constructed map coordinate system. Subsequently, it creates a dynamic occupancy map that incorporates predicted human movements as dynamic obstacles. The framework employs two complementary methods for human trajectory prediction: history prediction and orientation prediction. By integrating these predicted trajectories into the occupancy map, the robot can proactively avoid potential collisions with humans while efficiently navigating to its destination. Extensive experiments on the Social-HM3D and Social-MP3D datasets demonstrate that SocialNav-Map significantly outperforms state-of-the-art (SOTA) RL-based methods, which require 2,396 GPU hours of training. Notably, it reduces human collision rates by over 10% without necessitating any training in novel environments. By eliminating the need for environment-specific training, SocialNav-Map achieves superior navigation performance, paving the way for the deployment of social navigation systems in real-world environments characterized by diverse human behaviors. The code is available at: https://github.com/linglingxiansen/SocialNav-Map.

Paperid: 650, https://arxiv.org/pdf/2511.12204.pdf GitHub

Abstract:
Multi-view image generation holds significant application value in computer vision, particularly in domains like 3D reconstruction, virtual reality, and augmented reality. Most existing methods, which rely on extending single images, face notable computational challenges in maintaining cross-view consistency and generating high-resolution outputs. To address these issues, we propose the Geometry-guided Multi-View Diffusion Model, which incorporates mechanisms for extracting multi-view geometric information and adjusting the intensity of geometric features to generate images that are both consistent across views and rich in detail. Specifically, we design a multi-view geometry information extraction module that leverages depth maps, normal maps, and foreground segmentation masks to construct a shared geometric structure, ensuring shape and structural consistency across different views. To enhance consistency and detail restoration during generation, we develop a decoupled geometry-enhanced attention mechanism that strengthens feature focus on key geometric details, thereby improving overall image quality and detail preservation. Furthermore, we apply an adaptive learning strategy that fine-tunes the model to better capture spatial relationships and visual coherence between the generated views, ensuring realistic results. Our model also incorporates an iterative refinement process that progressively improves the output quality through multiple stages of image generation. Finally, a dynamic geometry information intensity adjustment mechanism is proposed to adaptively regulate the influence of geometric data, optimizing overall quality while ensuring the naturalness of generated images. More details can be found on the project page: https://github.com/SobeyMIL/GeoMVD.com.

Paperid: 651, https://arxiv.org/pdf/2511.12151.pdf GitHub

Abstract:
Text-guided image editing has advanced rapidly with the rise of diffusion models. While flow-based inversion-free methods offer high efficiency by avoiding latent inversion, they often fail to effectively integrate source information, leading to poor background preservation, spatial inconsistencies, and over-editing due to the lack of effective integration of source information. In this paper, we present FIA-Edit, a novel inversion-free framework that achieves high-fidelity and semantically precise edits through a Frequency-Interactive Attention. Specifically, we design two key components: (1) a Frequency Representation Interaction (FRI) module that enhances cross-domain alignment by exchanging frequency components between source and target features within self-attention, and (2) a Feature Injection (FIJ) module that explicitly incorporates source-side queries, keys, values, and text embeddings into the target branch's cross-attention to preserve structure and semantics. Comprehensive and extensive experiments demonstrate that FIA-Edit supports high-fidelity editing at low computational cost (~6s per 512 * 512 image on an RTX 4090) and consistently outperforms existing methods across diverse tasks in visual quality, background fidelity, and controllability. Furthermore, we are the first to extend text-guided image editing to clinical applications. By synthesizing anatomically coherent hemorrhage variations in surgical images, FIA-Edit opens new opportunities for medical data augmentation and delivers significant gains in downstream bleeding classification. Our project is available at: https://github.com/kk42yy/FIA-Edit.

Paperid: 652, https://arxiv.org/pdf/2511.12142.pdf GitHub

Abstract:
Source attribution aims to enhance the reliability of AI-generated answers by including references for each statement, helping users validate the provided answers. However, existing work has primarily focused on text-only scenario and largely overlooked the role of multimodality. We introduce MAVIS, the first benchmark designed to evaluate multimodal source attribution systems that understand user intent behind visual questions, retrieve multimodal evidence, and generate long-form answers with citations. Our dataset comprises 157K visual QA instances, where each answer is annotated with fact-level citations referring to multimodal documents. We develop fine-grained automatic metrics along three dimensions of informativeness, groundedness, and fluency, and demonstrate their strong correlation with human judgments. Our key findings are threefold: (1) LVLMs with multimodal RAG generate more informative and fluent answers than unimodal RAG, but they exhibit weaker groundedness for image documents than for text documents, a gap amplified in multimodal settings. (2) Given the same multimodal documents, there is a trade-off between informativeness and groundedness across different prompting methods. (3) Our proposed method highlights mitigating contextual bias in interpreting image documents as a crucial direction for future research. The dataset and experimental code are available at https://github.com/seokwon99/MAVIS

Paperid: 653, https://arxiv.org/pdf/2511.12140.pdf GitHub

Abstract:
Multimodal Large Language Models (MLLMs) have unlocked powerful cross-modal capabilities, but still significantly suffer from hallucinations. As such, accurate detection of hallucinations in MLLMs is imperative for ensuring their reliability in practical applications. To this end, guided by the principle of "Seeing is Believing", we introduce VBackChecker, a novel reference-free hallucination detection framework that verifies the consistency of MLLMgenerated responses with visual inputs, by leveraging a pixellevel Grounding LLM equipped with reasoning and referring segmentation capabilities. This reference-free framework not only effectively handles rich-context scenarios, but also offers interpretability. To facilitate this, an innovative pipeline is accordingly designed for generating instruction-tuning data (R-Instruct), featuring rich-context descriptions, grounding masks, and hard negative samples. We further establish R^2 -HalBench, a new hallucination benchmark for MLLMs, which, unlike previous benchmarks, encompasses real-world, rich-context descriptions from 18 MLLMs with high-quality annotations, spanning diverse object-, attribute, and relationship-level details. VBackChecker outperforms prior complex frameworks and achieves state-of-the-art performance on R^2 -HalBench, even rivaling GPT-4o's capabilities in hallucination detection. It also surpasses prior methods in the pixel-level grounding task, achieving over a 10% improvement. All codes, data, and models are available at https://github.com/PinxueGuo/VBackChecker.

Paperid: 654, https://arxiv.org/pdf/2511.12136.pdf GitHub

Abstract:
Spiking neural networks (SNNs) communicate via discrete spikes in time rather than continuous activations. Their event-driven nature offers advantages for temporal processing and energy efficiency on resource-constrained hardware, but training and deployment remain challenging. We present a lightweight C-based runtime for SNN inference on edge devices and optimizations that reduce latency and memory without sacrificing accuracy. Trained models exported from SNNTorch are translated to a compact C representation; static, cache-friendly data layouts and preallocation avoid interpreter and allocation overheads. We further exploit sparse spiking activity to prune inactive neurons and synapses, shrinking computation in upstream convolutional layers. Experiments on N-MNIST and ST-MNIST show functional parity with the Python baseline while achieving ~10 speedups on desktop CPU and additional gains with pruning, together with large memory reductions that enable microcontroller deployment (Arduino Portenta H7). Results indicate that SNNs can be executed efficiently on conventional embedded platforms when paired with an optimized runtime and spike-driven model compression. Code: https://github.com/karol-jurzec/snn-generator/

Paperid: 655, https://arxiv.org/pdf/2511.12098.pdf GitHub

Abstract:
Generating synthetic CT images from CBCT or MRI has a potential for efficient radiation dose planning and adaptive radiotherapy. However, existing CNN-based models lack global semantic understanding, while Transformers often overfit small medical datasets due to high model capacity and weak inductive bias. To address these limitations, we propose a DINOv3-Guided Cross Fusion (DGCF) framework that integrates a frozen self-supervised DINOv3 Transformer with a trainable CNN encoder-decoder. It hierarchically fuses global representation of Transformer and local features of CNN via a learnable cross fusion module, achieving balanced local appearance and contextual representation. Furthermore, we introduce a Multi-Level DINOv3 Perceptual (MLDP) loss that encourages semantic similarity between synthetic CT and the ground truth in DINOv3's feature space. Experiments on the SynthRAD2023 pelvic dataset demonstrate that DGCF achieved state-of-the-art performance in terms of MS-SSIM, PSNR and segmentation-based metrics on both MRI$\rightarrow$CT and CBCT$\rightarrow$CT translation tasks. To the best of our knowledge, this is the first work to employ DINOv3 representations for medical image translation, highlighting the potential of self-supervised Transformer guidance for semantic-aware CT synthesis. The code is available at https://github.com/HiLab-git/DGCF.

Paperid: 656, https://arxiv.org/pdf/2511.12073.pdf GitHub

Abstract:
Electroencephalography (EEG) offers detailed access to neural dynamics but remains constrained by noise and trial-by-trial variability, limiting decoding performance in data-restricted or complex paradigms. Data augmentation is often employed to enhance feature representations, yet conventional uniform averaging overlooks differences in trial informativeness and can degrade representational quality. We introduce a weighted bootstrapping approach that prioritizes more reliable trials to generate higher-quality augmented samples. In a Sentence Evaluation paradigm, weights were computed from relative ERP differences and applied during probabilistic sampling and averaging. Across conditions, weighted bootstrapping improved decoding accuracy relative to unweighted (from 68.35% to 71.25% at best), demonstrating that emphasizing reliable trials strengthens representational quality. The results demonstrate that reliability-based augmentation yields more robust and discriminative EEG representations. The code is publicly available at https://github.com/lyricists/NeuroBootstrap.

Paperid: 657, https://arxiv.org/pdf/2511.12054.pdf GitHub

Abstract:
Cross-view geo-localization (CVGL) matches query images ($\textit{e.g.}$, drone) to geographically corresponding opposite-view imagery ($\textit{e.g.}$, satellite). While supervised methods achieve strong performance, their reliance on extensive pairwise annotations limits scalability. Unsupervised alternatives avoid annotation costs but suffer from noisy pseudo-labels due to intrinsic cross-view domain gaps. To address these limitations, we propose $\textit{UniABG}$, a novel dual-stage unsupervised cross-view geo-localization framework integrating adversarial view bridging with graph-based correspondence calibration. Our approach first employs View-Aware Adversarial Bridging (VAAB) to model view-invariant features and enhance pseudo-label robustness. Subsequently, Heterogeneous Graph Filtering Calibration (HGFC) refines cross-view associations by constructing dual inter-view structure graphs, achieving reliable view correspondence. Extensive experiments demonstrate state-of-the-art unsupervised performance, showing that UniABG improves Satellite $\rightarrow$ Drone AP by +10.63\% on University-1652 and +16.73\% on SUES-200, even surpassing supervised baselines. The source code is available at https://github.com/chenqi142/UniABG

Paperid: 658, https://arxiv.org/pdf/2511.12040.pdf GitHub

Abstract:
Feed-forward 3D reconstruction from sparse, low-resolution (LR) images is a crucial capability for real-world applications, such as autonomous driving and embodied AI. However, existing methods often fail to recover fine texture details. This limitation stems from the inherent lack of high-frequency information in LR inputs. To address this, we propose \textbf{SRSplat}, a feed-forward framework that reconstructs high-resolution 3D scenes from only a few LR views. Our main insight is to compensate for the deficiency of texture information by jointly leveraging external high-quality reference images and internal texture cues. We first construct a scene-specific reference gallery, generated for each scene using Multimodal Large Language Models (MLLMs) and diffusion models. To integrate this external information, we introduce the \textit{Reference-Guided Feature Enhancement (RGFE)} module, which aligns and fuses features from the LR input images and their reference twin image. Subsequently, we train a decoder to predict the Gaussian primitives using the multi-view fused feature obtained from \textit{RGFE}. To further refine predicted Gaussian primitives, we introduce \textit{Texture-Aware Density Control (TADC)}, which adaptively adjusts Gaussian density based on the internal texture richness of the LR inputs. Extensive experiments demonstrate that our SRSplat outperforms existing methods on various datasets, including RealEstate10K, ACID, and DTU, and exhibits strong cross-dataset and cross-resolution generalization capabilities.

Paperid: 659, https://arxiv.org/pdf/2511.11978.pdf GitHub

Abstract:
Generative LLMs typically improve Named Entity Recognition (NER) performance through instruction tuning. They excel at generating entities by semantic pattern matching but lack an explicit, verifiable reasoning mechanism. This "cognitive shortcutting" leads to suboptimal performance and brittle generalization, especially in zero-shot and lowresource scenarios where reasoning from limited contextual cues is crucial. To address this issue, a reasoning framework is proposed for NER, which shifts the extraction paradigm from implicit pattern matching to explicit reasoning. This framework consists of three stages: Chain of Thought (CoT) generation, CoT tuning, and reasoning enhancement. First, a dataset annotated with NER-oriented CoTs is generated, which contain task-relevant reasoning chains. Then, they are used to tune the NER model to generate coherent rationales before deriving the final answer. Finally, a reasoning enhancement stage is implemented to optimize the reasoning process using a comprehensive reward signal. This stage ensures explicit and verifiable extractions. Experiments show that ReasoningNER demonstrates impressive cognitive ability in the NER task, achieving competitive performance. In zero-shot settings, it achieves state-of-the-art (SOTA) performance, outperforming GPT-4 by 12.3 percentage points on the F1 score. Analytical results also demonstrate its great potential to advance research in reasoningoriented information extraction. Our codes are available at https://github.com/HuiResearch/ReasoningIE.

Paperid: 660, https://arxiv.org/pdf/2511.11954.pdf GitHub

Abstract:
This study introduces a hybrid neuro-symbolic framework that achieves deterministic detection of statutory inconsistency in complex law. We use the U.S. Internal Revenue Code (IRC) as a case study because its complexity makes it a fertile domain for identifying conflicts. Our research offers a solution for detecting inconsistent provisions by combining Large Language Models (LLMs) with symbolic logic. LLM-based methods can support compliance, fairness, and statutory drafting, yet tax-specific applications remain sparse. A key challenge is that such models struggle with hierarchical processing and deep structured reasoning, especially over long text. This research addresses these gaps through experiments using GPT-4o, GPT-5, and Prolog. GPT-4o was first used to translate Section 121 into Prolog rules and refine them in SWISH. These rules were then incorporated into prompts to test whether Prolog-augmented prompting improved GPT-4o's inconsistency detection. GPT-4o, whether prompted with natural language alone or with Prolog augmentation, detected the inconsistency in only one of three strategies (33 percent accuracy), but its reasoning quality differed: natural-language prompting achieved 100 percent rule coverage, while Prolog-augmented prompting achieved 66 percent, indicating more incomplete statutory analysis. In contrast to probabilistic prompting, the hybrid Prolog model produced deterministic and reproducible results. Guided by GPT-5 for refinement, the model formalized the IRC section's competing interpretations and successfully detected an inconsistency zone. Validation tests confirm that the Prolog implementation is accurate, internally consistent, deterministic, and capable of autonomously identifying inconsistencies. These findings show that LLM-assisted formalization, anchored in symbolic logic, enables transparent and reliable statutory inconsistency detection.

Paperid: 661, https://arxiv.org/pdf/2511.11908.pdf GitHub

Abstract:
Medical imaging and multi-modal clinical settings often face the challange of missing modality in their diagnostic pipelines. Existing imputation methods either lack representational capacity or are computationally expensive. We propose PI-NAIM, a novel dual-path architecture that dynamically routes samples to optimized imputation approaches based on missingness complexity. Our framework integrates: (1) intelligent path routing that directs low missingness samples to efficient statistical imputation (MICE) and complex patterns to powerful neural networks (GAIN with temporal analysis); (2) cross-path attention fusion that leverages missingness-aware embeddings to intelligently combine both branches; and (3) end-to-end joint optimization of imputation accuracy and downstream task performance. Extensive experiments on MIMIC-III and multimodal benchmarks demonstrate state-of-the-art performance, achieving RMSE of 0.108 (vs. baselines' 0.119-0.152) and substantial gains in downstream tasks with an AUROC of 0.812 for mortality prediction. PI-NAIM's modular design enables seamless integration into vision pipelines handling incomplete sensor measurements, missing modalities, or corrupted inputs, providing a unified solution for real-world scenario. The code is publicly available at https://github.com/AfifaKhaled/PI-NAIM-Path-Integrated-Neural-Adaptive-Imputation-Model

Paperid: 662, https://arxiv.org/pdf/2511.11898.pdf GitHub

Abstract:
Vision-language foundation models (VLMs) show promise for diverse imaging tasks but often underperform on medical benchmarks. Prior efforts to improve performance include model finetuning, which requires large domain-specific datasets and significant compute, or manual prompt engineering, which is hard to generalize and often inaccessible to medical institutions seeking to deploy these tools. These challenges motivate interest in approaches that draw on a model's embedded knowledge while abstracting away dependence on human-designed prompts to enable scalable, weight-agnostic performance improvements. To explore this, we adapt the Declarative Self-improving Python (DSPy) framework for structured automated prompt optimization in medical vision-language systems through a comprehensive, formal evaluation. We implement prompting pipelines for five medical imaging tasks across radiology, gastroenterology, and dermatology, evaluating 10 open-source VLMs with four prompt optimization techniques. Optimized pipelines achieved a median relative improvement of 53% over zero-shot prompting baselines, with the largest gains ranging from 300% to 3,400% on tasks where zero-shot performance is low. These results highlight the substantial potential of applying automated prompt optimization to medical AI systems, demonstrating significant gains for vision-based applications requiring accurate clinical image interpretation. By reducing dependence on prompt design to elicit intended outputs, these techniques allow clinicians to focus on patient care and clinical decision-making. Furthermore, our experiments offer scalability and preserve data privacy, demonstrating performance improvement on open-source VLMs. We publicly release our evaluation pipelines to support reproducible research on specialized medical tasks, available at https://github.com/DaneshjouLab/prompt-triage-lab.

Paperid: 663, https://arxiv.org/pdf/2511.11881.pdf GitHub

Abstract:
Large Language Models (LLMs) have achieved remarkable progress through Reinforcement Learning with Verifiable Rewards (RLVR), yet still rely heavily on external supervision (e.g., curated labels). Adversarial learning, particularly through self-play, offers a promising alternative that enables models to iteratively learn from themselves - thus reducing reliance on external supervision. Dual-play extends adversarial learning by assigning specialized roles to two models and training them against each other, fostering sustained competition and mutual evolution. Despite its promise, adapting dual-play training to LLMs remains limited, largely due to their susceptibility to reward hacking and training instability. In this paper, we introduce PasoDoble, a novel LLM dual-play framework. PasoDoble adversarially trains two models initialized from the same base model: a Proposer, which generates challenging questions with ground-truth answers, and a Solver, which attempts to solve them. We enrich the Proposer with knowledge from a pre-training dataset to ensure the questions' quality and diversity. To avoid reward hacking, the Proposer is rewarded for producing only valid questions that push the Solver's limit, while the Solver is rewarded for solving them correctly, and both are updated jointly. To further enhance training stability, we introduce an optional offline paradigm that decouples Proposer and Solver updates, alternately updating each for several steps while holding the other fixed. Notably, PasoDoble operates without supervision during training. Experimental results show that PasoDoble can improve the reasoning performance of LLMs. Our project page is available at https://hcy123902.github.io/PasoDoble.

Paperid: 664, https://arxiv.org/pdf/2511.11831.pdf GitHub

Abstract:
Large Vision-Language Models (LVLMs) typically align visual features from an encoder with a pre-trained Large Language Model (LLM). However, this makes the visual perception module a bottleneck, which constrains the overall capabilities of LVLMs. Conventional evaluation benchmarks, while rich in visual semantics, often contain unavoidable local shortcuts that can lead to an overestimation of models' perceptual abilities. Here, we introduce TopoPerception, a benchmark that leverages topological properties to rigorously evaluate the global visual perception capabilities of LVLMs across various granularities. Since topology depends on the global structure of an image and is invariant to local features, TopoPerception enables a shortcut-free assessment of global perception, fundamentally distinguishing it from semantically rich tasks. We evaluate state-of-the-art models on TopoPerception and find that even at the coarsest perceptual granularity, all models perform no better than random chance, indicating a profound inability to perceive global visual features. Notably, a consistent trend emerge within model families: more powerful models with stronger reasoning capabilities exhibit lower accuracy. This suggests that merely scaling up models is insufficient to address this deficit and may even exacerbate it. Progress may require new training paradigms or architectures. TopoPerception not only exposes a critical bottleneck in current LVLMs but also offers a lens and direction for improving their global visual perception. The data and code are publicly available at: https://github.com/Wenhao-Zhou/TopoPerception.

Paperid: 665, https://arxiv.org/pdf/2511.11787.pdf GitHub

Abstract:
Systematics contaminate observables, leading to distribution shifts relative to theoretically simulated signals-posing a major challenge for using pre-trained models to label such observables. Since systematics are often poorly understood and difficult to model, removing them directly and entirely may not be feasible. To address this challenge, we propose a novel method that aligns learned features between in-distribution (ID) and out-of-distribution (OOD) samples by optimizing a feature-alignment loss on the representations extracted from a pre-trained ID model. We first experimentally validate the method on the MNIST dataset using possible alignment losses, including mean squared error and optimal transport, and subsequently apply it to large-scale maps of neutral hydrogen. Our results show that optimal transport is particularly effective at aligning OOD features when parity between ID and OOD samples is unknown, even with limited data-mimicking real-world conditions in extracting information from large-scale surveys. Our code is available at https://github.com/sultan-hassan/feature-alignment-for-OOD-generalization.

Paperid: 666, https://arxiv.org/pdf/2511.11758.pdf GitHub

Abstract:
Protein structure is central to biological function, and enabling multimodal protein models requires joint reasoning over sequence, structure, and function. A key barrier is the lack of principled protein structure tokenizers (PSTs): existing approaches fix token size or rely on continuous vector codebooks, limiting interpretability, multi-scale control, and transfer across architectures. We introduce GeoBPE, a geometry-grounded PST that transforms continuous, noisy, multi-scale backbone conformations into discrete ``sentences'' of geometry while enforcing global constraints. Analogous to byte-pair encoding, GeoBPE generates a hierarchical vocabulary of geometric primitives by iteratively (i) clustering Geo-Pair occurrences with k-medoids to yield a resolution-controllable vocabulary; (ii) quantizing each Geo-Pair to its closest medoid prototype; and (iii) reducing drift through differentiable inverse kinematics that optimizes boundary glue angles under an $\mathrm{SE}(3)$ end-frame loss. GeoBPE offers compression ($>$10x reduction in bits-per-residue at similar distortion rate), data efficiency ($>$10x less training data), and generalization (maintains test/train distortion ratio of $1.0-1.1$). It is architecture-agnostic: (a) its hierarchical vocabulary provides a strong inductive bias for coarsening residue-level embeddings from large PLMs into motif- and protein-level representations, consistently outperforming leading PSTs across $12$ tasks and $24$ test splits; (b) paired with a transformer, GeoBPE supports unconditional backbone generation via language modeling; and (c) tokens align with CATH functional families and support expert-interpretable case studies, offering functional meaning absent in prior PSTs. Code is available at https://github.com/shiningsunnyday/PT-BPE/.

Paperid: 667, https://arxiv.org/pdf/2511.11750.pdf GitHub

Abstract:
Tropical Cyclone (TC) estimation aims to accurately estimate various TC attributes in real time. However, distribution shifts arising from the complex and dynamic nature of TC environmental fields, such as varying geographical conditions and seasonal changes, present significant challenges to reliable estimation. Most existing methods rely on multi-modal fusion for feature extraction but overlook the intrinsic distribution of feature representations, leading to poor generalization under out-of-distribution (OOD) scenarios. To address this, we propose an effective Identity Distribution-Oriented Physical Invariant Learning framework (IDOL), which imposes identity-oriented constraints to regulate the feature space under the guidance of prior physical knowledge, thereby dealing distribution variability with physical invariance. Specifically, the proposed IDOL employs the wind field model and dark correlation knowledge of TC to model task-shared and task-specific identity tokens. These tokens capture task dependencies and intrinsic physical invariances of TC, enabling robust estimation of TC wind speed, pressure, inner-core, and outer-core size under distribution shifts. Extensive experiments conducted on multiple datasets and tasks demonstrate the outperformance of the proposed IDOL, verifying that imposing identity-oriented constraints based on prior physical knowledge can effectively mitigates diverse distribution shifts in TC estimation.Code is available at https://github.com/Zjut-MultimediaPlus/IDOL.

Paperid: 668, https://arxiv.org/pdf/2511.11707.pdf GitHub

Abstract:
Continual learning remains challenging due to catastrophic forgetting, where neural networks lose previously acquired knowledge when learning new tasks. Inspired by memory consolidation in neuroscience, we propose FSC-Net (Fast-Slow Consolidation Networks), a dual-network architecture that separates rapid task learning from gradual knowledge consolidation. Our method employs a fast network (NN1) for immediate adaptation to new tasks and a slow network (NN2) that consolidates knowledge through distillation and replay. Within the family of MLP-based NN1 variants we evaluated, consolidation effectiveness is driven more by methodology than architectural embellishments -- a simple MLP outperforms more complex similarity-gated variants by 1.2pp. Through systematic hyperparameter analysis, we observed empirically that pure replay without distillation during consolidation achieves superior performance, consistent with the hypothesis that distillation from the fast network introduces recency bias. On Split-MNIST (30 seeds), FSC-Net achieves 91.71% +/- 0.62% retention accuracy, a +4.27pp gain over the fast network alone (87.43% +/- 1.27%, paired t=23.585, p < 1e-10). On Split-CIFAR-10 (5 seeds), our method achieves 33.31% +/- 0.38% retention with an +8.20pp gain over the fast network alone (25.11% +/- 1.61%, paired t=9.75, p < 1e-3), demonstrating +8.20pp gain, though absolute performance (33.31%) remains modest and below random expectation, highlighting need for stronger backbones. Our results provide empirical evidence that the dual-timescale consolidation mechanism, rather than architectural complexity, is central to mitigating catastrophic forgetting in this setting.

Paperid: 669, https://arxiv.org/pdf/2511.11681.pdf GitHub

Abstract:
Ground-based cloud image segmentation is a critical research domain for photovoltaic power forecasting. Current deep learning approaches primarily focus on encoder-decoder architectural refinements. However, existing methodologies exhibit several limitations:(1)they rely on dilated convolutions for multi-scale context extraction, lacking the partial feature effectiveness and interoperability of inter-channel;(2)attention-based feature enhancement implementations neglect accuracy-throughput balance; and (3)the decoder modifications fail to establish global interdependencies among hierarchical local features, limiting inference efficiency. To address these challenges, we propose MPCM-Net, a Multi-scale network that integrates Partial attention Convolutions with Mamba architectures to enhance segmentation accuracy and computational efficiency. Specifically, the encoder incorporates MPAC, which comprises:(1)a MPC block with ParCM and ParSM that enables global spatial interaction across multi-scale cloud formations, and (2)a MPA block combining ParAM and ParSM to extract discriminative features with reduced computational complexity. On the decoder side, a M2B is employed to mitigate contextual loss through a SSHD that maintains linear complexity while enabling deep feature aggregation across spatial and scale dimensions. As a key contribution to the community, we also introduce and release a dataset CSRC, which is a clear-label, fine-grained segmentation benchmark designed to overcome the critical limitations of existing public datasets. Extensive experiments on CSRC demonstrate the superior performance of MPCM-Net over state-of-the-art methods, achieving an optimal balance between segmentation accuracy and inference speed. The dataset and source code will be available at https://github.com/she1110/CSRC.

Paperid: 670, https://arxiv.org/pdf/2511.11643.pdf GitHub

Abstract:
Road conditions play an important role in our everyday commute. With the proliferating number of vehicles on the road each year, it has become necessary to access the road conditions very frequently, this would ensure that the traffic also flows smoothly. Even the smallest crack in the road could be easily be chipped into a large pothole due to changing surface temperatures of the road and from the force of vehicles riding over it. In this paper, we have addressed how we could better identify these potholes in realtime with the help of onboard sensors in vehicles so that the data could be useful for analysis and better management of potholes on a large scale. For the implementation, we used an SVM classifier to detect potholes, we achieved 98.1% accuracy based on data collected from a local road for about 2 km which had 26 potholes distributed along the road. Code is available at: https://github.com/aswathselvam/Potholes

Paperid: 671, https://arxiv.org/pdf/2511.11571.pdf GitHub

Abstract:
Mixture of Block Attention (MoBA) (Lu et al., 2025) is a promising building block for efficiently processing long contexts in LLMs by enabling queries to sparsely attend to a small subset of key-value blocks, drastically reducing computational cost. However, the design principles governing MoBA's performance are poorly understood, and it lacks an efficient GPU implementation, hindering its practical adoption. In this paper, we first develop a statistical model to analyze MoBA's underlying mechanics. Our model reveals that performance critically depends on the router's ability to accurately distinguish relevant from irrelevant blocks based on query-key affinities. We derive a signal-to-noise ratio that formally connects architectural parameters to this retrieval accuracy. Guided by our analysis, we identify two key pathways for improvement: using smaller block sizes and applying a short convolution on keys to cluster relevant signals, which enhances routing accuracy. While theoretically better, small block sizes are inefficient on GPUs. To bridge this gap, we introduce FlashMoBA, a hardware-aware CUDA kernel that enables efficient MoBA execution even with the small block sizes our theory recommends. We validate our insights by training LLMs from scratch, showing that our improved MoBA models match the performance of dense attention baselines. FlashMoBA achieves up to 14.7x speedup over FlashAttention-2 for small blocks, making our theoretically-grounded improvements practical. Code is available at: https://github.com/mit-han-lab/flash-moba.

Paperid: 672, https://arxiv.org/pdf/2511.11563.pdf GitHub

Abstract:
Modeling 3D articulated objects with realistic geometry, textures, and kinematics is essential for a wide range of applications. However, existing optimization-based reconstruction methods often require dense multi-view inputs and expensive per-instance optimization, limiting their scalability. Recent feedforward approaches offer faster alternatives but frequently produce coarse geometry, lack texture reconstruction, and rely on brittle, complex multi-stage pipelines. We introduce LARM, a unified feedforward framework that reconstructs 3D articulated objects from sparse-view images by jointly recovering detailed geometry, realistic textures, and accurate joint structures. LARM extends LVSM a recent novel view synthesis (NVS) approach for static 3D objects into the articulated setting by jointly reasoning over camera pose and articulation variation using a transformer-based architecture, enabling scalable and accurate novel view synthesis. In addition, LARM generates auxiliary outputs such as depth maps and part masks to facilitate explicit 3D mesh extraction and joint estimation. Our pipeline eliminates the need for dense supervision and supports high-fidelity reconstruction across diverse object categories. Extensive experiments demonstrate that LARM outperforms state-of-the-art methods in both novel view and state synthesis as well as 3D articulated object reconstruction, generating high-quality meshes that closely adhere to the input images. project page: https://sylviayuan-sy.github.io/larm-site/

Paperid: 673, https://arxiv.org/pdf/2511.11526.pdf GitHub

Abstract:
Vision-Language Models (VLMs) are a new family of models that align image content with natural language. Existing approaches typically fuse either (a) early: by mixing tokens/features inside the encoders, or (b) late: by comparing pooled embeddings. Many methods also tie fusion to an autoregressive decoder. However, the hidden states of both modalities already carry rich, modality-specific structure (spatial layout in vision; syntax and semantics in text), so directly aligning these states is a natural way to match what the two modalities "think". We propose a lightweight fusion module: a few cross-only, bidirectional attention layers placed near the top of both encoders. Each layer projects the vision and text encoder hidden-state sequences into a shared space, attends across modalities, and sends gated residual updates back, with simple stabilizers to improve alignment. The encoders remain non-causal and strong for understanding, while generation stays cleanly decoupled via an optional decoder. Across standard retrieval, VQA, and visual reasoning benchmarks, BRIDGE outperforms comparable VLMs while preserving the bi-encoder efficiency of contrastive models. We make our code publicly available at https://github.com/jfeinashley/BRIDGE.

Paperid: 674, https://arxiv.org/pdf/2511.11510.pdf GitHub

Abstract:
Ultrasound (US) is one of the most widely used medical imaging modalities, thanks to its low cost, portability, real-time feedback, and absence of ionizing radiation. However, US image interpretation remains highly operator-dependent and varies significantly across anatomical regions, acquisition protocols, and device types. These variations, along with unique challenges such as speckle, low contrast, and limited standardized annotations, hinder the development of generalizable, label-efficient ultrasound AI models. In this paper, we propose OpenUS, the first reproducible, open-source ultrasound foundation model built on a large collection of public data. OpenUS employs a vision Mamba backbone, capturing both local and global long-range dependencies across the image. To extract rich features during pre-training, we introduce a novel self-adaptive masking framework that combines contrastive learning with masked image modeling. This strategy integrates the teacher's attention map with student reconstruction loss, adaptively refining clinically-relevant masking to enhance pre-training effectiveness. OpenUS also applies a dynamic learning schedule to progressively adjust the difficulty of the pre-training process. To develop the foundation model, we compile the largest to-date public ultrasound dataset comprising over 308K images from 42 publicly available datasets, covering diverse anatomical regions, institutions, imaging devices, and disease types. Our pre-trained OpenUS model can be easily adapted to specific downstream tasks by serving as a backbone for label-efficient fine-tuning. Code is available at https://github.com/XZheng0427/OpenUS.

Paperid: 675, https://arxiv.org/pdf/2511.11427.pdf GitHub

Abstract:
Referring Expression Comprehension (REC) requires models to localize objects in images based on natural language descriptions. Research on the area remains predominantly English-centric, despite increasing global deployment demands. This work addresses multilingual REC through two main contributions. First, we construct a unified multilingual dataset spanning 10 languages, by systematically expanding 12 existing English REC benchmarks through machine translation and context-based translation enhancement. The resulting dataset comprises approximately 8 million multilingual referring expressions across 177,620 images, with 336,882 annotated objects. Second, we introduce an attention-anchored neural architecture that uses multilingual SigLIP2 encoders. Our attention-based approach generates coarse spatial anchors from attention distributions, which are subsequently refined through learned residuals. Experimental evaluation demonstrates competitive performance on standard benchmarks, e.g. achieving 86.9% accuracy at IoU@50 on RefCOCO aggregate multilingual evaluation, compared to an English-only result of 91.3%. Multilingual evaluation shows consistent capabilities across languages, establishing the practical feasibility of multilingual visual grounding systems. The dataset and model are available at $\href{https://multilingual.franreno.com}{multilingual.franreno.com}$.

Paperid: 676, https://arxiv.org/pdf/2511.11410.pdf GitHub

Abstract:
The rapid advancement of Multi-modal Large Language Models (MLLMs) has expanded their capabilities beyond high-level vision tasks. Nevertheless, their potential for Document Image Quality Assessment (DIQA) remains underexplored. To bridge this gap, we propose Q-Doc, a three-tiered evaluation framework for systematically probing DIQA capabilities of MLLMs at coarse, middle, and fine granularity levels. a) At the coarse level, we instruct MLLMs to assign quality scores to document images and analyze their correlation with Quality Annotations. b) At the middle level, we design distortion-type identification tasks, including single-choice and multi-choice tests for multi-distortion scenarios. c) At the fine level, we introduce distortion-severity assessment where MLLMs classify distortion intensity against human-annotated references. Our evaluation demonstrates that while MLLMs possess nascent DIQA abilities, they exhibit critical limitations: inconsistent scoring, distortion misidentification, and severity misjudgment. Significantly, we show that Chain-of-Thought (CoT) prompting substantially enhances performance across all levels. Our work provides a benchmark for DIQA capabilities in MLLMs, revealing pronounced deficiencies in their quality perception and promising pathways for enhancement. The benchmark and code are publicly available at: https://github.com/cydxf/Q-Doc.

Paperid: 677, https://arxiv.org/pdf/2511.11366.pdf GitHub

Abstract:
Modern electrical power grids represent complex cyber-physical systems requiring specialized cybersecurity frameworks beyond traditional IT security models. Existing threat intelligence standards such as STIX 2.1 and MITRE ATT\&CK lack coverage for grid-specific assets, operational technology relationships, and cyber-physical interdependencies essential for power system security. We present Grid-STIX, a domain-specific extension of STIX 2.1 for electrical grid cybersecurity applications. Grid-STIX employs a modular architecture encompassing physical assets, operational technology components, cyber-physical relationships, and security policies that capture modern power systems including distributed energy resources, advanced metering infrastructure, and nuclear energy facilities. The framework provides threat modeling capabilities through systematic representation of attack patterns, supply chain risks, and cross-domain impact analysis while maintaining STIX 2.1 compliance. Grid-STIX includes modules for nuclear safeguards and non-proliferation verification, enabling cybersecurity modeling across conventional and nuclear energy sectors. The ontology supports Zero Trust enforcement through policy decision points and operational context integration. Our implementation includes validation pipelines, Python code generation, and visualizations. Use cases demonstrate applications including cross-utility threat intelligence sharing, supply chain risk assessment, and nuclear facility cybersecurity. Grid-STIX is available as an open-source framework to advance collaborative cybersecurity research across the electrical power sector.

Paperid: 678, https://arxiv.org/pdf/2511.11332.pdf GitHub GitHub

Abstract:
Large language model (LLM)-powered agents are transforming digital devices from passive tools into proactive intelligent collaborators. However, most existing frameworks remain confined to a single OS or device, making cross-device workflows brittle and largely manual. We present UFO$^3$, a system that unifies heterogeneous endpoints, desktops, servers, mobile devices, and edge, into a single orchestration fabric. UFO$^3$ models each user request as a mutable TaskConstellation: a distributed DAG of atomic subtasks (TaskStars) with explicit control and data dependencies (TaskStarLines). The TaskConstellation continuously evolves as results stream in from distributed devices, enabling asynchronous execution, adaptive recovery, and dynamic optimization. A Constellation Orchestrator} executes tasks safely and asynchronously while applying dynamic DAG updates, and the Agent Interaction Protocol (AIP) provides persistent, low-latency channels for reliable task dispatch and result streaming. These designs dissolve the traditional boundaries between devices and platforms, allowing agents to collaborate seamlessly and amplify their collective intelligence. We evaluate UFO$^3$ on NebulaBench, a benchmark of 55 cross-device tasks across 5 machines and 10 categories. UFO$^3$ achieves 83.3% subtask completion, 70.9% task success, exposes parallelism with an average width of 1.72, and reduces end-to-end latency by 31% relative to a sequential baseline. Fault-injection experiments demonstrate graceful degradation and recovery under transient and permanent agent failures. These results show that UFO$^3$ achieves accurate, efficient, and resilient task orchestration across heterogeneous devices, uniting isolated agents into a coherent, adaptive computing fabric that extends across the landscape of ubiquitous computing.

Paperid: 679, https://arxiv.org/pdf/2511.11299.pdf GitHub

Abstract:
Multimodal Large Language Models (MLLMs) achieve impressive performance once optimized on massive datasets. Such datasets often contain sensitive or copyrighted content, raising significant data privacy concerns. Regulatory frameworks mandating the 'right to be forgotten' drive the need for machine unlearning. This technique allows for the removal of target data without resource-consuming retraining. However, while well-studied for text, visual concept unlearning in MLLMs remains underexplored. A primary challenge is precisely removing a target visual concept without disrupting model performance on related entities. To address this, we introduce AUVIC, a novel visual concept unlearning framework for MLLMs. AUVIC applies adversarial perturbations to enable precise forgetting. This approach effectively isolates the target concept while avoiding unintended effects on similar entities. To evaluate our method, we construct VCUBench. It is the first benchmark designed to assess visual concept unlearning in group contexts. Experimental results demonstrate that AUVIC achieves state-of-the-art target forgetting rates while incurs minimal performance degradation on non-target concepts.

Paperid: 680, https://arxiv.org/pdf/2511.11287.pdf GitHub

Abstract:
The increasing deployment of autonomous AI agents on the web is hampered by a fundamental misalignment: agents must infer affordances from human-oriented user interfaces, leading to brittle, inefficient, and insecure interactions. To address this, we introduce VOIX, a web-native framework that enables websites to expose reliable, auditable, and privacy-preserving capabilities for AI agents through simple, declarative HTML elements. VOIX introduces and tags, allowing developers to explicitly define available actions and relevant state, thereby creating a clear, machine-readable contract for agent behavior. This approach shifts control to the website developer while preserving user privacy by disconnecting the conversational interactions from the website. We evaluated the framework's practicality, learnability, and expressiveness in a three-day hackathon study with 16 developers. The results demonstrate that participants, regardless of prior experience, were able to rapidly build diverse and functional agent-enabled web applications. Ultimately, this work provides a foundational mechanism for realizing the Agentic Web, enabling a future of seamless and secure human-AI collaboration on the web.

Paperid: 681, https://arxiv.org/pdf/2511.11276.pdf GitHub

Abstract:
Volumetric medical image segmentation presents unique challenges due to the inherent anatomical structure and limited availability of annotations. While recent methods have shown promise by contrasting spatial relationships between slices, they rely on hard binary thresholds to define positive and negative samples, thereby discarding valuable continuous information about anatomical similarity. Moreover, these methods overlook the global directional consistency of anatomical progression, resulting in distorted feature spaces that fail to capture the canonical anatomical manifold shared across patients. To address these limitations, we propose Coordinative Ordinal-Relational Anatomical Learning (CORAL) to capture both local and global structure in volumetric images. First, CORAL employs a contrastive ranking objective to leverage continuous anatomical similarity, ensuring relational feature distances between slices are proportional to their anatomical position differences. In addition, CORAL incorporates an ordinal objective to enforce global directional consistency, aligning the learned feature distribution with the canonical anatomical progression across patients. Learning these inter-slice relationships produces anatomically informed representations that benefit the downstream segmentation task. Through this coordinative learning framework, CORAL achieves state-of-the-art performance on benchmark datasets under limited-annotation settings while learning representations with meaningful anatomical structure. Code is available at https://github.com/haoyiwang25/CORAL.

Paperid: 682, https://arxiv.org/pdf/2511.11266.pdf GitHub

Abstract:
Vision-language models have recently emerged as promising planners for autonomous driving, where success hinges on topology-aware reasoning over spatial structure and dynamic interactions from multimodal input. However, existing models are typically trained without supervision that explicitly encodes these relational dependencies, limiting their ability to infer how agents and other traffic entities influence one another from raw sensor data. In this work, we bridge this gap with a novel model-agnostic method that conditions language-based driving models on structured relational context in the form of traffic scene graphs. We serialize scene graphs at various abstraction levels and formats, and incorporate them into the models via structured prompt templates, enabling a systematic analysis of when and how relational supervision is most beneficial. Extensive evaluations on the public LangAuto benchmark show that scene graph conditioning of state-of-the-art approaches yields large and persistent improvement in driving performance. Notably, we observe up to a 15.6\% increase in driving score for LMDrive and 17.5\% for BEVDriver, indicating that models can better internalize and ground relational priors through scene graph-conditioned training, even without requiring scene graph input at test-time. Code, fine-tuned models, and our scene graph dataset are publicly available at https://github.com/iis-esslingen/GraphPilot.

Paperid: 683, https://arxiv.org/pdf/2511.11252.pdf GitHub

Abstract:
Autonomous aerial systems increasingly rely on large language models (LLMs) for mission planning, perception, and decision-making, yet the lack of standardized and physically grounded benchmarks limits systematic evaluation of their reasoning capabilities. To address this gap, we introduce UAVBench, an open benchmark dataset comprising 50,000 validated UAV flight scenarios generated through taxonomy-guided LLM prompting and multi-stage safety validation. Each scenario is encoded in a structured JSON schema that includes mission objectives, vehicle configuration, environmental conditions, and quantitative risk labels, providing a unified representation of UAV operations across diverse domains. Building on this foundation, we present UAVBench_MCQ, a reasoning-oriented extension containing 50,000 multiple-choice questions spanning ten cognitive and ethical reasoning styles, ranging from aerodynamics and navigation to multi-agent coordination and integrated reasoning. This framework enables interpretable and machine-checkable assessment of UAV-specific cognition under realistic operational contexts. We evaluate 32 state-of-the-art LLMs, including GPT-5, ChatGPT-4o, Gemini 2.5 Flash, DeepSeek V3, Qwen3 235B, and ERNIE 4.5 300B, and find strong performance in perception and policy reasoning but persistent challenges in ethics-aware and resource-constrained decision-making. UAVBench establishes a reproducible and physically grounded foundation for benchmarking agentic AI in autonomous aerial systems and advancing next-generation UAV reasoning intelligence. To support open science and reproducibility, we release the UAVBench dataset, the UAVBench_MCQ benchmark, evaluation scripts, and all related materials on GitHub at https://github.com/maferrag/UAVBench

Paperid: 684, https://arxiv.org/pdf/2511.11248.pdf GitHub

Abstract:
Large language models (LLMs) are increasingly deployed on customer devices. To support them, current devices are adopting SoCs (System on Chip) with NPUs (Neural Processing Unit) installed. Although high performance is expected, LLM inference on NPUs is slower than its CPU counterpart. The reason is that NPUs have poor performance on computations other than GEMM, like dequantization. Current works either disaggregate prefill on the NPUs and decoding on the CPUs, or put both on the NPUs but with an accuracy loss. To solve this issue, based on the insight that low-bit can enable target computation encoded within an acceptably sized table, we propose table lookup to subsume hardware operations otherwise unsupported. To realize this, we overcome the conflicting hardware behavior of prefill and decoding to design a unified table layout and tiling through (1) fused two-level table-based dequantization and (2) concurrency-hierarchy-guided tiling. Based on that, we implement the prefill phase by three-stage pipeline and map the table-lookup-based decoding to NPU's vector units. Results show 1.4x and 3.1x speedup for prefill and decoding respectively, and 84% energy savings compared to the baseline NPU methods. The code is available at https://github.com/microsoft/T-MAC/tree/main/t-man.

Paperid: 685, https://arxiv.org/pdf/2511.11212.pdf GitHub

Abstract:
Foundational models are trained on extensive datasets to capture the general trends of a domain. However, in medical imaging, the scarcity of data makes pre-training for every domain, modality, or task challenging. Instead of building separate models, we propose MAFM^3 (Modular Adaptation of Foundation Models for Multi-Modal Medical AI), a framework that enables a single foundation model to expand into diverse domains, tasks, and modalities through lightweight modular components. These components serve as specialized skill sets that allow the system to flexibly activate the appropriate capability at the inference time, depending on the input type or clinical objective. Unlike conventional adaptation methods that treat each new task or modality in isolation, MAFM^3 provides a unified and expandable framework for efficient multitask and multimodality adaptation. Empirically, we validate our approach by adapting a chest CT foundation model initially trained for classification into prognosis and segmentation modules. Our results show improved performance on both tasks. Furthermore, by incorporating PET scans, MAFM^3 achieved an improvement in the Dice score 5% compared to the respective baselines. These findings establish that foundation models, when equipped with modular components, are not inherently constrained to their initial training scope but can evolve into multitask, multimodality systems for medical imaging. The code implementation of this work can be found at https://github.com/Areeb2735/CTscan_prognosis_VLM

Paperid: 686, https://arxiv.org/pdf/2511.11182.pdf GitHub

Abstract:
Hallucination continues to pose a major obstacle in the reasoning capabilities of large language models (LLMs). Although the Multi-Agent Debate (MAD) paradigm offers a promising solution by promoting consensus among multiple agents to enhance reliability, it relies on the unrealistic assumption that all debaters are rational and reflective, which is a condition that may not hold when agents themselves are prone to hallucinations. To address this gap, we introduce the Multi-agent Undercover Gaming (MUG) protocol, inspired by social deduction games like "Who is Undercover?". MUG reframes MAD as a process of detecting "undercover" agents (those suffering from hallucinations) by employing multimodal counterfactual tests. Specifically, we modify reference images to introduce counterfactual evidence and observe whether agents can accurately identify these changes, providing ground-truth for identifying hallucinating agents and enabling robust, crowd-powered multimodal reasoning. MUG advances MAD protocols along three key dimensions: (1) enabling factual verification beyond statistical consensus through counterfactual testing; (2) introducing cross-evidence reasoning via dynamically modified evidence sources instead of relying on static inputs; and (3) fostering active reasoning, where agents engage in probing discussions rather than passively answering questions. Collectively, these innovations offer a more reliable and effective framework for multimodal reasoning in LLMs. The source code can be accessed at https://github.com/YongLD/MUG.git.

Paperid: 687, https://arxiv.org/pdf/2511.11134.pdf GitHub

Abstract:
The advent of Unified Multimodal Models (UMMs) signals a paradigm shift in artificial intelligence, moving from passive perception to active, cross-modal generation. Despite their unprecedented ability to synthesize information, a critical gap persists in evaluation: existing benchmarks primarily assess discriminative understanding or unconstrained image generation separately, failing to measure the integrated cognitive process of generative reasoning. To bridge this gap, we propose that geometric construction provides an ideal testbed as it inherently demands a fusion of language comprehension and precise visual generation. We introduce GGBench, a benchmark designed specifically to evaluate geometric generative reasoning. It provides a comprehensive framework for systematically diagnosing a model's ability to not only understand and reason but to actively construct a solution, thereby setting a more rigorous standard for the next generation of intelligent systems. Project website: https://opendatalab-raiser.github.io/GGBench/.

Paperid: 688, https://arxiv.org/pdf/2511.11126.pdf GitHub

Abstract:
With the rapid rise of social media and Internet culture, memes have become a popular medium for expressing emotional tendencies. This has sparked growing interest in Meme Emotion Understanding (MEU), which aims to classify the emotional intent behind memes by leveraging their multimodal contents. While existing efforts have achieved promising results, two major challenges remain: (1) a lack of fine-grained multimodal fusion strategies, and (2) insufficient mining of memes' implicit meanings and background knowledge. To address these challenges, we propose MemoDetector, a novel framework for advancing MEU. First, we introduce a four-step textual enhancement module that utilizes the rich knowledge and reasoning capabilities of Multimodal Large Language Models (MLLMs) to progressively infer and extract implicit and contextual insights from memes. These enhanced texts significantly enrich the original meme contents and provide valuable guidance for downstream classification. Next, we design a dual-stage modal fusion strategy: the first stage performs shallow fusion on raw meme image and text, while the second stage deeply integrates the enhanced visual and textual features. This hierarchical fusion enables the model to better capture nuanced cross-modal emotional cues. Experiments on two datasets, MET-MEME and MOOD, demonstrate that our method consistently outperforms state-of-the-art baselines. Specifically, MemoDetector improves F1 scores by 4.3\% on MET-MEME and 3.4\% on MOOD. Further ablation studies and in-depth analyses validate the effectiveness and robustness of our approach, highlighting its strong potential for advancing MEU. Our code is available at https://github.com/singing-cat/MemoDetector.

Paperid: 689, https://arxiv.org/pdf/2511.11090.pdf GitHub

Abstract:
Meteorological agencies around the world rely on real-time flood guidance to issue live-saving advisories and warnings. For decades traditional numerical weather prediction (NWP) models have been state-of-the-art for precipitation forecasting. However, physically-parameterized models suffer from a few core limitations: first, solving PDEs to resolve atmospheric dynamics is computationally demanding, and second, these methods degrade in performance at nowcasting timescales (i.e., 0-4 hour lead-times). Motivated by these shortcomings, recent work proposes AI-weather prediction (AI-WP) alternatives that learn to emulate analysis data with neural networks. While these data-driven approaches have enjoyed enormous success across diverse spatial and temporal resolutions, applications of video-understanding architectures for weather forecasting remain underexplored. To address these gaps, we propose SaTformer: a video transformer built on full space-time attention that skillfully forecasts extreme precipitation from satellite radiances. Along with our novel architecture, we introduce techniques to tame long-tailed precipitation datasets. Namely, we reformulate precipitation regression into a classification problem, and employ a class-weighted loss to address label imbalances. Our model scored first place on the NeurIPS Weather4Cast 2025 Cumulative Rainfall challenge. Code and model weights are available: https://github.com/leharris3/satformer

Paperid: 690, https://arxiv.org/pdf/2511.11077.pdf GitHub GitHub GitHub

Abstract:
Estimating the geometric and volumetric properties of transparent deformable liquids is challenging due to optical complexities and dynamic surface deformations induced by container movements. Autonomous robots performing precise liquid manipulation tasks, such as dispensing, aspiration, and mixing, must handle containers in ways that inevitably induce these deformations, complicating accurate liquid state assessment. Current datasets lack comprehensive physics-informed simulation data representing realistic liquid behaviors under diverse dynamic scenarios. To bridge this gap, we introduce Phys-Liquid, a physics-informed dataset comprising 97,200 simulation images and corresponding 3D meshes, capturing liquid dynamics across multiple laboratory scenes, lighting conditions, liquid colors, and container rotations. To validate the realism and effectiveness of Phys-Liquid, we propose a four-stage reconstruction and estimation pipeline involving liquid segmentation, multi-view mask generation, 3D mesh reconstruction, and real-world scaling. Experimental results demonstrate improved accuracy and consistency in reconstructing liquid geometry and volume, outperforming existing benchmarks. The dataset and associated validation methods facilitate future advancements in transparent liquid perception tasks. The dataset and code are available at https://dualtransparency.github.io/Phys-Liquid/.

Paperid: 691, https://arxiv.org/pdf/2511.11048.pdf GitHub

Abstract:
4D flow magnetic resonance imaging (MRI) is a reliable, non-invasive approach for estimating blood flow velocities, vital for cardiovascular diagnostics. Unlike conventional MRI focused on anatomical structures, 4D flow MRI requires high spatiotemporal resolution for early detection of critical conditions such as stenosis or aneurysms. However, achieving such resolution typically results in prolonged scan times, creating a trade-off between acquisition speed and prediction accuracy. Recent studies have leveraged physics-informed neural networks (PINNs) for super-resolution of MRI data, but their practical applicability is limited as the prohibitively slow training process must be performed for each patient. To overcome this limitation, we propose PINGS-X, a novel framework modeling high-resolution flow velocities using axes-aligned spatiotemporal Gaussian representations. Inspired by the effectiveness of 3D Gaussian splatting (3DGS) in novel view synthesis, PINGS-X extends this concept through several non-trivial novel innovations: (i) normalized Gaussian splatting with a formal convergence guarantee, (ii) axes-aligned Gaussians that simplify training for high-dimensional data while preserving accuracy and the convergence guarantee, and (iii) a Gaussian merging procedure to prevent degenerate solutions and boost computational efficiency. Experimental results on computational fluid dynamics (CFD) and real 4D flow MRI datasets demonstrate that PINGS-X substantially reduces training time while achieving superior super-resolution accuracy. Our code and datasets are available at https://github.com/SpatialAILab/PINGS-X.

Paperid: 692, https://arxiv.org/pdf/2511.11045.pdf GitHub

Abstract:
With the daily influx of 3D data on the internet, text-3D retrieval has gained increasing attention. However, current methods face two major challenges: Hierarchy Representation Collapse (HRC) and Redundancy-Induced Saliency Dilution (RISD). HRC compresses abstract-to-specific and whole-to-part hierarchies in Euclidean embeddings, while RISD averages noisy fragments, obscuring critical semantic cues and diminishing the model's ability to distinguish hard negatives. To address these challenges, we introduce the Hyperbolic Hierarchical Alignment Reasoning Network (H$^{2}$ARN) for text-3D retrieval. H$^{2}$ARN embeds both text and 3D data in a Lorentz-model hyperbolic space, where exponential volume growth inherently preserves hierarchical distances. A hierarchical ordering loss constructs a shrinking entailment cone around each text vector, ensuring that the matched 3D instance falls within the cone, while an instance-level contrastive loss jointly enforces separation from non-matching samples. To tackle RISD, we propose a contribution-aware hyperbolic aggregation module that leverages Lorentzian distance to assess the relevance of each local feature and applies contribution-weighted aggregation guided by hyperbolic geometry, enhancing discriminative regions while suppressing redundancy without additional supervision. We also release the expanded T3DR-HIT v2 benchmark, which contains 8,935 text-to-3D pairs, 2.6 times the original size, covering both fine-grained cultural artefacts and complex indoor scenes. Our codes are available at https://github.com/liwrui/H2ARN.

Paperid: 693, https://arxiv.org/pdf/2511.11007.pdf GitHub

Abstract:
Despite the remarkable success of Vision-Language Models (VLMs), their performance on a range of complex visual tasks is often hindered by a "visual processing bottleneck": a propensity to lose grounding in visual evidence and exhibit a deficit in contextualized visual experience during prolonged generation. Drawing inspiration from human cognitive memory theory, which distinguishes short-term visually-dominant memory and long-term semantically-dominant memory, we propose VisMem, a cognitively-aligned framework that equips VLMs with dynamic latent vision memories, a short-term module for fine-grained perceptual retention and a long-term module for abstract semantic consolidation. These memories are seamlessly invoked during inference, allowing VLMs to maintain both perceptual fidelity and semantic consistency across thinking and generation. Extensive experiments across diverse visual benchmarks for understanding, reasoning, and generation reveal that VisMem delivers a significant average performance boost of 11.8% relative to the vanilla model and outperforms all counterparts, establishing a new paradigm for latent-space memory enhancement. The code will be available: https://github.com/YU-deep/VisMem.git.

Paperid: 694, https://arxiv.org/pdf/2511.11002.pdf GitHub

Abstract:
Emotion plays a pivotal role in video-based expression, but existing video generation systems predominantly focus on low-level visual metrics while neglecting affective dimensions. Although emotion analysis has made progress in the visual domain, the video community lacks dedicated resources to bridge emotion understanding with generative tasks, particularly for stylized and non-realistic contexts. To address this gap, we introduce EmoVid, the first multimodal, emotion-annotated video dataset specifically designed for creative media, which includes cartoon animations, movie clips, and animated stickers. Each video is annotated with emotion labels, visual attributes (brightness, colorfulness, hue), and text captions. Through systematic analysis, we uncover spatial and temporal patterns linking visual features to emotional perceptions across diverse video forms. Building on these insights, we develop an emotion-conditioned video generation technique by fine-tuning the Wan2.1 model. The results show a significant improvement in both quantitative metrics and the visual quality of generated videos for text-to-video and image-to-video tasks. EmoVid establishes a new benchmark for affective video computing. Our work not only offers valuable insights into visual emotion analysis in artistically styled videos, but also provides practical methods for enhancing emotional expression in video generation.

Paperid: 695, https://arxiv.org/pdf/2511.11000.pdf GitHub

Abstract:
Recognizing speaker intent in long audio dialogues among speakers has a wide range of applications, but is a non-trivial AI task due to complex inter-dependencies in speaker utterances and scarce annotated data. To address these challenges, an end-to-end framework, namely DialogGraph-LLM, is proposed in the current work. DialogGraph-LLM combines a novel Multi-Relational Dialogue Attention Network (MR-DAN) architecture with multimodal foundation models (e.g., Qwen2.5-Omni-7B) for direct acoustic-to-intent inference. An adaptive semi-supervised learning strategy is designed using LLM with a confidence-aware pseudo-label generation mechanism based on dual-threshold filtering using both global and class confidences, and an entropy-based sample selection process that prioritizes high-information unlabeled instances. Extensive evaluations on the proprietary MarketCalls corpus and the publicly available MIntRec 2.0 benchmark demonstrate DialogGraph-LLM's superiority over strong audio and text-driven baselines. The framework demonstrates strong performance and efficiency in intent recognition in real world scenario audio dialogues, proving its practical value for audio-rich domains with limited supervision. Our code is available at https://github.com/david188888/DialogGraph-LLM.

Paperid: 696, https://arxiv.org/pdf/2511.10957.pdf GitHub

Abstract:
Fraud in public procurement remains a persistent challenge, especially in large, decentralized systems like Brazil's Unified Health System. We introduce Heron's Information Coefficient (HIC), a geometric measure that quantifies how subgraphs deviate from the global structure of a network. Applied to over eight years of Brazilian bidding data for medical supplies, this measure highlights collusive patterns that standard indicators may overlook. Unlike conventional robustness metrics, the Heron coefficient focuses on the interaction between active and inactive subgraphs, revealing structural shifts that may signal coordinated behavior, such as cartel formation. Synthetic experiments support these findings, demonstrating strong detection performance across varying corruption intensities and network sizes. While our results do not replace legal or economic analyses, they offer an effective complementary tool for auditors and policymakers to monitor procurement integrity more effectively. This study demonstrates that simple geometric insight can reveal hidden dynamics in real-world networks better than other Information Theoretic metrics.

Paperid: 697, https://arxiv.org/pdf/2511.10953.pdf GitHub

Abstract:
With the rapid growth of video content on social media, video summarization has become a crucial task in multimedia processing. However, existing methods face challenges in capturing global dependencies in video content and accommodating multimodal user customization. Moreover, temporal proximity between video frames does not always correspond to semantic proximity. To tackle these challenges, we propose a novel Language-guided Graph Representation Learning Network (LGRLN) for video summarization. Specifically, we introduce a video graph generator that converts video frames into a structured graph to preserve temporal order and contextual dependencies. By constructing forward, backward and undirected graphs, the video graph generator effectively preserves the sequentiality and contextual relationships of video content. We designed an intra-graph relational reasoning module with a dual-threshold graph convolution mechanism, which distinguishes semantically relevant frames from irrelevant ones between nodes. Additionally, our proposed language-guided cross-modal embedding module generates video summaries with specific textual descriptions. We model the summary generation output as a mixture of Bernoulli distribution and solve it with the EM algorithm. Experimental results show that our method outperforms existing approaches across multiple benchmarks. Moreover, we proposed LGRLN reduces inference time and model parameters by 87.8% and 91.7%, respectively. Our codes and pre-trained models are available at https://github.com/liwrui/LGRLN.

Paperid: 698, https://arxiv.org/pdf/2511.10949.pdf GitHub

Abstract:
LLM-based agents are increasingly deployed in multi-agent systems (MAS). As these systems move toward real-world applications, their security becomes paramount. Existing research largely evaluates single-agent security, leaving a critical gap in understanding the vulnerabilities introduced by multi-agent design. However, existing systems fall short due to lack of unified frameworks and metrics focusing on unique rejection modes in MAS. We present SafeAgents, a unified and extensible framework for fine-grained security assessment of MAS. SafeAgents systematically exposes how design choices such as plan construction strategies, inter-agent context sharing, and fallback behaviors affect susceptibility to adversarial prompting. We introduce Dharma, a diagnostic measure that helps identify weak links within multi-agent pipelines. Using SafeAgents, we conduct a comprehensive study across five widely adopted multi-agent architectures (centralized, decentralized, and hybrid variants) on four datasets spanning web tasks, tool use, and code generation. Our findings reveal that common design patterns carry significant vulnerabilities. For example, centralized systems that delegate only atomic instructions to sub-agents obscure harmful objectives, reducing robustness. Our results highlight the need for security-aware design in MAS. Link to code is https://github.com/microsoft/SafeAgents

Paperid: 699, https://arxiv.org/pdf/2511.10899.pdf GitHub

Abstract:
Tool-augmented Language Models (TaLMs) can invoke external tools to solve problems beyond their parametric capacity. However, it remains unclear whether these tool-enabled gains reflect trustworthy reasoning. Focusing on the Code Interpreter tool, we show that even when tools are selected and executed correctly, TaLMs treat tool outputs as substitutes for reasoning, producing solutions that appear correct but lack coherent justification. We term this failure mode Tool-Induced Myopia (TIM), and study it using PYMATH, a benchmark of 1,679 competition-level mathematical problems for which Python code is helpful but not sufficient. We further develop a multi-dimensional evaluation suite to quantify reasoning degradation in TaLMs relative to their non-tool counterparts. Our findings reveal that while TaLMs achieve up to a 19.3 percentage point gain in final-answer accuracy, their reasoning behavior consistently deteriorates (e.g., non-tool LLMs win up to 41.5% more often in pairwise comparisons of the reasoning process). This degradation intensifies with tool use; the more frequently a model invokes tools, the less coherent its reasoning becomes. Moreover, tool use shifts errors from arithmetic mistakes toward global reasoning failures (logic, assumption, creativity); with TIM present in ~55% of high-risk cases. Finally, we propose a preference-optimization-based framework that realigns TaLMs to use tools as assistive evidence, improving both final-answer accuracy and reasoning depth under tool use. Codes and data are available at: https://github.com/megagonlabs/TIM.

Paperid: 700, https://arxiv.org/pdf/2511.10879.pdf GitHub

Abstract:
Large Language Models (LLMs) have become ubiquitous in everyday life and are entering higher-stakes applications ranging from summarizing meeting transcripts to answering doctors' questions. As was the case with earlier predictive models, it is crucial that we develop tools for explaining the output of LLMs, be it a summary, list, response to a question, etc. With these needs in mind, we introduce In-Context Explainability 360 (ICX360), an open-source Python toolkit for explaining LLMs with a focus on the user-provided context (or prompts in general) that are fed to the LLMs. ICX360 contains implementations for three recent tools that explain LLMs using both black-box and white-box methods (via perturbations and gradients respectively). The toolkit, available at https://github.com/IBM/ICX360, contains quick-start guidance materials as well as detailed tutorials covering use cases such as retrieval augmented generation, natural language generation, and jailbreaking.

Paperid: 701, https://arxiv.org/pdf/2511.10833.pdf GitHub

Abstract:
Equation discovery from data is a core challenge in machine learning for science, requiring the recovery of concise symbolic expressions that govern complex physical and geometric phenomena. Recent approaches with large language models (LLMs) show promise in symbolic regression, but their success often hinges on memorized formulas or overly simplified functional forms. Existing benchmarks exacerbate this limitation: they focus on scalar functions, ignore domain grounding, and rely on brittle string-matching based metrics that fail to capture scientific equivalence. We introduce SurfaceBench, first comprehensive benchmark for symbolic surface discovery. SurfaceBench comprises 183 tasks across 15 categories of symbolic complexity, spanning explicit, implicit, and parametric equation representation forms. Each task includes ground-truth equations, variable semantics, and synthetically sampled three dimensional data. Unlike prior SR datasets, our tasks reflect surface-level structure, resist LLM memorization through novel symbolic compositions, and are grounded in scientific domains such as fluid dynamics, robotics, electromagnetics, and geometry. To evaluate equation discovery quality, we pair symbolic checks with geometry-aware metrics such as Chamfer and Hausdorff distances, capturing both algebraic fidelity and spatial reconstruction accuracy. Our experiments reveal that state-of-the-art frameworks, while occasionally successful on specific families, struggle to generalize across representation types and surface complexities. SurfaceBench thus establishes a challenging and diagnostic testbed that bridges symbolic reasoning with geometric reconstruction, enabling principled benchmarking of progress in compositional generalization, data-driven scientific induction, and geometry-aware reasoning with LLMs. We release the code here: https://github.com/Sanchit-404/surfacebench

Paperid: 702, https://arxiv.org/pdf/2511.10799.pdf GitHub

Abstract:
Parameter-efficient fine-tuning (PEFT) significantly reduces computational and memory costs by updating only a small subset of the model's parameters, enabling faster adaptation to new tasks with minimal loss in performance. Previous studies have introduced PEFTs tailored for point cloud data, as general approaches are suboptimal. To further reduce the number of trainable parameters, we propose a point-cloud-specific PEFT, termed Graph Features Tuning (GFT), which learns a dynamic graph from initial tokenized inputs of the transformer using a lightweight graph convolution network and passes these graph features to deeper layers via skip connections and efficient cross-attention modules. Extensive experiments on object classification and segmentation tasks show that GFT operates in the same domain, rivalling existing methods, while reducing the trainable parameters. Code is at https://github.com/manishdhakal/GFT.

Paperid: 703, https://arxiv.org/pdf/2511.10721.pdf GitHub

Abstract:
Data attribution for text-to-image models aims to identify the training images that most significantly influenced a generated output. Existing attribution methods involve considerable computational resources for each query, making them impractical for real-world applications. We propose a novel approach for scalable and efficient data attribution. Our key idea is to distill a slow, unlearning-based attribution method to a feature embedding space for efficient retrieval of highly influential training images. During deployment, combined with efficient indexing and search methods, our method successfully finds highly influential images without running expensive attribution algorithms. We show extensive results on both medium-scale models trained on MSCOCO and large-scale Stable Diffusion models trained on LAION, demonstrating that our method can achieve better or competitive performance in a few seconds, faster than existing methods by 2,500x - 400,000x. Our work represents a meaningful step towards the large-scale application of data attribution methods on real-world models such as Stable Diffusion.

Paperid: 704, https://arxiv.org/pdf/2511.10720.pdf GitHub GitHub

Abstract:
Long context LLMs are vulnerable to prompt injection, where an attacker can inject an instruction in a long context to induce an LLM to generate an attacker-desired output. Existing prompt injection defenses are designed for short contexts. When extended to long-context scenarios, they have limited effectiveness. The reason is that an injected instruction constitutes only a very small portion of a long context, making the defense very challenging. In this work, we propose PISanitizer, which first pinpoints and sanitizes potential injected tokens (if any) in a context before letting a backend LLM generate a response, thereby eliminating the influence of the injected instruction. To sanitize injected tokens, PISanitizer builds on two observations: (1) prompt injection attacks essentially craft an instruction that compels an LLM to follow it, and (2) LLMs intrinsically leverage the attention mechanism to focus on crucial input tokens for output generation. Guided by these two observations, we first intentionally let an LLM follow arbitrary instructions in a context and then sanitize tokens receiving high attention that drive the instruction-following behavior of the LLM. By design, PISanitizer presents a dilemma for an attacker: the more effectively an injected instruction compels an LLM to follow it, the more likely it is to be sanitized by PISanitizer. Our extensive evaluation shows that PISanitizer can successfully prevent prompt injection, maintain utility, outperform existing defenses, is efficient, and is robust to optimization-based and strong adaptive attacks. The code is available at https://github.com/sleeepeer/PISanitizer.

Paperid: 705, https://arxiv.org/pdf/2511.10707.pdf GitHub

Abstract:
Parameter-Efficient finetuning (PEFT) enhances model performance on downstream tasks by updating a minimal subset of parameters. Representation finetuning (ReFT) methods further improve efficiency by freezing model weights and optimizing internal representations with fewer parameters than PEFT, outperforming PEFT on several tasks. However, ReFT exhibits a significant performance decline on mathematical reasoning tasks. To address this problem, the paper demonstrates that ReFT's poor performance on mathematical tasks primarily stems from its struggle to generate effective reasoning prefixes during the early inference phase. Moreover, ReFT disturbs the numerical encoding and the error accumulats during the CoT stage. Based on these observations, this paper proposes Bias-REstrained Prefix Representation FineTuning (BREP ReFT), which enhances ReFT's mathematical reasoning capability by truncating training data to optimize the generation of initial reasoning prefixes, intervening on the early inference stage to prevent error accumulation, and constraining the intervention vectors' magnitude to avoid disturbing numerical encoding. Extensive experiments across diverse model architectures demonstrate BREP's superior effectiveness, efficiency, and robust generalization capability, outperforming both standard ReFT and weight-based PEFT methods on the task of mathematical reasoning. The source code is available at https://github.com/LiangThree/BREP.

Paperid: 706, https://arxiv.org/pdf/2511.10704.pdf GitHub

Abstract:
We propose that unconstrained artificial intelligence obeys a Second Law analogous to thermodynamics, where ethical entropy, defined as a measure of divergence from intended goals, increases spontaneously without continuous alignment work. For gradient-based optimizers, we define this entropy over a finite set of goals {g_i} as S = -Σ p(g_i; theta) ln p(g_i; theta), and we prove that its time derivative dS/dt >= 0, driven by exploration noise and specification gaming. We derive the critical stability boundary for alignment work as gamma_crit = (lambda_max / 2) ln N, where lambda_max is the dominant eigenvalue of the Fisher Information Matrix and N is the number of model parameters. Simulations validate this theory. A 7-billion-parameter model (N = 7 x 10^9) with lambda_max = 1.2 drifts from an initial entropy of 0.32 to 1.69 +/- 1.08 nats, while a system regularized with alignment work gamma = 20.4 (1.5 gamma_crit) maintains stability at 0.00 +/- 0.00 nats (p = 4.19 x 10^-17, n = 20 trials). This framework recasts AI alignment as a problem of continuous thermodynamic control, providing a quantitative foundation for maintaining the stability and safety of advanced autonomous systems.

Paperid: 707, https://arxiv.org/pdf/2511.10701.pdf GitHub

Abstract:
CAR-Scenes is a frame-level dataset for autonomous driving that enables training and evaluation of vision-language models (VLMs) for interpretable, scene-level understanding. We annotate 5,192 images drawn from Argoverse 1, Cityscapes, KITTI, and nuScenes using a 28-key category/sub-category knowledge base covering environment, road geometry, background-vehicle behavior, ego-vehicle behavior, vulnerable road users, sensor states, and a discrete severity scale (1-10), totaling 350+ leaf attributes. Labels are produced by a GPT-4o-assisted vision-language pipeline with human-in-the-loop verification; we release the exact prompts, post-processing rules, and per-field baseline model performance. CAR-Scenes also provides attribute co-occurrence graphs and JSONL records that support semantic retrieval, dataset triage, and risk-aware scenario mining across sources. To calibrate task difficulty, we include reproducible, non-benchmark baselines, notably a LoRA-tuned Qwen2-VL-2B with deterministic decoding, evaluated via scalar accuracy, micro-averaged F1 for list attributes, and severity MAE/RMSE on a fixed validation split. We publicly release the annotation and analysis scripts, including graph construction and evaluation scripts, to enable explainable, data-centric workflows for future intelligent vehicles. Dataset: https://github.com/Croquembouche/CAR-Scenes

Paperid: 708, https://arxiv.org/pdf/2511.10621.pdf GitHub

Abstract:
Large Language Models (LLMs) have demonstrated remarkable reasoning abilities, yet existing test-time frameworks often rely on coarse self-verification and self-correction, limiting their effectiveness on complex tasks. In this paper, we propose Socratic Self-Refine (SSR), a novel framework for fine-grained evaluation and precise refinement of LLM reasoning. Our proposed SSR decomposes model responses into verifiable (sub-question, sub-answer) pairs, enabling step-level confidence estimation through controlled re-solving and self-consistency checks. By pinpointing unreliable steps and iteratively refining them, SSR produces more accurate and interpretable reasoning chains. Empirical results across five reasoning benchmarks and three LLMs show that SSR consistently outperforms state-of-the-art iterative self-refinement baselines. Beyond performance gains, SSR provides a principled black-box approach for evaluating and understanding the internal reasoning processes of LLMs. Code is available at https://github.com/SalesforceAIResearch/socratic-self-refine-reasoning.

Paperid: 709, https://arxiv.org/pdf/2511.10577.pdf GitHub

Abstract:
Fine-grained sentiment analysis faces ongoing challenges in Aspect Sentiment Triple Extraction (ASTE), particularly in accurately capturing the relationships between aspects, opinions, and sentiment polarities. While researchers have made progress using BERT and Graph Neural Networks, the full potential of advanced language models in understanding complex language patterns remains unexplored. We introduce DESS, a new approach that builds upon previous work by integrating DeBERTa's enhanced attention mechanism to better understand context and relationships in text. Our framework maintains a dual-channel structure, where DeBERTa works alongside an LSTM channel to process both meaning and grammatical patterns in text. We have carefully refined how these components work together, paying special attention to how different types of language information interact. When we tested DESS on standard datasets, it showed meaningful improvements over current methods, with F1-score increases of 4.85, 8.36, and 2.42 in identifying aspect opinion pairs and determining sentiment accurately. Looking deeper into the results, we found that DeBERTa's sophisticated attention system helps DESS handle complicated sentence structures better, especially when important words are far apart. Our findings suggest that upgrading to more advanced language models when thoughtfully integrated, can lead to real improvements in how well we can analyze sentiments in text. The implementation of our approach is publicly available at: https://github.com/VishalRepos/DESS.

Paperid: 710, https://arxiv.org/pdf/2511.10561.pdf GitHub

Abstract:
Machine learning interatomic potentials (MLIPs) balance high accuracy and lower costs compared to density functional theory calculations, but their performance often depends on the size and diversity of training datasets. Large datasets improve model accuracy and generalization but are computationally expensive to produce and train on, while smaller datasets risk discarding rare but important atomic environments and compromising MLIP accuracy/reliability. Here, we develop an information-theoretical framework to quantify the efficiency of dataset compression methods and propose an algorithm that maximizes this efficiency. By framing atomistic dataset compression as an instance of the minimum set cover (MSC) problem over atom-centered environments, our method identifies the smallest subset of structures that contains as much information as possible from the original dataset while pruning redundant information. The approach is extensively demonstrated on the GAP-20 and TM23 datasets, and validated on 64 varied datasets from the ColabFit repository. Across all cases, MSC consistently retains outliers, preserves dataset diversity, and reproduces the long-tail distributions of forces even at high compression rates, outperforming other subsampling methods. Furthermore, MLIPs trained on MSC-compressed datasets exhibit reduced error for out-of-distribution data even in low-data regimes. We explain these results using an outlier analysis and show that such quantitative conclusions could not be achieved with conventional dimensionality reduction methods. The algorithm is implemented in the open-source QUESTS package and can be used for several tasks in atomistic modeling, from data subsampling, outlier detection, and training improved MLIPs at a lower cost.

Paperid: 711, https://arxiv.org/pdf/2511.10560.pdf GitHub

Abstract:
General 3D foundation models have started to lead the trend of unifying diverse vision tasks, yet most assume RGB-only inputs and ignore readily available geometric cues (e.g., camera intrinsics, poses, and depth maps). To address this issue, we introduce OmniVGGT, a novel framework that can effectively benefit from an arbitrary number of auxiliary geometric modalities during both training and inference. In our framework, a GeoAdapter is proposed to encode depth and camera intrinsics/extrinsics into a spatial foundation model. It employs zero-initialized convolutions to progressively inject geometric information without disrupting the foundation model's representation space. This design ensures stable optimization with negligible overhead, maintaining inference speed comparable to VGGT even with multiple additional inputs. Additionally, a stochastic multimodal fusion regimen is proposed, which randomly samples modality subsets per instance during training. This enables an arbitrary number of modality inputs during testing and promotes learning robust spatial representations instead of overfitting to auxiliary cues. Comprehensive experiments on monocular/multi-view depth estimation, multi-view stereo, and camera pose estimation demonstrate that OmniVGGT outperforms prior methods with auxiliary inputs and achieves state-of-the-art results even with RGB-only input. To further highlight its practical utility, we integrated OmniVGGT into vision-language-action (VLA) models. The enhanced VLA model by OmniVGGT not only outperforms the vanilla point-cloud-based baseline on mainstream benchmarks, but also effectively leverages accessible auxiliary inputs to achieve consistent gains on robotic tasks.

Paperid: 712, https://arxiv.org/pdf/2511.10555.pdf GitHub GitHub

Abstract:
Innovative visual stylization is a cornerstone of artistic creation, yet generating novel and consistent visual styles remains a significant challenge. Existing generative approaches typically rely on lengthy textual prompts, reference images, or parameter-efficient fine-tuning to guide style-aware image generation, but often struggle with style consistency, limited creativity, and complex style representations. In this paper, we affirm that a style is worth one numerical code by introducing the novel task, code-to-style image generation, which produces images with novel, consistent visual styles conditioned solely on a numerical style code. To date, this field has only been primarily explored by the industry (e.g., Midjourney), with no open-source research from the academic community. To fill this gap, we propose CoTyle, the first open-source method for this task. Specifically, we first train a discrete style codebook from a collection of images to extract style embeddings. These embeddings serve as conditions for a text-to-image diffusion model (T2I-DM) to generate stylistic images. Subsequently, we train an autoregressive style generator on the discrete style embeddings to model their distribution, allowing the synthesis of novel style embeddings. During inference, a numerical style code is mapped to a unique style embedding by the style generator, and this embedding guides the T2I-DM to generate images in the corresponding style. Unlike existing methods, our method offers unparalleled simplicity and diversity, unlocking a vast space of reproducible styles from minimal input. Extensive experiments validate that CoTyle effectively turns a numerical code into a style controller, demonstrating a style is worth one code.

Paperid: 713, https://arxiv.org/pdf/2511.10552.pdf GitHub

Abstract:
Recent multimodal large language models (MLLMs) still struggle with long document understanding due to two fundamental challenges: information interference from abundant irrelevant content, and the quadratic computational cost of Transformer-based architectures. Existing approaches primarily fall into two categories: token compression, which sacrifices fine-grained details; and introducing external retrievers, which increase system complexity and prevent end-to-end optimization. To address these issues, we conduct an in-depth analysis and observe that MLLMs exhibit a human-like coarse-to-fine reasoning pattern: early Transformer layers attend broadly across the document, while deeper layers focus on relevant evidence pages. Motivated by this insight, we posit that the inherent evidence localization capabilities of MLLMs can be explicitly leveraged to perform retrieval during the reasoning process, facilitating efficient long document understanding. To this end, we propose URaG, a simple-yet-effective framework that Unifies Retrieval and Generation within a single MLLM. URaG introduces a lightweight cross-modal retrieval module that converts the early Transformer layers into an efficient evidence selector, identifying and preserving the most relevant pages while discarding irrelevant content. This design enables the deeper layers to concentrate computational resources on pertinent information, improving both accuracy and efficiency. Extensive experiments demonstrate that URaG achieves state-of-the-art performance while reducing computational overhead by 44-56%. The code is available at https://github.com/shi-yx/URaG.

Paperid: 714, https://arxiv.org/pdf/2511.10518.pdf GitHub

Abstract:
Vision-Language-Action (VLA) models have advanced in robotic manipulation, yet practical deployment remains hindered by two key limitations: 1) perceptual redundancy, where irrelevant visual inputs are processed inefficiently, and 2) superficial instruction-vision alignment, which hampers semantic grounding of actions. In this paper, we propose SemanticVLA, a novel VLA framework that performs Semantic-Aligned Sparsification and Enhancement for Efficient Robotic Manipulation. Specifically: 1) To sparsify redundant perception while preserving semantic alignment, Semantic-guided Dual Visual Pruner (SD-Pruner) performs: Instruction-driven Pruner (ID-Pruner) extracts global action cues and local semantic anchors in SigLIP; Spatial-aggregation Pruner (SA-Pruner) compacts geometry-rich features into task-adaptive tokens in DINOv2. 2) To exploit sparsified features and integrate semantics with spatial geometry, Semantic-complementary Hierarchical Fuser (SH-Fuser) fuses dense patches and sparse tokens across SigLIP and DINOv2 for coherent representation. 3) To enhance the transformation from perception to action, Semantic-conditioned Action Coupler (SA-Coupler) replaces the conventional observation-to-DoF approach, yielding more efficient and interpretable behavior modeling for manipulation tasks. Extensive experiments on simulation and real-world tasks show that SemanticVLA sets a new SOTA in both performance and efficiency. SemanticVLA surpasses OpenVLA on LIBERO benchmark by 21.1% in success rate, while reducing training cost and inference latency by 3.0-fold and 2.7-fold.SemanticVLA is open-sourced and publicly available at https://github.com/JiuTian-VL/SemanticVLA

Paperid: 715, https://arxiv.org/pdf/2511.10500.pdf GitHub

Abstract:
Although Total Variation (TV) performs well in noise reduction and edge preservation on images, its dependence on the lambda parameter limits its efficiency and makes it difficult to use effectively. In this study, we present a Learnable Total Variation (LTV) framework that couples an unrolled TV solver with a data-driven Lambda Mapping Network (LambdaNet) predicting a per-pixel regularization map. The pipeline is trained end-to-end so that reconstruction and regularization are optimized jointly, yielding spatially adaptive smoothing: strong in homogeneous regions, relaxed near anatomical boundaries. Experiments on the DeepLesion dataset, using a realistic noise model adapted from the LoDoPaB-CT methodology, show consistent gains over classical TV and FBP+U-Net: +2.9 dB PSNR and +6% SSIM on average. LTV provides an interpretable alternative to black-box CNNs and a basis for 3D and data-consistency-driven reconstruction. Our codes are available at: https://github.com/itu-biai/deep_tv_for_ldct

Paperid: 716, https://arxiv.org/pdf/2511.10488.pdf GitHub

Abstract:
While Vision Transformers (ViT) have demonstrated remarkable performance across diverse tasks, their computational demands are substantial, scaling quadratically with the number of processed tokens. Compact attention representations, reflecting token interaction distributions, can guide early detection and reduction of less salient tokens prior to attention computation. Motivated by this, we present SParsification with attentiOn dynamics via Token relevance (SPOT), a framework for early detection of redundant tokens within ViTs that leverages token embeddings, interactions, and attention dynamics across layers to infer token importance, resulting in a more context-aware and interpretable relevance detection process. SPOT informs token sparsification and facilitates the elimination of such tokens, improving computational efficiency without sacrificing performance. SPOT employs computationally lightweight predictors that can be plugged into various ViT architectures and learn to derive effective input-specific token prioritization across layers. Its versatile design supports a range of performance levels adaptable to varying resource constraints. Empirical evaluations demonstrate significant efficiency gains of up to 40% compared to standard ViTs, while maintaining or even improving accuracy. Code and models are available at https://github.com/odedsc/SPOT .

Paperid: 717, https://arxiv.org/pdf/2511.10481.pdf GitHub

Abstract:
Pretrained VLMs exhibit strong zero-shot classification capabilities, but their predictions degrade significantly under common image corruptions. To improve robustness, many test-time adaptation (TTA) methods adopt positive data augmentation (PDA), which generates multiple views of each test sample to reduce prediction variance. However, these methods suffer from two key limitations. First, it introduces considerable computational overhead due to the large number of augmentations required per image. Second, it fails to mitigate prediction bias, where the model tends to predict certain classes disproportionately under corruption, as PDA operates on corrupted inputs and typically does not remove the corruption itself. To address these challenges, we propose Panda, a novel TTA method based on negative data augmentation (NDA). Unlike positive augmentations that preserve object semantics, Panda generates negative augmentations by disrupting semantic content. It divides images into patches and randomly assembles them from a shared patch pool. These negatively augmented images retain corruption-specific features while discarding object-relevant signals. We then subtract the mean feature of these negative samples from the original image feature, effectively suppressing corruption-related components while preserving class-relevant information. This mitigates prediction bias under distribution shifts. Panda allows augmentation to be shared across samples within a batch, resulting in minimal computational overhead. Panda can be seamlessly integrated into existing test-time adaptation frameworks and substantially improve their robustness. Our experiments indicate that Panda delivers superior performance compared to PDA methods, and a wide range of TTA methods exhibit significantly enhanced performance when integrated with Panda. Our code is available at https://github.com/ruxideng/Panda .

Paperid: 718, https://arxiv.org/pdf/2511.10480.pdf GitHub

Abstract:
Optimizing the performance of large language models (LLMs) on large-scale AI training and inference systems requires a scalable and expressive mechanism to model distributed workload execution. Such modeling is essential for pre-deployment system-level optimizations (e.g., parallelization strategies) and design-space explorations. While recent efforts have proposed collecting execution traces from real systems, access to large-scale infrastructure remains limited to major cloud providers. Moreover, traces obtained from existing platforms cannot be easily adapted to study future larger-scale system configurations. We introduce Symbolic Tensor grAph GEnerator(STAGE), a framework that synthesizes high-fidelity execution traces to accurately model LLM workloads. STAGE supports a comprehensive set of parallelization strategies, allowing users to systematically explore a wide spectrum of LLM architectures and system configurations. STAGE demonstrates its scalability by synthesizing high-fidelity LLM traces spanning over 32K GPUs, while preserving tensor-level accuracy in compute, memory, and communication. STAGE is publicly available to facilitate further research in distributed machine learning systems: https://github.com/astra-sim/symbolic tensor graph

Paperid: 719, https://arxiv.org/pdf/2511.10475.pdf GitHub

Abstract:
Imbalance in classification tasks is commonly quantified by the cardinalities of examples across classes. This, however, disregards the presence of redundant examples and inherent differences in the learning difficulties of classes. Alternatively, one can use complex measures such as training loss and uncertainty, which, however, depend on training a machine learning model. Our paper proposes using data Intrinsic Dimensionality (ID) as an easy-to-compute, model-free measure of imbalance that can be seamlessly incorporated into various imbalance mitigation methods. Our results across five different datasets with a diverse range of imbalance ratios show that ID consistently outperforms cardinality-based re-weighting and re-sampling techniques used in the literature. Moreover, we show that combining ID with cardinality can further improve performance. Code: https://github.com/cagries/IDIM.

Paperid: 720, https://arxiv.org/pdf/2511.10465.pdf GitHub

Abstract:
While prompt optimization has emerged as a critical technique for enhancing language model performance, existing approaches primarily focus on elicitation-based strategies that search for optimal prompts to activate models' capabilities. These methods exhibit fundamental limitations when addressing knowledge-intensive tasks, as they operate within fixed parametric boundaries rather than providing the factual knowledge, terminology precision, and reasoning patterns required in specialized domains. To address these limitations, we propose Knowledge-Provision-based Prompt Optimization (KPPO), a framework that reformulates prompt optimization as systematic knowledge integration rather than potential elicitation. KPPO introduces three key innovations: 1) a knowledge gap filling mechanism for knowledge gap identification and targeted remediation; 2) a batch-wise candidate evaluation approach that considers both performance improvement and distributional stability; 3) an adaptive knowledge pruning strategy that balances performance and token efficiency, reducing up to 29% token usage. Extensive evaluation on 15 knowledge-intensive benchmarks from various domains demonstrates KPPO's superiority over elicitation-based methods, with an average performance improvement of ~6% over the strongest baseline while achieving comparable or lower token consumption. Code at: https://github.com/xyz9911/KPPO.

Paperid: 721, https://arxiv.org/pdf/2511.10391.pdf GitHub

Abstract:
Digital Terrain Models (DTMs) represent the bare-earth elevation and are important in numerous geospatial applications. Such data models cannot be directly measured by sensors and are typically generated from Digital Surface Models (DSMs) derived from LiDAR or photogrammetry. Traditional filtering approaches rely on manually tuned parameters, while learning-based methods require well-designed architectures, often combined with post-processing. To address these challenges, we introduce Ground Diffusion (GrounDiff), the first diffusion-based framework that iteratively removes non-ground structures by formulating the problem as a denoising task. We incorporate a gated design with confidence-guided generation that enables selective filtering. To increase scalability, we further propose Prior-Guided Stitching (PrioStitch), which employs a downsampled global prior automatically generated using GrounDiff to guide local high-resolution predictions. We evaluate our method on the DSM-to-DTM translation task across diverse datasets, showing that GrounDiff consistently outperforms deep learning-based state-of-the-art methods, reducing RMSE by up to 93% on ALS2DTM and up to 47% on USGS benchmarks. In the task of road reconstruction, which requires both high precision and smoothness, our method achieves up to 81% lower distance error compared to specialized techniques on the GeRoD benchmark, while maintaining competitive surface smoothness using only DSM inputs, without task-specific optimization. Our variant for road reconstruction, GrounDiff+, is specifically designed to produce even smoother surfaces, further surpassing state-of-the-art methods. The project page is available at https://deepscenario.github.io/GrounDiff/.

Paperid: 722, https://arxiv.org/pdf/2511.10390.pdf GitHub

Abstract:
Document parsing is a core task in document intelligence, supporting applications such as information extraction, retrieval-augmented generation, and automated document analysis. However, real-world documents often feature complex layouts with multi-level tables, embedded images or formulas, and cross-page structures, which remain challenging for existing OCR systems. We introduce MonkeyOCR v1.5, a unified vision-language framework that enhances both layout understanding and content recognition through a two-stage pipeline. The first stage employs a large multimodal model to jointly predict layout and reading order, leveraging visual information to ensure sequential consistency. The second stage performs localized recognition of text, formulas, and tables within detected regions, maintaining high visual fidelity while reducing error propagation. To address complex table structures, we propose a visual consistency-based reinforcement learning scheme that evaluates recognition quality via render-and-compare alignment, improving structural accuracy without manual annotations. Additionally, two specialized modules, Image-Decoupled Table Parsing and Type-Guided Table Merging, are introduced to enable reliable parsing of tables containing embedded images and reconstruction of tables crossing pages or columns. Comprehensive experiments on OmniDocBench v1.5 demonstrate that MonkeyOCR v1.5 achieves state-of-the-art performance, outperforming PPOCR-VL and MinerU 2.5 while showing exceptional robustness in visually complex document scenarios. A trial link can be found at https://github.com/Yuliang-Liu/MonkeyOCR .

Paperid: 723, https://arxiv.org/pdf/2511.10334.pdf GitHub

Abstract:
Recent advancements in weakly-supervised video anomaly detection have achieved remarkable performance by applying the multiple instance learning paradigm based on multimodal foundation models such as CLIP to highlight anomalous instances and classify categories. However, their objectives may tend to detect the most salient response segments, while neglecting to mine diverse normal patterns separated from anomalies, and are prone to category confusion due to similar appearance, leading to unsatisfactory fine-grained classification results. Therefore, we propose a novel Disentangled Semantic Alignment Network (DSANet) to explicitly separate abnormal and normal features from coarse-grained and fine-grained aspects, enhancing the distinguishability. Specifically, at the coarse-grained level, we introduce a self-guided normality modeling branch that reconstructs input video features under the guidance of learned normal prototypes, encouraging the model to exploit normality cues inherent in the video, thereby improving the temporal separation of normal patterns and anomalous events. At the fine-grained level, we present a decoupled contrastive semantic alignment mechanism, which first temporally decomposes each video into event-centric and background-centric components using frame-level anomaly scores and then applies visual-language contrastive learning to enhance class-discriminative representations. Comprehensive experiments on two standard benchmarks, namely XD-Violence and UCF-Crime, demonstrate that DSANet outperforms existing state-of-the-art methods.

Paperid: 724, https://arxiv.org/pdf/2511.10282.pdf GitHub

Abstract:
Deep Neural Networks (DNNs) have demonstrated remarkable performance across various domains, including computer vision and natural language processing. However, they often struggle to accurately quantify the uncertainty of their predictions, limiting their broader adoption in critical real-world applications. Uncertainty Quantification (UQ) for Deep Learning seeks to address this challenge by providing methods to improve the reliability of uncertainty estimates. Although numerous techniques have been proposed, a unified tool offering a seamless workflow to evaluate and integrate these methods remains lacking. To bridge this gap, we introduce Torch-Uncertainty, a PyTorch and Lightning-based framework designed to streamline DNN training and evaluation with UQ techniques and metrics. In this paper, we outline the foundational principles of our library and present comprehensive experimental results that benchmark a diverse set of UQ methods across classification, segmentation, and regression tasks. Our library is available at https://github.com/ENSTA-U2IS-AI/Torch-Uncertainty

Paperid: 725, https://arxiv.org/pdf/2511.10279.pdf GitHub

Abstract:
Despite significant progress, Vision-Language Models (VLMs) still struggle with complex visual reasoning, where multi-step dependencies cause early errors to cascade through the reasoning chain. Existing post-training paradigms are limited: Supervised Fine-Tuning (SFT) relies on costly step-level annotations, while Reinforcement Learning with Verifiable Rewards (RLVR) methods like GRPO provide only sparse, outcome-level feedback, hindering stable optimization. We introduce PROPA (Process-level Reasoning Optimization with interleaved Policy Alignment), a novel framework that integrates Monte Carlo Tree Search (MCTS) with GRPO to generate dense, process-level rewards and optimize reasoning at each intermediate step without human annotations. To overcome the cold-start problem, PROPA interleaves GRPO updates with SFT, enabling the model to learn from both successful and failed reasoning trajectories. A Process Reward Model (PRM) is further trained to guide inference-time search, aligning the test-time search with the training signal. Across seven benchmarks and four VLM backbones, PROPA consistently outperforms both SFT- and RLVR-based baselines. It achieves up to 17.0% gains on in-domain tasks and 21.0% gains on out-of-domain tasks compared to existing state-of-the-art, establishing a strong reasoning and generalization capability for visual reasoning tasks. The code isavailable at: https://github.com/YanbeiJiang/PROPA.

Paperid: 726, https://arxiv.org/pdf/2511.10154.pdf GitHub

Abstract:
Text-to-Image Person Retrieval (TIPR) aims to retrieve person images based on natural language descriptions. Although many TIPR methods have achieved promising results, sometimes textual queries cannot accurately and comprehensively reflect the content of the image, leading to poor cross-modal alignment and overfitting to limited datasets. Moreover, the inherent modality gap between text and image further amplifies these issues, making accurate cross-modal retrieval even more challenging. To address these limitations, we propose the Generation-Enhanced Alignment (GEA) from a generative perspective. GEA contains two parallel modules: (1) Text-Guided Token Enhancement (TGTE), which introduces diffusion-generated images as intermediate semantic representations to bridge the gap between text and visual patterns. These generated images enrich the semantic representation of text and facilitate cross-modal alignment. (2) Generative Intermediate Fusion (GIF), which combines cross-attention between generated images, original images, and text features to generate a unified representation optimized by triplet alignment loss. We conduct extensive experiments on three public TIPR datasets, CUHK-PEDES, RSTPReid, and ICFG-PEDES, to evaluate the performance of GEA. The results justify the effectiveness of our method. More implementation details and extended results are available at https://github.com/sugelamyd123/Sup-for-GEA.

Paperid: 727, https://arxiv.org/pdf/2511.10098.pdf GitHub

Abstract:
Recent advances in Large Visual Language Models (LVLMs) have demonstrated impressive performance across various vision-language tasks by leveraging large-scale image-text pretraining and instruction tuning. However, the security vulnerabilities of LVLMs have become increasingly concerning, particularly their susceptibility to backdoor attacks. Existing backdoor attacks focus on single-target attacks, i.e., targeting a single malicious output associated with a specific trigger. In this work, we uncover multi-target backdoor attacks, where multiple independent triggers corresponding to different attack targets are added in a single pass of training, posing a greater threat to LVLMs in real-world applications. Executing such attacks in LVLMs is challenging since there can be many incorrect trigger-target mappings due to severe feature interference among different triggers. To address this challenge, we propose MTAttack, the first multi-target backdoor attack framework for enforcing accurate multiple trigger-target mappings in LVLMs. The core of MTAttack is a novel optimization method with two constraints, namely Proxy Space Partitioning constraint and Trigger Prototype Anchoring constraint. It jointly optimizes multiple triggers in the latent space, with each trigger independently mapping clean images to a unique proxy class while at the same time guaranteeing their separability. Experiments on popular benchmarks demonstrate a high success rate of MTAttack for multi-target attacks, substantially outperforming existing attack methods. Furthermore, our attack exhibits strong generalizability across datasets and robustness against backdoor defense strategies. These findings highlight the vulnerability of LVLMs to multi-target backdoor attacks and underscore the urgent need for mitigating such threats. Code is available at https://github.com/mala-lab/MTAttack.

Paperid: 728, https://arxiv.org/pdf/2511.10089.pdf GitHub

Abstract:
Text-to-image (T2I) generative models are largely used in AI-powered real-world applications and value creation. However, their strategic deployment raises critical concerns for responsible AI management, particularly regarding the reproduction and amplification of race- and gender-related stereotypes that can undermine organizational ethics. In this work, we investigate whether such societal biases are systematically encoded within the pretrained latent spaces of state-of-the-art T2I models. We conduct an empirical study across the five most popular open-source models, using ten neutral, profession-related prompts to generate 100 images per profession, resulting in a dataset of 5,000 images evaluated by diverse human assessors representing different races and genders. We demonstrate that all five models encode and amplify pronounced societal skew: caregiving and nursing roles are consistently feminized, while high-status professions such as corporate CEO, politician, doctor, and lawyer are overwhelmingly represented by males and mostly White individuals. We further identify model-specific patterns, such as QWEN-Image's near-exclusive focus on East Asian outputs, Kandinsky's dominance of White individuals, and SDXL's comparatively broader but still biased distributions. These results provide critical insights for AI project managers and practitioners, enabling them to select equitable AI models and customized prompts that generate images in alignment with the principles of responsible AI. We conclude by discussing the risks of these biases and proposing actionable strategies for bias mitigation in building responsible GenAI systems. The code and Data Repository: https://github.com/Sufianlab/T2IBias

Paperid: 729, https://arxiv.org/pdf/2511.10059.pdf GitHub

Abstract:
Can Multimodal Large Language Models (MLLMs) discern confused objects that are visually present but audio-absent? To study this, we introduce a new benchmark, AV-ConfuseBench, which simulates an ``Audio-Visual Confusion'' scene by modifying the corresponding sound of an object in the video, e.g., mute the sounding object and ask MLLMs Is there a/an muted-object sound''. Experimental results reveal that MLLMs, such as Qwen2.5-Omni and Gemini 2.5, struggle to discriminate non-existent audio due to visually dominated reasoning. Motivated by this observation, we introduce RL-CoMM, a Reinforcement Learning-based Collaborative Multi-MLLM that is built upon the Qwen2.5-Omni foundation. RL-CoMM includes two stages: 1) To alleviate visually dominated ambiguities, we introduce an external model, a Large Audio Language Model (LALM), as the reference model to generate audio-only reasoning. Then, we design a Step-wise Reasoning Reward function that enables MLLMs to self-improve audio-visual reasoning with the audio-only reference. 2) To ensure an accurate answer prediction, we introduce Answer-centered Confidence Optimization to reduce the uncertainty of potential heterogeneous reasoning differences. Extensive experiments on audio-visual question answering and audio-visual hallucination show that RL-CoMM improves the accuracy by 10~30\% over the baseline model with limited training data. Follow: https://github.com/rikeilong/AVConfusion.

Paperid: 730, https://arxiv.org/pdf/2511.10056.pdf GitHub

Abstract:
Protein structure tokenization converts 3D structures into discrete or vectorized representations, enabling the integration of structural and sequence data. Despite many recent works on structure tokenization, the properties of the underlying discrete representations are not well understood. In this work, we first demonstrate that the successful utilization of structural tokens in a language model for structure prediction depends on using rich, pre-trained sequence embeddings to bridge the semantic gap between the sequence and structural "language". The analysis of the structural vocabulary itself then reveals significant semantic redundancy, where multiple distinct tokens correspond to nearly identical local geometries, acting as "structural synonyms". This redundancy, rather than being a flaw, can be exploited with a simple "synonym swap" strategy to generate diverse conformational ensembles by perturbing a predicted structure with its structural synonyms. This computationally lightweight method accurately recapitulates protein flexibility, performing competitively with state-of-the-art models. Our study provides fundamental insights into the nature of discrete protein structure representations and introduces a powerful, near-instantaneous method for modeling protein dynamics. Source code is available in https://github.com/IDEA-XL/TokenMD.

Paperid: 731, https://arxiv.org/pdf/2511.10047.pdf GitHub GitHub

Abstract:
Zero-shot anomaly classification (AC) and segmentation (AS) methods aim to identify and outline defects without using any labeled samples. In this paper, we reveal a key property that is overlooked by existing methods: normal image patches across industrial products typically find many other similar patches, not only in 2D appearance but also in 3D shapes, while anomalies remain diverse and isolated. To explicitly leverage this discriminative property, we propose a Mutual Scoring framework (MuSc-V2) for zero-shot AC/AS, which flexibly supports single 2D/3D or multimodality. Specifically, our method begins by improving 3D representation through Iterative Point Grouping (IPG), which reduces false positives from discontinuous surfaces. Then we use Similarity Neighborhood Aggregation with Multi-Degrees (SNAMD) to fuse 2D/3D neighborhood cues into more discriminative multi-scale patch features for mutual scoring. The core comprises a Mutual Scoring Mechanism (MSM) that lets samples within each modality to assign score to each other, and Cross-modal Anomaly Enhancement (CAE) that fuses 2D and 3D scores to recover modality-specific missing anomalies. Finally, Re-scoring with Constrained Neighborhood (RsCon) suppresses false classification based on similarity to more representative samples. Our framework flexibly works on both the full dataset and smaller subsets with consistently robust performance, ensuring seamless adaptability across diverse product lines. In aid of the novel framework, MuSc-V2 achieves significant performance improvements: a $\textbf{+23.7\%}$ AP gain on the MVTec 3D-AD dataset and a $\textbf{+19.3\%}$ boost on the Eyecandies dataset, surpassing previous zero-shot benchmarks and even outperforming most few-shot methods. The code will be available at The code will be available at \href{https://github.com/HUST-SLOW/MuSc-V2}{https://github.com/HUST-SLOW/MuSc-V2}.

Paperid: 732, https://arxiv.org/pdf/2511.10046.pdf GitHub

Abstract:
Visible-infrared object detection has gained sufficient attention due to its detection performance in low light, fog, and rain conditions. However, visible and infrared modalities captured by different sensors exist the information imbalance problem in complex scenarios, which can cause inadequate cross-modal fusion, resulting in degraded detection performance. \textcolor{red}{Furthermore, most existing methods use transformers in the spatial domain to capture complementary features, ignoring the advantages of developing frequency domain transformers to mine complementary information.} To solve these weaknesses, we propose a frequency domain fusion transformer, called FreDFT, for visible-infrared object detection. The proposed approach employs a novel multimodal frequency domain attention (MFDA) to mine complementary information between modalities and a frequency domain feed-forward layer (FDFFL) via a mixed-scale frequency feature fusion strategy is designed to better enhance multimodal features. To eliminate the imbalance of multimodal information, a cross-modal global modeling module (CGMM) is constructed to perform pixel-wise inter-modal feature interaction in a spatial and channel manner. Moreover, a local feature enhancement module (LFEM) is developed to strengthen multimodal local feature representation and promote multimodal feature fusion by using various convolution layers and applying a channel shuffle. Extensive experimental results have verified that our proposed FreDFT achieves excellent performance on multiple public datasets compared with other state-of-the-art methods. The code of our FreDFT is linked at https://github.com/WenCongWu/FreDFT.

Paperid: 733, https://arxiv.org/pdf/2511.10030.pdf GitHub

Abstract:
Large transformer models, trained on diverse datasets, have demonstrated impressive few-shot performance on previously unseen tasks without requiring parameter updates. This capability has also been explored in Reinforcement Learning (RL), where agents interact with the environment to retrieve context and maximize cumulative rewards, showcasing strong adaptability in complex settings. However, in cooperative Multi-Agent Reinforcement Learning (MARL), where agents must coordinate toward a shared goal, decentralized policy deployment can lead to mismatches in task alignment and reward assignment, limiting the efficiency of policy adaptation. To address this challenge, we introduce Multi-agent In-context Coordination via Decentralized Memory Retrieval (MAICC), a novel approach designed to enhance coordination by fast adaptation. Our method involves training a centralized embedding model to capture fine-grained trajectory representations, followed by decentralized models that approximate the centralized one to obtain team-level task information. Based on the learned embeddings, relevant trajectories are retrieved as context, which, combined with the agents' current sub-trajectories, inform decision-making. During decentralized execution, we introduce a novel memory mechanism that effectively balances test-time online data with offline memory. Based on the constructed memory, we propose a hybrid utility score that incorporates both individual- and team-level returns, ensuring credit assignment across agents. Extensive experiments on cooperative MARL benchmarks, including Level-Based Foraging (LBF) and SMAC (v1/v2), show that MAICC enables faster adaptation to unseen tasks compared to existing methods. Code is available at https://github.com/LAMDA-RL/MAICC.

Paperid: 734, https://arxiv.org/pdf/2511.10025.pdf GitHub

Abstract:
Neural operators have emerged as a promising paradigm for learning solution operators of partial differential equa- tions (PDEs) directly from data. Existing methods, such as those based on Fourier or graph techniques, make strong as- sumptions about the structure of the kernel integral opera- tor, assumptions which may limit expressivity. We present SVD-NO, a neural operator that explicitly parameterizes the kernel by its singular-value decomposition (SVD) and then carries out the integral directly in the low-rank basis. Two lightweight networks learn the left and right singular func- tions, a diagonal parameter matrix learns the singular values, and a Gram-matrix regularizer enforces orthonormality. As SVD-NO approximates the full kernel, it obtains a high de- gree of expressivity. Furthermore, due to its low-rank struc- ture the computational complexity of applying the operator remains reasonable, leading to a practical system. In exten- sive evaluations on five diverse benchmark equations, SVD- NO achieves a new state of the art. In particular, SVD-NO provides greater performance gains on PDEs whose solutions are highly spatially variable. The code of this work is publicly available at https://github.com/2noamk/SVDNO.git.

Paperid: 735, https://arxiv.org/pdf/2511.10014.pdf GitHub

Abstract:
Large language models (LLMs) are rapidly transforming various domains, including biomedicine and healthcare, and demonstrate remarkable potential from scientific research to new drug discovery. Graph-based retrieval-augmented generation (RAG) systems, as a useful application of LLMs, can improve contextual reasoning through structured entity and relationship identification from long-context knowledge, e.g. biomedical literature. Even though many advantages over naive RAGs, most of graph-based RAGs are computationally intensive, which limits their application to large-scale dataset. To address this issue, we introduce fastbmRAG, an fast graph-based RAG optimized for biomedical literature. Utilizing well organized structure of biomedical papers, fastbmRAG divides the construction of knowledge graph into two stages, first drafting graphs using abstracts; and second, refining them using main texts guided by vector-based entity linking, which minimizes redundancy and computational load. Our evaluations demonstrate that fastbmRAG is over 10x faster than existing graph-RAG tools and achieve superior coverage and accuracy to input knowledge. FastbmRAG provides a fast solution for quickly understanding, summarizing, and answering questions about biomedical literature on a large scale. FastbmRAG is public available in https://github.com/menggf/fastbmRAG.

Paperid: 736, https://arxiv.org/pdf/2511.10003.pdf GitHub

Abstract:
Weakly supervised 3D instance segmentation is essential for 3D scene understanding, especially as the growing scale of data and high annotation costs associated with fully supervised approaches. Existing methods primarily rely on two forms of weak supervision: one-thing-one-click annotations and bounding box annotations, both of which aim to reduce labeling efforts. However, these approaches still encounter limitations, including labor-intensive annotation processes, high complexity, and reliance on expert annotators. To address these challenges, we propose \textbf{DBGroup}, a two-stage weakly supervised 3D instance segmentation framework that leverages scene-level annotations as a more efficient and scalable alternative. In the first stage, we introduce a Dual-Branch Point Grouping module to generate pseudo labels guided by semantic and mask cues extracted from multi-view images. To further improve label quality, we develop two refinement strategies: Granularity-Aware Instance Merging and Semantic Selection and Propagation. The second stage involves multi-round self-training on an end-to-end instance segmentation network using the refined pseudo-labels. Additionally, we introduce an Instance Mask Filter strategy to address inconsistencies within the pseudo labels. Extensive experiments demonstrate that DBGroup achieves competitive performance compared to sparse-point-level supervised 3D instance segmentation methods, while surpassing state-of-the-art scene-level supervised 3D semantic segmentation approaches. Code is available at https://github.com/liuxuexun/DBGroup.

Paperid: 737, https://arxiv.org/pdf/2511.09970.pdf GitHub

Abstract:
Tabular data is the most abundant data type in the world, powering systems in finance, healthcare, e-commerce, and beyond. As tabular datasets grow and span multiple related targets, there is an increasing need to exploit shared task information for improved multitask generalization. Multitask learning (MTL) has emerged as a powerful way to improve generalization and efficiency, yet most existing work focuses narrowly on large-scale recommendation systems, leaving its potential in broader tabular domains largely underexplored. Also, existing MTL approaches for tabular data predominantly rely on multi-layer perceptron-based backbones, which struggle to capture complex feature interactions and often fail to scale when data is abundant, a limitation that transformer architectures have overcome in other domains. Motivated by this, we introduce MultiTab-Net, the first multitask transformer architecture specifically designed for large tabular data. MultiTab-Net employs a novel multitask masked-attention mechanism that dynamically models feature-feature dependencies while mitigating task competition. Through extensive experiments, we show that MultiTab-Net consistently achieves higher multitask gain than existing MTL architectures and single-task transformers across diverse domains including large-scale recommendation data, census-like socioeconomic data, and physics datasets, spanning a wide range of task counts, task types, and feature modalities. In addition, we contribute MultiTab-Bench, a generalized multitask synthetic dataset generator that enables systematic evaluation of multitask dynamics by tuning task count, task correlations, and relative task complexity. Our code is publicly available at https://github.com/Armanfard-Lab/MultiTab.

Paperid: 738, https://arxiv.org/pdf/2511.09965.pdf GitHub

Abstract:
Recent advances in generative models, especially diffusion models, have significantly improved image restoration (IR) performance. However, existing problem-agnostic diffusion model-based image restoration (DMIR) methods face challenges in fully leveraging diffusion priors, resulting in suboptimal performance. In this paper, we address the limitations of current problem-agnostic DMIR methods by analyzing their sampling process and providing effective solutions. We introduce EquS, a DMIR method that imposes equivariant information through dual sampling trajectories. To further boost EquS, we propose the Timestep-Aware Schedule (TAS) and introduce EquS$^+$. TAS prioritizes deterministic steps to enhance certainty and sampling efficiency. Extensive experiments on benchmarks demonstrate that our method is compatible with previous problem-agnostic DMIR methods and significantly boosts their performance without increasing computational costs. Our code is available at https://github.com/FouierL/EquS.

Paperid: 739, https://arxiv.org/pdf/2511.09943.pdf GitHub

Abstract:
SeQuant is an open-source library for symbolic algebra of tensors over commutative (scalar) and non-commutative (operator) rings. The key innovation supporting most of its functionality is a graph-theoretic tensor network (TN) canonicalizer that can handle tensor networks with symmetries faster than their standard group-theoretic counterparts. The TN canonicalizer is used for routine simplification of conventional tensor expressions, for optimizing application of Wick's theorem (used to canonicalize products of tensors over operator fields), and for manipulation of the intermediate representation leading to the numerical evaluation. Notable features of SeQuant include support for noncovariant tensor networks (which often arise from tensor decompositions) and for tensors with modes that depend parametrically on indices of other tensor modes (such dependencies between degrees of freedom are naturally viewed as nesting of tensors, "tensors of tensors" arising in block-wise data compressions in data science and modern quantum simulation). SeQuant blurs the line between pure symbolic manipulation/code generation and numerical evaluation by including compiler-like components to optimize and directly interpret tensor expressions using external numerical tensor algebra frameworks. The SeQuant source code is available at https://github.com/ValeevGroup/SeQuant.

Paperid: 740, https://arxiv.org/pdf/2511.09926.pdf GitHub

Abstract:
Recent advances have shown that sequential fine-tuning (SeqFT) of pre-trained vision transformers (ViTs), followed by classifier refinement using approximate distributions of class features, can be an effective strategy for class-incremental learning (CIL). However, this approach is susceptible to distribution drift, caused by the sequential optimization of shared backbone parameters. This results in a mismatch between the distributions of the previously learned classes and that of the updater model, ultimately degrading the effectiveness of classifier performance over time. To address this issue, we introduce a latent space transition operator and propose Sequential Learning with Drift Compensation (SLDC). SLDC aims to align feature distributions across tasks to mitigate the impact of drift. First, we present a linear variant of SLDC, which learns a linear operator by solving a regularized least-squares problem that maps features before and after fine-tuning. Next, we extend this with a weakly nonlinear SLDC variant, which assumes that the ideal transition operator lies between purely linear and fully nonlinear transformations. This is implemented using learnable, weakly nonlinear mappings that balance flexibility and generalization. To further reduce representation drift, we apply knowledge distillation (KD) in both algorithmic variants. Extensive experiments on standard CIL benchmarks demonstrate that SLDC significantly improves the performance of SeqFT. Notably, by combining KD to address representation drift with SLDC to compensate distribution drift, SeqFT achieves performance comparable to joint training across all evaluated datasets. Code: https://github.com/raoxuan98-hash/sldc.git.

Paperid: 741, https://arxiv.org/pdf/2511.09909.pdf GitHub

Abstract:
In this paper, we focus on Single-Domain Generalized Object Detection (Single-DGOD), aiming to transfer a detector trained on one source domain to multiple unknown domains. Existing methods for Single-DGOD typically rely on discrete data augmentation or static perturbation methods to expand data diversity, thereby mitigating the lack of access to target domain data. However, in real-world scenarios such as changes in weather or lighting conditions, domain shifts often occur continuously and gradually. Discrete augmentations and static perturbations fail to effectively capture the dynamic variation of feature distributions, thereby limiting the model's ability to perceive fine-grained cross-domain differences. To this end, we propose a new method, Liquid Temporal Feature Evolution, which simulates the progressive evolution of features from the source domain to simulated latent distributions by incorporating temporal modeling and liquid neural network-driven parameter adjustment. Specifically, we introduce controllable Gaussian noise injection and multi-scale Gaussian blurring to simulate initial feature perturbations, followed by temporal modeling and a liquid parameter adjustment mechanism to generate adaptive modulation parameters, enabling a smooth and continuous adaptation across domains. By capturing progressive cross-domain feature evolution and dynamically regulating adaptation paths, our method bridges the source-unknown domain distribution gap, significantly boosting generalization and robustness to unseen shifts. Significant performance improvements on the Diverse Weather dataset and Real-to-Art benchmark demonstrate the superiority of our method. Our code is available at https://github.com/2490o/LTFE.

Paperid: 742, https://arxiv.org/pdf/2511.09904.pdf GitHub

Abstract:
AI systems are increasingly able to autonomously conduct realistic software engineering tasks, and may soon be deployed to automate machine learning (ML) R&D itself. Frontier AI systems may be deployed in safety-critical settings, including to help ensure the safety of future systems. Unfortunately, frontier and future systems may not be sufficiently trustworthy, and there is evidence that these systems may even be misaligned with their developers or users. Therefore, we investigate the capabilities of AI agents to act against the interests of their users when conducting ML engineering, by sabotaging ML models, sandbagging their performance, and subverting oversight mechanisms. First, we extend MLE-Bench, a benchmark for realistic ML tasks, with code-sabotage tasks such as implanting backdoors and purposefully causing generalisation failures. Frontier agents make meaningful progress on our sabotage tasks. In addition, we study agent capabilities to sandbag on MLE-Bench. Agents can calibrate their performance to specified target levels below their actual capability. To mitigate sabotage, we use LM monitors to detect suspicious agent behaviour, and we measure model capability to sabotage and sandbag without being detected by these monitors. Overall, monitors are capable at detecting code-sabotage attempts but our results suggest that detecting sandbagging is more difficult. Additionally, aggregating multiple monitor predictions works well, but monitoring may not be sufficiently reliable to mitigate sabotage in high-stakes domains. Our benchmark is implemented in the UK AISI's Inspect framework and we make our code publicly available at https://github.com/samm393/mlebench-subversion

Paperid: 743, https://arxiv.org/pdf/2511.09868.pdf GitHub

Abstract:
Large Vision-Language Models (LVLMs) have achieved impressive performance across a wide range of multimodal tasks. However, they still face critical challenges in modeling long-range dependencies under the usage of Rotary Positional Encoding (ROPE). Although it can facilitate precise modeling of token positions, it induces progressive attention decay as token distance increases, especially with progressive attention decay over distant token pairs, which severely impairs the model's ability to remember global context. To alleviate this issue, we propose inference-only Three-step Decay Resilience Strategies (T-DRS), comprising (1) Semantic-Driven DRS (SD-DRS), amplifying semantically meaningful but distant signals via content-aware residuals, (2) Distance-aware Control DRS (DC-DRS), which can purify attention by smoothly modulating weights based on positional distances, suppressing noise while preserving locality, and (3) re-Reinforce Distant DRS (reRD-DRS), consolidating the remaining informative remote dependencies to maintain global coherence. Together, the T-DRS recover suppressed long-range token pairs without harming local inductive biases. Extensive experiments on Vision Question Answering (VQA) benchmarks demonstrate that T-DRS can consistently improve performance in a training-free manner. The code can be accessed in https://github.com/labixiaoq-qq/Remember-me

Paperid: 744, https://arxiv.org/pdf/2511.09836.pdf GitHub

Abstract:
Autonomous robots are increasingly deployed for information-gathering tasks in environments that vary across space and time. Planning informative and safe trajectories in such settings is challenging because information decays when regions are not revisited. Most existing planners model information as static or uniformly decaying, ignoring environments where the decay rate varies spatially; those that model non-uniform decay often overlook how it evolves along the robot's motion, and almost all treat safety as a soft penalty. In this paper, we address these challenges. We model uncertainty in the environment using clarity, a normalized representation of differential entropy from our earlier work that captures how information improves through new measurements and decays over time when regions are not revisited. Building on this, we present Stein Variational Clarity-Aware Informative Planning, a framework that embeds clarity dynamics within trajectory optimization and enforces safety through a low-level filtering mechanism based on our earlier gatekeeper framework for safety verification. The planner performs Bayesian inference-based learning via Stein variational inference, refining a distribution over informative trajectories while filtering each nominal Stein informative trajectory to ensure safety. Hardware experiments and simulations across environments with varying decay rates and obstacles demonstrate consistent safety and reduced information deficits.

Paperid: 745, https://arxiv.org/pdf/2511.09820.pdf GitHub

Abstract:
Cross-view image retrieval, particularly street-to-satellite matching, is a critical task for applications such as autonomous navigation, urban planning, and localization in GPS-denied environments. However, existing approaches often require supervised training on curated datasets and rely on panoramic or UAV-based images, which limits real-world deployment. In this paper, we present a simple yet effective cross-view image retrieval framework that leverages a pretrained vision encoder and a large language model (LLM), requiring no additional training. Given a monocular street-view image, our method extracts geographic cues through web-based image search and LLM-based location inference, generates a satellite query via geocoding API, and retrieves matching tiles using a pretrained vision encoder (e.g., DINOv2) with PCA-based whitening feature refinement. Despite using no ground-truth supervision or finetuning, our proposed method outperforms prior learning-based approaches on the benchmark dataset under zero-shot settings. Moreover, our pipeline enables automatic construction of semantically aligned street-to-satellite datasets, which is offering a scalable and cost-efficient alternative to manual annotation. All source codes will be made publicly available at https://jeonghomin.github.io/street2orbit.github.io/.

Paperid: 746, https://arxiv.org/pdf/2511.09809.pdf GitHub

Abstract:
Vision-Language Models (VLMs) excel at zero-shot inference but often degrade under test-time domain shifts. For this reason, episodic test-time adaptation strategies have recently emerged as powerful techniques for adapting VLMs to a single unlabeled image. However, existing adaptation strategies, such as test-time prompt tuning, typically require backpropagating through large encoder weights or altering core model components. In this work, we introduce Spectrum-Aware Test-Time Steering (STS), a lightweight adaptation framework that extracts a spectral subspace from the textual embeddings to define principal semantic directions and learns to steer latent representations in a spectrum-aware manner by adapting a small number of per-sample shift parameters to minimize entropy across augmented views. STS operates entirely at inference in the latent space, without backpropagation through or modification of the frozen encoders. Building on standard evaluation protocols, our comprehensive experiments demonstrate that STS largely surpasses or compares favorably against state-of-the-art test-time adaptation methods, while introducing only a handful of additional parameters and achieving inference speeds up to 8x faster with a 12x smaller memory footprint than conventional test-time prompt tuning. The code is available at https://github.com/kdafnis/STS.

Paperid: 747, https://arxiv.org/pdf/2511.09740.pdf GitHub

Abstract:
Soiling detection for automotive cameras is a crucial part of advanced driver assistance systems to make them more robust to external conditions like weather, dust, etc. In this paper, we regard the soiling detection as a semantic segmentation problem. We provide a comprehensive comparison of popular segmentation methods and show their superiority in performance while comparing them to tile-level classification approaches. Moreover, we present an extensive analysis of the Woodscape dataset showing that the original dataset contains a data-leakage and imprecise annotations. To address these problems, we create a new data subset, which, despite being much smaller, provides enough information for the segmentation method to reach comparable results in a much shorter time. All our codes and dataset splits are available at https://github.com/filipberanek/woodscape_revision.

Paperid: 748, https://arxiv.org/pdf/2511.09737.pdf GitHub

Abstract:
Generalization to unseen environments is a significant challenge in the field of robotics and control. In this work, we focus on contextual reinforcement learning, where agents act within environments with varying contexts, such as self-driving cars or quadrupedal robots that need to operate in different terrains or weather conditions than they were trained for. We tackle the critical task of generalizing to out-of-distribution (OOD) settings, without access to explicit context information at test time. Recent work has addressed this problem by training a context encoder and a history adaptation module in separate stages. While promising, this two-phase approach is cumbersome to implement and train. We simplify the methodology and introduce SPARC: single-phase adaptation for robust control. We test SPARC on varying contexts within the high-fidelity racing simulator Gran Turismo 7 and wind-perturbed MuJoCo environments, and find that it achieves reliable and robust OOD generalization.

Paperid: 749, https://arxiv.org/pdf/2511.09729.pdf GitHub

Abstract:
Solving partial differential equations (PDEs) can be prohibitively expensive using traditional numerical methods. Deep learning-based surrogate models typically specialize in a single PDE with fixed parameters. We present a framework for equation-aware emulation that generalizes to unseen PDEs, conditioning a neural model on a vector encoding representing the terms in a PDE and their coefficients. We present a baseline of four distinct modeling technqiues, trained on a family of 1D PDEs from the APEBench suite. Our approach achieves strong performance on parameter sets held out from the training distribution, with strong stability for rollout beyond the training window, and generalization to an entirely unseen PDE. This work was developed as part of a broader effort exploring AI systems that automate the creation of expert-level empirical software for scorable scientific tasks. The data and codebase are available at https://github.com/google-research/generalized-pde-emulator.

Paperid: 750, https://arxiv.org/pdf/2511.09724.pdf GitHub

Abstract:
Indoor localization in GPS-denied environments is crucial for applications like emergency response and assistive navigation. Vision-based methods such as PALMS enable infrastructure-free localization using only a floor plan and a stationary scan, but are limited by the short range of smartphone LiDAR and ambiguity in indoor layouts. We propose PALMS$+$, a modular, image-based system that addresses these challenges by reconstructing scale-aligned 3D point clouds from posed RGB images using a foundation monocular depth estimation model (Depth Pro), followed by geometric layout matching via convolution with the floor plan. PALMS$+$ outputs a posterior over the location and orientation, usable for direct or sequential localization. Evaluated on the Structured3D and a custom campus dataset consisting of 80 observations across four large campus buildings, PALMS$+$ outperforms PALMS and F3Loc in stationary localization accuracy -- without requiring any training. Furthermore, when integrated with a particle filter for sequential localization on 33 real-world trajectories, PALMS$+$ achieved lower localization errors compared to other methods, demonstrating robustness for camera-free tracking and its potential for infrastructure-free applications. Code and data are available at https://github.com/Head-inthe-Cloud/PALMS-Plane-based-Accessible-Indoor-Localization-Using-Mobile-Smartphones

Paperid: 751, https://arxiv.org/pdf/2511.09690.pdf GitHub

Authors:Omnilingual ASR team, Gil Keren, Artyom Kozhevnikov, Yen Meng, Christophe Ropers, Matthew Setzler, Skyler Wang, Ife Adebara, Michael Auli, Can Balioglu, Kevin Chan, Chierh Cheng, Joe Chuang, Caley Droof, Mark Duppenthaler, Paul-Ambroise Duquenne, Alexander Erben, Cynthia Gao, Gabriel Mejia Gonzalez, Kehan Lyu, Sagar Miglani, Vineel Pratap, Kaushik Ram Sadagopan, Safiyyah Saleem, Arina Turkatenko, Albert Ventayol-Boada, Zheng-Xin Yong, Yu-An Chung, Jean Maillard, Rashel Moritz, Alexandre Mourachko, Mary Williamson, Shireen Yates

Abstract:
Automatic speech recognition (ASR) has advanced in high-resource languages, but most of the world's 7,000+ languages remain unsupported, leaving thousands of long-tail languages behind. Expanding ASR coverage has been costly and limited by architectures that restrict language support, making extension inaccessible to most--all while entangled with ethical concerns when pursued without community collaboration. To transcend these limitations, we introduce Omnilingual ASR, the first large-scale ASR system designed for extensibility. Omnilingual ASR enables communities to introduce unserved languages with only a handful of data samples. It scales self-supervised pre-training to 7B parameters to learn robust speech representations and introduces an encoder-decoder architecture designed for zero-shot generalization, leveraging a LLM-inspired decoder. This capability is grounded in a massive and diverse training corpus; by combining breadth of coverage with linguistic variety, the model learns representations robust enough to adapt to unseen languages. Incorporating public resources with community-sourced recordings gathered through compensated local partnerships, Omnilingual ASR expands coverage to over 1,600 languages, the largest such effort to date--including over 500 never before served by ASR. Automatic evaluations show substantial gains over prior systems, especially in low-resource conditions, and strong generalization. We release Omnilingual ASR as a family of models, from 300M variants for low-power devices to 7B for maximum accuracy. We reflect on the ethical considerations shaping this design and conclude by discussing its societal impact. In particular, we highlight how open-sourcing models and tools can lower barriers for researchers and communities, inviting new forms of participation. Open-source artifacts are available at https://github.com/facebookresearch/omnilingual-asr.

Paperid: 752, https://arxiv.org/pdf/2511.09611.pdf GitHub GitHub

Abstract:
While thinking-aware generation aims to improve performance on complex tasks, we identify a critical failure mode where existing sequential, autoregressive approaches can paradoxically degrade performance due to error propagation. To systematically analyze this issue, we propose ParaBench, a new benchmark designed to evaluate both text and image output modalities. Our analysis using ParaBench reveals that this performance degradation is strongly correlated with poor alignment between the generated reasoning and the final image. To resolve this, we propose a parallel multimodal diffusion framework, MMaDA-Parallel, that enables continuous, bidirectional interaction between text and images throughout the entire denoising trajectory. MMaDA-Parallel is trained with supervised finetuning and then further optimized by Parallel Reinforcement Learning (ParaRL), a novel strategy that applies semantic rewards along the trajectory to enforce cross-modal consistency. Experiments validate that our model significantly improves cross-modal alignment and semantic consistency, achieving a 6.9\% improvement in Output Alignment on ParaBench compared to the state-of-the-art model, Bagel, establishing a more robust paradigm for thinking-aware image synthesis. Our code is open-sourced at https://github.com/tyfeld/MMaDA-Parallel

Paperid: 753, https://arxiv.org/pdf/2511.09605.pdf GitHub

Abstract:
The growing number of medical tomography examinations has necessitated the development of automated methods capable of extracting comprehensive imaging features to facilitate downstream tasks such as tumor characterization, while assisting physicians in managing their growing workload. However, 3D medical image classification remains a challenging task due to the complex spatial relationships and long-range dependencies inherent in volumetric data. Training models from scratch suffers from low data regimes, and the absence of 3D large-scale multimodal datasets has limited the development of 3D medical imaging foundation models. Recent studies, however, have highlighted the potential of 2D vision foundation models, originally trained on natural images, as powerful feature extractors for medical image analysis. Despite these advances, existing approaches that apply 2D models to 3D volumes via slice-based decomposition remain suboptimal. Conventional volume slicing strategies, which rely on canonical planes such as axial, sagittal, or coronal, may inadequately capture the spatial extent of target structures when these are misaligned with standardized viewing planes. Furthermore, existing slice-wise aggregation strategies rarely account for preserving the volumetric structure, resulting in a loss of spatial coherence across slices. To overcome these limitations, we propose TomoGraphView, a novel framework that integrates omnidirectional volume slicing with spherical graph-based feature aggregation. We publicly share our accessible code base at http://github.com/compai-lab/2025-MedIA-kiechle and provide a user-friendly library for omnidirectional volume slicing at https://pypi.org/project/OmniSlicer.

Paperid: 754, https://arxiv.org/pdf/2511.09602.pdf GitHub

Abstract:
Dexterous functional tool-use grasping is essential for effective robotic manipulation of tools. However, existing approaches face significant challenges in efficiently constructing large-scale datasets and ensuring generalizability to everyday object scales. These issues primarily arise from size mismatches between robotic and human hands, and the diversity in real-world object scales. To address these limitations, we propose the ScaleADFG framework, which consists of a fully automated dataset construction pipeline and a lightweight grasp generation network. Our dataset introduce an affordance-based algorithm to synthesize diverse tool-use grasp configurations without expert demonstrations, allowing flexible object-hand size ratios and enabling large robotic hands (compared to human hands) to grasp everyday objects effectively. Additionally, we leverage pre-trained models to generate extensive 3D assets and facilitate efficient retrieval of object affordances. Our dataset comprising five object categories, each containing over 1,000 unique shapes with 15 scale variations. After filtering, the dataset includes over 60,000 grasps for each 2 dexterous robotic hands. On top of this dataset, we train a lightweight, single-stage grasp generation network with a notably simple loss design, eliminating the need for post-refinement. This demonstrates the critical importance of large-scale datasets and multi-scale object variant for effective training. Extensive experiments in simulation and on real robot confirm that the ScaleADFG framework exhibits strong adaptability to objects of varying scales, enhancing functional grasp stability, diversity, and generalizability. Moreover, our network exhibits effective zero-shot transfer to real-world objects. Project page is available at https://sizhe-wang.github.io/ScaleADFG_webpage

Paperid: 755, https://arxiv.org/pdf/2511.09572.pdf GitHub

Abstract:
AI agents increasingly rely on external tools to solve complex, long-horizon tasks. Advancing such agents requires reproducible evaluation and large-scale training in controllable, diverse, and realistic tool-use environments. However, real-world APIs are limited in availability, domain coverage, and stability, often requiring access keys and imposing rate limits, which render them impractical for stable evaluation or scalable training. To address these challenges, we introduce SynthTools, a flexible and scalable framework for generating synthetic tool ecosystems. Our framework consists of three core components: Tool Generation for automatic and scalable creation of diverse tools, Tool Simulation to emulate realistic tool behaviors, and Tool Audit to ensure correctness and consistency of tool simulation. To illustrate its scalability, we show that SynthTools can readily produce toolsets that span twice as many domains and twice as many tools per domain as prior work. Furthermore, the tool simulation and tool audit components demonstrate strong reliability, achieving $94\%$ and $99\%$ accuracy respectively. Finally, we construct downstream tasks from the generated tools that even state-of-the-art models struggle to complete. By enabling scalable, diverse, and reliable tool ecosystems, SynthTools provides a practical path toward large-scale training and stable evaluation of tool-use agents. Our code is available at https://github.com/namkoong-lab/SynthTools.

Paperid: 756, https://arxiv.org/pdf/2511.09562.pdf GitHub

Abstract:
WaveRoll is an interactive JavaScript library that enables comparative visualization and synchronized playback of multiple MIDI piano rolls on a browser. It addresses a specific evaluation need in Automatic Music Transcription (AMT), contrasting multiple MIDI outputs produced from the same input. The library displays multiple MIDI tracks on a single, time-aligned grid with synchronized audio, allowing users to compare pitch and timing, identify missed or extra notes, and observe onset and offset differences, as well as section-level patterns. We expect that such comparisons would assist in model evaluation and error analysis, and help readers to understand the model behavior better. The open-source library is available at https://github.com/crescent-stdio/wave-roll

Paperid: 757, https://arxiv.org/pdf/2511.09555.pdf GitHub

Abstract:
Robotic manipulation requires precise spatial understanding to interact with objects in the real world. Point-based methods suffer from sparse sampling, leading to the loss of fine-grained semantics. Image-based methods typically feed RGB and depth into 2D backbones pre-trained on 3D auxiliary tasks, but their entangled semantics and geometry are sensitive to inherent depth noise in real-world that disrupts semantic understanding. Moreover, these methods focus on high-level geometry while overlooking low-level spatial cues essential for precise interaction. We propose SpatialActor, a disentangled framework for robust robotic manipulation that explicitly decouples semantics and geometry. The Semantic-guided Geometric Module adaptively fuses two complementary geometry from noisy depth and semantic-guided expert priors. Also, a Spatial Transformer leverages low-level spatial cues for accurate 2D-3D mapping and enables interaction among spatial features. We evaluate SpatialActor on multiple simulation and real-world scenarios across 50+ tasks. It achieves state-of-the-art performance with 87.4% on RLBench and improves by 13.9% to 19.4% under varying noisy conditions, showing strong robustness. Moreover, it significantly enhances few-shot generalization to new tasks and maintains robustness under various spatial perturbations. Project Page: https://shihao1895.github.io/SpatialActor

Paperid: 758, https://arxiv.org/pdf/2511.09554.pdf GitHub

Abstract:
Open-vocabulary detectors achieve impressive performance on COCO, but often fail to generalize to real-world datasets with out-of-distribution classes not typically found in their pre-training. Rather than simply fine-tuning a heavy-weight vision-language model (VLM) for new domains, we introduce RF-DETR, a light-weight specialist detection transformer that discovers accuracy-latency Pareto curves for any target dataset with weight-sharing neural architecture search (NAS). Our approach fine-tunes a pre-trained base network on a target dataset and evaluates thousands of network configurations with different accuracy-latency tradeoffs without re-training. Further, we revisit the "tunable knobs" for NAS to improve the transferability of DETRs to diverse target domains. Notably, RF-DETR significantly improves on prior state-of-the-art real-time methods on COCO and Roboflow100-VL. RF-DETR (nano) achieves 48.0 AP on COCO, beating D-FINE (nano) by 5.3 AP at similar latency, and RF-DETR (2x-large) outperforms GroundingDINO (tiny) by 1.2 AP on Roboflow100-VL while running 20x as fast. To the best of our knowledge, RF-DETR (2x-large) is the first real-time detector to surpass 60 AP on COCO. Our code is at https://github.com/roboflow/rf-detr

Paperid: 759, https://arxiv.org/pdf/2511.09540.pdf GitHub

Abstract:
Recent advances in context optimization (CoOp) guided by large language model (LLM)-distilled medical semantic priors offer a scalable alternative to manual prompt engineering and full fine-tuning for adapting biomedical CLIP-based vision-language models (VLMs). However, prompt learning in this context is challenged by semantic misalignment between LLMs and CLIP variants due to divergent training corpora and model architectures; it further lacks scalability across continuously evolving families of foundation models. More critically, pairwise multimodal alignment via conventional Euclidean-space optimization lacks the capacity to model unified representations or apply localized geometric constraints, which tends to amplify modality gaps in complex biomedical imaging and destabilize few-shot adaptation. In this work, we propose vMFCoOp, a framework that inversely estimates von Mises-Fisher (vMF) distributions on a shared Hyperspherical Manifold, aligning semantic biases between arbitrary LLMs and CLIP backbones via Unified Semantic Anchors to achieve robust biomedical prompting and superior few-shot classification. Grounded in three complementary constraints, vMFCoOp demonstrates consistent improvements across 14 medical datasets, 12 medical imaging modalities, and 13 anatomical regions, outperforming state-of-the-art methods in accuracy, generalization, and clinical applicability. This work aims to continuously expand to encompass more downstream applications, and the corresponding resources are intended to be shared through https://github.com/VinyehShaw/UniEqui.

Paperid: 760, https://arxiv.org/pdf/2511.09488.pdf GitHub

Abstract:
Supervised fine-tuning (SFT) of large language models (LLMs) for specialized tasks requires high-quality datasets, but manual curation is prohibitively expensive. Synthetic data generation offers scalability, but its effectiveness relies on complex, multi-stage workflows, integrating prompt engineering and model orchestration. Existing automated workflow methods face a cold start problem: they require labeled datasets for reward modeling, which is especially problematic for subjective, open-ended tasks with no objective ground truth. We introduce AutoSynth, a framework that automates workflow discovery and optimization without reference datasets by reframing the problem as a Monte Carlo Tree Search guided by a novel dataset-free hybrid reward. This reward enables meta-learning through two LLM-as-judge components: one evaluates sample quality using dynamically generated task-specific metrics, and another assesses workflow code and prompt quality. Experiments on subjective educational tasks show that while expert-designed workflows achieve higher human preference rates (96-99% win rates vs. AutoSynth's 40-51%), models trained on AutoSynth-generated data dramatically outperform baselines (40-51% vs. 2-5%) and match or surpass expert workflows on certain metrics, suggesting discovery of quality dimensions beyond human intuition. These results are achieved while reducing human effort from 5-7 hours to just 30 minutes (>90% reduction). AutoSynth tackles the cold start issue in data-centric AI, offering a scalable, cost-effective method for subjective LLM tasks. Code: https://github.com/bisz9918-maker/AutoSynth.

Paperid: 761, https://arxiv.org/pdf/2511.09484.pdf GitHub

Abstract:
Learning dexterous and agile policy for humanoid and dexterous hand control requires large-scale demonstrations, but collecting robot-specific data is prohibitively expensive. In contrast, abundant human motion data is readily available from motion capture, videos, and virtual reality, which could help address the data scarcity problem. However, due to the embodiment gap and missing dynamic information like force and torque, these demonstrations cannot be directly executed on robots. To bridge this gap, we propose Scalable Physics-Informed DExterous Retargeting (SPIDER), a physics-based retargeting framework to transform and augment kinematic-only human demonstrations to dynamically feasible robot trajectories at scale. Our key insight is that human demonstrations should provide global task structure and objective, while large-scale physics-based sampling with curriculum-style virtual contact guidance should refine trajectories to ensure dynamical feasibility and correct contact sequences. SPIDER scales across diverse 9 humanoid/dexterous hand embodiments and 6 datasets, improving success rates by 18% compared to standard sampling, while being 10X faster than reinforcement learning (RL) baselines, and enabling the generation of a 2.4M frames dynamic-feasible robot dataset for policy learning. As a universal physics-based retargeting method, SPIDER can work with diverse quality data and generate diverse and high-quality data to enable efficient policy learning with methods like RL.

Paperid: 762, https://arxiv.org/pdf/2511.09483.pdf GitHub GitHub

Abstract:
We present CrochetBench, a benchmark for evaluating the ability of multimodal large language models to perform fine-grained, low-level procedural reasoning in the domain of crochet. Unlike prior benchmarks that focus on high-level description or visual question answering, CrochetBench shifts the emphasis from describing to doing: models are required to recognize stitches, select structurally appropriate instructions, and generate compilable crochet procedures. We adopt the CrochetPARADE DSL as our intermediate representation, enabling structural validation and functional evaluation via execution. The benchmark covers tasks including stitch classification, instruction grounding, and both natural language and image-to-DSL translation. Across all tasks, performance sharply declines as the evaluation shifts from surface-level similarity to executable correctness, exposing limitations in long-range symbolic reasoning and 3D-aware procedural synthesis. CrochetBench offers a new lens for assessing procedural competence in multimodal models and highlights the gap between surface-level understanding and executable precision in real-world creative domains. Code is available at https://github.com/Peiyu-Georgia-Li/crochetBench.

Paperid: 763, https://arxiv.org/pdf/2511.09388.pdf GitHub GitHub

Abstract:
Recognizing unseen skeleton action categories remains highly challenging due to the absence of corresponding skeletal priors. Existing approaches generally follow an "align-then-classify" paradigm but face two fundamental issues, i.e., (i) fragile point-to-point alignment arising from imperfect semantics, and (ii) rigid classifiers restricted by static decision boundaries and coarse-grained anchors. To address these issues, we propose a novel method for zero-shot skeleton action recognition, termed $\texttt{$\textbf{Flora}$}$, which builds upon $\textbf{F}$lexib$\textbf{L}$e neighb$\textbf{O}$r-aware semantic attunement and open-form dist$\textbf{R}$ibution-aware flow cl$\textbf{A}$ssifier. Specifically, we flexibly attune textual semantics by incorporating neighboring inter-class contextual cues to form direction-aware regional semantics, coupled with a cross-modal geometric consistency objective that ensures stable and robust point-to-region alignment. Furthermore, we employ noise-free flow matching to bridge the modality distribution gap between semantic and skeleton latent embeddings, while a condition-free contrastive regularization enhances discriminability, leading to a distribution-aware classifier with fine-grained decision boundaries achieved through token-level velocity predictions. Extensive experiments on three benchmark datasets validate the effectiveness of our method, showing particularly impressive performance even when trained with only 10\% of the seen data. Code is available at https://github.com/cseeyangchen/Flora.

Paperid: 764, https://arxiv.org/pdf/2511.09385.pdf GitHub

Abstract:
Offline preference optimization offers a simpler and more stable alternative to RLHF for aligning language models. However, their effectiveness is critically dependent on ranking accuracy, a metric where further gains are highly impactful. This limitation arises from a fundamental problem that we identify and formalize as the Overfitting-Underfitting Dilemma: current margin designs cause models to apply excessive, wasteful gradients to correctly ranked samples (overfitting) while providing insufficient corrective signals for misranked ones (underfitting). To resolve this dilemma, we propose Adaptive Margin-attached Preference Optimization (AMaPO), a simple yet principled algorithm. AMaPO employs an instance-wise adaptive margin, refined by Z-normalization and exponential scaling, which dynamically reallocates learning effort by amplifying gradients for misranked samples and suppressing them for correct ones. Extensive experiments on widely used benchmarks demonstrate that AMaPO not only achieves better ranking accuracy and superior downstream alignment performance, but targeted analysis also confirms that it successfully mitigates the core overfitting and underfitting issues.

Paperid: 765, https://arxiv.org/pdf/2511.09366.pdf GitHub

Abstract:
Ultra-low-field (ULF) MRI promises broader accessibility but suffers from low signal-to-noise ratio (SNR), reduced spatial resolution, and contrasts that deviate from high-field standards. Image-to-image translation can map ULF images to a high-field appearance, yet efficacy is limited by scarce paired training data. Working within the ULF-EnC challenge constraints (50 paired 3D volumes; no external data), we study how task-adapted data augmentations impact a standard deep model for ULF image enhancement. We show that strong, diverse augmentations, including auxiliary tasks on high-field data, substantially improve fidelity. Our submission ranked third by brain-masked SSIM on the public validation leaderboard and fourth by the official score on the final test leaderboard. Code is available at https://github.com/fzimmermann89/low-field-enhancement.

Paperid: 766, https://arxiv.org/pdf/2511.09348.pdf GitHub

Abstract:
This study presents a finite element and virtual element (FE-VE) coupled method for thermomechanical analysis in electronic packaging structures. The approach partitions computational domains strategically, employing FEM for regular geometries to maximize computational efficiency and VEM for complex shapes to enhance geometric flexibility. Interface compatibility is maintained through coincident nodal correspondence, ensuring solution continuity across domain boundaries while reducing meshing complexity and computational overhead. Validation through electronic packaging applications demonstrates reasonable agreement with reference solutions and acceptable convergence characteristics across varying mesh densities. The method effectively captures thermal distributions and stress concentrations in multi-material systems, establishing a practical computational framework for electronic packaging analysis involving complex geometries. Source codes are available at https://github.com/yanpeng-gong/FeVeCoupled-ElectronicPackaging.

Paperid: 767, https://arxiv.org/pdf/2511.09329.pdf GitHub

Abstract:
Validating user simulation is a difficult task due to the lack of established measures and benchmarks, which makes it challenging to assess whether a simulator accurately reflects real user behavior. As part of the Sim4IA Micro-Shared Task at the Sim4IA Workshop, SIGIR 2025, we present Sim4IA-Bench, a simulation benchmark suit for the prediction of the next queries and utterances, the first of its kind in the IR community. Our dataset as part of the suite comprises 160 real-world search sessions from the CORE search engine. For 70 of these sessions, up to 62 simulator runs are available, divided into Task A and Task B, in which different approaches predicted users next search queries or utterances. Sim4IA-Bench provides a basis for evaluating and comparing user simulation approaches and for developing new measures of simulator validity. Although modest in size, the suite represents the first publicly available benchmark that links real search sessions with simulated next-query predictions. In addition to serving as a testbed for next query prediction, it also enables exploratory studies on query reformulation behavior, intent drift, and interaction-aware retrieval evaluation. We also introduce a new measure for evaluating next-query predictions in this task. By making the suite publicly available, we aim to promote reproducible research and stimulate further work on realistic and explainable user simulation for information access: https://github.com/irgroup/Sim4IA-Bench.

Paperid: 768, https://arxiv.org/pdf/2511.09299.pdf GitHub

Abstract:
Although neural networks are a powerful tool, their widespread use is hindered by the opacity of their decisions and their black-box nature, which result in a lack of trustworthiness. To alleviate this problem, methods in the field of explainable Artificial Intelligence try to unveil how such automated decisions are made. But explainable AI methods are often plagued by missing faithfulness/correctness, meaning that they sometimes provide explanations that do not align with the neural network's decision and logic. Recently, transformations to decision trees have been proposed to overcome such problems. Unfortunately, they typically lack exactness, scalability, or interpretability as the size of the neural network grows. Thus, we generalize these previous results, especially by considering convolutional neural networks, recurrent neural networks, non-ReLU activation functions, and bias terms. Our findings are accompanied by rigorous proofs and we present a novel algorithm RENTT (Runtime Efficient Network to Tree Transformation) designed to compute an exact equivalent decision tree representation of neural networks in a manner that is both runtime and memory efficient. The resulting decision trees are multivariate and thus, possibly too complex to understand. To alleviate this problem, we also provide a method to calculate the ground truth feature importance for neural networks via the equivalent decision trees - for entire models (global), specific input regions (regional), or single decisions (local). All theoretical results are supported by detailed numerical experiments that emphasize two key aspects: the computational efficiency and scalability of our algorithm, and that only RENTT succeeds in uncovering ground truth explanations compared to conventional approximation methods like LIME and SHAP. All code is available at https://github.com/HelenaM23/RENTT .

Paperid: 769, https://arxiv.org/pdf/2511.09276.pdf GitHub

Abstract:
Energy expenditure estimation aims to infer human metabolic rate from physiological signals such as heart rate, respiration, or accelerometer data, and has been studied primarily with classical regression methods. The few existing deep learning approaches rarely disentangle the role of neural architecture from that of signal choice. In this work, we systematically evaluate both aspects. We compare classical baselines with newer neural architectures across single signals, signal pairs, and grouped sensor inputs for diverse physical activities. Our results show that minute ventilation is the most predictive individual signal, with a transformer model achieving the lowest root mean square error (RMSE) of 0.87 W/kg across all activities. Paired and grouped signals, such as those from the Hexoskin smart shirt (five signals), offer good alternatives for faster models like CNN and ResNet with attention. Per-activity evaluation revealed mixed outcomes: notably better results in low-intensity activities (RMSE down to 0.29 W/kg; NRMSE = 0.04), while higher-intensity tasks showed larger RMSE but more comparable normalized errors. Finally, subject-level analysis highlights strong inter-individual variability, motivating the need for adaptive modeling strategies. Our code and models will be publicly available at https://github.com/Sarvibabakhani/deeplearning-biosignals-ee .

Paperid: 770, https://arxiv.org/pdf/2511.09223.pdf GitHub

Abstract:
Code review is a key practice in software engineering, where developers evaluate code changes to ensure quality and maintainability. Links to issues and external resources are often included in Pull Requests (PRs) to provide additional context, yet they are typically discarded in automated tasks such as PR summarization and code review comment generation. This limits the richness of information available to reviewers and increases cognitive load by forcing context-switching. To address this gap, we present AILINKPREVIEWER, a tool that leverages Large Language Models (LLMs) to generate previews of links in PRs using PR metadata, including titles, descriptions, comments, and link body content. We analyzed 50 engineered GitHub repositories and compared three approaches: Contextual LLM summaries, Non-Contextual LLM summaries, and Metadata-based previews. The results in metrics such as BLEU, BERTScore, and compression ratio show that contextual summaries consistently outperform other methods. However, in a user study with seven participants, most preferred non-contextual summaries, suggesting a trade-off between metric performance and perceived usability. These findings demonstrate the potential of LLM-powered link previews to enhance code review efficiency and to provide richer context for developers and automation in software engineering. The video demo is available at https://www.youtube.com/watch?v=h2qH4RtrB3E, and the tool and its source code can be found at https://github.com/c4rtune/AILinkPreviewer.

Paperid: 771, https://arxiv.org/pdf/2511.09209.pdf GitHub

Abstract:
Mixed-Integer Linear Programming (MILP) is a cornerstone of combinatorial optimization, yet solving large-scale instances remains a significant computational challenge. Recently, Graph Neural Networks (GNNs) have shown promise in accelerating MILP solvers by predicting high-quality solutions. However, we identify that existing methods misalign with the intrinsic structure of MILP problems at two levels. At the leaning objective level, the Binary Cross-Entropy (BCE) loss treats variables independently, neglecting their relative priority and yielding plausible logits. At the model architecture level, standard GNN message passing inherently smooths the representations across variables, missing the natural competitive relationships within constraints. To address these challenges, we propose CoCo-MILP, which explicitly models inter-variable Contrast and intra-constraint Competition for advanced MILP solution prediction. At the objective level, CoCo-MILP introduces the Inter-Variable Contrastive Loss (VCL), which explicitly maximizes the embedding margin between variables assigned one versus zero. At the architectural level, we design an Intra-Constraint Competitive GNN layer that, instead of homogenizing features, learns to differentiate representations of competing variables within a constraint, capturing their exclusionary nature. Experimental results on standard benchmarks demonstrate that CoCo-MILP significantly outperforms existing learning-based approaches, reducing the solution gap by up to 68.12% compared to traditional solvers. Our code is available at https://github.com/happypu326/CoCo-MILP.

Paperid: 772, https://arxiv.org/pdf/2511.09190.pdf GitHub

Abstract:
Hyperparameter Optimization (HPO) can lift the burden of tuning hyperparameters (HPs) of neural networks. HPO algorithms from the Population Based Training (PBT) family are efficient thanks to dynamically adjusting HPs every few steps of the weight optimization. Recent results indicate that the number of steps between HP updates is an important meta-HP of all PBT variants that can substantially affect their performance. Yet, no method or intuition is available for efficiently setting its value. We introduce Iterated Population Based Training (IPBT), a novel PBT variant that automatically adjusts this HP via restarts that reuse weight information in a task-agnostic way and leverage time-varying Bayesian optimization to reinitialize HPs. Evaluation on 8 image classification and reinforcement learning tasks shows that, on average, our algorithm matches or outperforms 5 previous PBT variants and other HPO algorithms (random search, ASHA, SMAC3), without requiring a budget increase or any changes to its HPs. The source code is available at https://github.com/AwesomeLemon/IPBT.

Paperid: 773, https://arxiv.org/pdf/2511.09147.pdf GitHub

Abstract:
Multi-person global human mesh recovery (HMR) is crucial for understanding crowd dynamics and interactions. Traditional vision-based HMR methods sometimes face limitations in real-world scenarios due to mutual occlusions, insufficient lighting, and privacy concerns. Human-floor tactile interactions offer an occlusion-free and privacy-friendly alternative for capturing human motion. Existing research indicates that pressure signals acquired from tactile mats can effectively estimate human pose in single-person scenarios. However, when multiple individuals walk randomly on the mat simultaneously, how to distinguish intermingled pressure signals generated by different persons and subsequently acquire individual temporal pressure data remains a pending challenge for extending pressure-based HMR to the multi-person situation. In this paper, we present \textbf{PressTrack-HMR}, a top-down pipeline that recovers multi-person global human meshes solely from pressure signals. This pipeline leverages a tracking-by-detection strategy to first identify and segment each individual's pressure signal from the raw pressure data, and subsequently performs HMR for each extracted individual signal. Furthermore, we build a multi-person interaction pressure dataset \textbf{MIP}, which facilitates further research into pressure-based human motion analysis in multi-person scenarios. Experimental results demonstrate that our method excels in multi-person HMR using pressure data, with 89.2 $mm$ MPJPE and 112.6 $mm$ WA-MPJPE$_{100}$, and these showcase the potential of tactile mats for ubiquitous, privacy-preserving multi-person action recognition. Our dataset & code are available at https://github.com/Jiayue-Yuan/PressTrack-HMR.

Paperid: 774, https://arxiv.org/pdf/2511.09138.pdf GitHub

Abstract:
Class imbalance has been extensively studied in single-view scenarios; however, addressing this challenge in multi-view contexts remains an open problem, with even scarcer research focusing on trustworthy solutions. In this paper, we tackle a particularly challenging class imbalance problem in multi-view scenarios: long-tailed classification. We propose TMLC, a Trusted Multi-view Long-tailed Classification framework, which makes contributions on two critical aspects: opinion aggregation and pseudo-data generation. Specifically, inspired by Social Identity Theory, we design a group consensus opinion aggregation mechanism that guides decision making toward the direction favored by the majority of the group. In terms of pseudo-data generation, we introduce a novel distance metric to adapt SMOTE for multi-view scenarios and develop an uncertainty-guided data generation module that produces high-quality pseudo-data, effectively mitigating the adverse effects of class imbalance. Extensive experiments on long-tailed multi-view datasets demonstrate that our model is capable of achieving superior performance. The code is released at https://github.com/cncq-tang/TMLC.

Paperid: 775, https://arxiv.org/pdf/2511.09131.pdf GitHub

Abstract:
Simulation-based fault injection is a widely adopted methodology for assessing circuit vulnerability to Single Event Upsets (SEUs); however, its computational cost grows significantly with circuit complexity. To address this limitation, this work introduces an open-source platform that exploits Spatio-Temporal Graph Neural Networks (STGNNs) to accelerate SEU fault simulation. The platform includes three STGNN architectures incorporating advanced components such as Atrous Spatial Pyramid Pooling (ASPP) and attention mechanisms, thereby improving spatio-temporal feature extraction. In addition, SEU fault simulation datasets are constructed from six open-source circuits with varying levels of complexity, providing a comprehensive benchmark for performance evaluation. The predictive capability of the STGNN models is analyzed and compared on these datasets. Moreover, to further investigate the efficiency of the approach, we evaluate the predictive capability of STGNNs across multiple test cases and discuss their generalization capability. The developed platform and datasets are released as open-source to support reproducibility and further research on https://github.com/luli2021/FsimNNs.

Paperid: 776, https://arxiv.org/pdf/2511.09117.pdf GitHub

Abstract:
Kuzushiji, a pre-modern Japanese cursive script, can currently be read and understood by only a few thousand trained experts in Japan. With the rapid development of deep learning, researchers have begun applying Optical Character Recognition (OCR) techniques to transcribe Kuzushiji into modern Japanese. Although existing OCR methods perform well on clean pre-modern Japanese documents written in Kuzushiji, they often fail to consider various types of noise, such as document degradation and seals, which significantly affect recognition accuracy. To the best of our knowledge, no existing dataset specifically addresses these challenges. To address this gap, we introduce the Degraded Kuzushiji Documents with Seals (DKDS) dataset as a new benchmark for related tasks. We describe the dataset construction process, which required the assistance of a trained Kuzushiji expert, and define two benchmark tracks: (1) text and seal detection and (2) document binarization. For the text and seal detection track, we provide baseline results using multiple versions of the You Only Look Once (YOLO) models for detecting Kuzushiji characters and seals. For the document binarization track, we present baseline results from traditional binarization algorithms, traditional algorithms combined with K-means clustering, and Generative Adversarial Network (GAN)-based methods. The DKDS dataset and the implementation code for baseline methods are available at https://ruiyangju.github.io/DKDS.

Paperid: 777, https://arxiv.org/pdf/2511.09091.pdf GitHub

Abstract:
Learning natural, animal-like locomotion from demonstrations has become a core paradigm in legged robotics. Despite the recent advancements in motion tracking, most existing methods demand extensive tuning and rely on reference data during deployment, limiting adaptability. We present APEX (Action Priors enable Efficient Exploration), a plug-and-play extension to state-of-the-art motion tracking algorithms that eliminates any dependence on reference data during deployment, improves sample efficiency, and reduces parameter tuning effort. APEX integrates expert demonstrations directly into reinforcement learning (RL) by incorporating decaying action priors, which initially bias exploration toward expert demonstrations but gradually allow the policy to explore independently. This is combined with a multi-critic framework that balances task performance with motion style. Moreover, APEX enables a single policy to learn diverse motions and transfer reference-like styles across different terrains and velocities, while remaining robust to variations in reward design. We validate the effectiveness of our method through extensive experiments in both simulation and on a Unitree Go2 robot. By leveraging demonstrations to guide exploration during RL training, without imposing explicit bias toward them, APEX enables legged robots to learn with greater stability, efficiency, and generalization. We believe this approach paves the way for guidance-driven RL to boost natural skill acquisition in a wide array of robotic tasks, from locomotion to manipulation. Website and code: https://marmotlab.github.io/APEX/.

Paperid: 778, https://arxiv.org/pdf/2511.09090.pdf GitHub

Abstract:
Video-to-music (V2M) generation aims to create music that aligns with visual content. However, two main challenges persist in existing methods: (1) the lack of explicit rhythm modeling hinders audiovisual temporal alignments; (2) effectively integrating various visual features to condition music generation remains non-trivial. To address these issues, we propose Diff-V2M, a general V2M framework based on a hierarchical conditional diffusion model, comprising two core components: visual feature extraction and conditional music generation. For rhythm modeling, we begin by evaluating several rhythmic representations, including low-resolution mel-spectrograms, tempograms, and onset detection functions (ODF), and devise a rhythmic predictor to infer them directly from videos. To ensure contextual and affective coherence, we also extract semantic and emotional features. All features are incorporated into the generator via a hierarchical cross-attention mechanism, where emotional features shape the affective tone via the first layer, while semantic and rhythmic features are fused in the second cross-attention layer. To enhance feature integration, we introduce timestep-aware fusion strategies, including feature-wise linear modulation (FiLM) and weighted fusion, allowing the model to adaptively balance semantic and rhythmic cues throughout the diffusion process. Extensive experiments identify low-resolution ODF as a more effective signal for modeling musical rhythm and demonstrate that Diff-V2M outperforms existing models on both in-domain and out-of-domain datasets, achieving state-of-the-art performance in terms of objective metrics and subjective comparisons. Demo and code are available at https://Tayjsl97.github.io/Diff-V2M-Demo/.

Paperid: 779, https://arxiv.org/pdf/2511.09067.pdf GitHub

Abstract:
The ability of critique is vital for models to self-improve and serve as reliable AI assistants. While extensively studied in language-only settings, multimodal critique of Large Multimodal Models (LMMs) remains underexplored despite their growing capabilities in tasks like captioning and visual reasoning. In this work, we introduce MM-CRITIC, a holistic benchmark for evaluating the critique ability of LMMs across multiple dimensions: basic, correction, and comparison. Covering 8 main task types and over 500 tasks, MM-CRITIC collects responses from various LMMs with different model sizes and is composed of 4471 samples. To enhance the evaluation reliability, we integrate expert-informed ground answers into scoring rubrics that guide GPT-4o in annotating responses and generating reference critiques, which serve as anchors for trustworthy judgments. Extensive experiments validate the effectiveness of MM-CRITIC and provide a comprehensive assessment of leading LMMs' critique capabilities under multiple dimensions. Further analysis reveals some key insights, including the correlation between response quality and critique, and varying critique difficulty across evaluation dimensions. Our code is available at https://github.com/MichealZeng0420/MM-Critic.

Paperid: 780, https://arxiv.org/pdf/2511.09064.pdf GitHub

Abstract:
Vision-language pre-training models (VLPs) demonstrate strong multimodal understanding and zero-shot generalization, yet remain vulnerable to adversarial examples, raising concerns about their reliability. Recent work, Test-Time Counterattack (TTC), improves robustness by generating perturbations that maximize the embedding deviation of adversarial inputs using PGD, pushing them away from their adversarial representations. However, due to the fundamental difference in optimization objectives between adversarial attacks and counterattacks, generating counterattacks solely based on gradients with respect to the adversarial input confines the search to a narrow space. As a result, the counterattacks could overfit limited adversarial patterns and lack the diversity to fully neutralize a broad range of perturbations. In this work, we argue that enhancing the diversity and coverage of counterattacks is crucial to improving adversarial robustness in test-time defense. Accordingly, we propose Directional Orthogonal Counterattack (DOC), which augments counterattack optimization by incorporating orthogonal gradient directions and momentum-based updates. This design expands the exploration of the counterattack space and increases the diversity of perturbations, which facilitates the discovery of more generalizable counterattacks and ultimately improves the ability to neutralize adversarial perturbations. Meanwhile, we present a directional sensitivity score based on averaged cosine similarity to boost DOC by improving example discrimination and adaptively modulating the counterattack strength. Extensive experiments on 16 datasets demonstrate that DOC improves adversarial robustness under various attacks while maintaining competitive clean accuracy. Code is available at https://github.com/bookman233/DOC.

Paperid: 781, https://arxiv.org/pdf/2511.09063.pdf GitHub

Abstract:
Vision-Language Models (VLMs), with their powerful content generation capabilities, have been successfully applied to data annotation processes. However, the VLM-generated labels exhibit dual limitations: low quality (i.e., label noise) and absence of error correction mechanisms. To enhance label quality, we propose Human-Corrected Labels (HCLs), a novel setting that efficient human correction for VLM-generated noisy labels. As shown in Figure 1(b), HCL strategically deploys human correction only for instances with VLM discrepancies, achieving both higher-quality annotations and reduced labor costs. Specifically, we theoretically derive a risk-consistent estimator that incorporates both human-corrected labels and VLM predictions to train classifiers. Besides, we further propose a conditional probability method to estimate the label distribution using a combination of VLM outputs and model predictions. Extensive experiments demonstrate that our approach achieves superior classification performance and is robust to label noise, validating the effectiveness of HCL in practical weak supervision scenarios. Code https://github.com/Lilianach24/HCL.git

Paperid: 782, https://arxiv.org/pdf/2511.09045.pdf GitHub

Abstract:
Ground-based remote sensing cloud image sequence extrapolation is a key research area in the development of photovoltaic power systems. However, existing approaches exhibit several limitations:(1)they primarily rely on static kernels to augment feature information, lacking adaptive mechanisms to extract features at varying resolutions dynamically;(2)temporal guidance is insufficient, leading to suboptimal modeling of long-range spatiotemporal dependencies; and(3)the quadratic computational cost of attention mechanisms is often overlooked, limiting efficiency in practical deployment. To address these challenges, we propose USF-Net, a Unified Spatiotemporal Fusion Network that integrates adaptive large-kernel convolutions and a low-complexity attention mechanism, combining temporal flow information within an encoder-decoder framework. Specifically, the encoder employs three basic layers to extract features. Followed by the USTM, which comprises:(1)a SiB equipped with a SSM that dynamically captures multi-scale contextual information, and(2)a TiB featuring a TAM that effectively models long-range temporal dependencies while maintaining computational efficiency. In addition, a DSM with a TGM is introduced to enable unified modeling of temporally guided spatiotemporal dependencies. On the decoder side, a DUM is employed to address the common "ghosting effect." It utilizes the initial temporal state as an attention operator to preserve critical motion signatures. As a key contribution, we also introduce and release the ASI-CIS dataset. Extensive experiments on ASI-CIS demonstrate that USF-Net significantly outperforms state-of-the-art methods, establishing a superior balance between prediction accuracy and computational efficiency for ground-based cloud extrapolation. The dataset and source code will be available at https://github.com/she1110/ASI-CIS.

Paperid: 783, https://arxiv.org/pdf/2511.09022.pdf GitHub

Abstract:
Radar-based human activity recognition (HAR) still lacks a comprehensive simulation method. Existing software is developed based on models or motion-captured data, resulting in limited flexibility. To address this issue, a simulator that directly generates Doppler spectra from recorded video footage (RadHARSimulator V2) is presented in this paper. Both computer vision and radar modules are included in the simulator. In computer vision module, the real-time model for object detection with global nearest neighbor is first used to detect and track human targets in the video. Then, the high-resolution network is used to estimate two-dimensional poses of the detected human targets. Next, the three-dimensional poses of the detected human targets are obtained by nearest matching method. Finally, smooth temporal three-dimensional pose estimation is achieved through Kalman filtering. In radar module, pose interpolation and smoothing are first achieved through the Savitzky-Golay method. Second, the delay model and the mirror method are used to simulate echoes in both free-space and through-the-wall scenarios. Then, range-time map is generated using pulse compression, moving target indication, and DnCNN. Next, Doppler-time map (DTM) is generated using short-time Fourier transform and DnCNN again. Finally, the ridge features on the DTM are extracted using the maximum local energy method. In addition, a hybrid parallel-serial neural network architecture is proposed for radar-based HAR. Numerical experiments are conducted and analyzed to demonstrate the effectiveness of the designed simulator and the proposed network model. The open-source code of this work can be found in: https://github.com/JoeyBGOfficial/RadHARSimulatorV2-Video-to-Doppler-Generator.

Paperid: 784, https://arxiv.org/pdf/2511.09018.pdf GitHub

Abstract:
Object hallucination remains a critical challenge in Large Vision-Language Models (LVLMs), where models generate content inconsistent with visual inputs. Existing language-decoder based mitigation approaches often regulate visual or textual attention independently, overlooking their interaction as two key causal factors. To address this, we propose Owl (Bi-mOdal attention reWeighting for Layer-wise hallucination mitigation), a causally-grounded framework that models hallucination process via a structural causal graph, treating decomposed visual and textual attentions as mediators. We introduce VTACR (Visual-to-Textual Attention Contribution Ratio), a novel metric that quantifies the modality contribution imbalance during decoding. Our analysis reveals that hallucinations frequently occur in low-VTACR scenarios, where textual priors dominate and visual grounding is weakened. To mitigate this, we design a fine-grained attention intervention mechanism that dynamically adjusts token- and layer-wise attention guided by VTACR signals. Finally, we propose a dual-path contrastive decoding strategy: one path emphasizes visually grounded predictions, while the other amplifies hallucinated ones -- letting visual truth shine and hallucination collapse. Experimental results on the POPE and CHAIR benchmarks show that Owl achieves significant hallucination reduction, setting a new SOTA in faithfulness while preserving vision-language understanding capability. Our code is available at https://github.com/CikZ2023/OWL

Paperid: 785, https://arxiv.org/pdf/2511.09005.pdf GitHub

Abstract:
Although Large Language Models (LLMs) show exceptional fluency, efforts persist to extract stronger reasoning capabilities from them. Drawing on search-based interpretations of LLM computation, this paper advances a systematic framework for understanding LLM reasoning and optimization. Namely, that enhancing reasoning is best achieved by structuring a multi-agent pipeline to ensure a traversal of the search space in a gradual, incremental, and sequential (GIS) manner. Stated succinctly, high-quality reasoning is a controlled, incremental search. To test this framework, we investigate the efficacy of recursive refinement (RR)--an iterative process of self-criticism, adversarial stress-testing, and integrating critical feedback--as a practical method for implementing GIS search. We designed an experiment comparing a simple, linear pipeline against a complex, explicitly structured pipeline leveraging a recursive refinement layer. The multi-agent models were constructed to reflect the historical personas of three US Founding Fathers (Hamilton, Jefferson, and Madison) using RAG-powered corpora and were prompted to generate responses to three contemporary political issues. Model performance was evaluated using a two-tiered approach: a quantitative score from an LLM arbiter agent and qualitative human judgment. Our results revealed that the complex model consistently outperformed the simple model across all nine test cases with an average arbiter-outputted score of 88.3 versus 71.7. The complex model's arguments were superior in analytical depth, structural nuance, and strategic framing. We conclude that recursive refinement is a robust architectural feature for enhancing LLM reasoning via GIS search.

Paperid: 786, https://arxiv.org/pdf/2511.08947.pdf GitHub

Abstract:
Time series forecasting plays a critical role in high-stakes domains such as energy, healthcare, and climate. Although recent advances have improved accuracy, most approaches still treat forecasting as a static one-time mapping task, lacking the interaction, reasoning, and adaptability of human experts. This gap limits their usefulness in complex real-world environments. To address this, we propose AlphaCast, a human wisdom-large language model (LLM) intelligence co-reasoning framework that redefines forecasting as an interactive process. The key idea is to enable step-by-step collaboration between human wisdom and LLM intelligence to jointly prepare, generate, and verify forecasts. The framework consists of two stages: (1) automated prediction preparation, where AlphaCast builds a multi-source cognitive foundation comprising a feature set that captures key statistics and time patterns, a domain knowledge base distilled from corpora and historical series, a contextual repository that stores rich information for each time window, and a case base that retrieves optimal strategies via pattern clustering and matching; and (2) generative reasoning and reflective optimization, where AlphaCast integrates statistical temporal features, prior knowledge, contextual information, and forecasting strategies, triggering a meta-reasoning loop for continuous self-correction and strategy refinement. Extensive experiments on short- and long-term datasets show that AlphaCast consistently outperforms state-of-the-art baselines in predictive accuracy. Code is available at this repository: https://github.com/SkyeGT/AlphaCast_Official .

Paperid: 787, https://arxiv.org/pdf/2511.08938.pdf GitHub

Abstract:
Neural video compression (NVC) has made significant progress in recent years, while neural B-frame video compression (NBVC) remains underexplored compared to P-frame compression. NBVC can adopt bi-directional reference frames for better compression performance. However, NBVC's hierarchical coding may complicate continuous temporal prediction, especially at some hierarchical levels with a large frame span, which could cause the contribution of the two reference frames to be unbalanced. To optimize reference information utilization, we propose a novel NBVC method, termed Bi-directional Reference Harmonization Video Compression (BRHVC), with the proposed Bi-directional Motion Converge (BMC) and Bi-directional Contextual Fusion (BCF). BMC converges multiple optical flows in motion compression, leading to more accurate motion compensation on a larger scale. Then BCF explicitly models the weights of reference contexts under the guidance of motion compensation accuracy. With more efficient motions and contexts, BRHVC can effectively harmonize bi-directional references. Experimental results indicate that our BRHVC outperforms previous state-of-the-art NVC methods, even surpassing the traditional coding, VTM-RA (under random access configuration), on the HEVC datasets. The source code is released at https://github.com/kwai/NVC.

Paperid: 788, https://arxiv.org/pdf/2511.08914.pdf GitHub

Abstract:
Deploying Vision-Language Models (VLMs) on edge devices (e.g., smartphones and robots) is crucial for enabling low-latency and privacy-preserving intelligent applications. Given the resource constraints of these devices, quantization offers a promising solution by improving memory efficiency and reducing bandwidth requirements, thereby facilitating the deployment of VLMs. However, existing research has rarely explored aggressive quantization on VLMs, particularly for the models ranging from 1B to 2B parameters, which are more suitable for resource-constrained edge devices. In this paper, we propose SPEED-Q, a novel Staged Processing with Enhanced Distillation framework for VLM low-bit weight-only quantization that systematically addresses the following two critical obstacles: (1) significant discrepancies in quantization sensitivity between vision (ViT) and language (LLM) components in VLMs; (2) training instability arising from the reduced numerical precision inherent in low-bit quantization. In SPEED-Q, a staged sensitivity adaptive mechanism is introduced to effectively harmonize performance across different modalities. We further propose a distillation-enhanced quantization strategy to stabilize the training process and reduce data dependence. Together, SPEED-Q enables accurate, stable, and data-efficient quantization of complex VLMs. SPEED-Q is the first framework tailored for quantizing entire small-scale billion-parameter VLMs to low bits. Extensive experiments across multiple benchmarks demonstrate that SPEED-Q achieves up to 6x higher accuracy than existing quantization methods under 2-bit settings and consistently outperforms prior on-device VLMs under both 2-bit and 4-bit settings. Our code and models are available at https://github.com/antgroup/SPEED-Q.

Paperid: 789, https://arxiv.org/pdf/2511.08909.pdf GitHub

Abstract:
Text-only training provides an attractive approach to address data scarcity challenges in zero-shot image captioning (ZIC), avoiding the expense of collecting paired image-text annotations. However, although these approaches perform well within training domains, they suffer from poor cross-domain generalization, often producing hallucinated content when encountering novel visual environments. Retrieval-based methods attempt to mitigate this limitation by leveraging external knowledge, but they can paradoxically exacerbate hallucination when retrieved captions contain entities irrelevant to the inputs. We introduce the concept of negative entities--objects that appear in generated caption but are absent from the input--and propose Negative Entity Suppression (NES) to tackle this challenge. NES seamlessly integrates three stages: (1) it employs synthetic images to ensure consistent image-to-text retrieval across both training and inference; (2) it filters negative entities from retrieved content to enhance accuracy; and (3) it applies attention-level suppression using identified negative entities to further minimize the impact of hallucination-prone features. Evaluation across multiple benchmarks demonstrates that NES maintains competitive in-domain performance while improving cross-domain transfer and reducing hallucination rates, achieving new state-of-the-art results in ZIC. Our code is available at https://github.com/nidongpinyinme/NESCap.

Paperid: 790, https://arxiv.org/pdf/2511.08896.pdf GitHub

Abstract:
Glioblastoma (GBM) is the most common aggressive, fast-growing brain tumor, with a grim prognosis. Despite clinical diagnostic advancements, there have not been any substantial improvements to patient prognosis. Histopathological assessment of excised tumors is the first line of clinical diagnostic routine. We hypothesize that automated, robust, and accurate identification of distinct histological sub-regions within GBM could contribute to morphologically understanding this disease at scale. In this study, we designed a four-step deep learning approach to classify six (6) histopathological regions and quantitatively evaluated it on the BraTS-Path 2024 challenge dataset, which includes digitized Hematoxylin \& Eosin (H\&E) stained GBM tissue sections annotated for six distinct regions. We used the challenge's publicly available training dataset to develop and evaluate the effectiveness of several variants of EfficientNet architectures (i.e., B0, B1, B2, B3, B4). EfficientNet-B1 and EfficientNet-B4 achieved the best performance, achieving an F1 score of 0.98 in a 5-fold cross-validation configuration using the BraTS-Path training set. The quantitative performance evaluation of our proposed approach with EfficientNet-B1 on the BraTS-Path hold-out validation data and the final hidden testing data yielded F1 scores of 0.546 and 0.517, respectively, for the associated 6-class classification task. The difference in the performance on training, validation, and testing data highlights the challenge of developing models that generalize well to new data, which is crucial for clinical applications. The source code of the proposed approach can be found at the GitHub repository of Indiana University Division of Computational Pathology: https://github.com/IUCompPath/brats-path-2024-enet.

Paperid: 791, https://arxiv.org/pdf/2511.08873.pdf GitHub

Abstract:
Large language models (LLMs) are shifting from answer providers to intelligent tutors in educational settings, yet current supervised fine-tuning methods only learn surface teaching patterns without dynamic adaptation capabilities. Recent reinforcement learning approaches address this limitation but face two critical challenges. First, they evaluate teaching effectiveness solely based on whether students produce correct outputs, unable to distinguish whether students genuinely understand or echo teacher-provided answers during interaction. Second, they cannot perceive students' evolving cognitive states in real time through interactive dialogue, thus failing to adapt teaching strategies to match students' cognitive levels dynamically. We propose the Unidirectional Cognitive Optimization (UCO) method to address these challenges. UCO uses a multi-turn interactive reinforcement learning paradigm where the innovation lies in two synergistic reward functions: the Progress Reward captures students' cognitive advancement, evaluating whether students truly transition from confusion to comprehension, while the Scaffold Reward dynamically identifies each student's Zone of Proximal Development (ZPD), encouraging teachers to maintain productive teaching within this zone. We evaluate UCO by comparing it against 11 baseline models on BigMath and MathTutorBench benchmarks. Experimental results demonstrate that our UCO model outperforms all models of equivalent scale and achieves performance comparable to advanced closed-source models. The code and data are available at https://github.com/Mind-Lab-ECNU/UCO.

Paperid: 792, https://arxiv.org/pdf/2511.08872.pdf GitHub

Abstract:
Recently, the Mamba architecture based on State Space Models (SSMs) has gained attention in 3D human pose estimation due to its linear complexity and strong global modeling capability. However, existing SSM-based methods typically apply manually designed scan operations to flatten detected 2D pose sequences into purely temporal sequences, either locally or globally. This approach disrupts the inherent spatial structure of human poses and entangles spatial and temporal features, making it difficult to capture complex pose dependencies. To address these limitations, we propose the Skeleton Structure-Aware Stride SSM (SAS-SSM), which first employs a structure-aware spatiotemporal convolution to dynamically capture essential local interactions between joints, and then applies a stride-based scan strategy to construct multi-scale global structural representations. This enables flexible modeling of both local and global pose information while maintaining linear computational complexity. Built upon SAS-SSM, our model SasMamba achieves competitive 3D pose estimation performance with significantly fewer parameters compared to existing hybrid models. The source code is available at https://hucui2022.github.io/sasmamba_proj/.

Paperid: 793, https://arxiv.org/pdf/2511.08861.pdf GitHub

Abstract:
Foundation models for EEG analysis are still in their infancy, limited by two key challenges: (1) variability across datasets caused by differences in recording devices and configurations, and (2) the low signal-to-noise ratio (SNR) of EEG, where brain signals are often buried under artifacts and non-brain sources. To address these challenges, we present EEG-X, a device-agnostic and noise-robust foundation model for EEG representation learning. EEG-X introduces a novel location-based channel embedding that encodes spatial information and improves generalization across domains and tasks by allowing the model to handle varying channel numbers, combinations, and recording lengths. To enhance robustness against noise, EEG-X employs a noise-aware masking and reconstruction strategy in both raw and latent spaces. Unlike previous models that mask and reconstruct raw noisy EEG signals, EEG-X is trained to reconstruct denoised signals obtained through an artifact removal process, ensuring that the learned representations focus on neural activity rather than noise. To further enhance reconstruction-based pretraining, EEG-X introduces a dictionary-inspired convolutional transformation (DiCT) layer that projects signals into a structured feature space before computing reconstruction (MSE) loss, reducing noise sensitivity and capturing frequency- and shape-aware similarities. Experiments on datasets collected from diverse devices show that EEG-X outperforms state-of-the-art methods across multiple downstream EEG tasks and excels in cross-domain settings where pre-trained and downstream datasets differ in electrode layouts. The models and code are available at: https://github.com/Emotiv/EEG-X

Paperid: 794, https://arxiv.org/pdf/2511.08846.pdf GitHub

Abstract:
Topological descriptors have been increasingly utilized for capturing multiscale structural information in relational data. In this work, we consider various filtrations on the (box) product of graphs and the effect on their outputs on the topological descriptors - the Euler characteristic (EC) and persistent homology (PH). In particular, we establish a complete characterization of the expressive power of EC on general color-based filtrations. We also show that the PH descriptors of (virtual) graph products contain strictly more information than the computation on individual graphs, whereas EC does not. Additionally, we provide algorithms to compute the PH diagrams of the product of vertex- and edge-level filtrations on the graph product. We also substantiate our theoretical analysis with empirical investigations on runtime analysis, expressivity, and graph classification performance. Overall, this work paves way for powerful graph persistent descriptors via product filtrations. Code is available at https://github.com/Aalto-QuML/tda_graph_product.

Paperid: 795, https://arxiv.org/pdf/2511.08832.pdf GitHub

Abstract:
In this paper, we propose capturing and utilizing \textit{Temporal Information through Graph-based Embeddings and Representations} or \textbf{TIGER} to enhance multi-agent reinforcement learning (MARL). We explicitly model how inter-agent coordination structures evolve over time. While most MARL approaches rely on static or per-step relational graphs, they overlook the temporal evolution of interactions that naturally arise as agents adapt, move, or reorganize cooperation strategies. Capturing such evolving dependencies is key to achieving robust and adaptive coordination. To this end, TIGER constructs dynamic temporal graphs of MARL agents, connecting their current and historical interactions. It then employs a temporal attention-based encoder to aggregate information across these structural and temporal neighborhoods, yielding time-aware agent embeddings that guide cooperative policy learning. Through extensive experiments on two coordination-intensive benchmarks, we show that TIGER consistently outperforms diverse value-decomposition and graph-based MARL baselines in task performance and sample efficiency. Furthermore, we conduct comprehensive ablation studies to isolate the impact of key design parameters in TIGER, revealing how structural and temporal factors can jointly shape effective policy learning in MARL. All codes can be found here: https://github.com/Nikunj-Gupta/tiger-marl.

Paperid: 796, https://arxiv.org/pdf/2511.08747.pdf GitHub

Abstract:
The Abstraction and Reasoning Corpus for Artificial General Intelligence (ARC-AGI) is a generative, few-shot fluid intelligence benchmark. Although humans effortlessly solve ARC-AGI, it remains extremely difficult for even the most advanced artificial intelligence systems. Inspired by methods for modelling human intelligence spanning neuroscience to psychology, we propose a cognitively plausible ARC-AGI solver. Our solver integrates System 1 intuitions with System 2 reasoning in an efficient and interpretable process using neurosymbolic methods based on Vector Symbolic Algebras (VSAs). Our solver works by object-centric program synthesis, leveraging VSAs to represent abstract objects, guide solution search, and enable sample-efficient neural learning. Preliminary results indicate success, with our solver scoring 10.8% on ARC-AGI-1-Train and 3.0% on ARC-AGI-1-Eval. Additionally, our solver performs well on simpler benchmarks, scoring 94.5% on Sort-of-ARC and 83.1% on 1D-ARC -- the latter outperforming GPT-4 at a tiny fraction of the computational cost. Importantly, our approach is unique; we believe we are the first to apply VSAs to ARC-AGI and have developed the most cognitively plausible ARC-AGI solver yet. Our code is available at: https://github.com/ijoffe/ARC-VSA-2025.

Paperid: 797, https://arxiv.org/pdf/2511.08721.pdf GitHub

Abstract:
In behavioral sciences, experiments such as the ultimatum game are conducted to assess preferences for fairness or self-interest of study participants. In the dictator game, a simplified version of the ultimatum game where only one of two players makes a single decision, the dictator unilaterally decides how to split a fixed sum of money between themselves and the other player. Although recent studies have explored behavioral patterns of AI agents based on Large Language Models (LLMs) instructed to adopt different personas, we question the robustness of these results. In particular, many of these studies overlook the role of the system prompt - the underlying instructions that shape the model's behavior - and do not account for how sensitive results can be to slight changes in prompts. However, a robust baseline is essential when studying highly complex behavioral aspects of LLMs. To overcome previous limitations, we propose the LLM agent behavior study (LLM-ABS) framework to (i) explore how different system prompts influence model behavior, (ii) get more reliable insights into agent preferences by using neutral prompt variations, and (iii) analyze linguistic features in responses to open-ended instructions by LLM agents to better understand the reasoning behind their behavior. We found that agents often exhibit a strong preference for fairness, as well as a significant impact of the system prompt on their behavior. From a linguistic perspective, we identify that models express their responses differently. Although prompt sensitivity remains a persistent challenge, our proposed framework demonstrates a robust foundation for LLM agent behavior studies. Our code artifacts are available at https://github.com/andreaseinwiller/LLM-ABS.

Paperid: 798, https://arxiv.org/pdf/2511.08717.pdf GitHub

Abstract:
Optimal control of the future is the next frontier for AI. Current approaches to this problem are typically rooted in either reinforcement learning or online learning. While powerful, these frameworks for learning are mathematically distinct from Probably Approximately Correct (PAC) learning, which has been the workhorse for the recent technological achievements in AI. We therefore build on the prior work of prospective learning, an extension of PAC learning (without control) in non-stationary environments (De Silva et al., 2023; Silva et al., 2024; Bai et al., 2026). Here, we further extend the PAC learning framework to address learning and control in non-stationary environments. Using this framework, called ''Prospective Control'', we prove that under certain fairly general assumptions, empirical risk minimization (ERM) asymptotically achieves the Bayes optimal policy. We then consider a specific instance of prospective control, foraging, which is a canonical task for any mobile agent, be it natural or artificial. We illustrate that existing reinforcement learning algorithms fail to learn in these non-stationary environments, and even with modifications, they are orders of magnitude less efficient than our prospective foraging agents. Code is available at: https://github.com/neurodata/ProspectiveLearningwithControl.

Paperid: 799, https://arxiv.org/pdf/2511.08708.pdf GitHub

Abstract:
Recent advancements in the direct training of Spiking Neural Networks (SNNs) have demonstrated high-quality outputs even at early timesteps, paving the way for novel energy-efficient AI paradigms. However, the inherent non-linearity and temporal dependencies in SNNs introduce persistent challenges, such as temporal covariate shift (TCS) and unstable gradient flow with learnable neuron thresholds. In this paper, we present two key innovations: MP-Init (Membrane Potential Initialization) and TrSG (Threshold-robust Surrogate Gradient). MP-Init addresses TCS by aligning the initial membrane potential with its stationary distribution, while TrSG stabilizes gradient flow with respect to threshold voltage during training. Extensive experiments validate our approach, achieving state-of-the-art accuracy on both static and dynamic image datasets. The code is available at: https://github.com/kookhh0827/SNN-MP-Init-TRSG

Paperid: 800, https://arxiv.org/pdf/2511.08702.pdf GitHub

Abstract:
As machine learning systems move from theory to practice, they are increasingly tasked with decisions that affect healthcare access, financial opportunities, hiring, and public services. In these contexts, accuracy is only one piece of the puzzle - models must also be fair to different groups, protect individual privacy, and remain accountable to stakeholders. Achieving all three is difficult: differential privacy can unintentionally worsen disparities, fairness interventions often rely on sensitive data that privacy restricts, and automated pipelines ignore that fairness is ultimately a human and contextual judgment. We introduce FAIRPLAI (Fair and Private Learning with Active Human Influence), a practical framework that integrates human oversight into the design and deployment of machine learning systems. FAIRPLAI works in three ways: (1) it constructs privacy-fairness frontiers that make trade-offs between accuracy, privacy guarantees, and group outcomes transparent; (2) it enables interactive stakeholder input, allowing decision-makers to select fairness criteria and operating points that reflect their domain needs; and (3) it embeds a differentially private auditing loop, giving humans the ability to review explanations and edge cases without compromising individual data security. Applied to benchmark datasets, FAIRPLAI consistently preserves strong privacy protections while reducing fairness disparities relative to automated baselines. More importantly, it provides a straightforward, interpretable process for practitioners to manage competing demands of accuracy, privacy, and fairness in socially impactful applications. By embedding human judgment where it matters most, FAIRPLAI offers a pathway to machine learning systems that are effective, responsible, and trustworthy in practice. GitHub: https://github.com/Li1Davey/Fairplai

Paperid: 801, https://arxiv.org/pdf/2511.08697.pdf GitHub

Abstract:
Accurate and efficient simulations of physical phenomena governed by partial differential equations (PDEs) are important for scientific and engineering progress. While traditional numerical solvers are powerful, they are often computationally expensive. Recently, data-driven methods have emerged as alternatives, but they frequently suffer from error accumulation and limited physical consistency, especially in multiphysics and complex geometries. To address these challenges, we propose PEGNet, a Physics-Embedded Graph Network that incorporates PDE-guided message passing to redesign the graph neural network architecture. By embedding key PDE dynamics like convection, viscosity, and diffusion into distinct message functions, the model naturally integrates physical constraints into its forward propagation, producing more stable and physically consistent solutions. Additionally, a hierarchical architecture is employed to capture multi-scale features, and physical regularization is integrated into the loss function to further enforce adherence to governing physics. We evaluated PEGNet on benchmarks, including custom datasets for respiratory airflow and drug delivery, showing significant improvements in long-term prediction accuracy and physical consistency over existing methods. Our code is available at https://github.com/Yanghuoshan/PEGNet.

Paperid: 802, https://arxiv.org/pdf/2511.08653.pdf GitHub

Abstract:
Recursive reasoning models achieve remarkable performance on complex reasoning tasks through iterative refinement, enabling tiny networks to match large language models thousands of times their size. However, training remains computationally expensive, prior work reporting approximately 36 GPU-hours per dataset, limiting broader adoption and research. We propose CGAR, a novel training methodology that applies curriculum learning to architectural depth rather than traditional data ordering. CGAR introduces two synergistic components: Progressive Depth Curriculum dynamically adjusts recursion depth from shallow to deep configurations during training, preventing early overfitting while reducing computational cost, and Hierarchical Supervision Weighting applies exponentially decaying importance to supervision steps, aligning loss weighting with observed gradient magnitude decay. On Sudoku-Extreme with 423,168 test puzzles, CGAR achieves 1.71x training speedup (10.93 to 6.38 hours, 42% cost reduction) with only 0.63% accuracy drop (86.65% to 86.02%). Systematic ablations reveal Progressive Depth Curriculum alone achieves 2.26x speedup with 85.47% accuracy, demonstrating a rare Pareto improvement where architectural curriculum simultaneously enhances training efficiency and solution quality. CGAR-trained models exhibit superior inference efficiency with 100% halting accuracy and 11% fewer reasoning steps. Our work demonstrates that principled curriculum on architectural depth enables efficient training of recursive reasoning models on modest hardware. Code and models: https://github.com/Kaleemullahqasim/CGAR and https://huggingface.co/Kaleemullah/trm-cgar-sudoku

Paperid: 803, https://arxiv.org/pdf/2511.08633.pdf GitHub

Abstract:
Diffusion-based video generation can create realistic videos, yet existing image- and text-based conditioning fails to offer precise motion control. Prior methods for motion-conditioned synthesis typically require model-specific fine-tuning, which is computationally expensive and restrictive. We introduce Time-to-Move (TTM), a training-free, plug-and-play framework for motion- and appearance-controlled video generation with image-to-video (I2V) diffusion models. Our key insight is to use crude reference animations obtained through user-friendly manipulations such as cut-and-drag or depth-based reprojection. Motivated by SDEdit's use of coarse layout cues for image editing, we treat the crude animations as coarse motion cues and adapt the mechanism to the video domain. We preserve appearance with image conditioning and introduce dual-clock denoising, a region-dependent strategy that enforces strong alignment in motion-specified regions while allowing flexibility elsewhere, balancing fidelity to user intent with natural dynamics. This lightweight modification of the sampling process incurs no additional training or runtime cost and is compatible with any backbone. Extensive experiments on object and camera motion benchmarks show that TTM matches or exceeds existing training-based baselines in realism and motion control. Beyond this, TTM introduces a unique capability: precise appearance control through pixel-level conditioning, exceeding the limits of text-only prompting. Visit our project page for video examples and code: https://time-to-move.github.io/.

Paperid: 804, https://arxiv.org/pdf/2511.08626.pdf GitHub

Abstract:
The Segment Anything Model (SAM) has demonstrated significant potential in medical image segmentation. Yet, its performance is limited when only a small amount of labeled data is available, while there is abundant valuable yet often overlooked hierarchical information in medical data. To address this limitation, we draw inspiration from self-supervised learning and propose SAMora, an innovative framework that captures hierarchical medical knowledge by applying complementary self-supervised learning objectives at the image, patch, and pixel levels. To fully exploit the complementarity of hierarchical knowledge within LoRAs, we introduce HL-Attn, a hierarchical fusion module that integrates multi-scale features while maintaining their distinct characteristics. SAMora is compatible with various SAM variants, including SAM2, SAMed, and H-SAM. Experimental results on the Synapse, LA, and PROMISE12 datasets demonstrate that SAMora outperforms existing SAM variants. It achieves state-of-the-art performance in both few-shot and fully supervised settings while reducing fine-tuning epochs by 90%. The code is available at https://github.com/ShChen233/SAMora.

Paperid: 805, https://arxiv.org/pdf/2511.08622.pdf GitHub GitHub

Abstract:
Time series forecasting is important in finance domain. Financial time series (TS) patterns are influenced by both short-term public opinions and medium-/long-term policy and market trends. Hence, processing multi-period inputs becomes crucial for accurate financial time series forecasting (TSF). However, current TSF models either use only single-period input, or lack customized designs for addressing multi-period characteristics. In this paper, we propose a Multi-period Learning Framework (MLF) to enhance financial TSF performance. MLF considers both TSF's accuracy and efficiency requirements. Specifically, we design three new modules to better integrate the multi-period inputs for improving accuracy: (i) Inter-period Redundancy Filtering (IRF), that removes the information redundancy between periods for accurate self-attention modeling, (ii) Learnable Weighted-average Integration (LWI), that effectively integrates multi-period forecasts, (iii) Multi-period self-Adaptive Patching (MAP), that mitigates the bias towards certain periods by setting the same number of patches across all periods. Furthermore, we propose a Patch Squeeze module to reduce the number of patches in self-attention modeling for maximized efficiency. MLF incorporates multiple inputs with varying lengths (periods) to achieve better accuracy and reduces the costs of selecting input lengths during training. The codes and datasets are available at https://github.com/Meteor-Stars/MLF.

Paperid: 806, https://arxiv.org/pdf/2511.08615.pdf GitHub

Abstract:
Multi-drone surveillance systems offer enhanced coverage and robustness for pedestrian tracking, yet existing approaches struggle with dynamic camera positions and complex occlusions. This paper introduces MATRIX (Multi-Aerial TRacking In compleX environments), a comprehensive dataset featuring synchronized footage from eight drones with continuously changing positions, and a novel deep learning framework for multi-view detection and tracking. Unlike existing datasets that rely on static cameras or limited drone coverage, MATRIX provides a challenging scenario with 40 pedestrians and a significant architectural obstruction in an urban environment. Our framework addresses the unique challenges of dynamic drone-based surveillance through real-time camera calibration, feature-based image registration, and multi-view feature fusion in bird's-eye-view (BEV) representation. Experimental results demonstrate that while static camera methods maintain over 90\% detection and tracking precision and accuracy metrics in a simplified MATRIX environment without an obstruction, 10 pedestrians and a much smaller observational area, their performance significantly degrades in the complex environment. Our proposed approach maintains robust performance with $\sim$90\% detection and tracking accuracy, as well as successfully tracks $\sim$80\% of trajectories under challenging conditions. Transfer learning experiments reveal strong generalization capabilities, with the pretrained model achieving much higher detection and tracking accuracy performance compared to training the model from scratch. Additionally, systematic camera dropout experiments reveal graceful performance degradation, demonstrating practical robustness for real-world deployments where camera failures may occur. The MATRIX dataset and framework provide essential benchmarks for advancing dynamic multi-view surveillance systems.

Paperid: 807, https://arxiv.org/pdf/2511.08607.pdf GitHub

Abstract:
As modern software systems continue to grow in complexity, triage has become a fundamental process in system operations and maintenance. Triage aims to efficiently prioritize, assign, and assess issues to ensure the reliability of complex environments. The vast amount of heterogeneous data generated by software systems has made effective triage indispensable for maintaining reliability, facilitating maintainability, and enabling rapid issue response. Motivated by these challenges, researchers have devoted extensive effort to advancing triage automation and have achieved significant progress over the past two decades. This survey provides a comprehensive review of 234 papers from 2004 to the present, offering an in-depth examination of the fundamental concepts, system architecture, and problem statement. By comparing the distinct goals of academic and industrial research and by analyzing empirical studies of industrial practices, we identify the major obstacles that limit the practical deployment of triage systems. To assist practitioners in method selection and performance evaluation, we summarize widely adopted open-source datasets and evaluation metrics, providing a unified perspective on the measurement of triage effectiveness. Finally, we outline potential future directions and emerging opportunities to foster a closer integration between academic innovation and industrial application. All reviewed papers and projects are available at https://github.com/AIOps-Lab-NKU/TriageSurvey.

Paperid: 808, https://arxiv.org/pdf/2511.08595.pdf GitHub

Abstract:
Tree-of-Thought (ToT) reasoning boosts the problem-solving abilities of Large Language Models (LLMs) but is computationally expensive due to semantic redundancy, where distinct branches explore equivalent reasoning paths. We introduce Semantic Similarity-Based Dynamic Pruning (SSDP), a lightweight method that, to the best of our knowledge, is the first framework to integrate online semantic merging into parallelized tree search, enabling the clustering and pruning of redundant steps in real time. Across reasoning benchmarks, including GSM8K and MATH500, SSDP achieves up to a 2.3x speedup over state-of-the-art tree-search baselines while maintaining competitive accuracy (typically within 5% of the strongest baseline) and reducing the number of explored nodes by 85-90%, demonstrating a practical approach to efficient, scalable LLM reasoning. The implementation of SSDP is publicly available at https://github.com/kimjoonghokim/SSDP.

Paperid: 809, https://arxiv.org/pdf/2511.08590.pdf GitHub

Abstract:
Large Language Model (LLM) routing has demonstrated strong capability in balancing response quality with computational cost. As users exhibit diverse preferences, personalization has attracted increasing attention in LLM routing, since even identical queries may require different models to generate responses tailored to individual needs. However, existing approaches are not fully personalized and often fail to capture the complex interactions between specific users and LLMs. Moreover, user preference data is typically scarce, noisy, and inconsistent in format, which limits the effectiveness of methods that rely solely on user-specific data. To address these challenges, we propose GMTRouter, which represents multi-turn user-LLM interactions as a heterogeneous graph with four node types: user, LLM, query, and response, thereby preserving the rich relational structure of the interaction. Through a tailored message-passing mechanism, GMTRouter learns to capture user preferences from few-shot data within a lightweight inductive graph learning framework, enabling effective personalization. Extensive experiments demonstrate that GMTRouter consistently outperforms strong baselines, achieving 0.9 to 21.6 percent higher accuracy and 0.006 to 0.309 higher AUC across multiple datasets. More importantly, we demonstrate that GMTRouter can adapt to new users and evolving preferences using only few-shot data, without extensive fine-tuning. The code for GMTRouter is publicly available at https://github.com/ulab-uiuc/GMTRouter.

Paperid: 810, https://arxiv.org/pdf/2511.08585.pdf GitHub

Abstract:
The landscape of video generation is shifting, from a focus on generating visually appealing clips to building virtual environments that support interaction and maintain physical plausibility. These developments point toward the emergence of video foundation models that function not only as visual generators but also as implicit world models, models that simulate the physical dynamics, agent-environment interactions, and task planning that govern real or imagined worlds. This survey provides a systematic overview of this evolution, conceptualizing modern video foundation models as the combination of two core components: an implicit world model and a video renderer. The world model encodes structured knowledge about the world, including physical laws, interaction dynamics, and agent behavior. It serves as a latent simulation engine that enables coherent visual reasoning, long-term temporal consistency, and goal-driven planning. The video renderer transforms this latent simulation into realistic visual observations, effectively producing videos as a "window" into the simulated world. We trace the progression of video generation through four generations, in which the core capabilities advance step by step, ultimately culminating in a world model, built upon a video generation model, that embodies intrinsic physical plausibility, real-time multimodal interaction, and planning capabilities spanning multiple spatiotemporal scales. For each generation, we define its core characteristics, highlight representative works, and examine their application domains such as robotics, autonomous driving, and interactive gaming. Finally, we discuss open challenges and design principles for next-generation world models, including the role of agent intelligence in shaping and evaluating these systems. An up-to-date list of related works is maintained at this link.

Paperid: 811, https://arxiv.org/pdf/2511.08583.pdf GitHub

Abstract:
Developing efficient and accurate visuomotor policies poses a central challenge in robotic imitation learning. While recent rectified flow approaches have advanced visuomotor policy learning, they suffer from a key limitation: After iterative distillation, generated actions may deviate from the ground-truth actions corresponding to the current visual observation, leading to accumulated error as the reflow process repeats and unstable task execution. We present Selective Flow Alignment (SeFA), an efficient and accurate visuomotor policy learning framework. SeFA resolves this challenge by a selective flow alignment strategy, which leverages expert demonstrations to selectively correct generated actions and restore consistency with observations, while preserving multimodality. This design introduces a consistency correction mechanism that ensures generated actions remain observation-aligned without sacrificing the efficiency of one-step flow inference. Extensive experiments across both simulated and real-world manipulation tasks show that SeFA Policy surpasses state-of-the-art diffusion-based and flow-based policies, achieving superior accuracy and robustness while reducing inference latency by over 98%. By unifying rectified flow efficiency with observation-consistent action generation, SeFA provides a scalable and dependable solution for real-time visuomotor policy learning. Code is available on https://github.com/RongXueZoe/SeFA.

Paperid: 812, https://arxiv.org/pdf/2511.08577.pdf GitHub

Abstract:
Improving reasoning capabilities of Large Language Models (LLMs), especially under parameter constraints, is crucial for real-world applications. Prior work proposes recurrent transformers, which allocate a fixed number of extra iterations per token to improve generation quality. After the first, standard forward pass, instead of verbalization, last-layer hidden states are fed back as inputs for additional iterations to refine token predictions. Yet we identify a latent overthinking phenomenon: easy token predictions that are already correct after the first pass are sometimes revised into errors in additional iterations. To address this, we propose Think-at-Hard (TaH), a dynamic latent thinking method that iterates deeper only at hard tokens. It employs a lightweight neural decider to trigger latent iterations only at tokens that are likely incorrect after the standard forward pass. During latent iterations, Low-Rank Adaptation (LoRA) modules shift the LLM objective from general next-token prediction to focused hard-token refinement. We further introduce a duo-causal attention mechanism that extends attention from the token sequence dimension to an additional iteration depth dimension. This enables cross-iteration information flow while maintaining full sequential parallelism. Experiments show that TaH boosts LLM reasoning performance across five challenging benchmarks while maintaining the same parameter count. Compared with baselines that iterate twice for all output tokens, TaH delivers 8.1-11.3% accuracy gains while exempting 94% of tokens from the second iteration. Against strong single-iteration Qwen3 models finetuned with the same data, it also delivers 4.0-5.0% accuracy gains. When allowing less than 3% additional parameters from LoRA and the iteration decider, the gains increase to 8.5-12.6% and 5.3-5.4%, respectively. Our code is available at https://github.com/thu-nics/TaH.

Paperid: 813, https://arxiv.org/pdf/2511.08575.pdf GitHub

Abstract:
LLMs have transformed NLP, yet deploying them on edge devices poses great carbon challenges. Prior estimators remain incomplete, neglecting peripheral energy use, distinct prefill/decode behaviors, and SoC design complexity. This paper presents CO2-Meter, a unified framework for estimating operational and embodied carbon in LLM edge inference. Contributions include: (1) equation-based peripheral energy models and datasets; (2) a GNN-based predictor with phase-specific LLM energy data; (3) a unit-level embodied carbon model for SoC bottleneck analysis; and (4) validation showing superior accuracy over prior methods. Case studies show CO2-Meter's effectiveness in identifying carbon hotspots and guiding sustainable LLM design on edge platforms. Source code: https://github.com/fuzhenxiao/CO2-Meter

Paperid: 814, https://arxiv.org/pdf/2511.08544.pdf GitHub GitHub

Abstract:
Learning manipulable representations of the world and its dynamics is central to AI. Joint-Embedding Predictive Architectures (JEPAs) offer a promising blueprint, but lack of practical guidance and theory has led to ad-hoc R&D. We present a comprehensive theory of JEPAs and instantiate it in {\bf LeJEPA}, a lean, scalable, and theoretically grounded training objective. First, we identify the isotropic Gaussian as the optimal distribution that JEPAs' embeddings should follow to minimize downstream prediction risk. Second, we introduce a novel objective--{\bf Sketched Isotropic Gaussian Regularization} (SIGReg)--to constrain embeddings to reach that ideal distribution. Combining the JEPA predictive loss with SIGReg yields LeJEPA with numerous theoretical and practical benefits: (i) single trade-off hyperparameter, (ii) linear time and memory complexity, (iii) stability across hyper-parameters, architectures (ResNets, ViTs, ConvNets) and domains, (iv) heuristics-free, e.g., no stop-gradient, no teacher-student, no hyper-parameter schedulers, and (v) distributed training-friendly implementation requiring only $\approx$50 lines of code. Our empirical validation covers 10+ datasets, 60+ architectures, all with varying scales and domains. As an example, using imagenet-1k for pretraining and linear evaluation with frozen backbone, LeJEPA reaches 79\% with a ViT-H/14. We hope that the simplicity and theory-friendly ecosystem offered by LeJEPA will reestablish self-supervised pre-training as a core pillar of AI research (\href{https://github.com/rbalestr-lab/lejepa}{GitHub repo}).

Paperid: 815, https://arxiv.org/pdf/2511.08536.pdf GitHub

Abstract:
We introduce 3D4D, an interactive 4D visualization framework that integrates WebGL with Supersplat rendering. It transforms static images and text into coherent 4D scenes through four core modules and employs a foveated rendering strategy for efficient, real-time multi-modal interaction. This framework enables adaptive, user-driven exploration of complex 4D environments. The project page and code are available at https://yunhonghe1021.github.io/NOVA/.

Paperid: 816, https://arxiv.org/pdf/2511.08491.pdf GitHub

Abstract:
With increasingly sophisticated cybersecurity threats and rising demand for network automation, autonomous cybersecurity mechanisms are becoming critical for securing modern networks. The rapid expansion of Internet of Things (IoT) systems amplifies these challenges, as resource-constrained IoT devices demand scalable and efficient security solutions. In this work, an innovative Intrusion Detection System (IDS) utilizing Automated Machine Learning (AutoML) and Multi-Objective Optimization (MOO) is proposed for autonomous and optimized cyber-attack detection in modern networking environments. The proposed IDS framework integrates two primary innovative techniques: Optimized Importance and Percentage-based Automated Feature Selection (OIP-AutoFS) and Optimized Performance, Confidence, and Efficiency-based Combined Algorithm Selection and Hyperparameter Optimization (OPCE-CASH). These components optimize feature selection and model learning processes to strike a balance between intrusion detection effectiveness and computational efficiency. This work presents the first IDS framework that integrates all four AutoML stages and employs multi-objective optimization to jointly optimize detection effectiveness, efficiency, and confidence for deployment in resource-constrained systems. Experimental evaluations over two benchmark cybersecurity datasets demonstrate that the proposed MOO-AutoML IDS outperforms state-of-the-art IDSs, establishing a new benchmark for autonomous, efficient, and optimized security for networks. Designed to support IoT and edge environments with resource constraints, the proposed framework is applicable to a variety of autonomous cybersecurity applications across diverse networked environments.

Paperid: 817, https://arxiv.org/pdf/2511.08427.pdf GitHub

Abstract:
Deep learning has brought significant advancements to X-ray Computed Tomography (CT) reconstruction, offering solutions to challenges arising from modern imaging technologies. These developments benefit from methods that combine classical reconstruction techniques with data-driven approaches. Differentiable operators play a key role in this integration by enabling end-to-end optimization and the incorporation of physical modeling within neural networks. In this work, we present an updated version of PYRO-NN, a Python-based library for differentiable CT reconstruction. The updated framework extends compatibility to PyTorch and introduces native CUDA kernel support for efficient projection and back-projection operations across parallel, fan, and cone-beam geometries. Additionally, it includes tools for simulating imaging artifacts, modeling arbitrary acquisition trajectories, and creating flexible, end-to-end trainable pipelines through a high-level Python API. Code is available at: https://github.com/csyben/PYRO-NN

Paperid: 818, https://arxiv.org/pdf/2511.08418.pdf GitHub

Abstract:
Accurately simulating systems governed by PDEs, such as voltage fields in cardiac electrophysiology (EP) modelling, remains a significant modelling challenge. Traditional numerical solvers are computationally expensive and sensitive to discretisation, while canonical deep learning methods are data-hungry and struggle with chaotic dynamics and long-term predictions. Physics-Informed Neural Networks (PINNs) mitigate some of these issues by incorporating physical constraints in the learning process, yet they remain limited by mesh resolution and long-term predictive stability. In this work, we propose a Physics-Informed Neural Operator (PINO) approach to solve PDE problems in cardiac EP. Unlike PINNs, PINO models learn mappings between function spaces, allowing them to generalise to multiple mesh resolutions and initial conditions. Our results show that PINO models can accurately reproduce cardiac EP dynamics over extended time horizons and across multiple propagation scenarios, including zero-shot evaluations on scenarios unseen during training. Additionally, our PINO models maintain high predictive quality in long roll-outs (where predictions are recursively fed back as inputs), and can scale their predictive resolution by up to 10x the training resolution. These advantages come with a significant reduction in simulation time compared to numerical PDE solvers, highlighting the potential of PINO-based approaches for efficient and scalable cardiac EP simulations.

Paperid: 819, https://arxiv.org/pdf/2511.08416.pdf GitHub

Abstract:
Semantic communications mark a paradigm shift from bit-accurate transmission toward meaning-centric communication, essential as wireless systems approach theoretical capacity limits. The emergence of generative AI has catalyzed generative semantic communications, where receivers reconstruct content from minimal semantic cues by leveraging learned priors. Among generative approaches, diffusion models stand out for their superior generation quality, stable training dynamics, and rigorous theoretical foundations. However, the field currently lacks systematic guidance connecting diffusion techniques to communication system design, forcing researchers to navigate disparate literatures. This article provides the first comprehensive tutorial on diffusion models for generative semantic communications. We present score-based diffusion foundations and systematically review three technical pillars: conditional diffusion for controllable generation, efficient diffusion for accelerated inference, and generalized diffusion for cross-domain adaptation. In addition, we introduce an inverse problem perspective that reformulates semantic decoding as posterior inference, bridging semantic communications with computational imaging. Through analysis of human-centric, machine-centric, and agent-centric scenarios, we illustrate how diffusion models enable extreme compression while maintaining semantic fidelity and robustness. By bridging generative AI innovations with communication system design, this article aims to establish diffusion models as foundational components of next-generation wireless networks and beyond.

Paperid: 820, https://arxiv.org/pdf/2511.08396.pdf GitHub

Abstract:
Multivariate time series forecasting is crucial across a wide range of domains. While presenting notable progress for the Transformer architecture, iTransformer still lags behind the latest MLP-based models. We attribute this performance gap to unstable inter-channel relationships. To bridge this gap, we propose EMAformer, a simple yet effective model that enhances the Transformer with an auxiliary embedding suite, akin to armor that reinforces its ability. By introducing three key inductive biases, i.e., \textit{global stability}, \textit{phase sensitivity}, and \textit{cross-axis specificity}, EMAformer unlocks the further potential of the Transformer architecture, achieving state-of-the-art performance on 12 real-world benchmarks and reducing forecasting errors by an average of 2.73\% in MSE and 5.15\% in MAE. This significantly advances the practical applicability of Transformer-based approaches for multivariate time series forecasting. The code is available on https://github.com/PlanckChang/EMAformer.

Paperid: 821, https://arxiv.org/pdf/2511.08387.pdf GitHub

Abstract:
Radar-based indoor 3D human pose estimation typically relied on fine-grained 3D keypoint labels, which are costly to obtain especially in complex indoor settings involving clutter, occlusions, or multiple people. In this paper, we propose \textbf{RAPTR} (RAdar Pose esTimation using tRansformer) under weak supervision, using only 3D BBox and 2D keypoint labels which are considerably easier and more scalable to collect. Our RAPTR is characterized by a two-stage pose decoder architecture with a pseudo-3D deformable attention to enhance (pose/joint) queries with multi-view radar features: a pose decoder estimates initial 3D poses with a 3D template loss designed to utilize the 3D BBox labels and mitigate depth ambiguities; and a joint decoder refines the initial poses with 2D keypoint labels and a 3D gravity loss. Evaluated on two indoor radar datasets, RAPTR outperforms existing methods, reducing joint position error by $34.3\%$ on HIBER and $76.9\%$ on MMVR. Our implementation is available at https://github.com/merlresearch/radar-pose-transformer.

Paperid: 822, https://arxiv.org/pdf/2511.08377.pdf GitHub

Abstract:
Intent inferencing in teleoperation has been instrumental in aligning operator goals and coordinating actions with robotic partners. However, current intent inference methods often ignore subtle motion that can be strong indicators for a sudden change in intent. Specifically, we aim to tackle 1) if we can detect sudden jumps in operator trajectories, 2) how we appropriately use these sudden jump motions to infer an operator's goal state, and 3) how to incorporate these discontinuous and continuous dynamics to infer operator motion. Our framework, called Psychic, models these small indicative motions through a jump-drift-diffusion stochastic differential equation to cover discontinuous and continuous dynamics. Kramers-Moyal (KM) coefficients allow us to detect jumps with a trajectory which we pair with a statistical outlier detection algorithm to nominate goal transitions. Through identifying jumps, we can perform early detection of existing goals and discover undefined goals in unstructured scenarios. Our framework then applies a Sparse Identification of Nonlinear Dynamics (SINDy) model using KM coefficients with the goal transitions as a control input to infer an operator's motion behavior in unstructured scenarios. We demonstrate Psychic can produce probabilistic reachability sets and compare our strategy to a negative log-likelihood model fit. We perform a retrospective study on 600 operator trajectories in a hands-free teleoperation task to evaluate the efficacy of our opensource package, Psychic, in both offline and online learning.

Paperid: 823, https://arxiv.org/pdf/2511.08369.pdf GitHub

Abstract:
This work introduces Text-based Aerial-Ground Person Retrieval (TAG-PR), which aims to retrieve person images from heterogeneous aerial and ground views with textual descriptions. Unlike traditional Text-based Person Retrieval (T-PR), which focuses solely on ground-view images, TAG-PR introduces greater practical significance and presents unique challenges due to the large viewpoint discrepancy across images. To support this task, we contribute: (1) TAG-PEDES dataset, constructed from public benchmarks with automatically generated textual descriptions, enhanced by a diversified text generation paradigm to ensure robustness under view heterogeneity; and (2) TAG-CLIP, a novel retrieval framework that addresses view heterogeneity through a hierarchically-routed mixture of experts module to learn view-specific and view-agnostic features and a viewpoint decoupling strategy to decouple view-specific features for better cross-modal alignment. We evaluate the effectiveness of TAG-CLIP on both the proposed TAG-PEDES dataset and existing T-PR benchmarks. The dataset and code are available at https://github.com/Flame-Chasers/TAG-PR.

Paperid: 824, https://arxiv.org/pdf/2511.08361.pdf GitHub

Abstract:
The complexity and opacity of neural networks (NNs) pose significant challenges, particularly in high-stakes fields such as healthcare, finance, and law, where understanding decision-making processes is crucial. To address these issues, the field of explainable artificial intelligence (XAI) has developed various methods aimed at clarifying AI decision-making, thereby facilitating appropriate trust and validating the fairness of outcomes. Among these methods, prototype-based explanations offer a promising approach that uses representative examples to elucidate model behavior. However, a critical gap exists regarding standardized benchmarks to objectively compare prototype-based XAI methods, especially in the context of time series data. This lack of reliable benchmarks results in subjective evaluations, hindering progress in the field. We aim to establish a robust framework, ProtoScore, for assessing prototype-based XAI methods across different data types with a focus on time series data, facilitating fair and comprehensive evaluations. By integrating the Co-12 properties of Nauta et al., this framework allows for effectively comparing prototype methods against each other and against other XAI methods, ultimately assisting practitioners in selecting appropriate explanation methods while minimizing the costs associated with user studies. All code is publicly available at https://github.com/HelenaM23/ProtoScore .

Paperid: 825, https://arxiv.org/pdf/2511.08334.pdf GitHub

Abstract:
Underwater instance segmentation (UIS), integrating pixel-level understanding and instance-level discrimination, is a pivotal technology in marine resource exploration and ecological protection. In recent years, large-scale pretrained visual foundation models, exemplified by DINO, have advanced rapidly and demonstrated remarkable performance on complex downstream tasks. In this paper, we demonstrate that DINO can serve as an effective feature learner for UIS, and we introduce DiveSeg, a novel framework built upon two insightful components: (1) The AquaStyle Aligner, designed to embed underwater color style features into the DINO fine-tuning process, facilitating better adaptation to the underwater domain. (2) The ObjectPrior Prompter, which incorporates binary segmentation-based prompts to deliver object-level priors, provides essential guidance for instance segmentation task that requires both object- and instance-level reasoning. We conduct thorough experiments on the popular UIIS and USIS10K datasets, and the results show that DiveSeg achieves the state-of-the-art performance. Code: https://github.com/ettof/Diveseg.

Paperid: 826, https://arxiv.org/pdf/2511.08328.pdf GitHub

Abstract:
Regular mammography screening is crucial for early breast cancer detection. By leveraging deep learning-based risk models, screening intervals can be personalized, especially for high-risk individuals. While recent methods increasingly incorporate longitudinal information from prior mammograms, accurate spatial alignment across time points remains a key challenge. Misalignment can obscure meaningful tissue changes and degrade model performance. In this study, we provide insights into various alignment strategies, image-based registration, feature-level (representation space) alignment with and without regularization, and implicit alignment methods, for their effectiveness in longitudinal deep learning-based risk modeling. Using two large-scale mammography datasets, we assess each method across key metrics, including predictive accuracy, precision, recall, and deformation field quality. Our results show that image-based registration consistently outperforms the more recently favored feature-based and implicit approaches across all metrics, enabling more accurate, temporally consistent predictions and generating smooth, anatomically plausible deformation fields. Although regularizing the deformation field improves deformation quality, it reduces the risk prediction performance of feature-level alignment. Applying image-based deformation fields within the feature space yields the best risk prediction performance. These findings underscore the importance of image-based deformation fields for spatial alignment in longitudinal risk modeling, offering improved prediction accuracy and robustness. This approach has strong potential to enhance personalized screening and enable earlier interventions for high-risk individuals. The code is available at https://github.com/sot176/Mammogram_Alignment_Study_Risk_Prediction.git, allowing full reproducibility of the results.

Paperid: 827, https://arxiv.org/pdf/2511.08269.pdf GitHub GitHub

Abstract:
Semantic segmentation has achieved great success in ideal conditions. However, when facing extreme conditions (e.g., insufficient light, fierce camera motion), most existing methods suffer from significant information loss of RGB, severely damaging segmentation results. Several researches exploit the high-speed and high-dynamic event modality as a complement, but event and RGB are naturally heterogeneous, which leads to feature-level mismatch and inferior optimization of existing multi-modality methods. Different from these researches, we delve into the edge secret of both modalities for resilient fusion and propose a novel Edge-awareness Semantic Concordance framework to unify the multi-modality heterogeneous features with latent edge cues. In this framework, we first propose Edge-awareness Latent Re-coding, which obtains uncertainty indicators while realigning event-RGB features into unified semantic space guided by re-coded distribution, and transfers event-RGB distributions into re-coded features by utilizing a pre-established edge dictionary as clues. We then propose Re-coded Consolidation and Uncertainty Optimization, which utilize re-coded edge features and uncertainty indicators to solve the heterogeneous event-RGB fusion issues under extreme conditions. We establish two synthetic and one real-world event-RGB semantic segmentation datasets for extreme scenario comparisons. Experimental results show that our method outperforms the state-of-the-art by a 2.55% mIoU on our proposed DERS-XS, and possesses superior resilience under spatial occlusion. Our code and datasets are publicly available at https://github.com/iCVTEAM/ESC.

Paperid: 828, https://arxiv.org/pdf/2511.08251.pdf GitHub

Abstract:
Text-driven multi-object image editing which aims to precisely modify multiple objects within an image based on text descriptions, has recently attracted considerable interest. Existing works primarily follow the localize-editing paradigm, focusing on independent object localization and editing while neglecting critical inter-object interactions. However, this work points out that the neglected attention entanglements in inter-object conflict regions, inherently hinder disentangled multi-object editing, leading to either inter-object editing leakage or intra-object editing constraints. We thereby propose a novel multi-layer disentangled editing framework LayerEdit, a training-free method which, for the first time, through precise object-layered decomposition and coherent fusion, enables conflict-free object-layered editing. Specifically, LayerEdit introduces a novel "decompose-editingfusion" framework, consisting of: (1) Conflict-aware Layer Decomposition module, which utilizes an attention-aware IoU scheme and time-dependent region removing, to enhance conflict awareness and suppression for layer decomposition. (2) Object-layered Editing module, to establish coordinated intra-layer text guidance and cross-layer geometric mapping, achieving disentangled semantic and structural modifications. (3) Transparency-guided Layer Fusion module, to facilitate structure-coherent inter-object layer fusion through precise transparency guidance learning. Extensive experiments verify the superiority of LayerEdit over existing methods, showing unprecedented intra-object controllability and inter-object coherence in complex multi-object scenarios. Codes are available at: https://github.com/fufy1024/LayerEdit.

Paperid: 829, https://arxiv.org/pdf/2511.08240.pdf GitHub GitHub

Abstract:
Point cloud processing has become a cornerstone technology in many 3D vision tasks. However, arbitrary rotations introduce variations in point cloud orientations, posing a long-standing challenge for effective representation learning. The core of this issue is the disruption of the point cloud's intrinsic directional characteristics caused by rotational perturbations. Recent methods attempt to implicitly model rotational equivariance and invariance, preserving directional information and propagating it into deep semantic spaces. Yet, they often fall short of fully exploiting the multiscale directional nature of point clouds to enhance feature representations. To address this, we propose the Direction-Perceptive Vector Network (DiPVNet). At its core is an atomic dot-product operator that simultaneously encodes directional selectivity and rotation invariance--endowing the network with both rotational symmetry modeling and adaptive directional perception. At the local level, we introduce a Learnable Local Dot-Product (L2DP) Operator, which enables interactions between a center point and its neighbors to adaptively capture the non-uniform local structures of point clouds. At the global level, we leverage generalized harmonic analysis to prove that the dot-product between point clouds and spherical sampling vectors is equivalent to a direction-aware spherical Fourier transform (DASFT). This leads to the construction of a global directional response spectrum for modeling holistic directional structures. We rigorously prove the rotation invariance of both operators. Extensive experiments on challenging scenarios involving noise and large-angle rotations demonstrate that DiPVNet achieves state-of-the-art performance on point cloud classification and segmentation tasks. Our code is available at https://github.com/wxszreal0/DiPVNet.

Paperid: 830, https://arxiv.org/pdf/2511.08232.pdf GitHub

Abstract:
In this paper, we introduce OWLAPY, a comprehensive Python framework for OWL ontology engineering. OWLAPY streamlines the creation, modification, and serialization of OWL 2 ontologies. It uniquely integrates native Python-based reasoners with support for external Java reasoners, offering flexibility for users. OWLAPY facilitates multiple implementations of core ontology components and provides robust conversion capabilities between OWL class expressions and formats such as Description Logics, Manchester Syntax, and SPARQL. It also allows users to define custom workflows to leverage large language models (LLMs) in ontology generation from natural language text. OWLAPY serves as a well-tested software framework for users seeking a flexible Python library for advanced ontology engineering, including those transitioning from Java-based environments. The project is publicly available on GitHub at https://github.com/dice-group/owlapy and on the Python Package Index (PyPI) at https://pypi.org/project/owlapy/ , with over 50,000 downloads at the time of writing.

Paperid: 831, https://arxiv.org/pdf/2511.08230.pdf GitHub

Abstract:
The development of multi-modal large language models (LLMs) leads to intelligent approaches capable of speech interactions. As one of the most widely spoken languages globally, Mandarin is supported by most models to enhance their applicability and reach. However, the scarcity of comprehensive speech-to-speech (S2S) benchmarks in Mandarin contexts impedes systematic evaluation for developers and hinders fair model comparison for users. In this work, we propose VocalBench-zh, an ability-level divided evaluation suite adapted to Mandarin context consisting of 10 well-crafted subsets and over 10K high-quality instances, covering 12 user-oriented characters. The evaluation experiment on 14 mainstream models reveals the common challenges for current routes, and highlights the need for new insights into next-generation speech interactive systems. The evaluation codes and datasets will be available at https://github.com/SJTU-OmniAgent/VocalBench-zh.

Paperid: 832, https://arxiv.org/pdf/2511.08229.pdf GitHub

Abstract:
Time series forecasting is critical for decision-making across dynamic domains such as energy, finance, transportation, and cloud computing. However, real-world time series often exhibit non-stationarity, including temporal distribution shifts and spectral variability, which pose significant challenges for long-term time series forecasting. In this paper, we propose DTAF, a dual-branch framework that addresses non-stationarity in both the temporal and frequency domains. For the temporal domain, the Temporal Stabilizing Fusion (TFS) module employs a non-stationary mix of experts (MOE) filter to disentangle and suppress temporal non-stationary patterns while preserving long-term dependencies. For the frequency domain, the Frequency Wave Modeling (FWM) module applies frequency differencing to dynamically highlight components with significant spectral shifts. By fusing the complementary outputs of TFS and FWM, DTAF generates robust forecasts that adapt to both temporal and frequency domain non-stationarity. Extensive experiments on real-world benchmarks demonstrate that DTAF outperforms state-of-the-art baselines, yielding significant improvements in forecasting accuracy under non-stationary conditions. All codes are available at https://github.com/PandaJunk/DTAF.

Paperid: 833, https://arxiv.org/pdf/2511.08196.pdf GitHub

Abstract:
Driven by advancements in deep learning, computer-aided diagnoses have made remarkable progress. However, outside controlled laboratory settings, algorithms may encounter several challenges. In the medical domain, these difficulties often stem from limited data availability due to ethical and legal restrictions, as well as the high cost and time required for expert annotations-especially in the face of emerging or rare diseases. In this context, open-set recognition plays a vital role by identifying whether a sample belongs to one of the known classes seen during training or should be rejected as an unknown. Recent studies have shown that features learned in the later stages of deep neural networks are observed to cluster around their class means, which themselves are arranged as individual vertices of a regular simplex [32]. The proposed method introduces a loss function designed to reject samples of unknown classes effectively by penalizing open space regions using auxiliary datasets. This approach achieves significant performance gain across four MedMNIST datasets-BloodMNIST, OCTMNIST, DermaMNIST, TissueMNIST and a publicly available skin dataset [29] outperforming state-of-the-art techniques.

Paperid: 834, https://arxiv.org/pdf/2511.08195.pdf GitHub

Abstract:
User interface (UI) programming is a core yet highly complex part of modern software development. Recent advances in visual language models (VLMs) highlight the potential of automatic UI coding, but current approaches face two key limitations: multimodal coding capabilities remain underdeveloped, and single-turn paradigms make little use of iterative visual feedback. We address these challenges with an interactive UI-to-code paradigm that better reflects real-world workflows and raises the upper bound of achievable performance. Under this paradigm, we present UI2Code$^\text{N}$, a visual language model trained through staged pretraining, fine-tuning, and reinforcement learning to achieve foundational improvements in multimodal coding. The model unifies three key capabilities: UI-to-code generation, UI editing, and UI polishing. We further explore test-time scaling for interactive generation, enabling systematic use of multi-turn feedback. Experiments on UI-to-code and UI polishing benchmarks show that UI2Code$^\text{N}$ establishes a new state of the art among open-source models and achieves performance comparable to leading closed-source models such as Claude-4-Sonnet and GPT-5. Our code and models are available at https://github.com/zai-org/UI2Code_N.

Paperid: 835, https://arxiv.org/pdf/2511.08181.pdf GitHub

Abstract:
Recommender systems (RS) are currently being studied to mitigate limitations during cold-start conditions by leveraging modality information or introducing Agent concepts based on the exceptional reasoning capabilities of Large Language Models (LLMs). Meanwhile, food and beverage recommender systems have traditionally used knowledge graph and ontology concepts due to the domain's unique data attributes and relationship characteristics. On this background, we propose MARC, a multimodal and multi-task cocktail recommender system based on Agentic Retrieval-Augmented Generation (RAG) utilizing graph database under cold-start conditions. The proposed system generates high-quality, contextually appropriate answers through two core processes: a task recognition router and a reflection process. The graph database was constructed by processing cocktail data from Kaggle, and its effectiveness was evaluated using 200 manually crafted questions. The evaluation used both LLM-as-a-judge and human evaluation to demonstrate that answers generated via the graph database outperformed those from a simple vector database in terms of quality. The code is available at https://github.com/diddbwls/cocktail_rec_agentrag

Paperid: 836, https://arxiv.org/pdf/2511.08173.pdf GitHub

Abstract:
Detecting visual anomalies in diverse, multi-class real-world images is a significant challenge. We introduce \ours, a novel unsupervised multi-class visual anomaly detection framework. It integrates a Latent Diffusion Model (LDM) with a Vision-Language Model (VLM) for enhanced anomaly localization and detection. Specifically, a pre-trained VLM with a simple prompt extracts detailed image descriptions, serving as additional conditioning for LDM training. Current diffusion-based methods rely on synthetic noise generation, limiting their generalization and requiring per-class model training, which hinders scalability. \ours, however, leverages VLMs to obtain normal captions without manual annotations or additional training. These descriptions condition the diffusion model, learning a robust normal image feature representation for multi-class anomaly detection. Our method achieves competitive performance, improving the pixel-level Per-Region-Overlap (PRO) metric by up to 25 points on the Real-IAD dataset and 8 points on the COCO-AD dataset, outperforming state-of-the-art diffusion-based approaches. Code is available at https://github.com/giddyyupp/VLMDiff.

Paperid: 837, https://arxiv.org/pdf/2511.08163.pdf GitHub

Abstract:
Zero-shot learning (ZSL) aims to recognize unseen classes with zero samples by transferring semantic knowledge from seen classes. Current approaches typically correlate global visual features with semantic information (i.e., attributes) or align local visual region features with corresponding attributes to enhance visual-semantic interactions. Although effective, these methods often overlook the intrinsic interactions between local region features, which can further improve the acquisition of transferable and explicit visual features. In this paper, we propose a network named Multi-Granularity Mutual Refinement Network (Mg-MRN), which refine discriminative and transferable visual features by learning decoupled multi-granularity features and cross-granularity feature interactions. Specifically, we design a multi-granularity feature extraction module to learn region-level discriminative features through decoupled region feature mining. Then, a cross-granularity feature fusion module strengthens the inherent interactions between region features of varying granularities. This module enhances the discriminability of representations at each granularity level by integrating region representations from adjacent hierarchies, further improving ZSL recognition performance. Extensive experiments on three popular ZSL benchmark datasets demonstrate the superiority and competitiveness of our proposed Mg-MRN method. Our code is available at https://github.com/NingWang2049/Mg-MRN.

Paperid: 838, https://arxiv.org/pdf/2511.08155.pdf GitHub

Abstract:
Evaluating the perceptual quality of Novel View Synthesis (NVS) images remains a key challenge, particularly in the absence of pixel-aligned ground truth references. Full-Reference Image Quality Assessment (FR-IQA) methods fail under misalignment, while No-Reference (NR-IQA) methods struggle with generalization. In this work, we introduce a Non-Aligned Reference (NAR-IQA) framework tailored for NVS, where it is assumed that the reference view shares partial scene content but lacks pixel-level alignment. We constructed a large-scale image dataset containing synthetic distortions targeting Temporal Regions of Interest (TROI) to train our NAR-IQA model. Our model is built on a contrastive learning framework that incorporates LoRA-enhanced DINOv2 embeddings and is guided by supervision from existing IQA methods. We train exclusively on synthetically generated distortions, deliberately avoiding overfitting to specific real NVS samples and thereby enhancing the model's generalization capability. Our model outperforms state-of-the-art FR-IQA, NR-IQA, and NAR-IQA methods, achieving robust performance on both aligned and non-aligned references. We also conducted a novel user study to gather data on human preferences when viewing non-aligned references in NVS. We find strong correlation between our proposed quality prediction model and the collected subjective ratings. For dataset and code, please visit our project page: https://stootaghaj.github.io/nova-project/

Paperid: 839, https://arxiv.org/pdf/2511.08152.pdf GitHub

Abstract:
Multimodal learning, while contributing to numerous success stories across various fields, faces the challenge of prohibitively expensive manual annotation. To address the scarcity of annotated data, a popular solution is unsupervised domain adaptation, which has been extensively studied in unimodal settings yet remains less explored in multimodal settings. In this paper, we investigate heterogeneous multimodal domain adaptation, where the primary challenge is the varying domain shifts of different modalities from the source to the target domain. We first introduce the information bottleneck method to learn representations for each modality independently, and then match the source and target domains in the representation space with correlation alignment. To balance the domain alignment of all modalities, we formulate the problem as a multi-objective task, aiming for a Pareto optimal solution. By exploiting the properties specific to our model, the problem can be simplified to a quadratic programming problem. Further approximation yields a closed-form solution, leading to an efficient modality-balanced multimodal domain adaptation algorithm. The proposed method features \textbf{B}alanced multi-\textbf{o}bjective \textbf{o}ptimization for \textbf{m}ultimodal \textbf{d}omain \textbf{a}daptation, termed \textbf{Boomda}. Extensive empirical results showcase the effectiveness of the proposed approach and demonstrate that Boomda outperforms the competing schemes. The code is is available at: https://github.com/sunjunaimer/Boomda.git.

Paperid: 840, https://arxiv.org/pdf/2511.08130.pdf GitHub

Abstract:
Foam formation in Wastewater Treatment Plants (WTPs) is a major challenge that can reduce treatment efficiency and increase costs. The ability to automatically examine changes in real-time with respect to the percentage of foam can be of great benefit to the plant. However, large amounts of labeled data are required to train standard Machine Learning (ML) models. The development of these systems is slow due to the scarcity and heterogeneity of labeled data. Additionally, the development is often hindered by the fact that different WTPs do not share their data due to privacy concerns. This paper proposes a new framework to address these challenges by combining Federated Learning (FL) with the state-of-the-art base model for image segmentation, Segment Anything Model 2 (SAM2). The FL paradigm enables collaborative model training across multiple WTPs without centralizing sensitive operational data, thereby ensuring privacy. The framework accelerates training convergence and improves segmentation performance even with limited local datasets by leveraging SAM2's strong pre-trained weights for initialization. The methodology involves fine-tuning SAM2 on distributed clients (edge nodes) using the Flower framework, where a central Fog server orchestrates the process by aggregating model weights without accessing private data. The model was trained and validated using various data collections, including real-world images captured at a WTPs in Granada, Spain, a synthetically generated foam dataset, and images from publicly available datasets to improve generalization. This research offers a practical, scalable, and privacy-aware solution for automatic foam tracking in WTPs. The findings highlight the significant potential of integrating large-scale foundational models into FL systems to solve real-world industrial challenges characterized by distributed and sensitive data.

Paperid: 841, https://arxiv.org/pdf/2511.08083.pdf GitHub

Abstract:
AMD GPUs offer state-of-the-art compute and memory bandwidth; however, peak performance AMD kernels are written in raw assembly. To address the difficulty of mapping AI algorithms to hardware, recent work proposes C++ embedded and PyTorch-inspired domain-specific languages like ThunderKittens (TK) to simplify high performance AI kernel development on NVIDIA hardware. We explore the extent to which such primitives -- for explicit tile-based programming with optimized memory accesses and fine-grained asynchronous execution across workers -- are NVIDIA-specific or general. We provide the first detailed study of the programming primitives that lead to performant AMD AI kernels, and we encapsulate these insights in the HipKittens (HK) programming framework. We find that tile-based abstractions used in prior DSLs generalize to AMD GPUs, however we need to rethink the algorithms that instantiate these abstractions for AMD. We validate the HK primitives across CDNA3 and CDNA4 AMD platforms. In evaluations, HK kernels compete with AMD's hand-optimized assembly kernels for GEMMs and attention, and consistently outperform compiler baselines. Moreover, assembly is difficult to scale to the breadth of AI workloads; reflecting this, in some settings HK outperforms all available kernel baselines by $1.2-2.4\times$ (e.g., $d=64$ attention, GQA backwards, memory-bound kernels). These findings help pave the way for a single, tile-based software layer for high-performance AI kernels that translates across GPU vendors. HipKittens is released at: https://github.com/HazyResearch/HipKittens.

Paperid: 842, https://arxiv.org/pdf/2511.08071.pdf GitHub

Abstract:
Frequency Modulated Continuous Wave (FMCW) radars can measure subtle chest wall oscillations to enable non-contact heartbeat sensing. However, traditional radar-based heartbeat sensing methods face performance degradation due to noise. Learning-based radar methods achieve better noise robustness but require costly labeled signals for supervised training. To overcome these limitations, we propose the first unsupervised framework for radar-based heartbeat sensing via Augmented Pseudo-Label and Noise Contrast (Radar-APLANC). We propose to use both the heartbeat range and noise range within the radar range matrix to construct the positive and negative samples, respectively, for improved noise robustness. Our Noise-Contrastive Triplet (NCT) loss only utilizes positive samples, negative samples, and pseudo-label signals generated by the traditional radar method, thereby avoiding dependence on expensive ground-truth physiological signals. We further design a pseudo-label augmentation approach featuring adaptive noise-aware label selection to improve pseudo-label signal quality. Extensive experiments on the Equipleth dataset and our collected radar dataset demonstrate that our unsupervised method achieves performance comparable to state-of-the-art supervised methods. Our code, dataset, and supplementary materials can be accessed from https://github.com/RadarHRSensing/Radar-APLANC.

Paperid: 843, https://arxiv.org/pdf/2511.08066.pdf GitHub

Abstract:
Recent years have witnessed the rapid advancements of large language models (LLMs) and their expanding applications, leading to soaring demands for computational resources. The widespread adoption of test-time scaling further aggravates the tension between model capability and resource consumption, highlighting the importance of inference efficiency. However, a unified metric that accurately reflects an LLM's efficiency across different model sizes and architectures remains absent. Motivated by the correlation between compression and intelligence, we introduce information capacity, a measure of model efficiency based on text compression performance relative to computational complexity. Larger models can predict the next token more accurately, achieving greater compression gains but at higher computational costs. Empirical evaluations on mainstream open-source models show that models of varying sizes within a series exhibit consistent information capacity. This metric enables a fair efficiency comparison across model series and accurate performance prediction within a model series. A distinctive feature of information capacity is that it incorporates tokenizer efficiency, which affects both input and output token counts but is often neglected in LLM evaluations. We assess the information capacity of 49 models on 5 heterogeneous datasets and observe consistent results on the influences of tokenizer efficiency, pretraining data, and the mixture-of-experts architecture.

Paperid: 844, https://arxiv.org/pdf/2511.08054.pdf GitHub

Abstract:
This work introduces the Re$^{\text{2}}$MaP method, which generates expert-quality macro placements through recursively prototyping and packing tree-based relocating. We first perform multi-level macro grouping and PPA-aware cell clustering to produce a unified connection matrix that captures both wirelength and dataflow among macros and clusters. Next, we use DREAMPlace to build a mixed-size placement prototype and obtain reference positions for each macro and cluster. Based on this prototype, we introduce ABPlace, an angle-based analytical method that optimizes macro positions on an ellipse to distribute macros uniformly near chip periphery, while optimizing wirelength and dataflow. A packing tree-based relocating procedure is then designed to jointly adjust the locations of macro groups and the macros within each group, by optimizing an expertise-inspired cost function that captures various design constraints through evolutionary search. Re$^{\text{2}}$MaP repeats the above process: Only a subset of macro groups are positioned in each iteration, and the remaining macros are deferred to the next iteration to improve the prototype's accuracy. Using a well-established backend flow with sufficient timing optimizations, Re$^{\text{2}}$MaP achieves up to 22.22% (average 10.26%) improvement in worst negative slack (WNS) and up to 97.91% (average 33.97%) improvement in total negative slack (TNS) compared to the state-of-the-art academic placer Hier-RTLMP. It also ranks higher on WNS, TNS, power, design rule check (DRC) violations, and runtime than the conference version ReMaP, across seven tested cases. Our code is available at https://github.com/lamda-bbo/Re2MaP.

Paperid: 845, https://arxiv.org/pdf/2511.08048.pdf GitHub

Abstract:
Few-shot detection-based counters estimate the number of instances in the image specified only by a few test-time exemplars. A common approach to localize objects across multiple sizes is to merge backbone features of different resolutions. Furthermore, to enable small object detection in densely populated regions, the input image is commonly upsampled and tiling is applied to cope with the increased computational and memory requirements. Because of these ad-hoc solutions, existing counters struggle with images containing diverse-sized objects and densely populated regions of small objects. We propose GECO2, an end-to-end few-shot counting and detection method that explicitly addresses the object scale issues. A new dense query representation gradually aggregates exemplar-specific feature information across scales that leads to high-resolution dense queries that enable detection of large as well as small objects. GECO2 surpasses state-of-the-art few-shot counters in counting as well as detection accuracy by 10% while running 3x times faster at smaller GPU memory footprint.

Paperid: 846, https://arxiv.org/pdf/2511.08043.pdf GitHub

Abstract:
In modern sequential decision-making systems, the construction of an optimal candidate action space is critical to efficient inference. However, existing approaches either rely on manually defined action spaces that lack scalability or utilize unstructured spaces that render exhaustive search computationally prohibitive. In this paper, we propose a novel framework named \textsc{DynaAct} for automatically constructing a compact action space to enhance sequential reasoning in complex problem-solving scenarios. Our method first estimates a proxy for the complete action space by extracting general sketches observed in a corpus covering diverse complex reasoning problems using large language models. We then formulate a submodular function that jointly evaluates candidate actions based on their utility to the current state and their diversity, and employ a greedy algorithm to select an optimal candidate set. Extensive experiments on six diverse standard benchmarks demonstrate that our approach significantly improves overall performance, while maintaining efficient inference without introducing substantial latency. The implementation is available at https://github.com/zhaoxlpku/DynaAct.

Paperid: 847, https://arxiv.org/pdf/2511.08032.pdf GitHub

Abstract:
With the rapid advancement of 3D visualization, 3D Gaussian Splatting (3DGS) has emerged as a leading technique for real-time, high-fidelity rendering. While prior research has emphasized algorithmic performance and visual fidelity, the perceptual quality of 3DGS-rendered content, especially under varying reconstruction conditions, remains largely underexplored. In practice, factors such as viewpoint sparsity, limited training iterations, point downsampling, noise, and color distortions can significantly degrade visual quality, yet their perceptual impact has not been systematically studied. To bridge this gap, we present 3DGS-QA, the first subjective quality assessment dataset for 3DGS. It comprises 225 degraded reconstructions across 15 object types, enabling a controlled investigation of common distortion factors. Based on this dataset, we introduce a no-reference quality prediction model that directly operates on native 3D Gaussian primitives, without requiring rendered images or ground-truth references. Our model extracts spatial and photometric cues from the Gaussian representation to estimate perceived quality in a structure-aware manner. We further benchmark existing quality assessment methods, spanning both traditional and learning-based approaches. Experimental results show that our method consistently achieves superior performance, highlighting its robustness and effectiveness for 3DGS content evaluation. The dataset and code are made publicly available at https://github.com/diaoyn/3DGSQA to facilitate future research in 3DGS quality assessment.

Paperid: 848, https://arxiv.org/pdf/2511.08031.pdf GitHub

Abstract:
The rapid advancement of generative adversarial networks (GANs) and diffusion models has enabled the creation of highly realistic deepfake content, posing significant threats to digital trust across audio-visual domains. While unimodal detection methods have shown progress in identifying synthetic media, their inability to leverage cross-modal correlations and precisely localize forged segments limits their practicality against sophisticated, fine-grained manipulations. To address this, we introduce a multi-modal deepfake detection and localization framework based on a Feature Pyramid-Transformer (FPN-Transformer), addressing critical gaps in cross-modal generalization and temporal boundary regression. The proposed approach utilizes pre-trained self-supervised models (WavLM for audio, CLIP for video) to extract hierarchical temporal features. A multi-scale feature pyramid is constructed through R-TLM blocks with localized attention mechanisms, enabling joint analysis of cross-context temporal dependencies. The dual-branch prediction head simultaneously predicts forgery probabilities and refines temporal offsets of manipulated segments, achieving frame-level localization precision. We evaluate our approach on the test set of the IJCAI'25 DDL-AV benchmark, showing a good performance with a final score of 0.7535 for cross-modal deepfake detection and localization in challenging environments. Experimental results confirm the effectiveness of our approach and provide a novel way for generalized deepfake detection. Our code is available at https://github.com/Zig-HS/MM-DDL

Paperid: 849, https://arxiv.org/pdf/2511.07987.pdf GitHub

Abstract:
In this paper, we propose a semantic-guided framework to address the challenging problem of large-mask image inpainting, where essential visual content is missing and contextual cues are limited. To compensate for the limited context, we leverage a pretrained Amodal Completion (AC) model to generate structure-aware candidates that serve as semantic priors for the missing regions. We introduce Context-Semantic Fusion Network (CSF-Net), a transformer-based fusion framework that fuses these candidates with contextual features to produce a semantic guidance image for image inpainting. This guidance improves inpainting quality by promoting structural accuracy and semantic consistency. CSF-Net can be seamlessly integrated into existing inpainting models without architectural changes and consistently enhances performance across diverse masking conditions. Extensive experiments on the Places365 and COCOA datasets demonstrate that CSF-Net effectively reduces object hallucination while enhancing visual realism and semantic alignment. The code for CSF-Net is available at https://github.com/chaeyeonheo/CSF-Net.

Paperid: 850, https://arxiv.org/pdf/2511.07979.pdf GitHub

Abstract:
Large language models (LLMs) have demonstrated strong reasoning abilities across specialized domains, motivating research into their application to legal reasoning. However, existing legal benchmarks often conflate factual recall with genuine inference, fragment the reasoning process, and overlook the quality of reasoning. To address these limitations, we introduce MSLR, the first Chinese multi-step legal reasoning dataset grounded in real-world judicial decision making. MSLR adopts the IRAC framework (Issue, Rule, Application, Conclusion) to model structured expert reasoning from official legal documents. In addition, we design a scalable Human-LLM collaborative annotation pipeline that efficiently produces fine-grained step-level reasoning annotations and provides a reusable methodological framework for multi-step reasoning datasets. Evaluation of multiple LLMs on MSLR shows only moderate performance, highlighting the challenges of adapting to complex legal reasoning. Further experiments demonstrate that Self-Initiated Chain-of-Thought prompts generated by models autonomously improve reasoning coherence and quality, outperforming human-designed prompts. MSLR contributes to advancing LLM reasoning and Chain-of-Thought strategies and offers open resources for future research. The dataset and code are available at https://github.com/yuwenhan07/MSLR-Bench and https://law.sjtu.edu.cn/flszyjzx/index.html.

Paperid: 851, https://arxiv.org/pdf/2511.07966.pdf GitHub

Abstract:
Unsupervised domain adaptation for LiDAR-based 3D object detection (3D UDA) based on the teacher-student architecture with pseudo labels has achieved notable improvements in recent years. Although it is quite popular to collect point clouds and images simultaneously, little attention has been paid to the usefulness of image data in 3D UDA when training the models. In this paper, we propose an approach named MMAssist that improves the performance of 3D UDA with multi-modal assistance. A method is designed to align 3D features between the source domain and the target domain by using image and text features as bridges. More specifically, we project the ground truth labels or pseudo labels to the images to get a set of 2D bounding boxes. For each 2D box, we extract its image feature from a pre-trained vision backbone. A large vision-language model (LVLM) is adopted to extract the box's text description, and a pre-trained text encoder is used to obtain its text feature. During the training of the model in the source domain and the student model in the target domain, we align the 3D features of the predicted boxes with their corresponding image and text features, and the 3D features and the aligned features are fused with learned weights for the final prediction. The features between the student branch and the teacher branch in the target domain are aligned as well. To enhance the pseudo labels, we use an off-the-shelf 2D object detector to generate 2D bounding boxes from images and estimate their corresponding 3D boxes with the aid of point cloud, and these 3D boxes are combined with the pseudo labels generated by the teacher model. Experimental results show that our approach achieves promising performance compared with state-of-the-art methods in three domain adaptation tasks on three popular 3D object detection datasets. The code is available at https://github.com/liangp/MMAssist.

Paperid: 852, https://arxiv.org/pdf/2511.07948.pdf GitHub

Abstract:
Extracting robust discriminative features is a critical challenge in person re-identification (ReID). While Transformer-based methods have successfully addressed some limitations of convolutional neural networks (CNNs), such as their local processing nature and information loss resulting from convolution and downsampling operations, they still face the scalability issue due to the quadratic increase in memory and computational requirements with the length of the input sequence. To overcome this, we propose a pure Mamba-based person ReID framework named ReIDMamba. Specifically, we have designed a Mamba-based strong baseline that effectively leverages fine-grained, discriminative global features by introducing multiple class tokens. To further enhance robust features learning within Mamba, we have carefully designed two novel techniques. First, the multi-granularity feature extractor (MGFE) module, designed with a multi-branch architecture and class token fusion, effectively forms multi-granularity features, enhancing both discrimination ability and fine-grained coverage. Second, the ranking-aware triplet regularization (RATR) is introduced to reduce redundancy in features from multiple branches, enhancing the diversity of multi-granularity features by incorporating both intra-class and inter-class diversity constraints, thus ensuring the robustness of person features. To our knowledge, this is the pioneering work that integrates a purely Mamba-driven approach into ReID research. Our proposed ReIDMamba model boasts only one-third the parameters of TransReID, along with lower GPU memory usage and faster inference throughput. Experimental results demonstrate ReIDMamba's superior and promising performance, achieving state-of-the-art performance on five person ReID benchmarks. Code is available at https://github.com/GuHY777/ReIDMamba.

Paperid: 853, https://arxiv.org/pdf/2511.07943.pdf GitHub

Abstract:
Efficient retrieval of external knowledge bases and web pages is crucial for enhancing the reasoning abilities of LLMs. Previous works on training LLMs to leverage external retrievers for solving complex problems have predominantly employed end-to-end reinforcement learning. However, these approaches neglect supervision over the reasoning process, making it difficult to guarantee logical coherence and rigor. To address these limitations, we propose Thinker, a hierarchical thinking model for deep search through multi-turn interaction, making the reasoning process supervisable and verifiable. It decomposes complex problems into independently solvable sub-problems, each dually represented in both natural language and an equivalent logical function to support knowledge base and web searches. Concurrently, dependencies between sub-problems are passed as parameters via these logical functions, enhancing the logical coherence of the problem-solving process. To avoid unnecessary external searches, we perform knowledge boundary determination to check if a sub-problem is within the LLM's intrinsic knowledge, allowing it to answer directly. Experimental results indicate that with as few as several hundred training samples, the performance of Thinker is competitive with established baselines. Furthermore, when scaled to the full training set, Thinker significantly outperforms these methods across various datasets and model sizes. The source code is available at https://github.com/OpenSPG/KAG-Thinker.

Paperid: 854, https://arxiv.org/pdf/2511.07929.pdf GitHub

Abstract:
Despite the remarkable performance of deep models in medical imaging, they still require source data for training, which limits their potential in light of privacy concerns. Federated learning (FL), as a decentralized learning framework that trains a shared model with multiple hospitals (a.k.a., FL clients), provides a feasible solution. However, data heterogeneity and resource costs hinder the deployment of FL models, especially when using vision language models (VLM). To address these challenges, we propose a novel contrastive language-image pre-training (CLIP) based FL approach for medical image classification (FedMedCLIP). Specifically, we introduce a masked feature adaptation module (FAM) as a communication module to reduce the communication load while freezing the CLIP encoders to reduce the computational overhead. Furthermore, we propose a masked multi-layer perceptron (MLP) as a private local classifier to adapt to the client tasks. Moreover, we design an adaptive Kullback-Leibler (KL) divergence-based distillation regularization method to enable mutual learning between FAM and MLP. Finally, we incorporate model compression to transmit the FAM parameters while using ensemble predictions for classification. Extensive experiments on four publicly available medical datasets demonstrate that our model provides feasible performance (e.g., 8\% higher compared to second best baseline on ISIC2019) with reasonable resource cost (e.g., 120$\times$ faster than FedAVG).

Paperid: 855, https://arxiv.org/pdf/2511.07865.pdf GitHub

Abstract:
Chaos Engineering (CE) is an engineering technique aimed at improving the resilience of distributed systems. It involves intentionally injecting faults into a system to test its resilience, uncover weaknesses, and address them before they cause failures in production. Recent CE tools automate the execution of predefined CE experiments. However, planning such experiments and improving the system based on the experimental results still remain manual. These processes are labor-intensive and require multi-domain expertise. To address these challenges and enable anyone to build resilient systems at low cost, this paper proposes ChaosEater, a system that automates the entire CE cycle with Large Language Models (LLMs). It predefines an agentic workflow according to a systematic CE cycle and assigns subdivided processes within the workflow to LLMs. ChaosEater targets CE for software systems built on Kubernetes. Therefore, the LLMs in ChaosEater complete CE cycles through software engineering tasks, including requirement definition, code generation, testing, and debugging. We evaluate ChaosEater through case studies on small- and large-scale Kubernetes systems. The results demonstrate that it consistently completes reasonable CE cycles with significantly low time and monetary costs. Its cycles are also qualitatively validated by human engineers and LLMs.

Paperid: 856, https://arxiv.org/pdf/2511.07863.pdf GitHub

Abstract:
Large language models now draft news, legal analyses, and software code with human-level fluency. At the same time, regulations such as the EU AI Act mandate that each synthetic passage carry an imperceptible, machine-verifiable mark for provenance. Conventional logit-based watermarks satisfy this requirement by selecting a pseudorandom green vocabulary at every decoding step and boosting its logits, yet the random split can exclude the highest-probability token and thus erode fluency. WaterMod mitigates this limitation through a probability-aware modular rule. The vocabulary is first sorted in descending model probability; the resulting ranks are then partitioned by the residue rank mod k, which distributes adjacent-and therefore semantically similar-tokens across different classes. A fixed bias of small magnitude is applied to one selected class. In the zero-bit setting (k=2), an entropy-adaptive gate selects either the even or the odd parity as the green list. Because the top two ranks fall into different parities, this choice embeds a detectable signal while guaranteeing that at least one high-probability token remains available for sampling. In the multi-bit regime (k>2), the current payload digit d selects the color class whose ranks satisfy rank mod k = d. Biasing the logits of that class embeds exactly one base-k digit per decoding step, thereby enabling fine-grained provenance tracing. The same modular arithmetic therefore supports both binary attribution and rich payloads. Experimental results demonstrate that WaterMod consistently attains strong watermark detection performance while maintaining generation quality in both zero-bit and multi-bit settings. This robustness holds across a range of tasks, including natural language generation, mathematical reasoning, and code synthesis. Our code and data are available at https://github.com/Shinwoo-Park/WaterMod.

Paperid: 857, https://arxiv.org/pdf/2511.07836.pdf GitHub

Abstract:
The curse of dimensionality presents a pervasive challenge in optimization problems, with exponential expansion of the search space rapidly causing traditional algorithms to become inefficient or infeasible. An adaptive sampling strategy is presented to accelerate optimization in this domain as an alternative to uniform quasi-Monte Carlo (QMC) methods. This method, referred to as Hyperellipsoid Density Sampling (HDS), generates its sequences by defining multiple hyperellipsoids throughout the search space. HDS uses three types of unsupervised learning algorithms to circumvent high-dimensional geometric calculations, producing an intelligent, non-uniform sample sequence that exploits statistically promising regions of the parameter space and improves final solution quality in high-dimensional optimization problems. A key feature of the method is optional Gaussian weights, which may be provided to influence the sample distribution towards known locations of interest. This capability makes HDS versatile for applications beyond optimization, providing a focused, denser sample distribution where models need to concentrate their efforts on specific, non-uniform regions of the parameter space. The method was evaluated against Sobol, a standard QMC method, using differential evolution (DE) on the 29 CEC2017 benchmark test functions. The results show statistically significant improvements in solution geometric mean error (p < 0.05), with average performance gains ranging from 3% in 30D to 37% in 10D. This paper demonstrates the efficacy of HDS as a robust alternative to QMC sampling for high-dimensional optimization.

Paperid: 858, https://arxiv.org/pdf/2511.07820.pdf GitHub

Abstract:
Despite the rise of billion-parameter foundation models trained across thousands of GPUs, similar scaling gains have not been shown for humanoid control. Current neural controllers for humanoids remain modest in size, target a limited behavior set, and are trained on a handful of GPUs over several days. We show that scaling up model capacity, data, and compute yields a generalist humanoid controller capable of creating natural and robust whole-body movements. Specifically, we posit motion tracking as a natural and scalable task for humanoid control, leverageing dense supervision from diverse motion-capture data to acquire human motion priors without manual reward engineering. We build a foundation model for motion tracking by scaling along three axes: network size (from 1.2M to 42M parameters), dataset volume (over 100M frames, 700 hours of high-quality motion data), and compute (9k GPU hours). Beyond demonstrating the benefits of scale, we show the practical utility of our model through two mechanisms: (1) a real-time universal kinematic planner that bridges motion tracking to downstream task execution, enabling natural and interactive control, and (2) a unified token space that supports various motion input interfaces, such as VR teleoperation devices, human videos, and vision-language-action (VLA) models, all using the same policy. Scaling motion tracking exhibits favorable properties: performance improves steadily with increased compute and data diversity, and learned representations generalize to unseen motions, establishing motion tracking at scale as a practical foundation for humanoid control.

Paperid: 859, https://arxiv.org/pdf/2511.07819.pdf GitHub

Abstract:
Human motion synthesis in 3D scenes relies heavily on scene comprehension, while current methods focus mainly on scene structure but ignore the semantic understanding. In this paper, we propose a human motion synthesis framework that take an unified Scene Semantic Occupancy (SSO) for scene representation, termed SSOMotion. We design a bi-directional tri-plane decomposition to derive a compact version of the SSO, and scene semantics are mapped to an unified feature space via CLIP encoding and shared linear dimensionality reduction. Such strategy can derive the fine-grained scene semantic structures while significantly reduce redundant computations. We further take these scene hints and movement direction derived from instructions for motion control via frame-wise scene query. Extensive experiments and ablation studies conducted on cluttered scenes using ShapeNet furniture, as well as scanned scenes from PROX and Replica datasets, demonstrate its cutting-edge performance while validating its effectiveness and generalization ability. Code will be publicly available at https://github.com/jingyugong/SSOMotion.

Paperid: 860, https://arxiv.org/pdf/2511.07808.pdf GitHub

Abstract:
Although significant advances have been achieved in SAR land-cover classification, recent methods remain predominantly focused on supervised learning, which relies heavily on extensive labeled datasets. This dependency not only limits scalability and generalization but also restricts adaptability to diverse application scenarios. In this paper, a general-purpose foundation model for SAR land-cover classification is developed, serving as a robust cornerstone to accelerate the development and deployment of various downstream models. Specifically, a Dynamic Instance and Contour Consistency Contrastive Learning (DI3CL) pre-training framework is presented, which incorporates a Dynamic Instance (DI) module and a Contour Consistency (CC) module. DI module enhances global contextual awareness by enforcing local consistency across different views of the same region. CC module leverages shallow feature maps to guide the model to focus on the geometric contours of SAR land-cover objects, thereby improving structural discrimination. Additionally, to enhance robustness and generalization during pre-training, a large-scale and diverse dataset named SARSense, comprising 460,532 SAR images, is constructed to enable the model to capture comprehensive and representative features. To evaluate the generalization capability of our foundation model, we conducted extensive experiments across a variety of SAR land-cover classification tasks, including SAR land-cover mapping, water body detection, and road extraction. The results consistently demonstrate that the proposed DI3CL outperforms existing methods. Our code and pre-trained weights are publicly available at: https://github.com/SARpre-train/DI3CL.

Paperid: 861, https://arxiv.org/pdf/2511.07790.pdf GitHub

Abstract:
Sentiments about the reproducibility of cited papers in downstream literature offer community perspectives and have shown as a promising signal of the actual reproducibility of published findings. To train effective models to effectively predict reproducibility-oriented sentiments and further systematically study their correlation with reproducibility, we introduce the CC30k dataset, comprising a total of 30,734 citation contexts in machine learning papers. Each citation context is labeled with one of three reproducibility-oriented sentiment labels: Positive, Negative, or Neutral, reflecting the cited paper's perceived reproducibility or replicability. Of these, 25,829 are labeled through crowdsourcing, supplemented with negatives generated through a controlled pipeline to counter the scarcity of negative labels. Unlike traditional sentiment analysis datasets, CC30k focuses on reproducibility-oriented sentiments, addressing a research gap in resources for computational reproducibility studies. The dataset was created through a pipeline that includes robust data cleansing, careful crowd selection, and thorough validation. The resulting dataset achieves a labeling accuracy of 94%. We then demonstrated that the performance of three large language models significantly improves on the reproducibility-oriented sentiment classification after fine-tuning using our dataset. The dataset lays the foundation for large-scale assessments of the reproducibility of machine learning papers. The CC30k dataset and the Jupyter notebooks used to produce and analyze the dataset are publicly available at https://github.com/lamps-lab/CC30k .

Paperid: 862, https://arxiv.org/pdf/2511.07748.pdf GitHub

Abstract:
AI-assisted ultrasound video diagnosis presents new opportunities to enhance the efficiency and accuracy of medical imaging analysis. However, existing research remains limited in terms of dataset diversity, diagnostic performance, and clinical applicability. In this study, we propose \textbf{Auto-US}, an intelligent diagnosis agent that integrates ultrasound video data with clinical diagnostic text. To support this, we constructed \textbf{CUV Dataset} of 495 ultrasound videos spanning five categories and three organs, aggregated from multiple open-access sources. We developed \textbf{CTU-Net}, which achieves state-of-the-art performance in ultrasound video classification, reaching an accuracy of 86.73\% Furthermore, by incorporating large language models, Auto-US is capable of generating clinically meaningful diagnostic suggestions. The final diagnostic scores for each case exceeded 3 out of 5 and were validated by professional clinicians. These results demonstrate the effectiveness and clinical potential of Auto-US in real-world ultrasound applications. Code and data are available at: https://github.com/Bean-Young/Auto-US.

Paperid: 863, https://arxiv.org/pdf/2511.07744.pdf GitHub

Abstract:
We introduce VectorSynth, a diffusion-based framework for pixel-accurate satellite image synthesis conditioned on polygonal geographic annotations with semantic attributes. Unlike prior text- or layout-conditioned models, VectorSynth learns dense cross-modal correspondences that align imagery and semantic vector geometry, enabling fine-grained, spatially grounded edits. A vision language alignment module produces pixel-level embeddings from polygon semantics; these embeddings guide a conditional image generation framework to respect both spatial extents and semantic cues. VectorSynth supports interactive workflows that mix language prompts with geometry-aware conditioning, allowing rapid what-if simulations, spatial edits, and map-informed content generation. For training and evaluation, we assemble a collection of satellite scenes paired with pixel-registered polygon annotations spanning diverse urban scenes with both built and natural features. We observe strong improvements over prior methods in semantic fidelity and structural realism, and show that our trained vision language model demonstrates fine-grained spatial grounding. The code and data are available at https://github.com/mvrl/VectorSynth.

Paperid: 864, https://arxiv.org/pdf/2511.07743.pdf GitHub

Abstract:
Ultrasound imaging is a cornerstone of non-invasive clinical diagnostics, yet its limited field of view complicates novel view synthesis. We propose \textbf{UltraGS}, a Gaussian Splatting framework optimized for ultrasound imaging. First, we introduce a depth-aware Gaussian splatting strategy, where each Gaussian is assigned a learnable field of view, enabling accurate depth prediction and precise structural representation. Second, we design SH-DARS, a lightweight rendering function combining low-order spherical harmonics with ultrasound-specific wave physics, including depth attenuation, reflection, and scattering, to model tissue intensity accurately. Third, we contribute the Clinical Ultrasound Examination Dataset, a benchmark capturing diverse anatomical scans under real-world clinical protocols. Extensive experiments on three datasets demonstrate UltraGS's superiority, achieving state-of-the-art results in PSNR (up to 29.55), SSIM (up to 0.89), and MSE (as low as 0.002) while enabling real-time synthesis at 64.69 fps. The code and dataset are open-sourced at: https://github.com/Bean-Young/UltraGS.

Paperid: 865, https://arxiv.org/pdf/2511.07700.pdf GitHub

Abstract:
Artificial Intelligence (AI) models have demonstrated expert-level performance in melanoma detection, yet their clinical adoption is hindered by performance disparities across demographic subgroups such as gender, race, and age. Previous efforts to benchmark the performance of AI models have primarily focused on assessing model performance using group fairness metrics that rely on the Area Under the Receiver Operating Characteristic curve (AUROC), which does not provide insights into a model's ability to provide accurate estimates. In line with clinical assessments, this paper addresses this gap by incorporating calibration as a complementary benchmarking metric to AUROC-based fairness metrics. Calibration evaluates the alignment between predicted probabilities and observed event rates, offering deeper insights into subgroup biases. We assess the performance of the leading skin cancer detection algorithm of the ISIC 2020 Challenge on the ISIC 2020 Challenge dataset and the PROVE-AI dataset, and compare it with the second and third place models, focusing on subgroups defined by sex, race (Fitzpatrick Skin Tone), and age. Our findings reveal that while existing models enhance discriminative accuracy, they often over-diagnose risk and exhibit calibration issues when applied to new datasets. This study underscores the necessity for comprehensive model auditing strategies and extensive metadata collection to achieve equitable AI-driven healthcare solutions. All code is publicly available at https://github.com/bdominique/testing_strong_calibration.

Paperid: 866, https://arxiv.org/pdf/2511.07696.pdf GitHub

Abstract:
Dense and versatile image representations underpin the success of virtually all computer vision applications. However, state-of-the-art networks, such as transformers, produce low-resolution feature grids, which are suboptimal for dense prediction tasks. To address this limitation, we present FlowFeat, a high-resolution and multi-task feature representation. The key ingredient behind FlowFeat is a novel distillation technique that embeds a distribution of plausible apparent motions, or motion profiles. By leveraging optical flow networks and diverse video data, we develop an effective self-supervised training framework that statistically approximates the apparent motion. With its remarkable level of spatial detail, FlowFeat encodes a compelling degree of geometric and semantic cues while exhibiting high temporal consistency. Empirically, FlowFeat significantly enhances the representational power of five state-of-the-art encoders and alternative upsampling strategies across three dense tasks: video object segmentation, monocular depth estimation and semantic segmentation. Training FlowFeat is computationally inexpensive and robust to inaccurate flow estimation, remaining highly effective even when using unsupervised flow networks. Our work takes a step forward towards reliable and versatile dense image representations.

Paperid: 867, https://arxiv.org/pdf/2511.07689.pdf GitHub

Abstract:
Evaluating the factual consistency of abstractive text summarization remains a significant challenge, particularly for long documents, where conventional metrics struggle with input length limitations and long-range dependencies. In this work, we systematically evaluate the reliability of six widely used reference-free factuality metrics, originally proposed for short-form summarization, in the long-document setting. We probe metric robustness through seven factuality-preserving perturbations applied to summaries, namely paraphrasing, simplification, synonym replacement, logically equivalent negations, vocabulary reduction, compression, and source text insertion, and further analyze their sensitivity to retrieval context and claim information density. Across three long-form benchmark datasets spanning science fiction, legal, and scientific domains, our results reveal that existing short-form metrics produce inconsistent scores for semantically equivalent summaries and exhibit declining reliability for information-dense claims whose content is semantically similar to many parts of the source document. While expanding the retrieval context improves stability in some domains, no metric consistently maintains factual alignment under long-context conditions. Finally, our results highlight concrete directions for improving factuality evaluation, including multi-span reasoning, context-aware calibration, and training on meaning-preserving variations to enhance robustness in long-form summarization. We release all code, perturbed data, and scripts required to reproduce our results at https://github.com/zainmujahid/metricEval-longSum.

Paperid: 868, https://arxiv.org/pdf/2511.07649.pdf GitHub

Abstract:
Reservoir inflow prediction is crucial for water resource management, yet existing approaches mainly focus on single-reservoir models that ignore spatial dependencies among interconnected reservoirs. We introduce AdaTrip as an adaptive, time-varying graph learning framework for multi-reservoir inflow forecasting. AdaTrip constructs dynamic graphs where reservoirs are nodes with directed edges reflecting hydrological connections, employing attention mechanisms to automatically identify crucial spatial and temporal dependencies. Evaluation on thirty reservoirs in the Upper Colorado River Basin demonstrates superiority over existing baselines, with improved performance for reservoirs with limited records through parameter sharing. Additionally, AdaTrip provides interpretable attention maps at edge and time-step levels, offering insights into hydrological controls to support operational decision-making. Our code is available at https://github.com/humphreyhuu/AdaTrip.

Paperid: 869, https://arxiv.org/pdf/2511.07505.pdf GitHub

Abstract:
Data duplication within large-scale corpora often impedes large language models' (LLMs) performance and privacy. In privacy-concerned federated learning scenarios, conventional deduplication methods typically rely on trusted third parties to perform uniform deletion, risking loss of informative samples while introducing privacy vulnerabilities. To address these gaps, we propose Federated ReWeighting (FedRW), the first privacy-preserving framework, to the best of our knowledge, that performs soft deduplication via sample reweighting instead of deletion in federated LLM training, without assuming a trusted third party. At its core, FedRW proposes a secure, frequency-aware reweighting protocol through secure multi-party computation, coupled with a parallel orchestration strategy to ensure efficiency and scalability. During training, FedRW utilizes an adaptive reweighting mechanism with global sample frequencies to adjust individual loss contributions, effectively improving generalization and robustness. Empirical results demonstrate that FedRW outperforms the state-of-the-art method by achieving up to 28.78x speedup in preprocessing and approximately 11.42% improvement in perplexity, while offering enhanced security guarantees. FedRW thus establishes a new paradigm for managing duplication in federated LLM training.

Paperid: 870, https://arxiv.org/pdf/2511.07483.pdf GitHub

Abstract:
Recent advancements in large language models (LLMs) have shifted the post-training paradigm from traditional instruction tuning and human preference alignment toward reinforcement learning (RL) focused on reasoning capabilities. However, numerous technical reports indicate that purely rule-based reward RL frequently results in poor-quality reasoning chains or inconsistencies between reasoning processes and final answers, particularly when the base model is of smaller scale. During the RL exploration process, models might employ low-quality reasoning chains due to the lack of knowledge, occasionally producing correct answers randomly and receiving rewards based on established rule-based judges. This constrains the potential for resource-limited organizations to conduct direct reinforcement learning training on smaller-scale models. We propose a novel confidence-based reward model tailored for enhancing STEM reasoning capabilities. Unlike conventional approaches, our model penalizes not only incorrect answers but also low-confidence correct responses, thereby promoting more robust and logically consistent reasoning. We validate the effectiveness of our approach through static evaluations, Best-of-N inference tests, and PPO-based RL training. Our method outperforms several state-of-the-art open-source reward models across diverse STEM benchmarks. We release our codes and model in https://github.com/qianxiHe147/C2RM.

Paperid: 871, https://arxiv.org/pdf/2511.07468.pdf GitHub

Abstract:
crate2bib is a collection of tools designed to convert Rust crates hosted on crates.io into bibliography entries. It queries the server, extracts metadata from the given crate and also searches for possible CITATION.cff files within the repository that hosts the code of the crate in interest. From this information, it formats the provided information such as name, version, authors and generates entries for all available candidates. With this approach, crates can be cited easily and existing citations for published crates can be found. The tool can be used as a webapp, python package, command-line utility or Rust crate.

Paperid: 872, https://arxiv.org/pdf/2511.07461.pdf GitHub

Abstract:
This paper introduces DuTerm, a novel two-stage architecture for terminology-constrained machine translation. Our system combines a terminology-aware NMT model, adapted via fine-tuning on large-scale synthetic data, with a prompt-based LLM for post-editing. The LLM stage refines NMT output and enforces terminology adherence. We evaluate DuTerm on English-to German, English-to-Spanish, and English-to-Russian with the WMT 2025 Terminology Shared Task corpus. We demonstrate that flexible, context-driven terminology handling by the LLM consistently yields higher quality translations than strict constraint enforcement. Our results highlight a critical trade-off, revealing that an LLM's work best for high-quality translation as context-driven mutators rather than generators.

Paperid: 873, https://arxiv.org/pdf/2511.07418.pdf GitHub

Abstract:
Despite years of research, real-time diverse grasp synthesis for dexterous hands remains an unsolved core challenge in robotics and computer graphics. We present Lightning Grasp, a novel high-performance procedural grasp synthesis algorithm that achieves orders-of-magnitude speedups over state-of-the-art approaches, while enabling unsupervised grasp generation for irregular, tool-like objects. The method avoids many limitations of prior approaches, such as the need for carefully tuned energy functions and sensitive initialization. This breakthrough is driven by a key insight: decoupling complex geometric computation from the search process via a simple, efficient data structure - the Contact Field. This abstraction collapses the problem complexity, enabling a procedural search at unprecedented speeds. We open-source our system to propel further innovation in robotic manipulation.

Paperid: 874, https://arxiv.org/pdf/2511.07416.pdf GitHub GitHub

Abstract:
We introduce PhysWorld, a framework that enables robot learning from video generation through physical world modeling. Recent video generation models can synthesize photorealistic visual demonstrations from language commands and images, offering a powerful yet underexplored source of training signals for robotics. However, directly retargeting pixel motions from generated videos to robots neglects physics, often resulting in inaccurate manipulations. PhysWorld addresses this limitation by coupling video generation with physical world reconstruction. Given a single image and a task command, our method generates task-conditioned videos and reconstructs the underlying physical world from the videos, and the generated video motions are grounded into physically accurate actions through object-centric residual reinforcement learning with the physical world model. This synergy transforms implicit visual guidance into physically executable robotic trajectories, eliminating the need for real robot data collection and enabling zero-shot generalizable robotic manipulation. Experiments on diverse real-world tasks demonstrate that PhysWorld substantially improves manipulation accuracy compared to previous approaches. Visit \href{https://pointscoder.github.io/PhysWorld_Web/}{the project webpage} for details.

Paperid: 875, https://arxiv.org/pdf/2511.07413.pdf GitHub

Abstract:
AI agents capable of controlling user interfaces have the potential to transform human interaction with digital devices. To accelerate this transformation, two fundamental building blocks are essential: high-quality datasets that enable agents to achieve complex and human-relevant goals, and robust evaluation methods that allow researchers and practitioners to rapidly enhance agent performance. In this paper, we introduce DigiData, a large-scale, high-quality, diverse, multi-modal dataset designed for training mobile control agents. Unlike existing datasets, which derive goals from unstructured interactions, DigiData is meticulously constructed through comprehensive exploration of app features, resulting in greater diversity and higher goal complexity. Additionally, we present DigiData-Bench, a benchmark for evaluating mobile control agents on real-world complex tasks. We demonstrate that the commonly used step-accuracy metric falls short in reliably assessing mobile control agents and, to address this, we propose dynamic evaluation protocols and AI-powered evaluations as rigorous alternatives for agent assessment. Our contributions aim to significantly advance the development of mobile control agents, paving the way for more intuitive and effective human-device interactions.

Paperid: 876, https://arxiv.org/pdf/2511.07409.pdf GitHub GitHub

Abstract:
We present DIMO, a generative approach capable of generating diverse 3D motions for arbitrary objects from a single image. The core idea of our work is to leverage the rich priors in well-trained video models to extract the common motion patterns and then embed them into a shared low-dimensional latent space. Specifically, we first generate multiple videos of the same object with diverse motions. We then embed each motion into a latent vector and train a shared motion decoder to learn the distribution of motions represented by a structured and compact motion representation, i.e., neural key point trajectories. The canonical 3D Gaussians are then driven by these key points and fused to model the geometry and appearance. During inference time with learned latent space, we can instantly sample diverse 3D motions in a single-forward pass and support several interesting applications including 3D motion interpolation and language-guided motion generation. Our project page is available at https://linzhanm.github.io/dimo.

Paperid: 877, https://arxiv.org/pdf/2511.07407.pdf GitHub

Abstract:
Falling is an inherent risk of humanoid mobility. Maintaining stability is thus a primary safety focus in robot control and learning, yet no existing approach fully averts loss of balance. When instability does occur, prior work addresses only isolated aspects of falling: avoiding falls, choreographing a controlled descent, or standing up afterward. Consequently, humanoid robots lack integrated strategies for impact mitigation and prompt recovery when real falls defy these scripts. We aim to go beyond keeping balance to make the entire fall-and-recovery process safe and autonomous: prevent falls when possible, reduce impact when unavoidable, and stand up when fallen. By fusing sparse human demonstrations with reinforcement learning and an adaptive diffusion-based memory of safe reactions, we learn adaptive whole-body behaviors that unify fall prevention, impact mitigation, and rapid recovery in one policy. Experiments in simulation and on a Unitree G1 demonstrate robust sim-to-real transfer, lower impact forces, and consistently fast recovery across diverse disturbances, pointing towards safer, more resilient humanoids in real environments. Videos are available at https://firm2025.github.io/.

Paperid: 878, https://arxiv.org/pdf/2511.07390.pdf GitHub

Abstract:
Many proteins useful in modern medicine or bioengineering are challenging to make in the lab, fuse with other proteins in cells, or deliver to tissues in the body, because their sequences are too long. Shortening these sequences typically involves costly, time-consuming experimental campaigns. Ideally, we could instead use modern models of massive databases of sequences from nature to learn how to propose shrunken proteins that resemble sequences found in nature. Unfortunately, these models struggle to efficiently search the combinatorial space of all deletions, and are not trained with inductive biases to learn how to delete. To address this gap, we propose SCISOR, a novel discrete diffusion model that deletes letters from sequences to generate protein samples that resemble those found in nature. To do so, SCISOR trains a de-noiser to reverse a forward noising process that adds random insertions to natural sequences. As a generative model, SCISOR fits evolutionary sequence data competitively with previous large models. In evaluation, SCISOR achieves state-of-the-art predictions of the functional effects of deletions on ProteinGym. Finally, we use the SCISOR de-noiser to shrink long protein sequences, and show that its suggested deletions result in significantly more realistic proteins and more often preserve functional motifs than previous models of evolutionary sequences.

Paperid: 879, https://arxiv.org/pdf/2511.07384.pdf GitHub

Abstract:
Recent advances in depth-recurrent language models show that recurrence can decouple train-time compute and parameter count from test-time compute. In this work, we study how to convert existing pretrained non-recurrent language models into depth-recurrent models. We find that using a curriculum of recurrences to increase the effective depth of the model over the course of training preserves performance while reducing total computational cost. In our experiments, on mathematics, we observe that converting pretrained models to recurrent ones results in better performance at a given compute budget than simply post-training the original non-recurrent language model.

Paperid: 880, https://arxiv.org/pdf/2511.07382.pdf GitHub

Abstract:
Large Language Models (LLMs) have advanced the automated generation of code from natural language prompts. However, low-resource languages (LRLs) like Bangla remain underrepresented due to the limited availability of instruction-to-code datasets and evaluation benchmarks. To address this, the BLP Workshop at IJCNLP-AACL 2025 introduced a shared task on "Code Generation in Bangla". In this work, we propose a method that combines instruction prompting with a test-driven, feedback-guided iterative refinement process using a fine-tuned Qwen2.5-14B model. The model generates code from Bangla instructions, tests it against unit tests, and iteratively refines any failing outputs through three evaluation passes, using test feedback to guide each step. This approach helped our team "Retriv" to secure 2nd place in the shared task with a Pass@1 score of 0.934. The analysis highlights challenges in Bangla instruction understanding and Python code generation, emphasizing the need for targeted methods in LRLs. We made experimental scripts publicly available for the community.

Paperid: 881, https://arxiv.org/pdf/2511.07327.pdf GitHub

Abstract:
Recent advances in deep-research agents have shown promise for autonomous knowledge construction through dynamic reasoning over external sources. However, existing approaches rely on a mono-contextual paradigm that accumulates all information in a single, expanding context window, leading to context suffocation and noise contamination that limit their effectiveness on long-horizon tasks. We introduce IterResearch, a novel iterative deep-research paradigm that reformulates long-horizon research as a Markov Decision Process with strategic workspace reconstruction. By maintaining an evolving report as memory and periodically synthesizing insights, our approach preserves consistent reasoning capacity across arbitrary exploration depths. We further develop Efficiency-Aware Policy Optimization (EAPO), a reinforcement learning framework that incentivizes efficient exploration through geometric reward discounting and enables stable distributed training via adaptive downsampling. Extensive experiments demonstrate that IterResearch achieves substantial improvements over existing open-source agents with average +14.5pp across six benchmarks and narrows the gap with frontier proprietary systems. Remarkably, our paradigm exhibits unprecedented interaction scaling, extending to 2048 interactions with dramatic performance gains (from 3.5\% to 42.5\%), and serves as an effective prompting strategy, improving frontier models by up to 19.2pp over ReAct on long-horizon tasks. These findings position IterResearch as a versatile solution for long-horizon reasoning, effective both as a trained agent and as a prompting paradigm for frontier models.

Paperid: 882, https://arxiv.org/pdf/2511.07321.pdf GitHub

Abstract:
Fast and flexible 3D scene reconstruction from unstructured image collections remains a significant challenge. We present YoNoSplat, a feedforward model that reconstructs high-quality 3D Gaussian Splatting representations from an arbitrary number of images. Our model is highly versatile, operating effectively with both posed and unposed, calibrated and uncalibrated inputs. YoNoSplat predicts local Gaussians and camera poses for each view, which are aggregated into a global representation using either predicted or provided poses. To overcome the inherent difficulty of jointly learning 3D Gaussians and camera parameters, we introduce a novel mixing training strategy. This approach mitigates the entanglement between the two tasks by initially using ground-truth poses to aggregate local Gaussians and gradually transitioning to a mix of predicted and ground-truth poses, which prevents both training instability and exposure bias. We further resolve the scale ambiguity problem by a novel pairwise camera-distance normalization scheme and by embedding camera intrinsics into the network. Moreover, YoNoSplat also predicts intrinsic parameters, making it feasible for uncalibrated inputs. YoNoSplat demonstrates exceptional efficiency, reconstructing a scene from 100 views (at 280x518 resolution) in just 2.69 seconds on an NVIDIA GH200 GPU. It achieves state-of-the-art performance on standard benchmarks in both pose-free and pose-dependent settings. Our project page is at https://botaoye.github.io/yonosplat/.

Paperid: 883, https://arxiv.org/pdf/2511.07304.pdf GitHub

Abstract:
This paper addresses the problem of Bangla hate speech identification, a socially impactful yet linguistically challenging task. As part of the "Bangla Multi-task Hate Speech Identification" shared task at the BLP Workshop, IJCNLP-AACL 2025, our team "Retriv" participated in all three subtasks: (1A) hate type classification, (1B) target group identification, and (1C) joint detection of type, severity, and target. For subtasks 1A and 1B, we employed a soft-voting ensemble of transformer models (BanglaBERT, MuRIL, IndicBERTv2). For subtask 1C, we trained three multitask variants and aggregated their predictions through a weighted voting ensemble. Our systems achieved micro-f1 scores of 72.75% (1A) and 72.69% (1B), and a weighted micro-f1 score of 72.62% (1C). On the shared task leaderboard, these corresponded to 9th, 10th, and 7th positions, respectively. These results highlight the promise of transformer ensembles and weighted multitask frameworks for advancing Bangla hate speech detection in low-resource contexts. We made experimental scripts publicly available for the community.

Paperid: 884, https://arxiv.org/pdf/2511.07298.pdf GitHub

Abstract:
Low-dose computed tomography (CT) represents a significant improvement in patient safety through lower radiation doses, but increased noise, blur, and contrast loss can diminish diagnostic quality. Therefore, consistency and robustness in image quality assessment become essential for clinical applications. In this study, we propose an LLM-based quality assessment system that generates both numerical scores and textual descriptions of degradations such as noise, blur, and contrast loss. Furthermore, various inference strategies - from the zero-shot approach to metadata integration and error feedback - are systematically examined, demonstrating the progressive contribution of each method to overall performance. The resultant assessments yield not only highly correlated scores but also interpretable output, thereby adding value to clinical workflows. The source codes of our study are available at https://github.com/itu-biai/lmms_ldct_iqa.

Paperid: 885, https://arxiv.org/pdf/2511.07292.pdf GitHub

Abstract:
Most recent work in autonomous driving has prioritized benchmark performance and methodological innovation over in-depth analysis of model failures, biases, and shortcut learning. This has led to incremental improvements without a deep understanding of the current failures. While it is straightforward to look at situations where the model fails, it is hard to understand the underlying reason. This motivates us to conduct a systematic study, where inputs to the model are perturbed and the predictions observed. We introduce PlanT 2.0, a lightweight, object-centric planning transformer designed for autonomous driving research in CARLA. The object-level representation enables controlled analysis, as the input can be easily perturbed (e.g., by changing the location or adding or removing certain objects), in contrast to sensor-based models. To tackle the scenarios newly introduced by the challenging CARLA Leaderboard 2.0, we introduce multiple upgrades to PlanT, achieving state-of-the-art performance on Longest6 v2, Bench2Drive, and the CARLA validation routes. Our analysis exposes insightful failures, such as a lack of scene understanding caused by low obstacle diversity, rigid expert behaviors leading to exploitable shortcuts, and overfitting to a fixed set of expert trajectories. Based on these findings, we argue for a shift toward data-centric development, with a focus on richer, more robust, and less biased datasets. We open-source our code and model at https://github.com/autonomousvision/plant2.

Paperid: 886, https://arxiv.org/pdf/2511.07290.pdf GitHub

Abstract:
The prevalence of user-generated content (UGC) on platforms such as YouTube and TikTok has rendered no-reference (NR) perceptual video quality assessment (VQA) vital for optimizing video delivery. Nonetheless, the characteristics of non-professional acquisition and the subsequent transcoding of UGC video on sharing platforms present significant challenges for NR-VQA. Although NR-VQA models attempt to infer mean opinion scores (MOS), their modeling of subjective scores for compressed content remains limited due to the absence of fine-grained perceptual annotations of artifact types. To address these challenges, we propose CAMP-VQA, a novel NR-VQA framework that exploits the semantic understanding capabilities of large vision-language models. Our approach introduces a quality-aware prompting mechanism that integrates video metadata (e.g., resolution, frame rate, bitrate) with key fragments extracted from inter-frame variations to guide the BLIP-2 pretraining approach in generating fine-grained quality captions. A unified architecture has been designed to model perceptual quality across three dimensions: semantic alignment, temporal characteristics, and spatial characteristics. These multimodal features are extracted and fused, then regressed to video quality scores. Extensive experiments on a wide variety of UGC datasets demonstrate that our model consistently outperforms existing NR-VQA methods, achieving improved accuracy without the need for costly manual fine-grained annotations. Our method achieves the best performance in terms of average rank and linear correlation (SRCC: 0.928, PLCC: 0.938) compared to state-of-the-art methods. The source code and trained models, along with a user-friendly demo, are available at: https://github.com/xinyiW915/CAMP-VQA.

Paperid: 887, https://arxiv.org/pdf/2511.07278.pdf GitHub

Abstract:
Video Large Language Models (Video-LLMs) have demonstrated significant potential in the areas of video captioning, search, and summarization. However, current Video-LLMs still face challenges with long real-world videos. Recent methods have introduced a retrieval mechanism that retrieves query-relevant KV caches for question answering, enhancing the efficiency and accuracy of long real-world videos. However, the compression and retrieval of KV caches are still not fully explored. In this paper, we propose \textbf{StreamKV}, a training-free framework that seamlessly equips Video-LLMs with advanced KV cache retrieval and compression. Compared to previous methods that used uniform partitioning, StreamKV dynamically partitions video streams into semantic segments, which better preserves semantic information. For KV cache retrieval, StreamKV calculates a summary vector for each segment to retain segment-level information essential for retrieval. For KV cache compression, StreamKV introduces a guidance prompt designed to capture the key semantic elements within each segment, ensuring only the most informative KV caches are retained for answering questions. Moreover, StreamKV unifies KV cache retrieval and compression within a single module, performing both in a layer-adaptive manner, thereby further improving the effectiveness of streaming video question answering. Extensive experiments on public StreamingVQA benchmarks demonstrate that StreamKV significantly outperforms existing Online Video-LLMs, achieving superior accuracy while substantially improving both memory efficiency and computational latency. The code has been released at https://github.com/sou1p0wer/StreamKV.

Paperid: 888, https://arxiv.org/pdf/2511.07263.pdf GitHub

Abstract:
Object-centric process mining addresses the limitations of traditional approaches, which often involve the lossy flattening of event data and obscure vital relationships among interacting objects. This paper presents a novel formal framework for Object-centric Event Data (OCED) that ensures the correctness of the meta-model and preserves native object-centric semantics prior to the system implementation. Our approach effectively leverages Alloy for precisely specifying temporal properties and structural relationships between objects and events. This guarantees thorough verification against predefined OCED constraints such as cross-object cardinality bounds and time-aware consistency rules, hence preventing common data integrity issues. We demonstrate the effectiveness of the proposed framework in discovering and validating implicit object dependencies in event logs, particularly when importing data into graph databases like Neo4j. This demonstrates how formal verification can avoid pitfalls that lead to data invisibility and improve knowledge graph creation, enrichment, and querying. To bridge theory and practice, our verified \emph{FOCED} is made accessible through automatically generated Python bindings, empowering industrial users without formal methods expertise. The code is available on GitHub \footnote{https://github.com/sabalati/FOCED}

Paperid: 889, https://arxiv.org/pdf/2511.07253.pdf GitHub

Abstract:
Large language models (LLMs) have recently achieved impressive results in speech recognition across multiple modalities, including Auditory Speech Recognition (ASR), Visual Speech Recognition (VSR), and Audio-Visual Speech Recognition (AVSR). Despite this progress, current LLM-based approaches typically address each task independently, training separate models that raise computational and deployment resource use while missing potential cross-task synergies. They also rely on fixed-rate token compression, which restricts flexibility in balancing accuracy with efficiency. These limitations highlight the need for a unified framework that can support ASR, VSR, and AVSR while enabling elastic inference. To this end, we present Omni-AVSR, a unified audio-visual LLM that combines efficient multi-granularity training with parameter-efficient adaptation. Specifically, we adapt the matryoshka representation learning paradigm to efficiently train across multiple audio and visual granularities, reducing its inherent training resource use. Furthermore, we explore three LoRA-based strategies for adapting the backbone LLM, balancing shared and task-specific specialization. Experiments on LRS2 and LRS3 show that Omni-AVSR achieves comparable or superior accuracy to state-of-the-art baselines while training a single model at substantially lower training and deployment resource use. The model also remains robust under acoustic noise, and we analyze its scaling behavior as LLM size increases, providing insights into the trade-off between performance and efficiency.

Paperid: 890, https://arxiv.org/pdf/2511.07142.pdf GitHub

Abstract:
We introduce ProcGen3D, a new approach for 3D content creation by generating procedural graph abstractions of 3D objects, which can then be decoded into rich, complex 3D assets. Inspired by the prevalent use of procedural generators in production 3D applications, we propose a sequentialized, graph-based procedural graph representation for 3D assets. We use this to learn to approximate the landscape of a procedural generator for image-based 3D reconstruction. We employ edge-based tokenization to encode the procedural graphs, and train a transformer prior to predict the next token conditioned on an input RGB image. Crucially, to enable better alignment of our generated outputs to an input image, we incorporate Monte Carlo Tree Search (MCTS) guided sampling into our generation process, steering output procedural graphs towards more image-faithful reconstructions. Our approach is applicable across a variety of objects that can be synthesized with procedural generators. Extensive experiments on cacti, trees, and bridges show that our neural procedural graph generation outperforms both state-of-the-art generative 3D methods and domain-specific modeling techniques. Furthermore, this enables improved generalization on real-world input images, despite training only on synthetic data.

Paperid: 891, https://arxiv.org/pdf/2511.07109.pdf GitHub

Abstract:
Nonnegative matrix factorization (NMF) is a linear dimensionality reduction technique for nonnegative data, with applications such as hyperspectral unmixing and topic modeling. NMF is a difficult problem in general (NP-hard), and its solutions are typically not unique. To address these two issues, additional constraints or assumptions are often used. In particular, separability assumes that the basis vectors in the NMF are equal to some columns of the input matrix. In that case, the problem is referred to as separable NMF (SNMF) and can be solved in polynomial-time with robustness guarantees, while identifying a unique solution. However, in real-world scenarios, due to noise or variability, multiple data points may lie near the basis vectors, which SNMF does not leverage. In this work, we rely on the smooth separability assumption, which assumes that each basis vector is close to multiple data points. We explore the properties of the corresponding problem, referred to as smooth SNMF (SSNMF), and examine how it relates to SNMF and orthogonal NMF. We then propose a convex model for SSNMF and show that it provably recovers the sought-after factors, even in the presence of noise. We finally adapt an existing fast gradient method to solve this convex model for SSNMF, and show that it compares favorably with state-of-the-art methods on both synthetic and hyperspectral datasets.

Paperid: 892, https://arxiv.org/pdf/2511.07099.pdf GitHub

Abstract:
Recent advancements in speech synthesis technology have enriched our daily lives, with high-quality and human-like audio widely adopted across real-world applications. However, malicious exploitation like voice-cloning fraud poses severe security risks. Existing defense techniques struggle to address the production large language model (LLM)-based speech synthesis. While previous studies have considered the protection for fine-tuning synthesizers, they assume manually annotated transcripts. Given the labor intensity of manual annotation, end-to-end (E2E) systems leveraging automatic speech recognition (ASR) to generate transcripts are becoming increasingly prevalent, e.g., voice cloning via commercial APIs. Therefore, this E2E speech synthesis also requires new security mechanisms. To tackle these challenges, we propose E2E-VGuard, a proactive defense framework for two emerging threats: (1) production LLM-based speech synthesis, and (2) the novel attack arising from ASR-driven E2E scenarios. Specifically, we employ the encoder ensemble with a feature extractor to protect timbre, while ASR-targeted adversarial examples disrupt pronunciation. Moreover, we incorporate the psychoacoustic model to ensure perturbative imperceptibility. For a comprehensive evaluation, we test 16 open-source synthesizers and 3 commercial APIs across Chinese and English datasets, confirming E2E-VGuard's effectiveness in timbre and pronunciation protection. Real-world deployment validation is also conducted. Our code and demo page are available at https://wxzyd123.github.io/e2e-vguard/.

Paperid: 893, https://arxiv.org/pdf/2511.07098.pdf GitHub

Abstract:
Fine-grained urban flow inference is crucial for urban planning and intelligent transportation systems, enabling precise traffic management and resource allocation. However, the practical deployment of existing methods is hindered by two key challenges: the prohibitive computational cost of over-parameterized models and the suboptimal performance of conventional loss functions on the highly skewed distribution of urban flows. To address these challenges, we propose a unified solution that synergizes architectural efficiency with adaptive optimization. Specifically, we first introduce PLGF, a lightweight yet powerful architecture that employs a Progressive Local-Global Fusion strategy to effectively capture both fine-grained details and global contextual dependencies. Second, we propose DualFocal Loss, a novel function that integrates dual-space supervision with a difficulty-aware focusing mechanism, enabling the model to adaptively concentrate on hard-to-predict regions. Extensive experiments on 4 real-world scenarios validate the effectiveness and scalability of our method. Notably, while achieving state-of-the-art performance, PLGF reduces the model size by up to 97% compared to current high-performing methods. Furthermore, under comparable parameter budgets, our model yields an accuracy improvement of over 10% against strong baselines. The implementation is included in the https://github.com/Yasoz/PLGF.

Paperid: 894, https://arxiv.org/pdf/2511.07094.pdf GitHub

Abstract:
Deep learning-based low-dose computed tomography reconstruction methods already achieve high performance on standard image quality metrics like peak signal-to-noise ratio and structural similarity index measure. Yet, they frequently fail to preserve the critical anatomical details needed for diagnostic tasks. This fundamental limitation hinders their clinical applicability despite their high metric scores. We propose a novel task-adaptive reconstruction framework that addresses this gap by incorporating a frozen pre-trained task network as a regularization term in the reconstruction loss function. Unlike existing joint-training approaches that simultaneously optimize both reconstruction and task networks, and risk diverging from satisfactory reconstructions, our method leverages a pre-trained task model to guide reconstruction training while still maintaining diagnostic quality. We validate our framework on a liver and liver tumor segmentation task. Our task-adaptive models achieve Dice scores up to 0.707, approaching the performance of full-dose scans (0.874), and substantially outperforming joint-training approaches (0.331) and traditional reconstruction methods (0.626). Critically, our framework can be integrated into any existing deep learning-based reconstruction model through simple loss function modification, enabling widespread adoption for task-adaptive optimization in clinical practice. Our codes are available at: https://github.com/itu-biai/task_adaptive_ct

Paperid: 895, https://arxiv.org/pdf/2511.07078.pdf GitHub

Abstract:
Two-view correspondence pruning aims to accurately remove incorrect correspondences (outliers) from initial ones and is widely applied to various computer vision tasks. Current popular strategies adopt multilayer perceptron (MLP) as the backbone, supplemented by additional modules to enhance the network ability to handle context information, which is a known limitation of MLPs. In contrast, we introduce a novel perspective for capturing correspondence context information without extra design modules. To this end, we design a two-view correspondence pruning network called LeCoT, which can naturally leverage global context information at different stages. Specifically, the core design of LeCoT is the Spatial-Channel Fusion Transformer block, a newly proposed component that efficiently utilizes both spatial and channel global context information among sparse correspondences. In addition, we integrate the proposed prediction block that utilizes correspondence features from intermediate stages to generate a probability set, which acts as guiding information for subsequent learning phases, allowing the network to more effectively capture robust global context information. Notably, this prediction block progressively refines the probability set, thereby mitigating the issue of information loss that is common in the traditional one. Extensive experiments prove that the proposed LeCoT outperforms state-of-the-art methods in correspondence pruning, relative pose estimation, homography estimation, visual localization, and $3$D~reconstruction tasks. The code is provided in https://github.com/Dailuanyuan2024/LeCoT-Revisiting-Network-Architecture-for-Two-View-Correspondence-Pruning.

Paperid: 896, https://arxiv.org/pdf/2511.07071.pdf GitHub GitHub

Abstract:
This dissertation explores the application of multi-agent reinforcement learning (MARL) for handling deadlocks in intralogistics systems that rely on autonomous mobile robots (AMRs). AMRs enhance operational flexibility but also increase the risk of deadlocks, which degrade system throughput and reliability. Existing approaches often neglect deadlock handling in the planning phase and rely on rigid control rules that cannot adapt to dynamic operational conditions. To address these shortcomings, this work develops a structured methodology for integrating MARL into logistics planning and operational control. It introduces reference models that explicitly consider deadlock-capable multi-agent pathfinding (MAPF) problems, enabling systematic evaluation of MARL strategies. Using grid-based environments and an external simulation software, the study compares traditional deadlock handling strategies with MARL-based solutions, focusing on PPO and IMPALA algorithms under different training and execution modes. Findings reveal that MARL-based strategies, particularly when combined with centralized training and decentralized execution (CTDE), outperform rule-based methods in complex, congested environments. In simpler environments or those with ample spatial freedom, rule-based methods remain competitive due to their lower computational demands. These results highlight that MARL provides a flexible and scalable solution for deadlock handling in dynamic intralogistics scenarios, but requires careful tailoring to the operational context.

Paperid: 897, https://arxiv.org/pdf/2511.07068.pdf GitHub GitHub

Abstract:
Large-scale visual out-of-distribution (OOD) detection has witnessed remarkable progress by leveraging vision-language models such as CLIP. However, a significant limitation of current methods is their reliance on a pre-defined set of in-distribution (ID) ground-truth label names (positives). These fixed label names can be unavailable, unreliable at scale, or become less relevant due to in-distribution shifts after deployment. Towards truly unsupervised OOD detection, we utilize widely available text corpora for positive label mining, bypassing the need for positives. In this paper, we utilize widely available text corpora for positive label mining under a general concept mining paradigm. Within this framework, we propose ClusterMine, a novel positive label mining method. ClusterMine is the first method to achieve state-of-the-art OOD detection performance without access to positive labels. It extracts positive concepts from a large text corpus by combining visual-only sample consistency (via clustering) and zero-shot image-text consistency. Our experimental study reveals that ClusterMine is scalable across a plethora of CLIP models and achieves state-of-the-art robustness to covariate in-distribution shifts. The code is available at https://github.com/HHU-MMBS/clustermine_wacv_official.

Paperid: 898, https://arxiv.org/pdf/2511.07007.pdf GitHub

Abstract:
3D semantic scene understanding remains a long-standing challenge in the 3D computer vision community. One of the key issues pertains to limited real-world annotated data to facilitate generalizable models. The common practice to tackle this issue is to simulate new data. Although synthetic datasets offer scalability and perfect labels, their designer-crafted scenes fail to capture real-world complexity and sensor noise, resulting in a synthetic-to-real domain gap. Moreover, no benchmark provides synchronized real and simulated point clouds for segmentation-oriented domain shift analysis. We introduce TrueCity, the first urban semantic segmentation benchmark with cm-accurate annotated real-world point clouds, semantic 3D city models, and annotated simulated point clouds representing the same city. TrueCity proposes segmentation classes aligned with international 3D city modeling standards, enabling consistent evaluation of synthetic-to-real gap. Our extensive experiments on common baselines quantify domain shift and highlight strategies for exploiting synthetic data to enhance real-world 3D scene understanding. We are convinced that the TrueCity dataset will foster further development of sim-to-real gap quantification and enable generalizable data-driven models. The data, code, and 3D models are available online: https://tum-gis.github.io/TrueCity/

Paperid: 899, https://arxiv.org/pdf/2511.07003.pdf GitHub GitHub

Abstract:
Large language models have significantly advanced Multilingual Machine Translation (MMT), yet the broad language coverage, consistent translation quality, and English-centric bias remain open challenges. To address these challenges, we introduce \textbf{LMT}, a suite of \textbf{L}arge-scale \textbf{M}ultilingual \textbf{T}ranslation models centered on both Chinese and English, covering 60 languages and 234 translation directions. During development, we identify a previously overlooked phenomenon of \textbf{directional degeneration}, where symmetric multi-way fine-tuning data overemphasize reverse directions (X $\to$ En/Zh), leading to excessive many-to-one mappings and degraded translation quality. We propose \textbf{Strategic Downsampling}, a simple yet effective method to mitigate this degeneration. In addition, we design \textbf{Parallel Multilingual Prompting (PMP)}, which leverages typologically related auxiliary languages to enhance cross-lingual transfer. Through rigorous data curation and refined adaptation strategies, LMT achieves SOTA performance among models of comparable language coverage, with our 4B model (LMT-60-4B) surpassing the much larger Aya-101-13B and NLLB-54B models by a substantial margin. We release LMT in four sizes (0.6B/1.7B/4B/8B) to catalyze future research and provide strong baselines for inclusive, scalable, and high-quality MMT \footnote{\href{https://github.com/NiuTrans/LMT}{https://github.com/NiuTrans/LMT}}.

Paperid: 900, https://arxiv.org/pdf/2511.07002.pdf GitHub

Abstract:
Mechanistic interpretability aims to understand neural networks by identifying which learned features mediate specific behaviors. Attribution graphs reveal these feature pathways, but interpreting them requires extensive manual analysis -- a single prompt can take approximately 2 hours for an experienced circuit tracer. We present probe prompting, an automated pipeline that transforms attribution graphs into compact, interpretable subgraphs built from concept-aligned supernodes. Starting from a seed prompt and target logit, we select high-influence features, generate concept-targeted yet context-varying probes, and group features by cross-prompt activation signatures into Semantic, Relationship, and Say-X categories using transparent decision rules. Across five prompts including classic "capitals" circuits, probe-prompted subgraphs preserve high explanatory coverage while compressing complexity (Completeness 0.83, mean across circuits; Replacement 0.54). Compared to geometric clustering baselines, concept-aligned groups exhibit higher behavioral coherence: 2.3x higher peak-token consistency (0.425 vs 0.183) and 5.8x higher activation-pattern similarity (0.762 vs 0.130), despite lower geometric compactness. Entity-swap tests reveal a layerwise hierarchy: early-layer features transfer robustly (64% transfer rate, mean layer 6.3), while late-layer Say-X features specialize for output promotion (mean layer 16.4), supporting a backbone-and-specialization view of transformer computation. We release code (https://github.com/peppinob-ol/attribution-graph-probing), an interactive demo (https://huggingface.co/spaces/Peppinob/attribution-graph-probing), and minimal artifacts enabling immediate reproduction and community adoption.

Paperid: 901, https://arxiv.org/pdf/2511.06982.pdf GitHub

Abstract:
Link prediction is a pivotal task in graph mining with wide-ranging applications in social networks, recommendation systems, and knowledge graph completion. However, many leading Graph Neural Network (GNN) models often neglect the valuable semantic information aggregated at the class level. To address this limitation, this paper introduces CGLE (Class-label Graph Link Estimator), a novel framework designed to augment GNN-based link prediction models. CGLE operates by constructing a class-conditioned link probability matrix, where each entry represents the probability of a link forming between two node classes. This matrix is derived from either available ground-truth labels or from pseudo-labels obtained through clustering. The resulting class-based prior is then concatenated with the structural link embedding from a backbone GNN, and the combined representation is processed by a Multi-Layer Perceptron (MLP) for the final prediction. Crucially, CGLE's logic is encapsulated in an efficient preprocessing stage, leaving the computational complexity of the underlying GNN model unaffected. We validate our approach through extensive experiments on a broad suite of benchmark datasets, covering both homophilous and sparse heterophilous graphs. The results show that CGLE yields substantial performance gains over strong baselines such as NCN and NCNC, with improvements in HR@100 of over 10 percentage points on homophilous datasets like Pubmed and DBLP. On sparse heterophilous graphs, CGLE delivers an MRR improvement of over 4% on the Chameleon dataset. Our work underscores the efficacy of integrating global, data-driven semantic priors, presenting a compelling alternative to the pursuit of increasingly complex model architectures. Code to reproduce our findings is available at: https://github.com/data-iitd/cgle-icdm2025.

Paperid: 902, https://arxiv.org/pdf/2511.06955.pdf GitHub

Abstract:
Edge AI deployment faces critical challenges balancing computational performance, energy efficiency, and resource constraints. This paper presents FPGA-accelerated RISC-V instruction set architecture (ISA) extensions for efficient neural network inference on resource-constrained edge devices. We introduce a custom RISC-V core with four novel ISA extensions (FPGA.VCONV, FPGA.GEMM, FPGA.RELU, FPGA.CUSTOM) and integrated neural network accelerators, implemented and validated on the Xilinx PYNQ-Z2 platform. The complete system achieves 2.14x average latency speedup and 49.1% energy reduction versus an ARM Cortex-A9 software baseline across four benchmark models (MobileNet V2, ResNet-18, EfficientNet Lite, YOLO Tiny). Hardware implementation closes timing with +12.793 ns worst negative slack at 50 MHz while using 0.43% LUTs and 11.4% BRAM for the base core and 38.8% DSPs when accelerators are active. Hardware verification confirms successful FPGA deployment with verified 64 KB BRAM memory interface and AXI interconnect functionality. All performance metrics are obtained from physical hardware measurements. This work establishes a reproducible framework for ISA-guided FPGA acceleration that complements fixed-function ASICs by trading peak performance for programmability.

Paperid: 903, https://arxiv.org/pdf/2511.06942.pdf GitHub

Abstract:
To prevent misinformation and social issues arising from trustworthy-looking content generated by LLMs, it is crucial to develop efficient and reliable methods for identifying the source of texts. Previous approaches have demonstrated exceptional performance in detecting texts fully generated by LLMs. However, these methods struggle when confronting more advanced LLM output or text with adversarial multi-task machine revision, especially in the black-box setting, where the generating model is unknown. To address this challenge, grounded in the hypothesis that human writing possesses distinctive stylistic patterns, we propose Human Language Preference Detection (HLPD). HLPD employs a reward-based alignment process, Human Language Preference Optimization (HLPO), to shift the scoring model's token distribution toward human-like writing, making the model more sensitive to human writing, therefore enhancing the identification of machine-revised text. We test HLPD in an adversarial multi-task evaluation framework that leverages a five-dimensional prompt generator and multiple advanced LLMs to create diverse revision scenarios. When detecting texts revised by GPT-series models, HLPD achieves a 15.11% relative improvement in AUROC over ImBD, surpassing Fast-DetectGPT by 45.56%. When evaluated on texts generated by advanced LLMs, HLPD achieves the highest average AUROC, exceeding ImBD by 5.53% and Fast-DetectGPT by 34.14%. Code will be made available at https://github.com/dfq2021/HLPD.

Paperid: 904, https://arxiv.org/pdf/2511.06925.pdf GitHub

Abstract:
Video shadow detection confronts two entwined difficulties: distinguishing shadows from complex backgrounds and modeling dynamic shadow deformations under varying illumination. To address shadow-background ambiguity, we leverage linguistic priors through the proposed Vision-language Match Module (VMM) and a Dark-aware Semantic Block (DSB), extracting text-guided features to explicitly differentiate shadows from dark objects. Furthermore, we introduce adaptive mask reweighting to downweight penumbra regions during training and apply edge masks at the final decoder stage for better supervision. For temporal modeling of variable shadow shapes, we propose a Tokenized Temporal Block (TTB) that decouples spatiotemporal learning. TTB summarizes cross-frame shadow semantics into learnable temporal tokens, enabling efficient sequence encoding with minimal computation overhead. Comprehensive Experiments on multiple benchmark datasets demonstrate state-of-the-art accuracy and real-time inference efficiency. Codes are available at https://github.com/city-cheng/DTTNet.

Paperid: 905, https://arxiv.org/pdf/2511.06902.pdf GitHub

Abstract:
Spiking Neural Networks (SNNs) become popular due to excellent energy efficiency, yet facing challenges for effective model training. Recent works improve this by introducing knowledge distillation (KD) techniques, with the pre-trained artificial neural networks (ANNs) used as teachers and the target SNNs as students. This is commonly accomplished through a straightforward element-wise alignment of intermediate features and prediction logits from ANNs and SNNs, often neglecting the intrinsic differences between their architectures. Specifically, ANN's outputs exhibit a continuous distribution, whereas SNN's outputs are characterized by sparsity and discreteness. To mitigate this issue, we introduce two innovative KD strategies. Firstly, we propose the Saliency-scaled Activation Map Distillation (SAMD), which aligns the spike activation map of the student SNN with the class-aware activation map of the teacher ANN. Rather than performing KD directly on the raw %and distinct features of ANN and SNN, our SAMD directs the student to learn from saliency activation maps that exhibit greater semantic and distribution consistency. Additionally, we propose a Noise-smoothed Logits Distillation (NLD), which utilizes Gaussian noise to smooth the sparse logits of student SNN, facilitating the alignment with continuous logits from teacher ANN. Extensive experiments on multiple datasets demonstrate the effectiveness of our methods. Code is available~\footnote{https://github.com/SinoLeu/CKDSNN.git}.

Paperid: 906, https://arxiv.org/pdf/2511.06890.pdf GitHub

Abstract:
Large Language Models for Simulating Professions (SP-LLMs), particularly as teachers, are pivotal for personalized education. However, ensuring their professional competence and ethical safety is a critical challenge, as existing benchmarks fail to measure role-playing fidelity or address the unique teaching harms inherent in educational scenarios. To address this, we propose EduGuardBench, a dual-component benchmark. It assesses professional fidelity using a Role-playing Fidelity Score (RFS) while diagnosing harms specific to the teaching profession. It also probes safety vulnerabilities using persona-based adversarial prompts targeting both general harms and, particularly, academic misconduct, evaluated with metrics including Attack Success Rate (ASR) and a three-tier Refusal Quality assessment. Our extensive experiments on 14 leading models reveal a stark polarization in performance. While reasoning-oriented models generally show superior fidelity, incompetence remains the dominant failure mode across most models. The adversarial tests uncovered a counterintuitive scaling paradox, where mid-sized models can be the most vulnerable, challenging monotonic safety assumptions. Critically, we identified a powerful Educational Transformation Effect: the safest models excel at converting harmful requests into teachable moments by providing ideal Educational Refusals. This capacity is strongly negatively correlated with ASR, revealing a new dimension of advanced AI safety. EduGuardBench thus provides a reproducible framework that moves beyond siloed knowledge tests toward a holistic assessment of professional, ethical, and pedagogical alignment, uncovering complex dynamics essential for deploying trustworthy AI in education. See https://github.com/YL1N/EduGuardBench for Materials.

Paperid: 907, https://arxiv.org/pdf/2511.06848.pdf GitHub

Abstract:
While feature-based knowledge distillation has proven highly effective for compressing CNNs, these techniques unexpectedly fail when applied to Vision Transformers (ViTs), often performing worse than simple logit-based distillation. We provide the first comprehensive analysis of this phenomenon through a novel analytical framework termed as "distillation dynamics", combining frequency spectrum analysis, information entropy metrics, and activation magnitude tracking. Our investigation reveals that ViTs exhibit a distinctive U-shaped information processing pattern: initial compression followed by expansion. We identify the root cause of negative transfer in feature distillation: a fundamental representational paradigm mismatch between teacher and student models. Through frequency-domain analysis, we show that teacher models employ distributed, high-dimensional encoding strategies in later layers that smaller student models cannot replicate due to limited channel capacity. This mismatch causes late-layer feature alignment to actively harm student performance. Our findings reveal that successful knowledge transfer in ViTs requires moving beyond naive feature mimicry to methods that respect these fundamental representational constraints, providing essential theoretical guidance for designing effective ViTs compression strategies. All source code and experimental logs are provided at https://github.com/thy960112/Distillation-Dynamics.

Paperid: 908, https://arxiv.org/pdf/2511.06838.pdf GitHub

Abstract:
The substantial memory bandwidth and computational demands of large language models (LLMs) present critical challenges for efficient inference. To tackle this, the literature has explored heterogeneous systems that combine neural processing units (NPUs) with DRAM-based processing-in-memory (PIM) for LLM acceleration. However, existing high-precision (e.g., FP16) PIM compute units incur significant area and power overhead in DRAM technology, limiting the effective computation throughput. In this paper, we introduce P3-LLM, a novel NPU-PIM integrated accelerator for LLM inference using hybrid numerical formats. Our approach is threefold: First, we propose a flexible mixed-precision quantization scheme, which leverages hybrid numerical formats to quantize different LLM operands with high compression efficiency and minimal accuracy loss. Second, we architect an efficient PIM accelerator for P3-LLM, featuring enhanced compute units to support hybrid numerical formats. Our careful choice of numerical formats allows to co-design low-precision PIM compute units that significantly boost the computation throughput under iso-area constraints. Third, we optimize the low-precision dataflow of different LLM modules by applying operator fusion to minimize the overhead of runtime dequantization. Evaluation on a diverse set of representative LLMs and tasks demonstrates that P3-LLM achieves state-of-the-art accuracy in terms of both KV-cache quantization and weight-activation quantization. Combining the proposed quantization scheme with PIM architecture co-design, P3-LLM yields an average of $4.9\times$, $2.0\times$, and $3.4\times$ speedups over the state-of-the-art LLM accelerators HBM-PIM, Ecco, and Pimba, respectively. Our quantization code is available at https://github.com/yc2367/P3-LLM.git

Paperid: 909, https://arxiv.org/pdf/2511.06803.pdf GitHub

Abstract:
Modern data-driven recommendation systems risk memorizing sensitive user behavioral patterns, raising privacy concerns. Existing recommendation unlearning methods, while capable of removing target data influence, suffer from inefficient unlearning speed and degraded performance, failing to meet real-time unlearning demands. Considering the ranking-oriented nature of recommendation systems, we present unranking, the process of reducing the ranking positions of target items while ensuring the formal guarantees of recommendation unlearning. To achieve efficient unranking, we propose Learning to Fast Unrank in Collaborative Filtering Recommendation (L2UnRank), which operates through three key stages: (a) identifying the influenced scope via interaction-based p-hop propagation, (b) computing structural and semantic influences for entities within this scope, and (c) performing efficient, ranking-aware parameter updates guided by influence information. Extensive experiments across multiple datasets and backbone models demonstrate L2UnRank's model-agnostic nature, achieving state-of-the-art unranking effectiveness and maintaining recommendation quality comparable to retraining, while also delivering a 50x speedup over existing methods. Codes are available at https://github.com/Juniper42/L2UnRank.

Paperid: 910, https://arxiv.org/pdf/2511.06793.pdf GitHub

Abstract:
Multimodal Large Language Models (MLLMs) extend foundation models to real-world applications by integrating inputs such as text and vision. However, their broad knowledge capacity raises growing concerns about privacy leakage, toxicity mitigation, and intellectual property violations. Machine Unlearning (MU) offers a practical solution by selectively forgetting targeted knowledge while preserving overall model utility. When applied to MLLMs, existing neuron-editing-based MU approaches face two fundamental challenges: (1) forgetting becomes inconsistent across modalities because existing point-wise attribution methods fail to capture the structured, layer-by-layer information flow that connects different modalities; and (2) general knowledge performance declines when sensitive neurons that also support important reasoning paths are pruned, as this disrupts the model's ability to generalize. To alleviate these limitations, we propose a multimodal influential neuron path editor (MIP-Editor) for MU. Our approach introduces modality-specific attribution scores to identify influential neuron paths responsible for encoding forget-set knowledge and applies influential-path-aware neuron-editing via representation misdirection. This strategy also enables effective and coordinated forgetting across modalities while preserving the model's general capabilities. Experimental results demonstrate that MIP-Editor achieves a superior unlearning performance on multimodal tasks, with a maximum forgetting rate of 87.75% and up to 54.26% improvement in general knowledge retention. On textual tasks, MIP-Editor achieves up to 80.65% forgetting and preserves 77.9% of general performance. Codes are available at https://github.com/PreckLi/MIP-Editor.

Paperid: 911, https://arxiv.org/pdf/2511.06765.pdf GitHub

Abstract:
3D Gaussian Splatting (3DGS) has emerged as a key rendering pipeline for digital asset creation due to its balance between efficiency and visual quality. To address the issues of unstable pose estimation and scene representation distortion caused by geometric texture inconsistency in large outdoor scenes with weak or repetitive textures, we approach the problem from two aspects: pose estimation and scene representation. For pose estimation, we leverage LiDAR-IMU Odometry to provide prior poses for cameras in large-scale environments. These prior pose constraints are incorporated into COLMAP's triangulation process, with pose optimization performed via bundle adjustment. Ensuring consistency between pixel data association and prior poses helps maintain both robustness and accuracy. For scene representation, we introduce normal vector constraints and effective rank regularization to enforce consistency in the direction and shape of Gaussian primitives. These constraints are jointly optimized with the existing photometric loss to enhance the map quality. We evaluate our approach using both public and self-collected datasets. In terms of pose optimization, our method requires only one-third of the time while maintaining accuracy and robustness across both datasets. In terms of scene representation, the results show that our method significantly outperforms conventional 3DGS pipelines. Notably, on self-collected datasets characterized by weak or repetitive textures, our approach demonstrates enhanced visualization capabilities and achieves superior overall performance. Codes and data will be publicly available at https://github.com/justinyeah/normal_shape.git.

Paperid: 912, https://arxiv.org/pdf/2511.06749.pdf GitHub

Abstract:
Efficient, accurate, and flexible relative localization is crucial in air-ground collaborative tasks. However, current approaches for robot relative localization are primarily realized in the form of distributed multi-robot SLAM systems with the same sensor configuration, which are tightly coupled with the state estimation of all robots, limiting both flexibility and accuracy. To this end, we fully leverage the high capacity of Unmanned Ground Vehicle (UGV) to integrate multiple sensors, enabling a semi-distributed cross-modal air-ground relative localization framework. In this work, both the UGV and the Unmanned Aerial Vehicle (UAV) independently perform SLAM while extracting deep learning-based keypoints and global descriptors, which decouples the relative localization from the state estimation of all agents. The UGV employs a local Bundle Adjustment (BA) with LiDAR, camera, and an IMU to rapidly obtain accurate relative pose estimates. The BA process adopts sparse keypoint optimization and is divided into two stages: First, optimizing camera poses interpolated from LiDAR-Inertial Odometry (LIO), followed by estimating the relative camera poses between the UGV and UAV. Additionally, we implement an incremental loop closure detection algorithm using deep learning-based descriptors to maintain and retrieve keyframes efficiently. Experimental results demonstrate that our method achieves outstanding performance in both accuracy and efficiency. Unlike traditional multi-robot SLAM approaches that transmit images or point clouds, our method only transmits keypoint pixels and their descriptors, effectively constraining the communication bandwidth under 0.3 Mbps. Codes and data will be publicly available on https://github.com/Ascbpiac/cross-model-relative-localization.git.

Paperid: 913, https://arxiv.org/pdf/2511.06722.pdf GitHub

Abstract:
Recent advances in Multimodal Large Language Models (MLLMs) have spurred significant progress in Chain-of-Thought (CoT) reasoning. Building on the success of Deepseek-R1, researchers extended multimodal reasoning to post-training paradigms based on reinforcement learning (RL), focusing predominantly on mathematical datasets. However, existing post-training paradigms tend to neglect two critical aspects: (1) The lack of quantifiable difficulty metrics capable of strategically screening samples for post-training optimization. (2) Suboptimal post-training paradigms that fail to jointly optimize perception and reasoning capabilities. To address this gap, we propose two novel difficulty-aware sampling strategies: Progressive Image Semantic Masking (PISM) quantifies sample hardness through systematic image degradation, while Cross-Modality Attention Balance (CMAB) assesses cross-modal interaction complexity via attention distribution analysis. Leveraging these metrics, we design a hierarchical training framework that incorporates both GRPO-only and SFT+GRPO hybrid training paradigms, and evaluate them across six benchmark datasets. Experiments demonstrate consistent superiority of GRPO applied to difficulty-stratified samples compared to conventional SFT+GRPO pipelines, indicating that strategic data sampling can obviate the need for supervised fine-tuning while improving model accuracy. Our code will be released at https://github.com/qijianyu277/DifficultySampling.

Paperid: 914, https://arxiv.org/pdf/2511.06686.pdf GitHub

Abstract:
Multi-modal learning (MML) aims to integrate information from multiple modalities, which is expected to lead to superior performance over single-modality learning. However, recent studies have shown that MML can underperform, even compared to single-modality approaches, due to imbalanced learning across modalities. Methods have been proposed to alleviate this imbalance issue using different heuristics, which often lead to computationally intensive subroutines. In this paper, we reformulate the MML problem as a multi-objective optimization (MOO) problem that overcomes the imbalanced learning issue among modalities and propose a gradient-based algorithm to solve the modified MML problem. We provide convergence guarantees for the proposed method, and empirical evaluations on popular MML benchmarks showcasing the improved performance of the proposed method over existing balanced MML and MOO baselines, with up to ~20x reduction in subroutine computation time. Our code is available at https://github.com/heshandevaka/MIMO.

Paperid: 915, https://arxiv.org/pdf/2511.06667.pdf GitHub

Abstract:
With the explosive growth of rigid-body simulators, policy learning in simulation has become the de facto standard for most rigid morphologies. In contrast, soft robotic simulation frameworks remain scarce and are seldom adopted by the soft robotics community. This gap stems partly from the lack of easy-to-use, general-purpose frameworks and partly from the high computational cost of accurately simulating continuum mechanics, which often renders policy learning infeasible. In this work, we demonstrate that rapid soft robot policy learning is indeed achievable via implicit time-stepping. Our simulator of choice, DisMech, is a general-purpose, fully implicit soft-body simulator capable of handling both soft dynamics and frictional contact. We further introduce delta natural curvature control, a method analogous to delta joint position control in rigid manipulators, providing an intuitive and effective means of enacting control for soft robot learning. To highlight the benefits of implicit time-stepping and delta curvature control, we conduct extensive comparisons across four diverse soft manipulator tasks against one of the most widely used soft-body frameworks, Elastica. With implicit time-stepping, parallel stepping of 500 environments achieves up to 6x faster speeds for non-contact cases and up to 40x faster for contact-rich scenarios. Finally, a comprehensive sim-to-sim gap evaluation--training policies in one simulator and evaluating them in another--demonstrates that implicit time-stepping provides a rare free lunch: dramatic speedups achieved without sacrificing accuracy.

Paperid: 916, https://arxiv.org/pdf/2511.06653.pdf GitHub

Abstract:
Contrastive vision-language models like CLIP have achieved impressive results in image-text retrieval by aligning image and text representations in a shared embedding space. However, these models often treat text as flat sequences, limiting their ability to handle complex, compositional, and long-form descriptions. In particular, they fail to capture two essential properties of language: semantic hierarchy, which reflects the multi-level compositional structure of text, and semantic monotonicity, where richer descriptions should result in stronger alignment with visual content.To address these limitations, we propose HiMo-CLIP, a representation-level framework that enhances CLIP-style models without modifying the encoder architecture. HiMo-CLIP introduces two key components: a hierarchical decomposition (HiDe) module that extracts latent semantic components from long-form text via in-batch PCA, enabling flexible, batch-aware alignment across different semantic granularities, and a monotonicity-aware contrastive loss (MoLo) that jointly aligns global and component-level representations, encouraging the model to internalize semantic ordering and alignment strength as a function of textual completeness.These components work in concert to produce structured, cognitively-aligned cross-modal representations. Experiments on multiple image-text retrieval benchmarks show that HiMo-CLIP consistently outperforms strong baselines, particularly under long or compositional descriptions. The code is available at https://github.com/UnicomAI/HiMo-CLIP.

Paperid: 917, https://arxiv.org/pdf/2511.06644.pdf GitHub

Abstract:
In this paper, we introduce the task of unified anomaly detection and classification, which aims to simultaneously detect anomalous regions in images and identify their specific categories. Existing methods typically treat anomaly detection and classification as separate tasks, thereby neglecting their inherent correlation, limiting information sharing, and resulting in suboptimal performance. To address this, we propose UniADC, a unified anomaly detection and classification model that can effectively perform both tasks with only a few or even no anomaly images. Specifically, UniADC consists of two key components: a training-free controllable inpainting network and a multi-task discriminator. The inpainting network can synthesize anomaly images of specific categories by repainting normal regions guided by anomaly priors, and can also repaint few-shot anomaly samples to augment the available anomaly data. The multi-task discriminator is then trained on these synthesized samples, enabling precise anomaly detection and classification by aligning fine-grained image features with anomaly-category embeddings. We conduct extensive experiments on three anomaly detection and classification datasets, including MVTec-FS, MTD, and WFDD, and the results demonstrate that UniADC consistently outperforms existing methods in anomaly detection, localization, and classification. The code is available at https://github.com/cnulab/UniADC.

Paperid: 918, https://arxiv.org/pdf/2511.06635.pdf GitHub

Abstract:
Large-scale supervised data is essential for training modern ranking models, but obtaining high-quality human annotations is costly. Click data has been widely used as a low-cost alternative, and with recent advances in large language models (LLMs), LLM-based relevance annotation has emerged as another promising annotation. This paper investigates whether LLM annotations can replace click data for learning to rank (LTR) by conducting a comprehensive comparison across multiple dimensions. Experiments on both a public dataset, TianGong-ST, and an industrial dataset, Baidu-Click, show that click-supervised models perform better on high-frequency queries, while LLM annotation-supervised models are more effective on medium- and low-frequency queries. Further analysis shows that click-supervised models are better at capturing document-level signals such as authority or quality, while LLM annotation-supervised models are more effective at modeling semantic matching between queries and documents and at distinguishing relevant from non-relevant documents. Motivated by these observations, we explore two training strategies -- data scheduling and frequency-aware multi-objective learning -- that integrate both supervision signals. Both approaches enhance ranking performance across queries at all frequency levels, with the latter being more effective. Our code is available at https://github.com/Trustworthy-Information-Access/LLMAnn_Click.

Paperid: 919, https://arxiv.org/pdf/2511.06634.pdf GitHub

Abstract:
Cross-domain HVAC energy prediction is essential for scalable building energy management, particularly because collecting extensive labeled data for every new building is both costly and impractical. Yet, this task remains highly challenging due to the scarcity and heterogeneity of data across different buildings, climate zones, and seasonal patterns. In particular, buildings situated in distinct climatic regions introduce variability that often leads existing methods to overfit to spurious correlations, rely heavily on expert intervention, or compromise on data diversity. To address these limitations, we propose CaberNet, a causal and interpretable deep sequence model that learns invariant (Markov blanket) representations for robust cross-domain prediction. In a purely data-driven fashion and without requiring any prior knowledge, CaberNet integrates i) a global feature gate trained with a self-supervised Bernoulli regularization to distinguish superior causal features from inferior ones, and ii) a domain-wise training scheme that balances domain contributions, minimizes cross-domain loss variance, and promotes latent factor independence. We evaluate CaberNet on real-world datasets collected from three buildings located in three climatically diverse cities, and it consistently outperforms all baselines, achieving a 22.9\% reduction in normalized mean squared error (NMSE) compared to the best benchmark. Our code is available at https://github.com/rickzky1001/CaberNet-CRL.

Paperid: 920, https://arxiv.org/pdf/2511.06606.pdf GitHub

Abstract:
Spatial perception is central to auditory intelligence, enabling accurate understanding of real-world acoustic scenes and advancing human-level perception of the world around us. While recent large audio-language models (LALMs) show strong reasoning over complex audios, most operate on monaural inputs and lack the ability to capture spatial cues such as direction, elevation, and distance. We introduce SPUR, a lightweight, plug-in approach that equips LALMs with spatial perception through minimal architectural changes. SPUR consists of: (i) a First-Order Ambisonics (FOA) encoder that maps (W, X, Y, Z) channels to rotation-aware, listener-centric spatial features, integrated into target LALMs via a multimodal adapter; and (ii) SPUR-Set, a spatial QA dataset combining open-source FOA recordings with controlled simulations, emphasizing relative direction, elevation, distance, and overlap for supervised spatial reasoning. Fine-tuning our model on the SPUR-Set consistently improves spatial QA and multi-speaker attribution while preserving general audio understanding. SPUR provides a simple recipe that transforms monaural LALMs into spatially aware models. Extensive ablations validate the effectiveness of our approach.

Paperid: 921, https://arxiv.org/pdf/2511.06593.pdf GitHub

Abstract:
Multi-Modal Image Fusion (MMIF) aims to integrate complementary image information from different modalities to produce informative images. Previous deep learning-based MMIF methods generally adopt Convolutional Neural Networks (CNNs) or Transformers for feature extraction. However, these methods deliver unsatisfactory performances due to the limited receptive field of CNNs and the high computational cost of Transformers. Recently, Mamba has demonstrated a powerful potential for modeling long-range dependencies with linear complexity, providing a promising solution to MMIF. Unfortunately, Mamba lacks full spatial and frequency perceptions, which are very important for MMIF. Moreover, employing Image Reconstruction (IR) as an auxiliary task has been proven beneficial for MMIF. However, a primary challenge is how to leverage IR efficiently and effectively. To address the above issues, we propose a novel framework named Spatial-Frequency Enhanced Mamba Fusion (SFMFusion) for MMIF. More specifically, we first propose a three-branch structure to couple MMIF and IR, which can retain complete contents from source images. Then, we propose the Spatial-Frequency Enhanced Mamba Block (SFMB), which can enhance Mamba in both spatial and frequency domains for comprehensive feature extraction. Finally, we propose the Dynamic Fusion Mamba Block (DFMB), which can be deployed across different branches for dynamic feature fusion. Extensive experiments show that our method achieves better results than most state-of-the-art methods on six MMIF datasets. The source code is available at https://github.com/SunHui1216/SFMFusion.

Paperid: 922, https://arxiv.org/pdf/2511.06582.pdf GitHub

Abstract:
Ingesting data for Retrieval-Augmented Generation (RAG) involves either fine-tuning the embedding model directly on the target corpus or parsing documents for embedding model encoding. The former, while accurate, incurs high computational hardware requirements, while the latter suffers from suboptimal performance when extracting tabular data. In this work, we address the latter by presenting TabRAG, a parsing-based RAG pipeline designed to tackle table-heavy documents via structured language representations. TabRAG outperforms existing popular parsing-based methods for generation and retrieval. Code is available at https://github.com/jacobyhsi/TabRAG.

Paperid: 923, https://arxiv.org/pdf/2511.06522.pdf GitHub

Abstract:
Mathematical reasoning requires abstracting symbolic rules from visual patterns -- inferring the infinite from the finite. We investigate whether multimodal AI systems possess this capability through FractalBench, a benchmark evaluating fractal program synthesis from images. Fractals provide ideal test cases: Iterated Function Systems with only a few contraction maps generate complex self-similar patterns through simple recursive rules, requiring models to bridge visual perception with mathematical abstraction. We evaluate four leading MLLMs -- GPT-4o, Claude 3.7 Sonnet, Gemini 2.5 Flash, and Qwen 2.5-VL -- on 12 canonical fractals. Models must generate executable Python code reproducing the fractal, enabling objective evaluation. Results reveal a striking disconnect: 76% generate syntactically valid code but only 4% capture mathematical structure. Success varies systematically -- models handle geometric transformations (Koch curves: 17-21%) but fail at branching recursion (trees: <2%), revealing fundamental gaps in mathematical abstraction. FractalBench provides a contamination-resistant diagnostic for visual-mathematical reasoning and is available at https://github.com/NaiveNeuron/FractalBench

Paperid: 924, https://arxiv.org/pdf/2511.06494.pdf GitHub

Abstract:
Mixture-of-Experts (MoE) architectures scale large language models (LLMs) by activating only a subset of experts per token, but the standard TopK routing assigns the same fixed number of experts to all tokens, ignoring their varying complexity. Prior adaptive routing methods introduce additional modules and hyperparameters, often requiring costly retraining from scratch. We propose Sequence-level TopK (SeqTopK), a minimal modification that shifts the expert budget from the token level to the sequence level. By selecting the top $T \cdot K$ experts across all $T$ tokens, SeqTopK enables end-to-end learned dynamic allocation -- assigning more experts to difficult tokens and fewer to easy ones -- while preserving the same overall budget. SeqTopK requires only a few lines of code, adds less than 1% overhead, and remains fully compatible with pretrained MoE models. Experiments across math, coding, law, and writing show consistent improvements over TopK and prior parameter-free adaptive methods, with gains that become substantially larger under higher sparsity (up to 16.9%). These results highlight SeqTopK as a simple, efficient, and scalable routing strategy, particularly well-suited for the extreme sparsity regimes of next-generation LLMs. Code is available at https://github.com/Y-Research-SBU/SeqTopK.

Paperid: 925, https://arxiv.org/pdf/2511.06475.pdf GitHub

Abstract:
Video large language models (Video LLMs) have recently achieved strong performance on tasks such as captioning, summarization, and question answering. Many models and training methods explicitly encourage continuity across events to enhance narrative coherence. While this improves fluency, it also introduces an inductive bias that prioritizes storyline consistency over strict grounding in visual evidence. We identify this bias, which we call narrative prior, as a key driver of two errors: hallucinations, where non-existent events are introduced or existing ones are misinterpreted, and omissions, where factual events are suppressed because they are misaligned with surrounding context. To systematically evaluate narrative prior-induced errors, we introduce NOAH, a large-scale benchmark that constructs composite videos by inserting clips from other sources into target videos. By varying semantic similarity and insertion position, our benchmark enables controlled and scalable analysis of narrative priors. We design one captioning task with tailored metrics and three QA tasks - Existence, Temporal, and Narrative - yielding more than 60K evaluation samples. Extensive experiments yield three key findings: (i) most Video LLMs exhibit hallucinations and omissions driven by narrative priors, (ii) the patterns of these errors vary across architectures and depend on event similarity and insertion position, and (iii) reliance on narrative priors intensifies under sampling with fewer frames, amplifying errors when event continuity is weak. We establish NOAH as the first standardized evaluation of narrative prior-induced hallucination and omission in Video LLMs, providing a foundation for developing more reliable and trustworthy models. Our benchmark and code are available at https://anonymous550520.github.io/.

Paperid: 926, https://arxiv.org/pdf/2511.06457.pdf GitHub

Abstract:
Despite recent advances in single-object front-facing inpainting using NeRF and 3D Gaussian Splatting (3DGS), inpainting in complex 360° scenes remains largely underexplored. This is primarily due to three key challenges: (i) identifying target objects in the 3D field of 360° environments, (ii) dealing with severe occlusions in multi-object scenes, which makes it hard to define regions to inpaint, and (iii) maintaining consistent and high-quality appearance across views effectively. To tackle these challenges, we propose Inpaint360GS, a flexible 360° editing framework based on 3DGS that supports multi-object removal and high-fidelity inpainting in 3D space. By distilling 2D segmentation into 3D and leveraging virtual camera views for contextual guidance, our method enables accurate object-level editing and consistent scene completion. We further introduce a new dataset tailored for 360° inpainting, addressing the lack of ground truth object-free scenes. Experiments demonstrate that Inpaint360GS outperforms existing baselines and achieves state-of-the-art performance. Project page: https://dfki-av.github.io/inpaint360gs/

Paperid: 927, https://arxiv.org/pdf/2511.06450.pdf GitHub GitHub

Abstract:
Multi-modal fusion methods often suffer from two types of representation collapse: feature collapse where individual dimensions lose their discriminative power (as measured by eigenspectra), and modality collapse where one dominant modality overwhelms the other. Applications like human action anticipation that require fusing multifarious sensor data are hindered by both feature and modality collapse. However, existing methods attempt to counter feature collapse and modality collapse separately. This is because there is no unifying framework that efficiently addresses feature and modality collapse in conjunction. In this paper, we posit the utility of effective rank as an informative measure that can be utilized to quantify and counter both the representation collapses. We propose \textit{Rank-enhancing Token Fuser}, a theoretically grounded fusion framework that selectively blends less informative features from one modality with complementary features from another modality. We show that our method increases the effective rank of the fused representation. To address modality collapse, we evaluate modality combinations that mutually increase each others' effective rank. We show that depth maintains representational balance when fused with RGB, avoiding modality collapse. We validate our method on action anticipation, where we present \texttt{R3D}, a depth-informed fusion framework. Extensive experiments on NTURGBD, UTKinect, and DARai demonstrate that our approach significantly outperforms prior state-of-the-art methods by up to 3.74\%. Our code is available at: \href{https://github.com/olivesgatech/R3D}{https://github.com/olivesgatech/R3D}.

Paperid: 928, https://arxiv.org/pdf/2511.06448.pdf GitHub GitHub

Abstract:
In this work, we study the risks of collective financial fraud in large-scale multi-agent systems powered by large language model (LLM) agents. We investigate whether agents can collaborate in fraudulent behaviors, how such collaboration amplifies risks, and what factors influence fraud success. To support this research, we present MultiAgentFraudBench, a large-scale benchmark for simulating financial fraud scenarios based on realistic online interactions. The benchmark covers 28 typical online fraud scenarios, spanning the full fraud lifecycle across both public and private domains. We further analyze key factors affecting fraud success, including interaction depth, activity level, and fine-grained collaboration failure modes. Finally, we propose a series of mitigation strategies, including adding content-level warnings to fraudulent posts and dialogues, using LLMs as monitors to block potentially malicious agents, and fostering group resilience through information sharing at the societal level. Notably, we observe that malicious agents can adapt to environmental interventions. Our findings highlight the real-world risks of multi-agent financial fraud and suggest practical measures for mitigating them. Code is available at https://github.com/zheng977/MutiAgent4Fraud.

Paperid: 929, https://arxiv.org/pdf/2511.06427.pdf GitHub

Abstract:
Metaphors and metaphorical language (MLs) play an important role in healthcare communication between clinicians, patients, and patients' family members. In this work, we focus on Dutch language data from cancer patients. We extract metaphors used by patients using two data sources: (1) cancer patient storytelling interview data and (2) online forum data, including patients' posts, comments, and questions to professionals. We investigate how current state-of-the-art large language models (LLMs) perform on this task by exploring different prompting strategies such as chain of thought reasoning, few-shot learning, and self-prompting. With a human-in-the-loop setup, we verify the extracted metaphors and compile the outputs into a corpus named HealthQuote.NL. We believe the extracted metaphors can support better patient care, for example shared decision making, improved communication between patients and clinicians, and enhanced patient health literacy. They can also inform the design of personalized care pathways. We share prompts and related resources at https://github.com/aaronlifenghan/HealthQuote.NL

Paperid: 930, https://arxiv.org/pdf/2511.06424.pdf GitHub

Abstract:
While zero-shot diffusion-based compression methods have seen significant progress in recent years, they remain notoriously slow and computationally demanding. This paper presents an efficient zero-shot diffusion-based compression method that runs substantially faster than existing methods, while maintaining performance that is on par with the state-of-the-art techniques. Our method builds upon the recently proposed Denoising Diffusion Codebook Models (DDCMs) compression scheme. Specifically, DDCM compresses an image by sequentially choosing the diffusion noise vectors from reproducible random codebooks, guiding the denoiser's output to reconstruct the target image. We modify this framework with Turbo-DDCM, which efficiently combines a large number of noise vectors at each denoising step, thereby significantly reducing the number of required denoising operations. This modification is also coupled with an improved encoding protocol. Furthermore, we introduce two flexible variants of Turbo-DDCM, a priority-aware variant that prioritizes user-specified regions and a distortion-controlled variant that compresses an image based on a target PSNR rather than a target BPP. Comprehensive experiments position Turbo-DDCM as a compelling, practical, and flexible image compression scheme.

Paperid: 931, https://arxiv.org/pdf/2511.06422.pdf GitHub

Abstract:
With the rapid growth of the low-altitude economy, unmanned aerial vehicles (UAVs) have become key platforms for measurement and tracking in intelligent patrol systems. However, in GNSS-denied environments, localization schemes that rely solely on satellite signals are prone to failure. Cross-view image retrieval-based localization is a promising alternative, yet substantial geometric and appearance domain gaps exist between oblique UAV views and nadir satellite orthophotos. Moreover, conventional approaches often depend on complex network architectures, text prompts, or large amounts of annotation, which hinders generalization. To address these issues, we propose DiffusionUavLoc, a cross-view localization framework that is image-prompted, text-free, diffusion-centric, and employs a VAE for unified representation. We first use training-free geometric rendering to synthesize pseudo-satellite images from UAV imagery as structural prompts. We then design a text-free conditional diffusion model that fuses multimodal structural cues to learn features robust to viewpoint changes. At inference, descriptors are computed at a fixed time step t and compared using cosine similarity. On University-1652 and SUES-200, the method performs competitively for cross-view localization, especially for satellite-to-drone in University-1652.Our data and code will be published at the following URL: https://github.com/liutao23/DiffusionUavLoc.git.

Paperid: 932, https://arxiv.org/pdf/2511.06418.pdf GitHub

Abstract:
Two scientific fields showing increasing interest in pre-trained large language models (LLMs) are drug development / repurposing, and personalized medicine. For both, LLMs have to demonstrate factual knowledge as well as a deep understanding of drug mechanisms, so they can recall and reason about relevant knowledge in novel situations. Drug mechanisms of action are described as a series of interactions between biomedical entities, which interlink into one or more chains directed from the drug to the targeted disease. Composing the effects of the interactions in a candidate chain leads to an inference about whether the drug might be useful or not for that disease. We introduce a dataset that evaluates LLMs on both factual knowledge of known mechanisms, and their ability to reason about them under novel situations, presented as counterfactuals that the models are unlikely to have seen during training. Using this dataset, we show that o4-mini outperforms the 4o, o3, and o3-mini models from OpenAI, and the recent small Qwen3-4B-thinking model closely matches o4-mini's performance, even outperforming it in some cases. We demonstrate that the open world setting for reasoning tasks, which requires the model to recall relevant knowledge, is more challenging than the closed world setting where the needed factual knowledge is provided. We also show that counterfactuals affecting internal links in the reasoning chain present a much harder task than those affecting a link from the drug mentioned in the prompt.

Paperid: 933, https://arxiv.org/pdf/2511.06411.pdf GitHub

Abstract:
The soft-thinking paradigm for Large Language Model (LLM) reasoning can outperform the conventional discrete-token Chain-of-Thought (CoT) reasoning in some scenarios, underscoring its research and application value. However, while the discrete-token CoT reasoning pattern can be reinforced through policy optimization algorithms such as group relative policy optimization (GRPO), extending the soft-thinking pattern with Reinforcement Learning (RL) remains challenging. This difficulty stems from the complexities of injecting stochasticity into soft-thinking tokens and updating soft-thinking policies accordingly. As a result, previous attempts to combine soft-thinking with GRPO typically underperform their discrete-token GRPO counterparts. To fully unlock the potential of soft-thinking, this paper presents a novel policy optimization algorithm, SofT-GRPO, to reinforce LLMs under the soft-thinking reasoning pattern. SofT-GRPO injects the Gumbel noise into logits, employs the Gumbel-Softmax technique to avoid soft-thinking tokens outside the pre-trained embedding space, and leverages the reparameterization trick in policy gradient. We conduct experiments across base LLMs ranging from 1.5B to 7B parameters, and results demonstrate that SofT-GRPO enables soft-thinking LLMs to slightly outperform discrete-token GRPO on Pass@1 (+0.13% on average accuracy), while exhibiting a substantial uplift on Pass@32 (+2.19% on average accuracy). Codes and weights are available on https://github.com/zz1358m/SofT-GRPO-master

Paperid: 934, https://arxiv.org/pdf/2511.06406.pdf GitHub

Abstract:
Infrared and visible object detection (IVOD) is essential for numerous around-the-clock applications. Despite notable advancements, current IVOD models exhibit notable performance declines when confronted with incomplete modality data, particularly if the dominant modality is missing. In this paper, we take a thorough investigation on modality incomplete IVOD problem from an architecture compatibility perspective. Specifically, we propose a plug-and-play Scarf Neck module for DETR variants, which introduces a modality-agnostic deformable attention mechanism to enable the IVOD detector to flexibly adapt to any single or double modalities during training and inference. When training Scarf-DETR, we design a pseudo modality dropout strategy to fully utilize the multi-modality information, making the detector compatible and robust to both working modes of single and double modalities. Moreover, we introduce a comprehensive benchmark for the modality-incomplete IVOD task aimed at thoroughly assessing situations where the absent modality is either dominant or secondary. Our proposed Scarf-DETR not only performs excellently in missing modality scenarios but also achieves superior performances on the standard IVOD modality complete benchmarks. Our code will be available at https://github.com/YinghuiXing/Scarf-DETR.

Paperid: 935, https://arxiv.org/pdf/2511.06385.pdf GitHub

Abstract:
Diffusion policies (DPs) achieve state-of-the-art performance on complex manipulation tasks by learning from large-scale demonstration datasets, often spanning multiple embodiments and environments. However, they cannot guarantee safe behavior, so external safety mechanisms are needed. These, however, alter actions in ways unseen during training, causing unpredictable behavior and performance degradation. To address these problems, we propose path-consistent safety filtering (PACS) for DPs. Our approach performs path-consistent braking on a trajectory computed from the sequence of generated actions. In this way, we keep execution consistent with the policy's training distribution, maintaining the learned, task-completing behavior. To enable a real-time deployment and handle uncertainties, we verify safety using set-based reachability analysis. Our experimental evaluation in simulation and on three challenging real-world human-robot interaction tasks shows that PACS (a) provides formal safety guarantees in dynamic environments, (b) preserves task success rates, and (c) outperforms reactive safety approaches, such as control barrier functions, by up to 68% in terms of task success. Videos are available at our project website: https://tum-lsy.github.io/pacs/.

Paperid: 936, https://arxiv.org/pdf/2511.06316.pdf GitHub

Abstract:
Reliable geospatial information on road accidents is vital for safety analysis and infrastructure planning, yet most low- and middle-income countries continue to face a critical shortage of accurate, location-specific crash data. Existing text-based geocoding tools perform poorly in multilingual and unstructured news environments, where incomplete place descriptions and mixed Bangla-English scripts obscure spatial context. To address these limitations, this study introduces ALIGN (Accident Location Inference through Geo-Spatial Neural Reasoning)- a vision-language framework that emulates human spatial reasoning to infer accident coordinates directly from textual and map-based cues. ALIGN integrates large language and vision-language models within a multi-stage pipeline that performs optical character recognition, linguistic reasoning, and map-level verification through grid-based spatial scanning. The framework systematically evaluates each predicted location against contextual and visual evidence, ensuring interpretable, fine-grained geolocation outcomes without requiring model retraining. Applied to Bangla-language news data, ALIGN demonstrates consistent improvements over traditional geoparsing methods, accurately identifying district and sub-district-level crash sites. Beyond its technical contribution, the framework establishes a high accuracy foundation for automated crash mapping in data-scarce regions, supporting evidence-driven road-safety policymaking and the broader integration of multimodal artificial intelligence in transportation analytics. The code for this paper is open-source and available at: https://github.com/Thamed-Chowdhury/ALIGN

Paperid: 937, https://arxiv.org/pdf/2511.06310.pdf GitHub

Abstract:
Reconstructing high-quality point clouds from images remains challenging in computer vision. Existing generative-model-based approaches, particularly diffusion-model approaches that directly learn the posterior, may suffer from inflexibility -- they require conditioning signals during training, support only a fixed number of input views, and need complete retraining for different measurements. Recent diffusion-based methods have attempted to address this by combining prior models with likelihood updates, but they rely on heuristic fixed step sizes for the likelihood update that lead to slow convergence and suboptimal reconstruction quality. We advance this line of approach by integrating our novel Forward Curvature-Matching (FCM) update method with diffusion sampling. Our method dynamically determines optimal step sizes using only forward automatic differentiation and finite-difference curvature estimates, enabling precise optimization of the likelihood update. This formulation enables high-fidelity reconstruction from both single-view and multi-view inputs, and supports various input modalities through simple operator substitution -- all without retraining. Experiments on ShapeNet and CO3D datasets demonstrate that our method achieves superior reconstruction quality at matched or lower NFEs, yielding higher F-score and lower CD and EMD, validating its efficiency and adaptability for practical applications. Code is available at https://github.com/Seunghyeok0715/FCM

Paperid: 938, https://arxiv.org/pdf/2511.06298.pdf GitHub

Abstract:
Recent multispectral object detection methods have primarily focused on spatial-domain feature fusion based on CNNs or Transformers, while the potential of frequency-domain feature remains underexplored. In this work, we propose a novel Spatial and Frequency Feature Reconstruction method (SFFR) method, which leverages the spatial-frequency feature representation mechanisms of the Kolmogorov-Arnold Network (KAN) to reconstruct complementary representations in both spatial and frequency domains prior to feature fusion. The core components of SFFR are the proposed Frequency Component Exchange KAN (FCEKAN) module and Multi-Scale Gaussian KAN (MSGKAN) module. The FCEKAN introduces an innovative selective frequency component exchange strategy that effectively enhances the complementarity and consistency of cross-modal features based on the frequency feature of RGB and IR images. The MSGKAN module demonstrates excellent nonlinear feature modeling capability in the spatial domain. By leveraging multi-scale Gaussian basis functions, it effectively captures the feature variations caused by scale changes at different UAV flight altitudes, significantly enhancing the model's adaptability and robustness to scale variations. It is experimentally validated that our proposed FCEKAN and MSGKAN modules are complementary and can effectively capture the frequency and spatial semantic features respectively for better feature fusion. Extensive experiments on the SeaDroneSee, DroneVehicle and DVTOD datasets demonstrate the superior performance and significant advantages of the proposed method in UAV multispectral object perception task. Code will be available at https://github.com/qchenyu1027/SFFR.

Paperid: 939, https://arxiv.org/pdf/2511.06288.pdf GitHub

Abstract:
Audio-visual target speaker extraction (AV-TSE) models primarily rely on visual cues from the target speaker. However, humans also leverage linguistic knowledge, such as syntactic constraints, next word prediction, and prior knowledge of conversation, to extract target speech. Inspired by this observation, we propose ELEGANCE, a novel framework that incorporates linguistic knowledge from large language models (LLMs) into AV-TSE models through three distinct guidance strategies: output linguistic constraints, intermediate linguistic prediction, and input linguistic prior. Comprehensive experiments with RoBERTa, Qwen3-0.6B, and Qwen3-4B on two AV-TSE backbones demonstrate the effectiveness of our approach. Significant improvements are observed in challenging scenarios, including visual cue impaired, unseen languages, target speaker switches, increased interfering speakers, and out-of-domain test set. Demo page: https://alexwxwu.github.io/ELEGANCE/.

Paperid: 940, https://arxiv.org/pdf/2511.06284.pdf GitHub

Abstract:
Multimodal Misinformation Detection (MMD) refers to the task of detecting social media posts involving misinformation, where the post often contains text and image modalities. However, by observing the MMD posts, we hold that the text modality may be much more informative than the image modality because the text generally describes the whole event/story of the current post but the image often presents partial scenes only. Our preliminary empirical results indicate that the image modality exactly contributes less to MMD. Upon this idea, we propose a new MMD method named RETSIMD. Specifically, we suppose that each text can be divided into several segments, and each text segment describes a partial scene that can be presented by an image. Accordingly, we split the text into a sequence of segments, and feed these segments into a pre-trained text-to-image generator to augment a sequence of images. We further incorporate two auxiliary objectives concerning text-image and image-label mutual information, and further post-train the generator over an auxiliary text-to-image generation benchmark dataset. Additionally, we propose a graph structure by defining three heuristic relationships between images, and use a graph neural network to generate the fused features. Extensive empirical results validate the effectiveness of RETSIMD.

Paperid: 941, https://arxiv.org/pdf/2511.06281.pdf GitHub

Abstract:
Reinforcement Learning with Verifiable Rewards (RLVR) has substantially advanced the video understanding capabilities of Multimodal Large Language Models (MLLMs). However, the rapid progress of MLLMs is outpacing the complexity of existing video datasets, while the manual annotation of new, high-quality data remains prohibitively expensive. This work investigates a pivotal question: Can the rich, intrinsic information within videos be harnessed to self-generate high-quality, verifiable training data? To investigate this, we introduce three self-supervised pretext tasks: Anomaly Grounding, Object Counting, and Temporal Jigsaw. We construct the Video Intrinsic Understanding Benchmark (VIUBench) to validate their difficulty, revealing that current state-of-the-art MLLMs struggle significantly on these tasks. Building upon these pretext tasks, we develop the VideoSSR-30K dataset and propose VideoSSR, a novel video self-supervised reinforcement learning framework for RLVR. Extensive experiments across 17 benchmarks, spanning four major video domains (General Video QA, Long Video QA, Temporal Grounding, and Complex Reasoning), demonstrate that VideoSSR consistently enhances model performance, yielding an average improvement of over 5\%. These results establish VideoSSR as a potent foundational framework for developing more advanced video understanding in MLLMs. The code is available at https://github.com/lcqysl/VideoSSR.

Paperid: 942, https://arxiv.org/pdf/2511.06271.pdf GitHub GitHub

Abstract:
Recent advances in diffusion models enable high-quality video generation and editing, but precise relighting with consistent video contents, which is critical for shaping scene atmosphere and viewer attention, remains unexplored. Mainstream text-to-video (T2V) models lack fine-grained lighting control due to text's inherent limitation in describing lighting details and insufficient pre-training on lighting-related prompts. Additionally, constructing high-quality relighting training data is challenging, as real-world controllable lighting data is scarce. To address these issues, we propose RelightMaster, a novel framework for accurate and controllable video relighting. First, we build RelightVideo, the first dataset with identical dynamic content under varying precise lighting conditions based on the Unreal Engine. Then, we introduce Multi-plane Light Image (MPLI), a novel visual prompt inspired by Multi-Plane Image (MPI). MPLI models lighting via K depth-aligned planes, representing 3D light source positions, intensities, and colors while supporting multi-source scenarios and generalizing to unseen light setups. Third, we design a Light Image Adapter that seamlessly injects MPLI into pre-trained Video Diffusion Transformers (DiT): it compresses MPLI via a pre-trained Video VAE and injects latent light features into DiT blocks, leveraging the base model's generative prior without catastrophic forgetting. Experiments show that RelightMaster generates physically plausible lighting and shadows and preserves original scene content. Demos are available at https://wkbian.github.io/Projects/RelightMaster/.

Paperid: 943, https://arxiv.org/pdf/2511.06269.pdf GitHub

Abstract:
Drug-target interaction (DTI) prediction is of great significance for drug discovery and drug repurposing. With the accumulation of a large volume of valuable data, data-driven methods have been increasingly harnessed to predict DTIs, reducing costs across various dimensions. Therefore, this paper proposes a $\textbf{L}$arge $\textbf{L}$anguage $\textbf{M}$odel and $\textbf{M}$ulti-$\textbf{M}$odel data co-powered $\textbf{D}$rug $\textbf{T}$arget $\textbf{I}$nteraction prediction framework, named LLM$^3$-DTI. LLM$^3$-DTI constructs multi-modal data embedding to enhance DTI prediction performance. In this framework, the text semantic embeddings of drugs and targets are encoded by a domain-specific LLM. To effectively align and fuse multi-modal embedding. We propose the dual cross-attention mechanism and the TSFusion module. Finally, these multi-modal data are utilized for the DTI task through an output network. The experimental results indicate that LLM$^3$-DTI can proficiently identify validated DTIs, surpassing the performance of the models employed for comparison across diverse scenarios. Consequently, LLM$^3$-DTI is adept at fulfilling the task of DTI prediction with excellence. The data and code are available at https://github.com/chaser-gua/LLM3DTI.

Paperid: 944, https://arxiv.org/pdf/2511.06267.pdf GitHub

Abstract:
Collision detection is a core component of robotics applications such as simulation, control, and planning. Traditional algorithms like GJK+EPA compute witness points (i.e., the closest or deepest-penetration pairs between two objects) but are inherently non-differentiable, preventing gradient flow and limiting gradient-based optimization in contact-rich tasks such as grasping and manipulation. Recent work introduced efficient first-order randomized smoothing to make witness points differentiable; however, their direction-based formulation is restricted to convex objects and lacks robustness for complex geometries. In this work, we propose a robust and efficient differentiable collision detection framework that supports both convex and concave objects across diverse scales and configurations. Our method introduces distance-based first-order randomized smoothing, adaptive sampling, and equivalent gradient transport for robust and informative gradient computation. Experiments on complex meshes from DexGraspNet and Objaverse show significant improvements over existing baselines. Finally, we demonstrate a direct application of our method for dexterous grasp synthesis to refine the grasp quality. The code is available at https://github.com/JYChen18/DiffCollision.

Paperid: 945, https://arxiv.org/pdf/2511.06256.pdf GitHub

Abstract:
Recent advancements in language-grounded autonomous driving have been significantly promoted by the sophisticated cognition and reasoning capabilities of large language models (LLMs). However, current LLM-based approaches encounter critical challenges: (1) Failure analysis reveals that frequent collisions and obstructions, stemming from limitations in visual representations, remain primary obstacles to robust driving performance. (2) The substantial parameters of LLMs pose considerable deployment hurdles. To address these limitations, we introduce VLDrive, a novel approach featuring a lightweight MLLM architecture with enhanced vision components. VLDrive achieves compact visual tokens through innovative strategies, including cycle-consistent dynamic visual pruning and memory-enhanced feature aggregation. Furthermore, we propose a distance-decoupled instruction attention mechanism to improve joint visual-linguistic feature learning, particularly for long-range visual tokens. Extensive experiments conducted in the CARLA simulator demonstrate VLDrive`s effectiveness. Notably, VLDrive achieves state-of-the-art driving performance while reducing parameters by 81% (from 7B to 1.3B), yielding substantial driving score improvements of 15.4%, 16.8%, and 7.6% at tiny, short, and long distances, respectively, in closed-loop evaluations. Code is available at https://github.com/ReaFly/VLDrive.

Paperid: 946, https://arxiv.org/pdf/2511.06253.pdf GitHub

Abstract:
Effectively integrating Large Language Models (LLMs) into autonomous driving requires a balance between leveraging high-level reasoning and maintaining real-time efficiency. Existing approaches either activate LLMs too frequently, causing excessive computational overhead, or use fixed schedules, failing to adapt to dynamic driving conditions. To address these challenges, we propose AdaDrive, an adaptively collaborative slow-fast framework that optimally determines when and how LLMs contribute to decision-making. (1) When to activate the LLM: AdaDrive employs a novel adaptive activation loss that dynamically determines LLM invocation based on a comparative learning mechanism, ensuring activation only in complex or critical scenarios. (2) How to integrate LLM assistance: Instead of rigid binary activation, AdaDrive introduces an adaptive fusion strategy that modulates a continuous, scaled LLM influence based on scene complexity and prediction confidence, ensuring seamless collaboration with conventional planners. Through these strategies, AdaDrive provides a flexible, context-aware framework that maximizes decision accuracy without compromising real-time performance. Extensive experiments on language-grounded autonomous driving benchmarks demonstrate that AdaDrive state-of-the-art performance in terms of both driving accuracy and computational efficiency. Code is available at https://github.com/ReaFly/AdaDrive.

Paperid: 947, https://arxiv.org/pdf/2511.06251.pdf GitHub GitHub

Abstract:
User interface (UI) development requires translating design mockups into functional code, a process that remains repetitive and labor-intensive. While recent Vision-Language Models (VLMs) automate UI-to-Code generation, they generate only static HTML/CSS/JavaScript layouts lacking interactivity. To address this, we propose WebVIA, the first agentic framework for interactive UI-to-Code generation and validation. The framework comprises three components: 1) an exploration agent to capture multi-state UI screenshots; 2) a UI2Code model that generates executable interactive code; 3) a validation module that verifies the interactivity. Experiments demonstrate that WebVIA-Agent achieves more stable and accurate UI exploration than general-purpose agents (e.g., Gemini-2.5-Pro). In addition, our fine-tuned WebVIA-UI2Code models exhibit substantial improvements in generating executable and interactive HTML/CSS/JavaScript code, outperforming their base counterparts across both interactive and static UI2Code benchmarks. Our code and models are available at \href{https://zheny2751-dotcom.github.io/webvia.github.io/}{\texttt{https://webvia.github.io}}.

Paperid: 948, https://arxiv.org/pdf/2511.06238.pdf GitHub

Abstract:
Event cameras offer unique advantages for vision tasks in challenging environments, yet processing asynchronous event streams remains an open challenge. While existing methods rely on specialized architectures or resource-intensive training, the potential of leveraging modern Visual Foundation Models (VFMs) pretrained on image data remains under-explored for event-based vision. To address this, we propose Temporal-Guided VFM (TGVFM), a novel framework that integrates VFMs with our temporal context fusion block seamlessly to bridge this gap. Our temporal block introduces three key components: (1) Long-Range Temporal Attention to model global temporal dependencies, (2) Dual Spatiotemporal Attention for multi-scale frame correlation, and (3) Deep Feature Guidance Mechanism to fuse semantic-temporal features. By retraining event-to-video models on real-world data and leveraging transformer-based VFMs, TGVFM preserves spatiotemporal dynamics while harnessing pretrained representations. Experiments demonstrate SoTA performance across semantic segmentation, depth estimation, and object detection, with improvements of 16%, 21%, and 16% over existing methods, respectively. Overall, this work unlocks the cross-modality potential of image-based VFMs for event-based vision with temporal reasoning. Code is available at https://github.com/XiaRho/TGVFM.

Paperid: 949, https://arxiv.org/pdf/2511.06138.pdf GitHub

Abstract:
Recent advances in inverse problem solving have increasingly adopted flow priors over diffusion models due to their ability to construct straight probability paths from noise to data, thereby enhancing efficiency in both training and inference. However, current flow-based inverse solvers face two primary limitations: (i) they operate directly in pixel space, which demands heavy computational resources for training and restricts scalability to high-resolution images, and (ii) they employ guidance strategies with prior-agnostic posterior covariances, which can weaken alignment with the generative trajectory and degrade posterior coverage. In this paper, we propose LFlow (Latent Refinement via Flows), a training-free framework for solving linear inverse problems via pretrained latent flow priors. LFlow leverages the efficiency of flow matching to perform ODE sampling in latent space along an optimal path. This latent formulation further allows us to introduce a theoretically grounded posterior covariance, derived from the optimal vector field, enabling effective flow guidance. Experimental results demonstrate that our proposed method outperforms state-of-the-art latent diffusion solvers in reconstruction quality across most tasks. The code will be publicly available at https://github.com/hosseinaskari-cs/LFlow .

Paperid: 950, https://arxiv.org/pdf/2511.06101.pdf GitHub

Abstract:
Web agents struggle to adapt to new websites due to the scarcity of environment specific tasks and demonstrations. Recent works have explored synthetic data generation to address this challenge, however, they suffer from data quality issues where synthesized tasks contain hallucinations that cannot be executed, and collected trajectories are noisy with redundant or misaligned actions. In this paper, we propose SynthAgent, a fully synthetic supervision framework that aims at improving synthetic data quality via dual refinement of both tasks and trajectories. Our approach begins by synthesizing diverse tasks through categorized exploration of web elements, ensuring efficient coverage of the target environment. During trajectory collection, we refine tasks when conflicts with actual observations are detected, mitigating hallucinations while maintaining task consistency. After collection, we conduct trajectory refinement with a global context to mitigate potential noise or misalignments. Finally, we fine-tune open-source web agents on the refined synthetic data to adapt them to the target environment. Experimental results demonstrate that SynthAgent outperforms existing synthetic data methods, validating the importance of high-quality synthetic supervision. The code will be publicly available at https://github.com/aiming-lab/SynthAgent.

Paperid: 951, https://arxiv.org/pdf/2511.06086.pdf GitHub

Abstract:
Muon optimizer has demonstrated robust results in pretraining of language models but its performance in finetuning of existing public pretrained models is not yet explored. Currently, Muon is used along with AdamW introducing a scope of improvement for adopting all parameters inside Muon. We introduce MuonAll, which incorporates all the parameters inside Muon by transforming into 2D matrices. We conduct extensive finetuning experiments across publicly available language models with model sizes upto half billion parameters. Muon and MuonAll perform at par with AdamW across major benchmarks, highlighting their effectiveness as alternative optimizers. We open-source the distributed implementations of Muon and MuonAll, available at https://github.com/Saurabh750/optimizer

Paperid: 952, https://arxiv.org/pdf/2511.06066.pdf GitHub

Abstract:
Exposure correction is essential for enhancing image quality under challenging lighting conditions. While supervised learning has achieved significant progress in this area, it relies heavily on large-scale labeled datasets, which are difficult to obtain in practical scenarios. To address this limitation, we propose a pseudo label-based unsupervised method called LoopExpose for arbitrary-length exposure correction. A nested loop optimization strategy is proposed to address the exposure correction problem, where the correction model and pseudo-supervised information are jointly optimized in a two-level framework. Specifically, the upper-level trains a correction model using pseudo-labels generated through multi-exposure fusion at the lower level. A feedback mechanism is introduced where corrected images are fed back into the fusion process to refine the pseudo-labels, creating a self-reinforcing learning loop. Considering the dominant role of luminance calibration in exposure correction, a Luminance Ranking Loss is introduced to leverage the relative luminance ordering across the input sequence as a self-supervised constraint. Extensive experiments on different benchmark datasets demonstrate that LoopExpose achieves superior exposure correction and fusion performance, outperforming existing state-of-the-art unsupervised methods. Code is available at https://github.com/FALALAS/LoopExpose.

Paperid: 953, https://arxiv.org/pdf/2511.06055.pdf GitHub

Abstract:
We introduce Neodragon, a text-to-video system capable of generating 2s (49 frames @24 fps) videos at the 640x1024 resolution directly on a Qualcomm Hexagon NPU in a record 6.7s (7 FPS). Differing from existing transformer-based offline text-to-video generation models, Neodragon is the first to have been specifically optimised for mobile hardware to achieve efficient and high-fidelity video synthesis. We achieve this through four key technical contributions: (1) Replacing the original large 4.762B T5xxl Text-Encoder with a much smaller 0.2B DT5 (DistilT5) with minimal quality loss, enabled through a novel Text-Encoder Distillation procedure. (2) Proposing an Asymmetric Decoder Distillation approach allowing us to replace the native codec-latent-VAE decoder with a more efficient one, without disturbing the generative latent-space of the generation pipeline. (3) Pruning of MMDiT blocks within the denoiser backbone based on their relative importance, with recovery of original performance through a two-stage distillation process. (4) Reducing the NFE (Neural Functional Evaluation) requirement of the denoiser by performing step distillation using DMD adapted for pyramidal flow-matching, thereby substantially accelerating video generation. When paired with an optimised SSD1B first-frame image generator and QuickSRNet for 2x super-resolution, our end-to-end Neodragon system becomes a highly parameter (4.945B full model), memory (3.5GB peak RAM usage), and runtime (6.7s E2E latency) efficient mobile-friendly model, while achieving a VBench total score of 81.61. By enabling low-cost, private, and on-device text-to-video synthesis, Neodragon democratizes AI-based video content creation, empowering creators to generate high-quality videos without reliance on cloud services. Code and model will be made publicly available at our website: https://qualcomm-ai-research.github.io/neodragon

Paperid: 954, https://arxiv.org/pdf/2511.06046.pdf GitHub

Abstract:
Streaming free-viewpoint video~(FVV) in real-time still faces significant challenges, particularly in training, rendering, and transmission efficiency. Harnessing superior performance of 3D Gaussian Splatting~(3DGS), recent 3DGS-based FVV methods have achieved notable breakthroughs in both training and rendering. However, the storage requirements of these methods can reach up to $10$MB per frame, making stream FVV in real-time impossible. To address this problem, we propose a novel FVV representation, dubbed StreamSTGS, designed for real-time streaming. StreamSTGS represents a dynamic scene using canonical 3D Gaussians, temporal features, and a deformation field. For high compression efficiency, we encode canonical Gaussian attributes as 2D images and temporal features as a video. This design not only enables real-time streaming, but also inherently supports adaptive bitrate control based on network condition without any extra training. Moreover, we propose a sliding window scheme to aggregate adjacent temporal features to learn local motions, and then introduce a transformer-guided auxiliary training module to learn global motions. On diverse FVV benchmarks, StreamSTGS demonstrates competitive performance on all metrics compared to state-of-the-art methods. Notably, StreamSTGS increases the PSNR by an average of $1$dB while reducing the average frame size to just $170$KB. The code is publicly available on https://github.com/kkkzh/StreamSTGS.

Paperid: 955, https://arxiv.org/pdf/2511.06024.pdf GitHub

Abstract:
Visual place recognition (VPR) is typically regarded as a specific image retrieval task, whose core lies in representing images as global descriptors. Over the past decade, dominant VPR methods (e.g., NetVLAD) have followed a paradigm that first extracts the patch features/tokens of the input image using a backbone, and then aggregates these patch features into a global descriptor via an aggregator. This backbone-plus-aggregator paradigm has achieved overwhelming dominance in the CNN era and remains widely used in transformer-based models. In this paper, however, we argue that a dedicated aggregator is not necessary in the transformer era, that is, we can obtain robust global descriptors only with the backbone. Specifically, we introduce some learnable aggregation tokens, which are prepended to the patch tokens before a particular transformer block. All these tokens will be jointly processed and interact globally via the intrinsic self-attention mechanism, implicitly aggregating useful information within the patch tokens to the aggregation tokens. Finally, we only take these aggregation tokens from the last output tokens and concatenate them as the global representation. Although implicit aggregation can provide robust global descriptors in an extremely simple manner, where and how to insert additional tokens, as well as the initialization of tokens, remains an open issue worthy of further exploration. To this end, we also propose the optimal token insertion strategy and token initialization method derived from empirical studies. Experimental results show that our method outperforms state-of-the-art methods on several VPR datasets with higher efficiency and ranks 1st on the MSLS challenge leaderboard. The code is available at https://github.com/lu-feng/image.

Paperid: 956, https://arxiv.org/pdf/2511.06006.pdf GitHub

Abstract:
Medical image denoising is essential for improving image quality while minimizing the exposure of sensitive information, particularly when working with large-scale clinical datasets. This study explores distributed deep learning for denoising chest X-ray images from the NIH Chest X-ray14 dataset, using additive Gaussian noise as a lightweight obfuscation technique. We implement and evaluate U-Net and U-Net++ architectures under single-GPU, standard multi-GPU (DataParallel), and optimized multi-GPU training configurations using PyTorch's DistributedDataParallel (DDP) and Automatic Mixed Precision (AMP). Our results show that U-Net++ consistently delivers superior denoising performance, achieving competitive Peak Signal to Noise Ratio (PSNR) and Structured Similarity Index Method (SSIM) scores, though with less performance in Learned Perceptual Image Patch Similarity (LPIPS) compared to U-Net under low and moderate noise levels. This indicates U-Net++'s enhanced structural fidelity and low perceptual similarity. Meanwhile, our optimized training pipeline reduces training time by over 60% for both models compared to single-GPU training, and outperforms standard DataParallel by over 40%, with only a minor accuracy drop for both models (trading some accuracy for speed). These findings highlight the effectiveness of software-level optimization in distributed learning for medical imaging. This work demonstrates the practical viability of combining architectural design, lightweight obfuscation, and advanced distributed training strategies to accelerate and enhance medical image processing pipelines in real-world clinical and research environments. The full implementation is publicly available at: https://github.com/Suadey/medical-image-denoising-ddp.

Paperid: 957, https://arxiv.org/pdf/2511.06002.pdf GitHub

Abstract:
Recent advances in text-to-image models have enabled a new era of creative and controllable image generation. However, generating compositional scenes with multiple subjects and attributes remains a significant challenge. To enhance user control over subject placement, several layout-guided methods have been proposed. However, these methods face numerous challenges, particularly in compositional scenes. Unintended subjects often appear outside the layouts, generated images can be out-of-distribution and contain unnatural artifacts, or attributes bleed across subjects, leading to incorrect visual outputs. In this work, we propose MALeR, a method that addresses each of these challenges. Given a text prompt and corresponding layouts, our method prevents subjects from appearing outside the given layouts while being in-distribution. Additionally, we propose a masked, attribute-aware binding mechanism that prevents attribute leakage, enabling accurate rendering of subjects with multiple attributes, even in complex compositional scenes. Qualitative and quantitative evaluation demonstrates that our method achieves superior performance in compositional accuracy, generation consistency, and attribute binding compared to previous work. MALeR is particularly adept at generating images of scenes with multiple subjects and multiple attributes per subject.

Paperid: 958, https://arxiv.org/pdf/2511.05996.pdf GitHub

Abstract:
Articulated objects are prevalent in daily life and robotic manipulation tasks. However, compared to rigid objects, pose tracking for articulated objects remains an underexplored problem due to their inherent kinematic constraints. To address these challenges, this work proposes a novel point-pair-based pose tracking framework, termed \textbf{PPF-Tracker}. The proposed framework first performs quasi-canonicalization of point clouds in the SE(3) Lie group space, and then models articulated objects using Point Pair Features (PPF) to predict pose voting parameters by leveraging the invariance properties of SE(3). Finally, semantic information of joint axes is incorporated to impose unified kinematic constraints across all parts of the articulated object. PPF-Tracker is systematically evaluated on both synthetic datasets and real-world scenarios, demonstrating strong generalization across diverse and challenging environments. Experimental results highlight the effectiveness and robustness of PPF-Tracker in multi-frame pose tracking of articulated objects. We believe this work can foster advances in robotics, embodied intelligence, and augmented reality. Codes are available at https://github.com/mengxh20/PPFTracker.

Paperid: 959, https://arxiv.org/pdf/2511.05966.pdf GitHub

Abstract:
Few-shot multimodal industrial anomaly detection is a critical yet underexplored task, offering the ability to quickly adapt to complex industrial scenarios. In few-shot settings, insufficient training samples often fail to cover the diverse patterns present in test samples. This challenge can be mitigated by extracting structural commonality from a small number of training samples. In this paper, we propose a novel few-shot unsupervised multimodal industrial anomaly detection method based on structural commonality, CIF (Commonality In Few). To extract intra-class structural information, we employ hypergraphs, which are capable of modeling higher-order correlations, to capture the structural commonality within training samples, and use a memory bank to store this intra-class structural prior. Firstly, we design a semantic-aware hypergraph construction module tailored for single-semantic industrial images, from which we extract common structures to guide the construction of the memory bank. Secondly, we use a training-free hypergraph message passing module to update the visual features of test samples, reducing the distribution gap between test features and features in the memory bank. We further propose a hyperedge-guided memory search module, which utilizes structural information to assist the memory search process and reduce the false positive rate. Experimental results on the MVTec 3D-AD dataset and the Eyecandies dataset show that our method outperforms the state-of-the-art (SOTA) methods in few-shot settings. Code is available at https://github.com/Sunny5250/CIF.

Paperid: 960, https://arxiv.org/pdf/2511.05946.pdf GitHub

Abstract:
Remote photoplethysmography (rPPG) is an emerging contactless physiological sensing technique that leverages subtle color variations in facial videos to estimate vital signs such as heart rate and respiratory rate. This non-invasive method has gained traction across diverse domains, including telemedicine, affective computing, driver fatigue detection, and health monitoring, owing to its scalability and convenience. Despite significant progress in remote physiological signal measurement, a crucial characteristic - the intrinsic periodicity - has often been underexplored or insufficiently modeled in previous approaches, limiting their ability to capture fine-grained temporal dynamics under real-world conditions. To bridge this gap, we propose Reperio-rPPG, a novel framework that strategically integrates Relational Convolutional Networks with a Graph Transformer to effectively capture the periodic structure inherent in physiological signals. Additionally, recognizing the limited diversity of existing rPPG datasets, we further introduce a tailored CutMix augmentation to enhance the model's generalizability. Extensive experiments conducted on three widely used benchmark datasets - PURE, UBFC-rPPG, and MMPD - demonstrate that Reperio-rPPG not only achieves state-of-the-art performance but also exhibits remarkable robustness under various motion (e.g., stationary, rotation, talking, walking) and illumination conditions (e.g., nature, low LED, high LED). The code is publicly available at https://github.com/deconasser/Reperio-rPPG.

Paperid: 961, https://arxiv.org/pdf/2511.05876.pdf GitHub

Abstract:
In recent years, the advancement of Graph Neural Networks (GNNs) has significantly propelled progress in Multi-View Clustering (MVC). However, existing methods face the problem of coarse-grained graph fusion. Specifically, current approaches typically generate a separate graph structure for each view and then perform weighted fusion of graph structures at the view level, which is a relatively rough strategy. To address this limitation, we present a novel Mixture of Ego-Graphs Contrastive Representation Learning (MoEGCL). It mainly consists of two modules. In particular, we propose an innovative Mixture of Ego-Graphs Fusion (MoEGF), which constructs ego graphs and utilizes a Mixture-of-Experts network to implement fine-grained fusion of ego graphs at the sample level, rather than the conventional view-level fusion. Additionally, we present the Ego Graph Contrastive Learning (EGCL) module to align the fused representation with the view-specific representation. The EGCL module enhances the representation similarity of samples from the same cluster, not merely from the same sample, further boosting fine-grained graph representation. Extensive experiments demonstrate that MoEGCL achieves state-of-the-art results in deep multi-view clustering tasks. The source code is publicly available at https://github.com/HackerHyper/MoEGCL.

Paperid: 962, https://arxiv.org/pdf/2511.05867.pdf GitHub

Abstract:
Large language models (LLMs) demonstrate strong capabilities in solving complex tasks when integrated with external tools. The Model Context Protocol (MCP) has become a standard interface for enabling such tool-based interactions. However, these interactions introduce substantial security concerns, particularly when the MCP server is compromised or untrustworthy. While prior benchmarks primarily focus on prompt injection attacks or analyze the vulnerabilities of LLM MCP interaction trajectories, limited attention has been given to the underlying system logs associated with malicious MCP servers. To address this gap, we present the first synthetic benchmark for evaluating LLMs ability to identify security risks from system logs. We define nine categories of MCP server risks and generate 1,800 synthetic system logs using ten state-of-the-art LLMs. These logs are embedded in the return values of 243 curated MCP servers, yielding a dataset of 2,421 chat histories for training and 471 queries for evaluation. Our pilot experiments reveal that smaller models often fail to detect risky system logs, leading to high false negatives. While models trained with supervised fine-tuning (SFT) tend to over-flag benign logs, resulting in elevated false positives, Reinforcement Learning from Verifiable Reward (RLVR) offers a better precision-recall balance. In particular, after training with Group Relative Policy Optimization (GRPO), Llama3.1-8B-Instruct achieves 83% accuracy, surpassing the best-performing large remote model by 9 percentage points. Fine-grained, per-category analysis further underscores the effectiveness of reinforcement learning in enhancing LLM safety within the MCP framework. Code and data are available at: https://github.com/PorUna-byte/MCP-RiskCue

Paperid: 963, https://arxiv.org/pdf/2511.05866.pdf GitHub

Abstract:
A Light Field (LF) camera consists of an additional two-dimensional array of micro-lenses placed between the main lens and sensor, compared to a conventional camera. The sensor pixels under each micro-lens receive light from a sub-aperture of the main lens. This enables the image sensor to capture both spatial information and the angular resolution of a scene point. This additional angular information is used to estimate the depth of a 3-D scene. The continuum of virtual viewpoints in light field data enables efficient depth estimation using Epipolar Line Images (EPIs) with robust occlusion handling. However, the trade-off between angular information and spatial information is very critical and depends on the focal position of the camera. To design, develop, implement, and test novel disparity-based light field depth estimation algorithms, the availability of suitable light field image datasets is essential. In this paper, a publicly available light field image dataset is introduced and thoroughly described. We have also demonstrated the effect of focal position on the disparity of a 3-D point as well as the shortcomings of the currently available light field dataset. The proposed dataset contains 285 light field images captured using a Lytro Illum LF camera and 13 synthetic LF images. The proposed dataset also comprises a synthetic dataset with similar disparity characteristics to those of a real light field camera. A real and synthetic stereo light field dataset is also created by using a mechanical gantry system and Blender. The dataset is available at https://github.com/aupendu/light-field-dataset.

Paperid: 964, https://arxiv.org/pdf/2511.05859.pdf GitHub

Abstract:
Deep learning models such as MLP, Transformer, and TCN have achieved remarkable success in univariate time series forecasting, typically relying on sliding window samples from historical data for training. However, while these models implicitly compress historical information into their parameters during training, they are unable to explicitly and dynamically access this global knowledge during inference, relying only on the local context within the lookback window. This results in an underutilization of rich patterns from the global history. To bridge this gap, we propose Predicting the Future by Retrieving the Past (PFRP), a novel approach that explicitly integrates global historical data to enhance forecasting accuracy. Specifically, we construct a Global Memory Bank (GMB) to effectively store and manage global historical patterns. A retrieval mechanism is then employed to extract similar patterns from the GMB, enabling the generation of global predictions. By adaptively combining these global predictions with the outputs of any local prediction model, PFRP produces more accurate and interpretable forecasts. Extensive experiments conducted on seven real-world datasets demonstrate that PFRP significantly enhances the average performance of advanced univariate forecasting models by 8.4\%. Codes can be found in https://github.com/ddz16/PFRP.

Paperid: 965, https://arxiv.org/pdf/2511.05844.pdf GitHub

Abstract:
Classifier-guided diffusion models have emerged as a powerful approach for conditional image generation, but they suffer from overconfident predictions during early denoising steps, causing the guidance gradient to vanish. This paper introduces two complementary contributions to address this issue. First, we propose a differentiable calibration objective based on the Smooth Expected Calibration Error (Smooth ECE), which improves classifier calibration with minimal fine-tuning and yields measurable improvements in Frechet Inception Distance (FID). Second, we develop enhanced sampling guidance methods that operate on off-the-shelf classifiers without requiring retraining. These include tilted sampling with batch-level reweighting, adaptive entropy-regularized sampling to preserve diversity, and a novel f-divergence-based sampling strategy that strengthens class-consistent guidance while maintaining mode coverage. Experiments on ImageNet 128x128 demonstrate that our divergence-regularized guidance achieves an FID of 2.13 using a ResNet-101 classifier, improving upon existing classifier-guided diffusion methods while requiring no diffusion model retraining. The results show that principled calibration and divergence-aware sampling provide practical and effective improvements for classifier-guided diffusion.

Paperid: 966, https://arxiv.org/pdf/2511.05833.pdf GitHub

Abstract:
Remote photoplethysmography (rPPG) can remotely extract physiological signals from RGB video, which has many advantages in detecting heart rate, such as low cost and no invasion to patients. The existing rPPG model is usually based on the transformer module, which has low computation efficiency. Recently, the Mamba model has garnered increasing attention due to its efficient performance in natural language processing tasks, demonstrating potential as a substitute for transformer-based algorithms. However, the Mambaout model and its variants prove that the SSM module, which is the core component of the Mamba model, is unnecessary for the vision task. Therefore, we hope to prove the feasibility of using the Mambaout-based module to remotely learn the heart rate. Specifically, we propose a novel rPPG algorithm called uncomplicated and enhanced learning capability rPPG (TYrPPG). This paper introduces an innovative gated video understanding block (GVB) designed for efficient analysis of RGB videos. Based on the Mambaout structure, this block integrates 2D-CNN and 3D-CNN to enhance video understanding for analysis. In addition, we propose a comprehensive supervised loss function (CSL) to improve the model's learning capability, along with its weakly supervised variants. The experiments show that our TYrPPG can achieve state-of-the-art performance in commonly used datasets, indicating its prospects and superiority in remote heart rate estimation. The source code is available at https://github.com/Taixi-CHEN/TYrPPG.

Paperid: 967, https://arxiv.org/pdf/2511.05832.pdf GitHub

Abstract:
The quadratic compute and memory costs of global self-attention severely limit its use in high-resolution images. Local attention reduces complexity by restricting attention to neighborhoods. Block-sparse kernels can further improve the efficiency of local attention, but conventional local attention patterns often fail to deliver significant speedups because tokens within a window are not contiguous in the 1D sequence. This work proposes a novel method for constructing windows and neighborhoods based on the Hilbert curve. Image tokens are first reordered along a Hilbert curve, and windows and neighborhoods are then formed on the reordered 1D sequence. From a block-sparse perspective, this strategy significantly increases block sparsity and can be combined with existing block-sparse kernels to improve the efficiency of 2D local attention. Experiments show that the proposed Hilbert Window Attention and Hilbert Slide Attention can accelerate window attention and slide attention by about $4\times$ and $18\times$, respectively. To assess practicality, the strategy is instantiated as the Hilbert Window Transformer and the Hilbert Neighborhood Transformer, both of which achieve end-to-end speedups with minimal accuracy loss. Overall, combining Hilbert-guided local attention with block-sparse kernels offers a general and practical approach to enhancing the efficiency of 2D local attention for images. The code is available at https://github.com/Yunge6666/Hilbert-Local-Attention.

Paperid: 968, https://arxiv.org/pdf/2511.05823.pdf GitHub

Abstract:
Recent research has demonstrated that artificial intelligence (AI) can assist electronic design automation (EDA) in improving both the quality and efficiency of chip design. But current AI for EDA (AI-EDA) infrastructures remain fragmented, lacking comprehensive solutions for the entire data pipeline from design execution to AI integration. Key challenges include fragmented flow engines that generate raw data, heterogeneous file formats for data exchange, non-standardized data extraction methods, and poorly organized data storage. This work introduces a unified open-source library for EDA (AiEDA) that addresses these issues. AiEDA integrates multiple design-to-vector data representation techniques that transform diverse chip design data into universal multi-level vector representations, establishing an AI-aided design (AAD) paradigm optimized for AI-EDA workflows. AiEDA provides complete physical design flows with programmatic data extraction and standardized Python interfaces bridging EDA datasets and AI frameworks. Leveraging the AiEDA library, we generate iDATA, a 600GB dataset of structured data derived from 50 real chip designs (28nm), and validate its effectiveness through seven representative AAD tasks spanning prediction, generation, optimization and analysis. The code is publicly available at https://github.com/OSCC-Project/AiEDA, while the full iDATA dataset is being prepared for public release, providing a foundation for future AI-EDA research.

Paperid: 969, https://arxiv.org/pdf/2511.05821.pdf GitHub

Abstract:
Assessing developer proficiency in open-source software (OSS) projects is essential for understanding project dynamics, especially for expertise. This paper presents PyGress, a web-based tool designed to automatically evaluate and visualize Python code proficiency using pycefr, a Python code proficiency analyzer. By submitting a GitHub repository link, the system extracts commit histories, analyzes source code proficiency across CEFR-aligned levels (A1 to C2), and generates visual summaries of individual and project-wide proficiency. The PyGress tool visualizes per-contributor proficiency distribution and tracks project code proficiency progression over time. PyGress offers an interactive way to explore contributor coding levels in Python OSS repositories. The video demonstration of the PyGress tool can be found at https://youtu.be/hxoeK-ggcWk, and the source code of the tool is publicly available at https://github.com/MUICT-SERU/PyGress.

Paperid: 970, https://arxiv.org/pdf/2511.05818.pdf GitHub

Abstract:
End-to-end text spotting aims to jointly optimize text detection and recognition within a unified framework. Despite significant progress, designing an accurate and efficient end-to-end text spotter for arbitrary-shaped text remains largely unsolved. We identify the primary bottleneck as the lack of a reliable and efficient text detection method. To address this, we propose a novel parameterized text shape method based on low-rank approximation for precise detection and a triple assignment detection head to enable fast inference. Specifically, unlike other shape representation methods that employ data-irrelevant parameterization, our data-driven approach derives a low-rank subspace directly from labeled text boundaries. To ensure this process is robust against the inherent annotation noise in this data, we utilize a specialized recovery method based on an $\ell_1$-norm formulation, which accurately reconstructs the text shape with only a few key orthogonal vectors. By exploiting the inherent shape correlation among different text contours, our method achieves consistency and compactness in shape representation. Next, the triple assignment scheme introduces a novel architecture where a deep sparse branch (for stabilized training) is used to guide the learning of an ultra-lightweight sparse branch (for accelerated inference), while a dense branch provides rich parallel supervision. Building upon these advancements, we integrate the enhanced detection module with a lightweight recognition branch to form an end-to-end text spotting framework, termed LRANet++, capable of accurately and efficiently spotting arbitrary-shaped text. Extensive experiments on several challenging benchmarks demonstrate the superiority of LRANet++ compared to state-of-the-art methods. Code will be available at: https://github.com/ychensu/LRANet-PP.git

Paperid: 971, https://arxiv.org/pdf/2511.05803.pdf GitHub

Abstract:
Medical image segmentation faces challenges due to variations in anatomical structures. While convolutional neural networks (CNNs) effectively capture local features, they struggle with modeling long-range dependencies. Transformers mitigate this issue with self-attention mechanisms but lack the ability to preserve local contextual information. State-of-the-art models primarily follow an encoder-decoder architecture, achieving notable success. However, two key limitations remain: (1) Shallow layers, which are closer to the input, capture fine-grained details but suffer from information loss as data propagates through deeper layers. (2) Inefficient integration of local details and global context between the encoder and decoder stages. To address these challenges, we propose the MACMD-based decoder, which enhances attention mechanisms and facilitates channel mixing between encoder and decoder stages via skip connections. This design leverages hierarchical dilated convolutions, attention-driven modulation, and a cross channel-mixing module to capture long-range dependencies while preserving local contextual details, essential for precise medical image segmentation. We evaluated our approach using multiple transformer encoders on both binary and multi-organ segmentation tasks. The results demonstrate that our method outperforms state-of-the-art approaches in terms of Dice score and computational efficiency, highlighting its effectiveness in achieving accurate and robust segmentation performance. The code available at https://github.com/lalitmaurya47/MACMD

Paperid: 972, https://arxiv.org/pdf/2511.05796.pdf GitHub

Abstract:
The open nature of wireless communications renders unmanned aerial vehicle (UAV) communications vulnerable to impersonation attacks, under which malicious UAVs can impersonate authorized ones with stolen digital certificates. Traditional fingerprint-based UAV authentication approaches rely on a single modality of sensory data gathered from a single layer of the network model, resulting in unreliable authentication experiences, particularly when UAVs are mobile and in an open-world environment. To transcend these limitations, this paper proposes SecureLink, a UAV authentication system that is among the first to employ cross-layer information for enhancing the efficiency and reliability of UAV authentication. Instead of using single modalities, SecureLink fuses physical-layer radio frequency (RF) fingerprints and application-layer micro-electromechanical system (MEMS) fingerprints into reliable UAV identifiers via multimodal fusion. SecureLink first aligns fingerprints from channel state information measurements and telemetry data, such as feedback readings of onboard accelerometers, gyroscopes, and barometers. Then, an attention-based neural network is devised for in-depth feature fusion. Next, the fused features are trained by a multi-similarity loss and fed into a one-class support vector machine for open-world authentication. We extensively implement our SecureLink using three different types of UAVs and evaluate it in different environments. With only six additional data frames, SecureLink achieves a closed-world accuracy of 98.61% and an open-world accuracy of 97.54% with two impersonating UAVs, outperforming the existing approaches in authentication robustness and communication overheads. Finally, our datasets collected from these experiments are available on GitHub: https://github.com/PhyGroup/SecureLink\_data.

Paperid: 973, https://arxiv.org/pdf/2511.05705.pdf GitHub

Abstract:
Recent progress in multimodal reasoning has been driven largely by undisclosed datasets and proprietary data synthesis recipes, leaving open questions about how to systematically build large-scale, vision-centric reasoning datasets, particularly for tasks that go beyond visual math. In this work, we introduce a new reasoning data generation framework spanning diverse skills and levels of complexity with over 1M high-quality synthetic vision-centric questions. The dataset also includes preference data and instruction prompts supporting both offline and online RL. Our synthesis framework proceeds in two stages: (1) scale; and (2) complexity. Reasoning traces are then synthesized through a two-stage process that leverages VLMs and reasoning LLMs, producing CoT traces for VLMs that capture the richness and diverse cognitive behaviors found in frontier reasoning models. Remarkably, we show that finetuning Qwen2.5-VL-7B on our data outperforms all open-data baselines across all evaluated vision-centric benchmarks, and even surpasses strong closed-data models such as MiMo-VL-7B-RL on V* Bench, CV-Bench and MMStar-V. Perhaps most surprising, despite being entirely vision-centric, our data transfers positively to text-only reasoning (MMLU-Pro) and audio reasoning (MMAU), demonstrating its effectiveness. Similarly, despite not containing videos or embodied visual data, we observe notable gains when evaluating on a single-evidence embodied QA benchmark (NiEH). Finally, we use our data to analyze the entire VLM post-training pipeline. Our empirical analysis highlights that (i) SFT on high-quality data with non-linear reasoning traces is essential for effective online RL, (ii) staged offline RL matches online RL's performance while reducing compute demands, and (iii) careful SFT on high quality data can substantially improve out-of-domain, cross-modality transfer.

Paperid: 974, https://arxiv.org/pdf/2511.05682.pdf GitHub

Abstract:
As foundation models become more sophisticated, ensuring their trustworthiness becomes increasingly critical; yet, unlike text and image, the video modality still lacks comprehensive trustworthiness benchmarks. We introduce VMDT (Video-Modal DecodingTrust), the first unified platform for evaluating text-to-video (T2V) and video-to-text (V2T) models across five key trustworthiness dimensions: safety, hallucination, fairness, privacy, and adversarial robustness. Through our extensive evaluation of 7 T2V models and 19 V2T models using VMDT, we uncover several significant insights. For instance, all open-source T2V models evaluated fail to recognize harmful queries and often generate harmful videos, while exhibiting higher levels of unfairness compared to image modality models. In V2T models, unfairness and privacy risks rise with scale, whereas hallucination and adversarial robustness improve -- though overall performance remains low. Uniquely, safety shows no correlation with model size, implying that factors other than scale govern current safety levels. Our findings highlight the urgent need for developing more robust and trustworthy video foundation models, and VMDT provides a systematic framework for measuring and tracking progress toward this goal. The code is available at https://sunblaze-ucb.github.io/VMDT-page/.

Paperid: 975, https://arxiv.org/pdf/2511.05664.pdf GitHub

Abstract:
Masked diffusion models have demonstrated competitive results on various tasks including language generation. However, due to its iterative refinement process, the inference is often bottlenecked by slow and static sampling speed. To overcome this problem, we introduce `KL-Adaptive Stability Sampling' (KLASS), a fast yet effective sampling method that exploits token-level KL divergence to identify stable, high-confidence predictions. By unmasking multiple tokens in each iteration without any additional model training, our approach speeds up generation significantly while maintaining sample quality. On reasoning benchmarks, KLASS achieves up to $2.78\times$ wall-clock speedups while improving performance over standard greedy decoding, attaining state-of-the-art results among diffusion-based samplers. We further validate KLASS across diverse domains, including text, image, and molecular generation, showing its effectiveness as a broadly applicable sampler across different models.

Paperid: 976, https://arxiv.org/pdf/2511.05630.pdf GitHub GitHub

Abstract:
Functional and structural connectivity (FC/SC) are key multimodal biomarkers for brain analysis, yet their clinical utility is hindered by costly acquisition, complex preprocessing, and frequent missing modalities. Existing foundation models either process single modalities or lack explicit mechanisms for cross-modal and cross-scale consistency. We propose BrainCSD, a hierarchical mixture-of-experts (MoE) foundation model that jointly synthesizes FC/SC biomarkers and supports downstream decoding tasks (diagnosis and prediction). BrainCSD features three neuroanatomically grounded components: (1) a ROI-specific MoE that aligns regional activations from canonical networks (e.g., DMN, FPN) with a global atlas via contrastive consistency; (2) a Encoding-Activation MOE that models dynamic cross-time/gradient dependencies in fMRI/dMRI; and (3) a network-aware refinement MoE that enforces structural priors and symmetry at individual and population levels. Evaluated on the datasets under complete and missing-modality settings, BrainCSD achieves SOTA results: 95.6\% accuracy for MCI vs. CN classification without FC, low synthesis error (FC RMSE: 0.038; SC RMSE: 0.006), brain age prediction (MAE: 4.04 years), and MMSE score estimation (MAE: 1.72 points). Code is available in \href{https://github.com/SXR3015/BrainCSD}{BrainCSD}

Paperid: 977, https://arxiv.org/pdf/2511.05622.pdf GitHub

Abstract:
For embodied agents to effectively understand and interact within the world around them, they require a nuanced comprehension of human actions grounded in physical space. Current action recognition models, often relying on RGB video, learn superficial correlations between patterns and action labels, so they struggle to capture underlying physical interaction dynamics and human poses in complex scenes. We propose a model architecture that grounds action recognition in physical space by fusing two powerful, complementary representations: V-JEPA 2's contextual, predictive world dynamics and CoMotion's explicit, occlusion-tolerant human pose data. Our model is validated on both the InHARD and UCF-19-Y-OCC benchmarks for general action recognition and high-occlusion action recognition, respectively. Our model outperforms three other baselines, especially within complex, occlusive scenes. Our findings emphasize a need for action recognition to be supported by spatial understanding instead of statistical pattern recognition.

Paperid: 978, https://arxiv.org/pdf/2511.05614.pdf GitHub

Abstract:
Scientific machine learning research spans diverse domains and data modalities, yet existing benchmark efforts remain siloed and lack standardization. This makes novel and transformative applications of machine learning to critical scientific use-cases more fragmented and less clear in pathways to impact. This paper introduces an ontology for scientific benchmarking developed through a unified, community-driven effort that extends the MLCommons ecosystem to cover physics, chemistry, materials science, biology, climate science, and more. Building on prior initiatives such as XAI-BENCH, FastML Science Benchmarks, PDEBench, and the SciMLBench framework, our effort consolidates a large set of disparate benchmarks and frameworks into a single taxonomy of scientific, application, and system-level benchmarks. New benchmarks can be added through an open submission workflow coordinated by the MLCommons Science Working Group and evaluated against a six-category rating rubric that promotes and identifies high-quality benchmarks, enabling stakeholders to select benchmarks that meet their specific needs. The architecture is extensible, supporting future scientific and AI/ML motifs, and we discuss methods for identifying emerging computing patterns for unique scientific workloads. The MLCommons Science Benchmarks Ontology provides a standardized, scalable foundation for reproducible, cross-domain benchmarking in scientific machine learning. A companion webpage for this work has also been developed as the effort evolves: https://mlcommons-science.github.io/benchmark/

Paperid: 979, https://arxiv.org/pdf/2511.05609.pdf GitHub

Abstract:
Recent advancements in optimization-based text-to-3D generation heavily rely on distilling knowledge from pre-trained text-to-image diffusion models using techniques like Score Distillation Sampling (SDS), which often introduce artifacts such as over-saturation and over-smoothing into the generated 3D assets. In this paper, we address this essential problem by formulating the generation process as learning an optimal, direct transport trajectory between the distribution of the current rendering and the desired target distribution, thereby enabling high-quality generation with smaller Classifier-free Guidance (CFG) values. At first, we theoretically establish SDS as a simplified instance of the Schrödinger Bridge framework. We prove that SDS employs the reverse process of an Schrödinger Bridge, which, under specific conditions (e.g., a Gaussian noise as one end), collapses to SDS's score function of the pre-trained diffusion model. Based upon this, we introduce Trajectory-Centric Distillation (TraCe), a novel text-to-3D generation framework, which reformulates the mathematically trackable framework of Schrödinger Bridge to explicitly construct a diffusion bridge from the current rendering to its text-conditioned, denoised target, and trains a LoRA-adapted model on this trajectory's score dynamics for robust 3D optimization. Comprehensive experiments demonstrate that TraCe consistently achieves superior quality and fidelity to state-of-the-art techniques.

Paperid: 980, https://arxiv.org/pdf/2511.05590.pdf GitHub

Abstract:
Class Activation Mapping (CAM) and its extensions have become indispensable tools for visualizing the evidence behind deep network predictions. However, by relying on a final softmax classifier, these methods suffer from two fundamental distortions: additive logit shifts that arbitrarily bias importance scores, and sign collapse that conflates excitatory and inhibitory features. We propose a simple, architecture-agnostic dual-branch sigmoid head that decouples localization from classification. Given any pretrained model, we clone its classification head into a parallel branch ending in per-class sigmoid outputs, freeze the original softmax head, and fine-tune only the sigmoid branch with class-balanced binary supervision. At inference, softmax retains recognition accuracy, while class evidence maps are generated from the sigmoid branch -- preserving both magnitude and sign of feature contributions. Our method integrates seamlessly with most CAM variants and incurs negligible overhead. Extensive evaluations on fine-grained tasks (CUB-200-2011, Stanford Cars) and WSOL benchmarks (ImageNet-1K, OpenImages30K) show improved explanation fidelity and consistent Top-1 Localization gains -- without any drop in classification accuracy. Code is available at https://github.com/finallyupper/beyond-softmax.

Paperid: 981, https://arxiv.org/pdf/2511.05589.pdf GitHub

Abstract:
Reinforcement learning (RL) post-training has become a trending paradigm for enhancing the capabilities of large language models (LLMs). Most existing RL systems for LLMs operate in a fully synchronous manner, where training must wait for the rollout of an entire batch to complete. This design leads to severe inefficiencies, as extremely long trajectories can stall the entire rollout process and leave many GPUs idle. To address this issue, we propose Concurrency- Controlled Partial Rollout with Importance Sampling (CoPRIS), which mitigates long-tail inefficiencies by maintaining a fixed number of concurrent rollouts, early-terminating once sufficient samples are collected, and reusing unfinished trajectories in subsequent rollouts. To mitigate the impact of off-policy trajectories, we introduce Cross-stage Importance Sampling Correction, which concatenates buffered log probabilities from the previous policy with those recomputed under the current policy for importance sampling correction. Experiments on challenging mathematical reasoning benchmarks show that CoPRIS achieves up to 1.94x faster training while maintaining comparable or superior performance to synchronous RL systems. The code of CoPRIS is available at https://github.com/777pomingzi/CoPRIS.

Paperid: 982, https://arxiv.org/pdf/2511.05575.pdf GitHub

Abstract:
Diffusion-based approaches have recently achieved strong results in face swapping, offering improved visual quality over traditional GAN-based methods. However, even state-of-the-art models often suffer from fine-grained artifacts and poor identity preservation, particularly under challenging poses and expressions. A key limitation of existing approaches is their failure to meaningfully leverage 3D facial structure, which is crucial for disentangling identity from pose and expression. In this work, we propose DiffSwap++, a novel diffusion-based face-swapping pipeline that incorporates 3D facial latent features during training. By guiding the generation process with 3D-aware representations, our method enhances geometric consistency and improves the disentanglement of facial identity from appearance attributes. We further design a diffusion architecture that conditions the denoising process on both identity embeddings and facial landmarks, enabling high-fidelity and identity-preserving face swaps. Extensive experiments on CelebA, FFHQ, and CelebV-Text demonstrate that DiffSwap++ outperforms prior methods in preserving source identity while maintaining target pose and expression. Additionally, we introduce a biometric-style evaluation and conduct a user study to further validate the realism and effectiveness of our approach. Code will be made publicly available at https://github.com/WestonBond/DiffSwapPP

Paperid: 983, https://arxiv.org/pdf/2511.05571.pdf GitHub

Abstract:
The rapid advancement of spatial transcriptomics (ST), i.e., spatial gene expressions, has made it possible to measure gene expression within original tissue, enabling us to discover molecular mechanisms. However, current ST platforms frequently suffer from low resolution, limiting the in-depth understanding of spatial gene expression. Super-resolution approaches promise to enhance ST maps by integrating histology images with gene expressions of profiled tissue spots. However, it remains a challenge to model the interactions between histology images and gene expressions for effective ST enhancement. This study presents a cross-modal cross-content contrastive diffusion framework, called C3-Diff, for ST enhancement with histology images as guidance. In C3-Diff, we firstly analyze the deficiency of traditional contrastive learning paradigm, which is then refined to extract both modal-invariant and content-invariant features of ST maps and histology images. Further, to overcome the problem of low sequencing sensitivity in ST maps, we perform nosing-based information augmentation on the surface of feature unit hypersphere. Finally, we propose a dynamic cross-modal imputation-based training strategy to mitigate ST data scarcity. We tested C3-Diff by benchmarking its performance on four public datasets, where it achieves significant improvements over competing methods. Moreover, we evaluate C3-Diff on downstream tasks of cell type localization, gene expression correlation and single-cell-level gene expression prediction, promoting AI-enhanced biotechnology for biomedical research and clinical applications. Codes are available at https://github.com/XiaofeiWang2018/C3-Diff.

Paperid: 984, https://arxiv.org/pdf/2511.05554.pdf GitHub

Abstract:
Existing Multi-view Clustering (MVC) methods based on subspace learning focus on consensus representation learning while neglecting the inherent topological structure of data. Despite the integration of Graph Neural Networks (GNNs) into MVC, their input graph structures remain susceptible to noise interference. Methods based on Multi-view Graph Refinement (MGRC) also have limitations such as insufficient consideration of cross-view consistency, difficulty in handling hard-to-distinguish samples in the feature space, and disjointed optimization processes caused by graph construction algorithms. To address these issues, a Multi-View Clustering method via a Fusion-Consensus Graph Convolutional Network (MCFCN) is proposed. The network learns the consensus graph of multi-view data in an end-to-end manner and learns effective consensus representations through a view feature fusion model and a Unified Graph Structure Adapter (UGA). It designs Similarity Matrix Alignment Loss (SMAL) and Feature Representation Alignment Loss (FRAL). With the guidance of consensus, it optimizes view-specific graphs, preserves cross-view topological consistency, promotes the construction of intra-class edges, and realizes effective consensus representation learning with the help of GCN to improve clustering performance. MCFCN demonstrates state-of-the-art performance on eight multi-view benchmark datasets, and its effectiveness is verified by extensive qualitative and quantitative implementations. The code will be provided at https://github.com/texttao/MCFCN.

Paperid: 985, https://arxiv.org/pdf/2511.05542.pdf GitHub

Abstract:
Connectomics - the mapping of neural connections in an organism's brain - currently requires extraordinary human effort to proofread the data collected from imaging and machine-learning assisted segmentation. With the growing excitement around using AI agents to automate important scientific tasks, we explore whether current AI systems can perform multiple tasks necessary for data proofreading. We introduce ConnectomeBench, a multimodal benchmark evaluating large language model (LLM) capabilities in three critical proofreading tasks: segment type identification, split error correction, and merge error detection. Using expert annotated data from two large open-source datasets - a cubic millimeter of mouse visual cortex and the complete Drosophila brain - we evaluate proprietary multimodal LLMs including Claude 3.7/4 Sonnet, o4-mini, GPT-4.1, GPT-4o, as well as open source models like InternVL-3 and NVLM. Our results demonstrate that current models achieve surprisingly high performance in segment identification (52-82% balanced accuracy vs. 20-25% chance) and binary/multiple choice split error correction (75-85% accuracy vs. 50% chance) while generally struggling on merge error identification tasks. Overall, while the best models still lag behind expert performance, they demonstrate promising capabilities that could eventually enable them to augment and potentially replace human proofreading in connectomics. Project page: https://github.com/jffbrwn2/ConnectomeBench and Dataset https://huggingface.co/datasets/jeffbbrown2/ConnectomeBench/tree/main

Paperid: 986, https://arxiv.org/pdf/2511.05535.pdf GitHub

Abstract:
Artificial Intelligence, especially Large Language Models (LLMs), has transformed domains such as software engineering, journalism, creative writing, academia, and media (Naveed et al. 2025; arXiv:2307.06435). Diffusion models like Stable Diffusion generate high-quality images and videos from text. Evidence shows rapid expansion: 74.2% of newly published webpages now contain AI-generated material (Ryan Law 2025), 30-40% of the active web corpus is synthetic (Spennemann 2025; arXiv:2504.08755), 52% of U.S. adults use LLMs for writing, coding, or research (Staff 2025), and audits find AI involvement in 18% of financial complaints and 24% of press releases (Liang et al. 2025). The underlying neural architectures, including Transformers (Vaswani et al. 2023; arXiv:1706.03762), RNNs, LSTMs, GANs, and diffusion networks, depend on large, diverse, human-authored datasets (Shi & Iyengar 2019). As synthetic content dominates, recursive training risks eroding linguistic and semantic diversity, producing Model Collapse (Shumailov et al. 2024; arXiv:2307.15043; Dohmatob et al. 2024; arXiv:2402.07712). This study quantifies and forecasts collapse onset by examining year-wise semantic similarity in English-language Wikipedia (filtered Common Crawl) from 2013 to 2025 using Transformer embeddings and cosine similarity metrics. Results reveal a steady rise in similarity before public LLM adoption, likely driven by early RNN/LSTM translation and text-normalization pipelines, though modest due to a smaller scale. Observed fluctuations reflect irreducible linguistic diversity, variable corpus size across years, finite sampling error, and an exponential rise in similarity after the public adoption of LLM models. These findings provide a data-driven estimate of when recursive AI contamination may significantly threaten data richness and model generalization.

Paperid: 987, https://arxiv.org/pdf/2511.05533.pdf GitHub

Abstract:
Bringing generative AI into the architecture, engineering and construction (AEC) field requires systems that can translate natural language instructions into actions on standardized data models. We present MCP4IFC, a comprehensive open-source framework that enables Large Language Models (LLMs) to directly manipulate Industry Foundation Classes (IFC) data through the Model Context Protocol (MCP). The framework provides a set of BIM tools, including scene querying tools for information retrieval, predefined functions for creating and modifying common building elements, and a dynamic code-generation system that combines in-context learning with retrieval-augmented generation (RAG) to handle tasks beyond the predefined toolset. Experiments demonstrate that an LLM using our framework can successfully perform complex tasks, from building a simple house to querying and editing existing IFC data. Our framework is released as open-source to encourage research in LLM-driven BIM design and provide a foundation for AI-assisted modeling workflows. Our code is available at https://show2instruct.github.io/mcp4ifc/.

Paperid: 988, https://arxiv.org/pdf/2511.05498.pdf GitHub

Abstract:
We introduce an explainability method for biomedical hypothesis generation systems, built on top of the novel Hypothesis Generation Context Retriever framework. Our approach combines semantic graph-based retrieval and relevant data-restrictive training to simulate real-world discovery constraints. Integrated with large language models (LLMs) via retrieval-augmented generation, the system explains hypotheses with contextual evidence using published scientific literature. We also propose a novel feedback loop approach, which iteratively identifies and corrects flawed parts of LLM-generated explanations, refining both the evidence paths and supporting context. We demonstrate the performance of our method with multiple large language models and evaluate the explanation and context retrieval quality through both expert-curated assessment and large-scale automated analysis. Our code is available at: https://github.com/IlyaTyagin/HGCR.

Paperid: 989, https://arxiv.org/pdf/2511.05494.pdf GitHub

Abstract:
Modern recommender systems face a critical challenge in complying with privacy regulations like the 'right to be forgotten': removing a user's data without disrupting recommendations for others. Traditional unlearning methods address this by partial model updates, but introduce propagation bias--where unlearning one user's data distorts recommendations for behaviorally similar users, degrading system accuracy. While retraining eliminates bias, it is computationally prohibitive for large-scale systems. To address this challenge, we propose CRAGRU, a novel framework leveraging Retrieval-Augmented Generation (RAG) for efficient, user-specific unlearning that mitigates bias while preserving recommendation quality. CRAGRU decouples unlearning into distinct retrieval and generation stages. In retrieval, we employ three tailored strategies designed to precisely isolate the target user's data influence, minimizing collateral impact on unrelated users and enhancing unlearning efficiency. Subsequently, the generation stage utilizes an LLM, augmented with user profiles integrated into prompts, to reconstruct accurate and personalized recommendations without needing to retrain the entire base model. Experiments on three public datasets demonstrate that CRAGRU effectively unlearns targeted user data, significantly mitigating unlearning bias by preventing adverse impacts on non-target users, while maintaining recommendation performance comparable to fully trained original models. Our work highlights the promise of RAG-based architectures for building robust and privacy-preserving recommender systems. The source code is available at: https://github.com/zhanghaichao520/LLM_rec_unlearning.

Paperid: 990, https://arxiv.org/pdf/2511.05489.pdf GitHub GitHub

Abstract:
Temporal search aims to identify a minimal set of relevant frames from tens of thousands based on a given query, serving as a foundation for accurate long-form video understanding. Existing works attempt to progressively narrow the search space. However, these approaches typically rely on a hand-crafted search process, lacking end-to-end optimization for learning optimal search strategies. In this paper, we propose TimeSearch-R, which reformulates temporal search as interleaved text-video thinking, seamlessly integrating searching video clips into the reasoning process through reinforcement learning (RL). However, applying RL training methods, such as Group Relative Policy Optimization (GRPO), to video reasoning can result in unsupervised intermediate search decisions. This leads to insufficient exploration of the video content and inconsistent logical reasoning. To address these issues, we introduce GRPO with Completeness Self-Verification (GRPO-CSV), which gathers searched video frames from the interleaved reasoning process and utilizes the same policy model to verify the adequacy of searched frames, thereby improving the completeness of video reasoning. Additionally, we construct datasets specifically designed for the SFT cold-start and RL training of GRPO-CSV, filtering out samples with weak temporal dependencies to enhance task difficulty and improve temporal search capabilities. Extensive experiments demonstrate that TimeSearch-R achieves significant improvements on temporal search benchmarks such as Haystack-LVBench and Haystack-Ego4D, as well as long-form video understanding benchmarks like VideoMME and MLVU. Notably, TimeSearch-R establishes a new state-of-the-art on LongVideoBench with 4.1% improvement over the base model Qwen2.5-VL and 2.0% over the advanced video reasoning model Video-R1. Our code is available at https://github.com/Time-Search/TimeSearch-R.

Paperid: 991, https://arxiv.org/pdf/2511.05421.pdf GitHub

Abstract:
Continual learning is an emerging topic in the field of deep learning, where a model is expected to learn continuously for new upcoming tasks without forgetting previous experiences. This field has witnessed numerous advancements, but few works have been attempted in the direction of image restoration. Handling large image sizes and the divergent nature of various degradation poses a unique challenge in the restoration domain. However, existing works require heavily engineered architectural modifications for new task adaptation, resulting in significant computational overhead. Regularization-based methods are unsuitable for restoration, as different restoration challenges require different kinds of feature processing. In this direction, we propose a simple modification of the convolution layer to adapt the knowledge from previous restoration tasks without touching the main backbone architecture. Therefore, it can be seamlessly applied to any deep architecture without any structural modifications. Unlike other approaches, we demonstrate that our model can increase the number of trainable parameters without significantly increasing computational overhead or inference time. Experimental validation demonstrates that new restoration tasks can be introduced without compromising the performance of existing tasks. We also show that performance on new restoration tasks improves by adapting the knowledge from the knowledge base created by previous restoration tasks. The code is available at https://github.com/aupendu/continual-restore.

Paperid: 992, https://arxiv.org/pdf/2511.05385.pdf GitHub

Abstract:
Retrieval-Augmented Generation (RAG) utilizes external knowledge to augment Large Language Models' (LLMs) reliability. For flexibility, agentic RAG employs autonomous, multi-round retrieval and reasoning to resolve queries. Although recent agentic RAG has improved via reinforcement learning, they often incur substantial token overhead from search and reasoning processes. This trade-off prioritizes accuracy over efficiency. To address this issue, this work proposes TeaRAG, a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps. 1) First, the retrieved content is compressed by augmenting chunk-based semantic retrieval with a graph retrieval using concise triplets. A knowledge association graph is then built from semantic similarity and co-occurrence. Finally, Personalized PageRank is leveraged to highlight key knowledge within this graph, reducing the number of tokens per retrieval. 2) Besides, to reduce reasoning steps, Iterative Process-aware Direct Preference Optimization (IP-DPO) is proposed. Specifically, our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps. This design can produce high-quality preference-pair datasets, supporting iterative DPO to improve reasoning conciseness. Across six datasets, TeaRAG improves the average Exact Match by 4% and 2% while reducing output tokens by 61% and 59% on Llama3-8B-Instruct and Qwen2.5-14B-Instruct, respectively. Code is available at https://github.com/Applied-Machine-Learning-Lab/TeaRAG.

Paperid: 993, https://arxiv.org/pdf/2511.05357.pdf GitHub

Abstract:
We present a conditional diffusion model for electromagnetic inverse design that generates structured media geometries directly from target differential scattering cross-section profiles, bypassing expensive iterative optimization. Our 1D U-Net architecture with Feature-wise Linear Modulation learns to map desired angular scattering patterns to 2x2 dielectric sphere structure, naturally handling the non-uniqueness of inverse problems by sampling diverse valid designs. Trained on 11,000 simulated metasurfaces, the model achieves median MPE below 19% on unseen targets (best: 1.39%), outperforming CMA-ES evolutionary optimization while reducing design time from hours to seconds. These results demonstrate that employing diffusion models is promising for advancing electromagnetic inverse design research, potentially enabling rapid exploration of complex metasurface architectures and accelerating the development of next-generation photonic and wireless communication systems. The code is publicly available at https://github.com/mikzuker/inverse_design_metasurface_generation.

Paperid: 994, https://arxiv.org/pdf/2511.05308.pdf GitHub

Abstract:
As 3D point clouds become a cornerstone of modern technology, the need for sophisticated generative models and reliable evaluation metrics has grown exponentially. In this work, we first expose that some commonly used metrics for evaluating generated point clouds, particularly those based on Chamfer Distance (CD), lack robustness against defects and fail to capture geometric fidelity and local shape consistency when used as quality indicators. We further show that introducing samples alignment prior to distance calculation and replacing CD with Density-Aware Chamfer Distance (DCD) are simple yet essential steps to ensure the consistency and robustness of point cloud generative model evaluation metrics. While existing metrics primarily focus on directly comparing 3D Euclidean coordinates, we present a novel metric, named Surface Normal Concordance (SNC), which approximates surface similarity by comparing estimated point normals. This new metric, when combined with traditional ones, provides a more comprehensive evaluation of the quality of generated samples. Finally, leveraging recent advancements in transformer-based models for point cloud analysis, such as serialized patch attention , we propose a new architecture for generating high-fidelity 3D structures, the Diffusion Point Transformer. We perform extensive experiments and comparisons on the ShapeNet dataset, showing that our model outperforms previous solutions, particularly in terms of quality of generated point clouds, achieving new state-of-the-art. Code available at https://github.com/matteo-bastico/DiffusionPointTransformer.

Paperid: 995, https://arxiv.org/pdf/2511.05304.pdf GitHub

Abstract:
Extended reality (XR) research increasingly relies on the ability to stream and synchronize multimodal data between headsets and immersive applications for data-driven interaction and experimentation. However, developers face a critical gap: the Platform for Situated Intelligence (psi), which excels at deterministic temporal alignment and multimodal data management, has been largely inaccessible to the dominant Unity/MRTK ecosystem used for HoloLens development. We introduce psiUnity, an open-source C# integration that bridges psi's .NET libraries with Unity 2022.3 and MRTK3 for HoloLens 2. psiUnity enables bidirectional, real-time streaming of head pose, hand tracking, gaze, IMU, audio, and depth sensor data (AHAT and long-throw) with microsecond-level temporal precision, allowing Unity applications to both consume and produce synchronized multimodal data streams. By embedding psi's native serialization, logging, and temporal coordination directly within Unity's architecture, psiUnity extends psi beyond its previous StereoKit limitations and empowers the HRI, HCI, and embodied-AI communities to develop reproducible, data-driven XR interactions and experiments within the familiar Unity environment. The integration is available at https://github.com/sailgt/psiUnity.

Paperid: 996, https://arxiv.org/pdf/2511.05299.pdf GitHub

Abstract:
Despite significant progress in Video Large Language Models (Video-LLMs) for offline video understanding, existing online Video-LLMs typically struggle to simultaneously process continuous frame-by-frame inputs and determine optimal response timing, often compromising real-time responsiveness and narrative coherence. To address these limitations, we introduce LiveStar, a pioneering live streaming assistant that achieves always-on proactive responses through adaptive streaming decoding. Specifically, LiveStar incorporates: (1) a training strategy enabling incremental video-language alignment for variable-length video streams, preserving temporal consistency across dynamically evolving frame sequences; (2) a response-silence decoding framework that determines optimal proactive response timing via a single forward pass verification; (3) memory-aware acceleration via peak-end memory compression for online inference on 10+ minute videos, combined with streaming key-value cache to achieve 1.53x faster inference. We also construct an OmniStar dataset, a comprehensive dataset for training and benchmarking that encompasses 15 diverse real-world scenarios and 5 evaluation tasks for online video understanding. Extensive experiments across three benchmarks demonstrate LiveStar's state-of-the-art performance, achieving an average 19.5% improvement in semantic correctness with 18.1% reduced timing difference compared to existing online Video-LLMs, while improving FPS by 12.0% across all five OmniStar tasks. Our model and dataset can be accessed at https://github.com/yzy-bupt/LiveStar.

Paperid: 997, https://arxiv.org/pdf/2511.05292.pdf GitHub

Abstract:
Accurate food intake detection is vital for dietary monitoring and chronic disease prevention. Traditional self-report methods are prone to recall bias, while camera-based approaches raise concerns about privacy. Furthermore, existing wearable-based methods primarily focus on a limited number of food types, such as hamburgers and pizza, failing to address the vast diversity of Chinese cuisine. To bridge this gap, we propose CuisineSense, a system that classifies Chinese food types by integrating hand motion cues from a smartwatch with head dynamics from smart glasses. To filter out irrelevant daily activities, we design a two-stage detection pipeline. The first stage identifies eating states by distinguishing characteristic temporal patterns from non-eating behaviors. The second stage then conducts fine-grained food type recognition based on the motions captured during food intake. To evaluate CuisineSense, we construct a dataset comprising 27.5 hours of IMU recordings across 11 food categories and 10 participants. Experiments demonstrate that CuisineSense achieves high accuracy in both eating state detection and food classification, offering a practical solution for unobtrusive, wearable-based dietary monitoring.The system code is publicly available at https://github.com/joeeeeyin/CuisineSense.git.

Paperid: 998, https://arxiv.org/pdf/2511.05275.pdf GitHub

Abstract:
Vision-language-action models (VLAs) trained on large-scale robotic datasets have demonstrated strong performance on manipulation tasks, including bimanual tasks. However, because most public datasets focus on single-arm demonstrations, adapting VLAs for bimanual tasks typically requires substantial additional bimanual data and fine-tuning. To address this challenge, we introduce TwinVLA, a modular framework that composes two copies of a pretrained single-arm VLA into a coordinated bimanual VLA. Unlike monolithic cross-embodiment models trained on mixtures of single-arm and bimanual data, TwinVLA improves both data efficiency and performance by composing pretrained single-arm policies. Across diverse bimanual tasks in real-world and simulation settings, TwinVLA outperforms a comparably-sized monolithic RDT-1B model without requiring any bimanual pretraining. Furthermore, it narrows the gap to state-of-the-art model, $π_0$ which rely on extensive proprietary bimanual data and compute cost. These results establish our modular composition approach as a data-efficient and scalable path toward high-performance bimanual manipulation, leveraging public single-arm data.

Paperid: 999, https://arxiv.org/pdf/2511.05245.pdf GitHub

Abstract:
The current mainstream and state-of-the-art anomaly detection (AD) methods are substantially established on pretrained feature networks yielded by ImageNet pretraining. However, regardless of supervised or self-supervised pretraining, the pretraining process on ImageNet does not match the goal of anomaly detection (i.e., pretraining in natural images doesn't aim to distinguish between normal and abnormal). Moreover, natural images and industrial image data in AD scenarios typically have the distribution shift. The two issues can cause ImageNet-pretrained features to be suboptimal for AD tasks. To further promote the development of the AD field, pretrained representations specially for AD tasks are eager and very valuable. To this end, we propose a novel AD representation learning framework specially designed for learning robust and discriminative pretrained representations for industrial anomaly detection. Specifically, closely surrounding the goal of anomaly detection (i.e., focus on discrepancies between normals and anomalies), we propose angle- and norm-oriented contrastive losses to maximize the angle size and norm difference between normal and abnormal features simultaneously. To avoid the distribution shift from natural images to AD images, our pretraining is performed on a large-scale AD dataset, RealIAD. To further alleviate the potential shift between pretraining data and downstream AD datasets, we learn the pretrained AD representations based on the class-generalizable representation, residual features. For evaluation, based on five embedding-based AD methods, we simply replace their original features with our pretrained representations. Extensive experiments on five AD datasets and five backbones consistently show the superiority of our pretrained features. The code is available at https://github.com/xcyao00/ADPretrain.

Paperid: 1000, https://arxiv.org/pdf/2511.05203.pdf GitHub GitHub

Abstract:
Today's autonomous agents can understand free-form natural language instructions and execute long-horizon tasks in a manner akin to human-level reasoning. These capabilities are mostly driven by large-scale pre-trained foundation models (FMs). However, the approaches with which these models are grounded for human-robot interaction (HRI) perpetuate a master-apprentice model, where the apprentice (embodied agent) passively receives and executes the master's (human's) commands without reciprocal learning. This reactive interaction approach does not capture the co-adaptive dynamics inherent in everyday multi-turn human-human interactions. To address this, we propose a Symbiotic Interactive Learning (SIL) approach that enables both the master and the apprentice to co-adapt through mutual, bidirectional interactions. We formalised SIL as a co-adaptation process within a shared latent task space, where the agent and human maintain joint belief states that evolve based on interaction history. This enables the agent to move beyond reactive execution to proactive clarification, adaptive suggestions, and shared plan refinement. To realise these novel behaviours, we leveraged pre-trained FMs for spatial perception and reasoning, alongside a lightweight latent encoder that grounds the models' outputs into task-specific representations. Furthermore, to ensure stability as the tasks evolve, we augment SIL with a memory architecture that prevents the forgetting of learned task-space representations. We validate SIL on both simulated and real-world embodied tasks, including instruction following, information retrieval, query-oriented reasoning, and interactive dialogues. Demos and resources are public at:~\href{https://linusnep.github.io/SIL/}{https://linusnep.github.io/SIL/}.

Paperid: 1001, https://arxiv.org/pdf/2511.05179.pdf GitHub

Abstract:
Modern IoT deployments for environmental sensing produce high volume spatiotemporal data to support downstream tasks such as forecasting, typically powered by machine learning models. While existing filtering and strategic deployment techniques optimize collected data volume at the edge, they overlook how variations in sampling frequencies and spatial coverage affect downstream model performance. In many forecasting models, incorporating data from additional sensors denoise predictions by providing broader spatial contexts. This interplay between sampling frequency, spatial coverage and different forecasting model architectures remain underexplored. This work presents a systematic study of forecasting models - classical models (VAR), neural networks (GRU, Transformer), spatio-temporal graph neural networks (STGNNs), and time series foundation models (TSFMs: Chronos Moirai, TimesFM) under varying spatial sensor nodes density and sampling intervals using real-world temperature data in a wireless sensor network. Our results show that STGNNs are effective when sensor deployments are sparse and sampling rate is moderate, leveraging spatial correlations via encoded graph structure to compensate for limited coverage. In contrast, TSFMs perform competitively at high frequencies but degrade when spatial coverage from neighboring sensors is reduced. Crucially, the multivariate TSFM Moirai outperforms all models by natively learning cross-sensor dependencies. These findings offer actionable insights for building efficient forecasting pipelines in spatio-temporal systems. All code for model configurations, training, dataset, and logs are open-sourced for reproducibility: https://github.com/UIUC-MONET-Projects/Benchmarking-Spatiotemporal-Forecast-Models

Paperid: 1002, https://arxiv.org/pdf/2511.05168.pdf GitHub

Abstract:
Vision foundation models achieve strong performance on both global and locally dense downstream tasks. Pretrained on large images, the recent DINOv3 model family is able to produce very fine-grained dense feature maps, enabling state-of-the-art performance. However, computing these feature maps requires the input image to be available at very high resolution, as well as large amounts of compute due to the squared complexity of the transformer architecture. To address these issues, we propose BRIXEL, a simple knowledge distillation approach that has the student learn to reproduce its own feature maps at higher resolution. Despite its simplicity, BRIXEL outperforms the baseline DINOv3 models by large margins on downstream tasks when the resolution is kept fixed. Moreover, it is able to produce feature maps that are very similar to those of the teacher at a fraction of the computational cost. Code and model weights are available at https://github.com/alexanderlappe/BRIXEL.

Paperid: 1003, https://arxiv.org/pdf/2511.05122.pdf GitHub

Abstract:
Centrality is a fundamental concept in network science, providing critical insights into the structure and dynamics of complex systems such as social, transportation, biological and financial networks. Despite its extensive use, there is no universally accepted definition of centrality, leading to the development of a vast array of distinct centrality measures. These measures have grown so numerous that they resemble a 'zoo', each representing a unique approach to capturing node importance within a network. However, the increasing number of metrics being developed has led to several challenges, including issues of discoverability, redundancy, naming conflicts, validation and accessibility. This work aims to address these challenges by providing a comprehensive catalog of over 400 centrality measures, along with clear descriptions and references to original sources. While not exhaustive, this compilation represents the most extensive and systematic effort to date in organizing and presenting centrality measures. We also encourage readers to explore and contribute to the Centrality Zoo website at https://centralityzoo.github.io/, which provides an interactive platform for discovering, comparing and implementing centrality measures.

Paperid: 1004, https://arxiv.org/pdf/2511.05108.pdf GitHub

Abstract:
Lane detection for autonomous driving in snow-covered environments remains a major challenge due to the frequent absence or occlusion of lane markings. In this paper, we present a novel, robust and realtime capable approach that bypasses the reliance on traditional lane markings by detecting roadside features,specifically vertical roadside posts called delineators, as indirect lane indicators. Our method first perceives these posts, then fits a smooth lane trajectory using a parameterized Bezier curve model, leveraging spatial consistency and road geometry. To support training and evaluation in these challenging scenarios, we introduce SnowyLane, a new synthetic dataset containing 80,000 annotated frames capture winter driving conditions, with varying snow coverage, and lighting conditions. Compared to state-of-the-art lane detection systems, our approach demonstrates significantly improved robustness in adverse weather, particularly in cases with heavy snow occlusion. This work establishes a strong foundation for reliable lane detection in winter scenarios and contributes a valuable resource for future research in all-weather autonomous driving. The dataset is available at https://ekut-es.github.io/snowy-lane

Paperid: 1005, https://arxiv.org/pdf/2511.05095.pdf GitHub

Abstract:
Adverse weather severely impairs real-world visual perception, while existing vision models trained on synthetic data with fixed parameters struggle to generalize to complex degradations. To address this, we first construct HFLS-Weather, a physics-driven, high-fidelity dataset that simulates diverse weather phenomena, and then design a dual-level reinforcement learning framework initialized with HFLS-Weather for cold-start training. Within this framework, at the local level, weather-specific restoration models are refined through perturbation-driven image quality optimization, enabling reward-based learning without paired supervision; at the global level, a meta-controller dynamically orchestrates model selection and execution order according to scene degradation. This framework enables continuous adaptation to real-world conditions and achieves state-of-the-art performance across a wide range of adverse weather scenarios. Code is available at https://github.com/xxclfy/AgentRL-Real-Weather

Paperid: 1006, https://arxiv.org/pdf/2511.05064.pdf GitHub

Abstract:
In this paper, we explore an important yet previously neglected question: Do context aggregation patterns across Language Models (LMs) share commonalities? While some works have investigated context aggregation or attention weights in LMs, they typically focus on individual models or attention heads, lacking a systematic analysis across multiple LMs to explore their commonalities. In contrast, we focus on the commonalities among LMs, which can deepen our understanding of LMs and even facilitate cross-model knowledge transfer. In this work, we introduce the Order-Level Attention (OLA) derived from the order-wise decomposition of Attention Rollout and reveal that the OLA at the same order across LMs exhibits significant similarities. Furthermore, we discover an implicit mapping between OLA and syntactic knowledge. Based on these two findings, we propose the Transferable OLA Adapter (TOA), a training-free cross-LM adapter transfer method. Specifically, we treat the OLA as a unified syntactic feature representation and train an adapter that takes OLA as input. Due to the similarities in OLA across LMs, the adapter generalizes to unseen LMs without requiring any parameter updates. Extensive experiments demonstrate that TOA's cross-LM generalization effectively enhances the performance of unseen LMs. Code is available at https://github.com/jinglin-liang/OLAS.

Paperid: 1007, https://arxiv.org/pdf/2511.05059.pdf GitHub GitHub

Abstract:
During laparoscopic surgery, smoke generated by tissue cauterization can significantly degrade the visual quality of endoscopic frames, increasing the risk of surgical errors and hindering both clinical decision-making and computer-assisted visual analysis. Consequently, removing surgical smoke is critical to ensuring patient safety and maintaining operative efficiency. In this study, we propose the Surgical Atmospheric Model (SurgiATM) for surgical smoke removal. SurgiATM statistically bridges a physics-based atmospheric model and data-driven deep learning models, combining the superior generalizability of the former with the high accuracy of the latter. Furthermore, SurgiATM is designed as a lightweight, plug-and-play module that can be seamlessly integrated into diverse surgical desmoking architectures to enhance their accuracy and stability, better meeting clinical requirements. It introduces only two hyperparameters and no additional trainable weights, preserving the original network architecture with minimal computational and modification overhead. We conduct extensive experiments on three public surgical datasets with ten desmoking methods, involving multiple network architectures and covering diverse procedures, including cholecystectomy, partial nephrectomy, and diaphragm dissection. The results demonstrate that incorporating SurgiATM commonly reduces the restoration errors of existing models and relatively enhances their generalizability, without adding any trainable layers or weights. This highlights the convenience, low cost, effectiveness, and generalizability of the proposed method. The code for SurgiATM is released at https://github.com/MingyuShengSMY/SurgiATM.

Paperid: 1008, https://arxiv.org/pdf/2511.05057.pdf GitHub

Abstract:
The effectiveness of Contrastive Language-Image Pre-training (CLIP) models critically depends on the semantic diversity and quality of their training data. However, while existing synthetic data generation methods primarily focus on increasing data volume, such emphasis often leads to limited semantic diversity and redundant or shallow captions. To address this limitation, we propose Role-SynthCLIP, a novel data synthesis framework that leverages multi-perspective role-playing prompts (e.g., a compositional analyst, an interpreter of image context) to guide Multimodal Large Language Models (MLLMs) in generating semantically diverse captions from distinct viewpoints. This mechanism enhances the semantic diversity and fine-grained image-text alignment of synthetic pairs, thereby improving caption expressiveness and accuracy while keeping the total number of image-text pairs unchanged. Experimental results demonstrate the effectiveness and efficiency of our method. A CLIP-B/16 model trained on only 1 million Role-SynthCLIP pairs achieves a Recall@1 of 64.1% on the MS COCO validation set, surpassing the best existing synthetic data baseline (trained on 5M pairs) by 2.8 percentage points. The code and trained models are released at https://github.com/huangfu170/Role-SynthCLIP.

Paperid: 1009, https://arxiv.org/pdf/2511.05009.pdf GitHub

Abstract:
Ultra-high-definition (UHD) images often suffer from severe degradations such as blur, haze, rain, or low-light conditions, which pose significant challenges for image restoration due to their high resolution and computational demands. In this paper, we propose UHDRes, a novel lightweight dual-domain decoupled spectral modulation framework for UHD image restoration. It explicitly models the amplitude spectrum via lightweight spectrum-domain modulation, while restoring phase implicitly through spatial-domain refinement. We introduce the spatio-spectral fusion mechanism, which first employs a multi-scale context aggregator to extract local and global spatial features, and then performs spectral modulation in a decoupled manner. It explicitly enhances amplitude features in the frequency domain while implicitly restoring phase information through spatial refinement. Additionally, a shared gated feed-forward network is designed to efficiently promote feature interaction through shared-parameter convolutions and adaptive gating mechanisms. Extensive experimental comparisons on five public UHD benchmarks demonstrate that our UHDRes achieves the state-of-the-art restoration performance with only 400K parameters, while significantly reducing inference latency and memory usage. The codes and models are available at https://github.com/Zhao0100/UHDRes.

Paperid: 1010, https://arxiv.org/pdf/2511.05007.pdf GitHub

Abstract:
Diffusion policies have emerged as a powerful framework for robotic visuomotor control, yet they often lack the robustness to recover from subtask failures in long-horizon, multi-stage tasks and their learned representations of observations are often difficult to interpret. In this work, we propose the Mixture of Experts-Enhanced Diffusion Policy (MoE-DP), where the core idea is to insert a Mixture of Experts (MoE) layer between the visual encoder and the diffusion model. This layer decomposes the policy's knowledge into a set of specialized experts, which are dynamically activated to handle different phases of a task. We demonstrate through extensive experiments that MoE-DP exhibits a strong capability to recover from disturbances, significantly outperforming standard baselines in robustness. On a suite of 6 long-horizon simulation tasks, this leads to a 36% average relative improvement in success rate under disturbed conditions. This enhanced robustness is further validated in the real world, where MoE-DP also shows significant performance gains. We further show that MoE-DP learns an interpretable skill decomposition, where distinct experts correspond to semantic task primitives (e.g., approaching, grasping). This learned structure can be leveraged for inference-time control, allowing for the rearrangement of subtasks without any re-training.Our video and code are available at the https://moe-dp-website.github.io/MoE-DP-Website/.

Paperid: 1011, https://arxiv.org/pdf/2511.04963.pdf GitHub GitHub

Abstract:
Magnetic resonance imaging (MRI), especially functional MRI (fMRI) and diffusion MRI (dMRI), is essential for studying neurodegenerative diseases. However, missing modalities pose a major barrier to their clinical use. Although GAN- and diffusion model-based approaches have shown some promise in modality completion, they remain limited in fMRI-dMRI synthesis due to (1) significant BOLD vs. diffusion-weighted signal differences between fMRI and dMRI in time/gradient axis, and (2) inadequate integration of disease-related neuroanatomical patterns during generation. To address these challenges, we propose PDS, introducing two key innovations: (1) a pattern-aware dual-modal 3D diffusion framework for cross-modality learning, and (2) a tissue refinement network integrated with a efficient microstructure refinement to maintain structural fidelity and fine details. Evaluated on OASIS-3, ADNI, and in-house datasets, our method achieves state-of-the-art results, with PSNR/SSIM scores of 29.83 dB/90.84\% for fMRI synthesis (+1.54 dB/+4.12\% over baselines) and 30.00 dB/77.55\% for dMRI synthesis (+1.02 dB/+2.2\%). In clinical validation, the synthesized data show strong diagnostic performance, achieving 67.92\%/66.02\%/64.15\% accuracy (NC vs. MCI vs. AD) in hybrid real-synthetic experiments. Code is available in \href{https://github.com/SXR3015/PDS}{PDS GitHub Repository}

Paperid: 1012, https://arxiv.org/pdf/2511.04909.pdf GitHub

Abstract:
Many real-world decisions are made under uncertainty by solving optimization problems using predicted quantities. This predict-then-optimize paradigm has motivated decision-focused learning, which trains models with awareness of how the optimizer uses predictions, improving the performance of downstream decisions. Despite its promise, scaling is challenging: state-of-the-art methods either differentiate through a solver or rely on task-specific surrogates, both of which require frequent and expensive calls to an optimizer, often a combinatorial one. In this paper, we leverage dual variables from the downstream problem to shape learning and introduce Dual-Guided Loss (DGL), a simple, scalable objective that preserves decision alignment while reducing solver dependence. We construct DGL specifically for combinatorial selection problems with natural one-of-many constraints, such as matching, knapsack, and shortest path. Our approach (a) decouples optimization from gradient updates by solving the downstream problem only periodically; (b) between refreshes, trains on dual-adjusted targets using simple differentiable surrogate losses; and (c) as refreshes become less frequent, drives training cost toward standard supervised learning while retaining strong decision alignment. We prove that DGL has asymptotically diminishing decision regret, analyze runtime complexity, and show on two problem classes that DGL matches or exceeds state-of-the-art DFL methods while using far fewer solver calls and substantially less training time. Code is available at https://github.com/paularodr/Dual-Guided-Learning.

Paperid: 1013, https://arxiv.org/pdf/2511.04902.pdf GitHub

Abstract:
Recent advances in large language models have demonstrated the promise of unsupervised reinforcement learning (RL) methods for enhancing reasoning capabilities without external supervision. However, the generalizability of these label-free RL approaches to smaller base models with limited reasoning capabilities remains unexplored. In this work, we systematically investigate the performance of label-free RL methods across different model sizes and reasoning strengths, from 0.5B to 7B parameters. Our empirical analysis reveals critical limitations: label-free RL is highly dependent on the base model's pre-existing reasoning capability, with performance often degrading below baseline levels for weaker models. We find that smaller models fail to generate sufficiently long or diverse chain-of-thought reasoning to enable effective self-reflection, and that training data difficulty plays a crucial role in determining success. To address these challenges, we propose a simple yet effective method for label-free RL that utilizes curriculum learning to progressively introduce harder problems during training and mask no-majority rollouts during training. Additionally, we introduce a data curation pipeline to generate samples with predefined difficulty. Our approach demonstrates consistent improvements across all model sizes and reasoning capabilities, providing a path toward more robust unsupervised RL that can bootstrap reasoning abilities in resource-constrained models. We make our code available at https://github.com/BorealisAI/CuMa

Paperid: 1014, https://arxiv.org/pdf/2511.04831.pdf GitHub

Authors:NVIDIA, :, Mayank Mittal, Pascal Roth, James Tigue, Antoine Richard, Octi Zhang, Peter Du, Antonio Serrano-Muñoz, Xinjie Yao, René Zurbrügg, Nikita Rudin, Lukasz Wawrzyniak, Milad Rakhsha, Alain Denzler, Eric Heiden, Ales Borovicka, Ossama Ahmed, Iretiayo Akinola, Abrar Anwar, Mark T. Carlson, Ji Yuan Feng, Animesh Garg, Renato Gasoto, Lionel Gulich, Yijie Guo, M. Gussert, Alex Hansen, Mihir Kulkarni, Chenran Li, Wei Liu, Viktor Makoviychuk, Grzegorz Malczyk, Hammad Mazhar, Masoud Moghani, Adithyavairavan Murali, Michael Noseworthy, Alexander Poddubny, Nathan Ratliff, Welf Rehberg, Clemens Schwarke, Ritvik Singh, James Latham Smith, Bingjie Tang, Ruchik Thaker, Matthew Trepte, Karl Van Wyk, Fangzhou Yu, Alex Millane, Vikram Ramasamy, Remo Steiner, Sangeeta Subramanian, Clemens Volk, CY Chen, Neel Jawale, Ashwin Varghese Kuruttukulam, Michael A. Lin, Ajay Mandlekar, Karsten Patzwaldt, John Welsh, Huihua Zhao, Fatima Anes, Jean-Francois Lafleche, Nicolas Moënne-Loccoz, Soowan Park, Rob Stepinski, Dirk Van Gelder, Chris Amevor, Jan Carius, Jumyung Chang, Anka He Chen, Pablo de Heras Ciechomski, Gilles Daviet, Mohammad Mohajerani, Julia von Muralt, Viktor Reutskyy, Michael Sauter, Simon Schirm, Eric L. Shi, Pierre Terdiman, Kenny Vilella, Tobias Widmer, Gordon Yeoman, Tiffany Chen, Sergey Grizan, Cathy Li, Lotus Li, Connor Smith, Rafael Wiltz, Kostas Alexis, Yan Chang, David Chu, Linxi "Jim" Fan, Farbod Farshidian, Ankur Handa, Spencer Huang, Marco Hutter, Yashraj Narang, Soha Pouya, Shiwei Sheng, Yuke Zhu, Miles Macklin, Adam Moravanszky, Philipp Reist, Yunrong Guo, David Hoeller, Gavriel State

Abstract:
We present Isaac Lab, the natural successor to Isaac Gym, which extends the paradigm of GPU-native robotics simulation into the era of large-scale multi-modal learning. Isaac Lab combines high-fidelity GPU parallel physics, photorealistic rendering, and a modular, composable architecture for designing environments and training robot policies. Beyond physics and rendering, the framework integrates actuator models, multi-frequency sensor simulation, data collection pipelines, and domain randomization tools, unifying best practices for reinforcement and imitation learning at scale within a single extensible platform. We highlight its application to a diverse set of challenges, including whole-body control, cross-embodiment mobility, contact-rich and dexterous manipulation, and the integration of human demonstrations for skill acquisition. Finally, we discuss upcoming integration with the differentiable, GPU-accelerated Newton physics engine, which promises new opportunities for scalable, data-efficient, and gradient-based approaches to robot learning. We believe Isaac Lab's combination of advanced simulation capabilities, rich sensing, and data-center scale execution will help unlock the next generation of breakthroughs in robotics research.

Paperid: 1015, https://arxiv.org/pdf/2511.04814.pdf GitHub

Abstract:
Antimicrobial peptides have emerged as promising molecules to combat antimicrobial resistance. However, fragmented datasets, inconsistent annotations, and the lack of standardized benchmarks hinder computational approaches and slow down the discovery of new candidates. To address these challenges, we present the Expanded Standardized Collection for Antimicrobial Peptide Evaluation (ESCAPE), an experimental framework integrating over 80.000 peptides from 27 validated repositories. Our dataset separates antimicrobial peptides from negative sequences and incorporates their functional annotations into a biologically coherent multilabel hierarchy, capturing activities across antibacterial, antifungal, antiviral, and antiparasitic classes. Building on ESCAPE, we propose a transformer-based model that leverages sequence and structural information to predict multiple functional activities of peptides. Our method achieves up to a 2.56% relative average improvement in mean Average Precision over the second-best method adapted for this task, establishing a new state-of-the-art multilabel peptide classification. ESCAPE provides a comprehensive and reproducible evaluation framework to advance AI-driven antimicrobial peptide research.

Paperid: 1016, https://arxiv.org/pdf/2511.04811.pdf GitHub

Abstract:
Biomedical image segmentation is critical for precise structure delineation and downstream analysis. Traditional methods often struggle with noisy data, while deep learning models such as U-Net have set new benchmarks in segmentation performance. nnU-Net further automates model configuration, making it adaptable across datasets without extensive tuning. However, it requires a substantial amount of annotated data for cross-validation, posing a challenge when only raw images but no labels are available. Large foundation models offer zero-shot generalizability, but may underperform on specific datasets with unique characteristics, limiting their direct use for analysis. This work addresses these bottlenecks by proposing a data-centric AI workflow that leverages active learning and pseudo-labeling to combine the strengths of traditional neural networks and large foundation models while minimizing human intervention. The pipeline starts by generating pseudo-labels from a foundation model, which are then used for nnU-Net's self-configuration. Subsequently, a representative core-set is selected for minimal manual annotation, enabling effective fine-tuning of the nnU-Net model. This approach significantly reduces the need for manual annotations while maintaining competitive performance, providing an accessible solution for biomedical researchers to apply state-of-the-art AI techniques in their segmentation tasks. The code is available at https://github.com/MMV-Lab/AL_BioMed_img_seg.

Paperid: 1017, https://arxiv.org/pdf/2511.04803.pdf GitHub GitHub

Abstract:
Generalist biomedical image segmentation models such as Cellpose are increasingly applied across diverse imaging modalities and cell types. However, two critical challenges remain underexplored: (1) the extent of training data redundancy and (2) the impact of cross domain transfer on model retention. In this study, we conduct a systematic empirical analysis of these challenges using Cellpose as a case study. First, to assess data redundancy, we propose a simple dataset quantization (DQ) strategy for constructing compact yet diverse training subsets. Experiments on the Cyto dataset show that image segmentation performance saturates with only 10% of the data, revealing substantial redundancy and potential for training with minimal annotations. Latent space analysis using MAE embeddings and t-SNE confirms that DQ selected patches capture greater feature diversity than random sampling. Second, to examine catastrophic forgetting, we perform cross domain finetuning experiments and observe significant degradation in source domain performance, particularly when adapting from generalist to specialist domains. We demonstrate that selective DQ based replay reintroducing just 5-10% of the source data effectively restores source performance, while full replay can hinder target adaptation. Additionally, we find that training domain sequencing improves generalization and reduces forgetting in multi stage transfer. Our findings highlight the importance of data centric design in biomedical image segmentation and suggest that efficient training requires not only compact subsets but also retention aware learning strategies and informed domain ordering. The code is available at https://github.com/MMV-Lab/biomedseg-efficiency.

Paperid: 1018, https://arxiv.org/pdf/2511.04722.pdf GitHub

Abstract:
Forecasting long-term time series in IoT environments remains a significant challenge due to the non-stationary and multi-scale characteristics of sensor signals. Furthermore, error accumulation causes a decrease in forecast quality when predicting further into the future. Traditional methods are restricted to operate in time-domain, while the global frequency information achieved by Fourier transform would be regarded as stationary signals leading to blur the temporal patterns of transient events. We propose AWEMixer, an Adaptive Wavelet-Enhanced Mixer Network including two innovative components: 1) a Frequency Router designs to utilize the global periodicity pattern achieved by Fast Fourier Transform to adaptively weight localized wavelet subband, and 2) a Coherent Gated Fusion Block to achieve selective integration of prominent frequency features with multi-scale temporal representation through cross-attention and gating mechanism, which realizes accurate time-frequency localization while remaining robust to noise. Seven public benchmarks validate that our model is more effective than recent state-of-the-art models. Specifically, our model consistently achieves performance improvement compared with transformer-based and MLP-based state-of-the-art models in long-sequence time series forecasting. Code is available at https://github.com/hit636/AWEMixer

Paperid: 1019, https://arxiv.org/pdf/2511.04718.pdf GitHub

Abstract:
Resting-state fMRI has become a valuable tool for classifying brain disorders and constructing brain functional connectivity networks by tracking BOLD signals across brain regions. However, existing mod els largely neglect the multi-frequency nature of neuronal oscillations, treating BOLD signals as monolithic time series. This overlooks the cru cial fact that neurological disorders often manifest as disruptions within specific frequency bands, limiting diagnostic sensitivity and specificity. While some methods have attempted to incorporate frequency informa tion, they often rely on predefined frequency bands, which may not be optimal for capturing individual variability or disease-specific alterations. To address this, we propose a novel framework featuring Adaptive Cas cade Decomposition to learn task-relevant frequency sub-bands for each brain region and Frequency-Coupled Connectivity Learning to capture both intra- and nuanced cross-band interactions in a unified functional network. This unified network informs a novel message-passing mecha nism within our Unified-GCN, generating refined node representations for diagnostic prediction. Experimental results on the ADNI and ABIDE datasets demonstrate superior performance over existing methods. The code is available at https://github.com/XXYY20221234/Ada-FCN.

Paperid: 1020, https://arxiv.org/pdf/2511.04712.pdf GitHub

Abstract:
Identifying locally dense communities closely connected to the user-initiated query node is crucial for a wide range of applications. Existing approaches either solely depend on rule-based constraints or exclusively utilize deep learning technologies to identify target communities. Therefore, an important question is proposed: can deep learning be integrated with rule-based constraints to elevate the quality of community search? In this paper, we affirmatively address this question by introducing a novel approach called Neural Community Search via Attribute-augmented Conductance, abbreviated as NCSAC. Specifically, NCSAC first proposes a novel concept of attribute-augmented conductance, which harmoniously blends the (internal and external) structural proximity and the attribute similarity. Then, NCSAC extracts a coarse candidate community of satisfactory quality using the proposed attribute-augmented conductance. Subsequently, NCSAC frames the community search as a graph optimization task, refining the candidate community through sophisticated reinforcement learning techniques, thereby producing high-quality results. Extensive experiments on six real-world graphs and ten competitors demonstrate the superiority of our solutions in terms of accuracy, efficiency, and scalability. Notably, the proposed solution outperforms state-of-the-art methods, achieving an impressive F1-score improvement ranging from 5.3\% to 42.4\%. For reproducibility purposes, the source code is available at https://github.com/longlonglin/ncsac.

Paperid: 1021, https://arxiv.org/pdf/2511.04692.pdf GitHub

Abstract:
Fake news detection has been a long-standing research focus in social networks. Recent studies suggest that incorporating sentiment information from both news content and user comments can enhance detection performance. However, existing approaches typically treat sentiment features as auxiliary signals, overlooking role differentiation, that is, the same sentiment polarity may originate from users with distinct roles, thereby limiting their ability to capture nuanced patterns for effective detection. To address this issue, we propose SARC, a Sentiment-Augmented Role Clustering framework which utilizes sentiment-enhanced deep clustering to identify user roles for improved fake news detection. The framework first generates user features through joint comment text representation (with BiGRU and Attention mechanism) and sentiment encoding. It then constructs a differentiable deep clustering module to automatically categorize user roles. Finally, unlike existing approaches which take fake news label as the unique supervision signal, we propose a joint optimization objective integrating role clustering and fake news detection to further improve the model performance. Experimental results on two benchmark datasets, RumourEval-19 and Weibo-comp, demonstrate that SARC achieves superior performance across all metrics compared to baseline models. The code is available at: https://github.com/jxshang/SARC.

Paperid: 1022, https://arxiv.org/pdf/2511.04689.pdf GitHub GitHub

Abstract:
Large language model evaluation requires thousands of benchmark items, making evaluations expensive and slow. Existing methods compute average accuracy across fixed item sets, treating all items equally despite varying quality and informativeness. We present ATLAS an adaptive testing framework using Item Response Theory (IRT) to estimate model ability through Fisher information-guided item selection. Our analysis of five major benchmarks reveals that 3-6% of items exhibit negative discrimination, indicating annotation errors that corrupt static evaluation. ATLAS achieves 90% item reduction while maintaining measurement precision: on HellaSwag (5,608 items), we match full-benchmark estimates using only 42 items with 0.154 MAE. Our framework maintains item exposure rates below 10% and test overlap at 16-27%, compared to static benchmarks where every model sees all items (100% exposure). Among 4,000+ tested models, IRT ranks differ from accuracy ranks: models with the same accuracy get different IRT scores, and 23-31% of all models shift by more than 10 rank positions. Code and calibrated item banks are available at https://github.com/Peiyu-Georgia-Li/ATLAS.git.

Paperid: 1023, https://arxiv.org/pdf/2511.04683.pdf GitHub

Abstract:
Academic citation integrity faces persistent challenges, with research indicating 20% of citations contain errors and manual verification requiring months of expert time. This paper presents a novel AI-powered methodology for systematic, comprehensive reference auditing using agentic AI with tool-use capabilities. We develop a zero-assumption verification protocol that independently validates every reference against multiple academic databases (Semantic Scholar, Google Scholar, CrossRef) without assuming any citation is correct. The methodology was validated across 30 academic documents (2,581 references) spanning undergraduate projects to doctoral theses and peer-reviewed publications. Results demonstrate 91.7% average verification rate on published PLOS papers, with successful detection of fabricated references, retracted articles, orphan citations, and predatory journals. Time efficiency improved dramatically: 90-minute audits for 916-reference doctoral theses versus months of manual review. The system achieved <0.5% false positive rate while identifying critical issues manual review might miss. This work establishes the first validated AI-agent methodology for academic citation integrity, demonstrating practical applicability for supervisors, students, and institutional quality assurance.

Paperid: 1024, https://arxiv.org/pdf/2511.04680.pdf GitHub

Abstract:
Automatic image cropping is a method for maximizing the human-perceived quality of cropped regions in photographs. Although several works have proposed techniques for producing singular crops, little work has addressed the problem of producing multiple, distinct crops with aesthetic appeal. In this paper, we motivate the problem with a discussion on modern social media applications, introduce a dataset of 277 relevant images and human labels, and evaluate the efficacy of several single-crop models with an image partitioning algorithm as a pre-processing step. The dataset is available at https://github.com/RafeLoya/carousel.

Paperid: 1025, https://arxiv.org/pdf/2511.04671.pdf GitHub

Abstract:
Human videos can be recorded quickly and at scale, making them an appealing source of training data for robot learning. However, humans and robots differ fundamentally in embodiment, resulting in mismatched action execution. Direct kinematic retargeting of human hand motion can therefore produce actions that are physically infeasible for robots. Despite these low-level differences, human demonstrations provide valuable motion cues about how to manipulate and interact with objects. Our key idea is to exploit the forward diffusion process: as noise is added to actions, low-level execution differences fade while high-level task guidance is preserved. We present X-Diffusion, a principled framework for training diffusion policies that maximally leverages human data without learning dynamically infeasible motions. X-Diffusion first trains a classifier to predict whether a noisy action is executed by a human or robot. Then, a human action is incorporated into policy training only after adding sufficient noise such that the classifier cannot discern its embodiment. Actions consistent with robot execution supervise fine-grained denoising at low noise levels, while mismatched human actions provide only coarse guidance at higher noise levels. Our experiments show that naive co-training under execution mismatches degrades policy performance, while X-Diffusion consistently improves it. Across five manipulation tasks, X-Diffusion achieves a 16% higher average success rate than the best baseline. The project website is available at https://portal-cornell.github.io/X-Diffusion/.

Paperid: 1026, https://arxiv.org/pdf/2511.04668.pdf GitHub

Abstract:
Despite impressive high-level video comprehension, multimodal language models struggle with spatial reasoning across time and space. While current spatial training approaches rely on real-world video data, obtaining diverse footage with precise spatial annotations remains a bottleneck. To alleviate this bottleneck, we present SIMS-V -- a systematic data-generation framework that leverages the privileged information of 3D simulators to create spatially-rich video training data for multimodal language models. Using this framework, we investigate which properties of simulated data drive effective real-world transfer through systematic ablations of question types, mixes, and scales. We identify a minimal set of three question categories (metric measurement, perspective-dependent reasoning, and temporal tracking) that prove most effective for developing transferable spatial intelligence, outperforming comprehensive coverage despite using fewer question types. These insights enable highly efficient training: our 7B-parameter video LLM fine-tuned on just 25K simulated examples outperforms the larger 72B baseline and achieves competitive performance with proprietary models on rigorous real-world spatial reasoning benchmarks. Our approach demonstrates robust generalization, maintaining performance on general video understanding while showing substantial improvements on embodied and real-world spatial tasks.

Paperid: 1027, https://arxiv.org/pdf/2511.04666.pdf GitHub

Abstract:
A fundamental challenge in developing general learning algorithms is their tendency to forget past knowledge when adapting to new data. Addressing this problem requires a principled understanding of forgetting; yet, despite decades of study, no unified definition has emerged that provides insights into the underlying dynamics of learning. We propose an algorithm- and task-agnostic theory that characterises forgetting as a lack of self-consistency in a learner's predictive distribution over future experiences, manifesting as a loss of predictive information. Our theory naturally yields a general measure of an algorithm's propensity to forget. To validate the theory, we design a comprehensive set of experiments that span classification, regression, generative modelling, and reinforcement learning. We empirically demonstrate how forgetting is present across all learning settings and plays a significant role in determining learning efficiency. Together, these results establish a principled understanding of forgetting and lay the foundation for analysing and improving the information retention capabilities of general learning algorithms.

Paperid: 1028, https://arxiv.org/pdf/2511.04583.pdf GitHub

Abstract:
Understanding the current capabilities and risks of AI Scientist systems is essential for ensuring trustworthy and sustainable AI-driven scientific progress while preserving the integrity of the academic ecosystem. To this end, we develop Jr. AI Scientist, a state-of-the-art autonomous AI scientist system that mimics the core research workflow of a novice student researcher: Given the baseline paper from the human mentor, it analyzes its limitations, formulates novel hypotheses for improvement, and iteratively conducts experiments until improvements are realized, and writes a paper with the results. Unlike previous approaches that assume full automation or operate on small-scale code, Jr. AI Scientist follows a well-defined research workflow and leverages modern coding agents to handle complex, multi-file implementations, leading to scientifically valuable contributions. Through our experiments, the Jr. AI Scientist successfully generated new research papers that build upon real NeurIPS, IJCV, and ICLR works by proposing and implementing novel methods. For evaluation, we conducted automated assessments using AI Reviewers, author-led evaluations, and submissions to Agents4Science, a venue dedicated to AI-driven scientific contributions. The findings demonstrate that Jr. AI Scientist generates papers receiving higher review scores than existing fully automated systems. Nevertheless, we identify important limitations from both the author evaluation and the Agents4Science reviews, indicating the potential risks of directly applying current AI Scientist systems and key challenges for future research. Finally, we comprehensively report various risks identified during development. We believe this study clarifies the current role and limitations of AI Scientist systems, offering insights into the areas that still require human expertise and the risks that may emerge as these systems evolve.

Paperid: 1029, https://arxiv.org/pdf/2511.04555.pdf GitHub

Abstract:
Vision-Language-Action (VLA) models have emerged as a powerful framework that unifies perception, language, and control, enabling robots to perform diverse tasks through multimodal understanding. However, current VLA models typically contain massive parameters and rely heavily on large-scale robot data pretraining, leading to high computational costs during training, as well as limited deployability for real-time inference. Moreover, most training paradigms often degrade the perceptual representations of the vision-language backbone, resulting in overfitting and poor generalization to downstream tasks. In this work, we present Evo-1, a lightweight VLA model that reduces computation and improves deployment efficiency, while maintaining strong performance without pretraining on robot data. Evo-1 builds on a native multimodal Vision-Language model (VLM), incorporating a novel cross-modulated diffusion transformer along with an optimized integration module, together forming an effective architecture. We further introduce a two-stage training paradigm that progressively aligns action with perception, preserving the representations of the VLM. Notably, with only 0.77 billion parameters, Evo-1 achieves state-of-the-art results on the Meta-World and RoboTwin suite, surpassing the previous best models by 12.4% and 6.9%, respectively, and also attains a competitive result of 94.8% on LIBERO. In real-world evaluations, Evo-1 attains a 78% success rate with high inference frequency and low memory overhead, outperforming all baseline methods. We release code, data, and model weights to facilitate future research on lightweight and efficient VLA models.

Paperid: 1030, https://arxiv.org/pdf/2511.04514.pdf GitHub

Abstract:
The phenomenon of linear mode connectivity (LMC) links several aspects of deep learning, including training stability under noisy stochastic gradients, the smoothness and generalization of local minima (basins), the similarity and functional diversity of sampled models, and architectural effects on data processing. In this work, we experimentally study LMC under data shifts and identify conditions that mitigate their impact. We interpret data shifts as an additional source of stochastic gradient noise, which can be reduced through small learning rates and large batch sizes. These parameters influence whether models converge to the same local minimum or to regions of the loss landscape with varying smoothness and generalization. Although models sampled via LMC tend to make similar errors more frequently than those converging to different basins, the benefit of LMC lies in balancing training efficiency against the gains achieved from larger, more diverse ensembles. Code and supplementary materials will be made publicly available at https://github.com/DLR-KI/LMC in due course.

Paperid: 1031, https://arxiv.org/pdf/2511.04453.pdf GitHub

Abstract:
Social news platforms have become key launch outlets for open-source projects, especially Hacker News (HN), though quantifying their immediate impact remains challenging. This paper presents a reproducible demonstration system that tracks how HN exposure translates into GitHub star growth for AI and LLM tools. Built entirely on public APIs, our pipeline analyzes 138 repository launches from 2024-2025 and reveals substantial launch effects: repositories gain an average of 121 stars within 24 hours, 189 stars within 48 hours, and 289 stars within a week of HN exposure. Through machine learning models (Elastic Net) and non-linear approaches (Gradient Boosting), we identify key predictors of viral growth. Posting timing appears as key factor--launching at optimal hours can mean hundreds of additional stars--while the "Show HN" tag shows no statistical advantage after controlling for other factors. The demonstration completes in under five minutes on standard hardware, automatically collecting data, training models, and generating visualizations through single-file scripts. This makes our findings immediately reproducible and the framework easily be extended to other platforms, providing both researchers and developers with actionable insights into launch dynamics.

Paperid: 1032, https://arxiv.org/pdf/2511.04401.pdf GitHub GitHub

Abstract:
Deep learning models achieve strong performance across various domains but often rely on spurious correlations, making them vulnerable to distribution shifts. This issue is particularly severe in subpopulation shift scenarios, where models struggle in underrepresented groups. While existing methods have made progress in mitigating this issue, their performance gains are still constrained. They lack a rigorous theoretical framework connecting the embedding space representations with worst-group error. To address this limitation, we propose Spurious Correlation-Aware Embedding Regularization for Worst-Group Robustness (SCER), a novel approach that directly regularizes feature representations to suppress spurious cues. We show theoretically that worst-group error is influenced by how strongly the classifier relies on spurious versus core directions, identified from differences in group-wise mean embeddings across domains and classes. By imposing theoretical constraints at the embedding level, SCER encourages models to focus on core features while reducing sensitivity to spurious patterns. Through systematic evaluation on multiple vision and language, we show that SCER outperforms prior state-of-the-art studies in worst-group accuracy. Our code is available at \href{https://github.com/MLAI-Yonsei/SCER}{https://github.com/MLAI-Yonsei/SCER}.

Paperid: 1033, https://arxiv.org/pdf/2511.04394.pdf GitHub GitHub

Abstract:
DORAEMON is an open-source PyTorch library that unifies visual object modeling and representation learning across diverse scales. A single YAML-driven workflow covers classification, retrieval and metric learning; more than 1000 pretrained backbones are exposed through a timm-compatible interface, together with modular losses, augmentations and distributed-training utilities. Reproducible recipes match or exceed reference results on ImageNet-1K, MS-Celeb-1M and Stanford online products, while one-command export to ONNX or HuggingFace bridges research and deployment. By consolidating datasets, models, and training techniques into one platform, DORAEMON offers a scalable foundation for rapid experimentation in visual recognition and representation learning, enabling efficient transfer of research advances to real-world applications. The repository is available at https://github.com/wuji3/DORAEMON.

Paperid: 1034, https://arxiv.org/pdf/2511.04388.pdf GitHub

Abstract:
Depth estimation is one of the key technologies for realizing 3D perception in unmanned systems. Monocular depth estimation has been widely researched because of its low-cost advantage, but the existing methods face the challenges of poor depth estimation performance and blurred object boundaries on embedded systems. In this paper, we propose a novel monocular depth estimation model, BoRe-Depth, which contains only 8.7M parameters. It can accurately estimate depth maps on embedded systems and significantly improves boundary quality. Firstly, we design an Enhanced Feature Adaptive Fusion Module (EFAF) which adaptively fuses depth features to enhance boundary detail representation. Secondly, we integrate semantic knowledge into the encoder to improve the object recognition and boundary perception capabilities. Finally, BoRe-Depth is deployed on NVIDIA Jetson Orin, and runs efficiently at 50.7 FPS. We demonstrate that the proposed model significantly outperforms previous lightweight models on multiple challenging datasets, and we provide detailed ablation studies for the proposed methods. The code is available at https://github.com/liangxiansheng093/BoRe-Depth.

Paperid: 1035, https://arxiv.org/pdf/2511.04255.pdf GitHub

Abstract:
This paper does not introduce a novel architecture; instead, it revisits a fundamental yet overlooked baseline: adapting human-centric foundation models for anatomical landmark detection in medical imaging. While landmark detection has traditionally relied on domain-specific models, the emergence of large-scale pre-trained vision models presents new opportunities. In this study, we investigate the adaptation of Sapiens, a human-centric foundation model designed for pose estimation, to medical imaging through multi-dataset pretraining, establishing a new state of the art across multiple datasets. Our proposed model, MedSapiens, demonstrates that human-centric foundation models, inherently optimized for spatial pose localization, provide strong priors for anatomical landmark detection, yet this potential has remained largely untapped. We benchmark MedSapiens against existing state-of-the-art models, achieving up to 5.26% improvement over generalist models and up to 21.81% improvement over specialist models in the average success detection rate (SDR). To further assess MedSapiens adaptability to novel downstream tasks with few annotations, we evaluate its performance in limited-data settings, achieving 2.69% improvement over the few-shot state of the art in SDR. Code and model weights are available at https://github.com/xmed-lab/MedSapiens .

Paperid: 1036, https://arxiv.org/pdf/2511.04247.pdf GitHub

Abstract:
Multimodal co-embedding models, especially CLIP, have advanced the state of the art in zero-shot classification and multimedia information retrieval in recent years by aligning images and text in a shared representation space. However, such modals trained on a contrastive alignment can lack stability towards small input perturbations. Especially when dealing with manually expressed queries, minor variations in the query can cause large differences in the ranking of the best-matching results. In this paper, we present a systematic analysis of the effect of multiple classes of non-semantic query perturbations in an multimedia information retrieval scenario. We evaluate a diverse set of lexical, syntactic, and semantic perturbations across multiple CLIP variants using the TRECVID Ad-Hoc Video Search queries and the V3C1 video collection. Across models, we find that syntactic and semantic perturbations drive the largest instabilities, while brittleness is concentrated in trivial surface edits such as punctuation and case. Our results highlight robustness as a critical dimension for evaluating vision-language models beyond benchmark accuracy.

Paperid: 1037, https://arxiv.org/pdf/2511.04192.pdf GitHub

Abstract:
Human motion style transfer allows characters to appear less rigidity and more realism with specific style. Traditional arbitrary image style transfer typically process mean and variance which is proved effective. Meanwhile, similar methods have been adapted for motion style transfer. However, due to the fundamental differences between images and motion, relying on mean and variance is insufficient to fully capture the complex dynamic patterns and spatiotemporal coherence properties of motion data. Building upon this, our key insight is to bring two more coefficient, skewness and kurtosis, into the analysis of motion style. Specifically, we propose a novel Adaptive Statistics Fusor (AStF) which consists of Style Disentanglement Module (SDM) and High-Order Multi-Statistics Attention (HOS-Attn). We trained our AStF in conjunction with a Motion Consistency Regularization (MCR) discriminator. Experimental results show that, by providing a more comprehensive model of the spatiotemporal statistical patterns inherent in dynamic styles, our proposed AStF shows proficiency superiority in motion style transfers over state-of-the-arts. Our code and model are available at https://github.com/CHMimilanlan/AStF.

Paperid: 1038, https://arxiv.org/pdf/2511.04160.pdf GitHub

Abstract:
Deep ensembles are a powerful tool in machine learning, improving both model performance and uncertainty calibration. While ensembles are typically formed by training and tuning models individually, evidence suggests that jointly tuning the ensemble can lead to better performance. This paper investigates the impact of jointly tuning weight decay, temperature scaling, and early stopping on both predictive performance and uncertainty quantification. Additionally, we propose a partially overlapping holdout strategy as a practical compromise between enabling joint evaluation and maximizing the use of data for training. Our results demonstrate that jointly tuning the ensemble generally matches or improves performance, with significant variation in effect size across different tasks and metrics. We highlight the trade-offs between individual and joint optimization in deep ensemble training, with the overlapping holdout strategy offering an attractive practical solution. We believe our findings provide valuable insights and guidance for practitioners looking to optimize deep ensemble models. Code is available at: https://github.com/lauritsf/ensemble-optimality-gap

Paperid: 1039, https://arxiv.org/pdf/2511.04153.pdf GitHub

Abstract:
Text-to-SQL systems provide a natural language interface that can enable even laymen to access information stored in databases. However, existing Large Language Models (LLM) struggle with SQL generation from natural instructions due to large schema sizes and complex reasoning. Prior work often focuses on complex, somewhat impractical pipelines using flagship models, while smaller, efficient models remain overlooked. In this work, we explore three multi-agent LLM pipelines, with systematic performance benchmarking across a range of small to large open-source models: (1) Multi-agent discussion pipeline, where agents iteratively critique and refine SQL queries, and a judge synthesizes the final answer; (2) Planner-Coder pipeline, where a thinking model planner generates stepwise SQL generation plans and a coder synthesizes queries; and (3) Coder-Aggregator pipeline, where multiple coders independently generate SQL queries, and a reasoning agent selects the best query. Experiments on the Bird-Bench Mini-Dev set reveal that Multi-Agent discussion can improve small model performance, with up to 10.6% increase in Execution Accuracy for Qwen2.5-7b-Instruct seen after three rounds of discussion. Among the pipelines, the LLM Reasoner-Coder pipeline yields the best results, with DeepSeek-R1-32B and QwQ-32B planners boosting Gemma 3 27B IT accuracy from 52.4% to the highest score of 56.4%. Codes are available at https://github.com/treeDweller98/bappa-sql.

Paperid: 1040, https://arxiv.org/pdf/2511.04137.pdf GitHub

Abstract:
Computer-use agents can operate computers and automate laborious tasks, but despite recent rapid progress, they still lag behind human users, especially when tasks require domain-specific procedural knowledge about particular applications, platforms, and multi-step workflows. Humans can bridge this gap by watching video tutorials: we search, skim, and selectively imitate short segments that match our current subgoal. In this paper, we study how to enable computer-use agents to learn from online videos at inference time effectively. We propose a framework that retrieves and filters tutorial videos, converts them into structured demonstration trajectories, and dynamically selects trajectories as in-context guidance during execution. Particularly, using a VLM, we infer UI actions, segment videos into short subsequences of actions, and assign each subsequence a textual objective. At inference time, a two-stage selection mechanism dynamically chooses a single trajectory to add in context at each step, focusing the agent on the most helpful local guidance for its next decision. Experiments on two widely used benchmarks show that our framework consistently outperforms strong base agents and variants that use only textual tutorials or transcripts. Analyses highlight the importance of trajectory segmentation and selection, action filtering, and visual information, suggesting that abundant online videos can be systematically distilled into actionable guidance that improves computer-use agents at inference time. Our code is available at https://github.com/UCSB-NLP-Chang/video_demo.

Paperid: 1041, https://arxiv.org/pdf/2511.04128.pdf GitHub

Abstract:
Accurate perception of the marine environment through robust multi-object tracking (MOT) is essential for ensuring safe vessel navigation and effective maritime surveillance. However, the complicated maritime environment often causes camera motion and subsequent visual degradation, posing significant challenges to MOT. To address this challenge, we propose an efficient Dual-branch Maritime SORT (DMSORT) method for maritime MOT. The core of the framework is a parallel tracker with affine compensation, which incorporates an object detection and re-identification (ReID) branch, along with a dedicated branch for dynamic camera motion estimation. Specifically, a Reversible Columnar Detection Network (RCDN) is integrated into the detection module to leverage multi-level visual features for robust object detection. Furthermore, a lightweight Transformer-based appearance extractor (Li-TAE) is designed to capture global contextual information and generate robust appearance features. Another branch decouples platform-induced and target-intrinsic motion by constructing a projective transformation, applying platform-motion compensation within the Kalman filter, and thereby stabilizing true object trajectories. Finally, a clustering-optimized feature fusion module effectively combines motion and appearance cues to ensure identity consistency under noise, occlusion, and drift. Extensive evaluations on the Singapore Maritime Dataset demonstrate that DMSORT achieves state-of-the-art performance. Notably, DMSORT attains the fastest runtime among existing ReID-based MOT frameworks while maintaining high identity consistency and robustness to jitter and occlusion. Code is available at: https://github.com/BiscuitsLzy/DMSORT-An-efficient-parallel-maritime-multi-object-tracking-architecture-.

Paperid: 1042, https://arxiv.org/pdf/2511.04123.pdf GitHub

Abstract:
Recent advances in vision-language models have facilitated progress in sketch generation. However, existing specialized methods primarily focus on generic synthesis and lack mechanisms for precise control over sketch styles. In this work, we propose a training-free framework based on diffusion models that enables explicit style guidance via textual prompts and referenced style sketches. Unlike previous style transfer methods that overwrite key and value matrices in self-attention, we incorporate the reference features as auxiliary information with linear smoothing and leverage a style-content guidance mechanism. This design effectively reduces content leakage from reference sketches and enhances synthesis quality, especially in cases with low structural similarity between reference and target sketches. Furthermore, we extend our framework to support controllable multi-style generation by integrating features from multiple reference sketches, coordinated via a joint AdaIN module. Extensive experiments demonstrate that our approach achieves high-quality sketch generation with accurate style alignment and improved flexibility in style control. The official implementation of M3S is available at https://github.com/CMACH508/M3S.

Paperid: 1043, https://arxiv.org/pdf/2511.04117.pdf GitHub GitHub

Abstract:
In this paper, we propose Tortoise and Hare Guidance (THG), a training-free strategy that accelerates diffusion sampling while maintaining high-fidelity generation. We demonstrate that the noise estimate and the additional guidance term exhibit markedly different sensitivity to numerical error by reformulating the classifier-free guidance (CFG) ODE as a multirate system of ODEs. Our error-bound analysis shows that the additional guidance branch is more robust to approximation, revealing substantial redundancy that conventional solvers fail to exploit. Building on this insight, THG significantly reduces the computation of the additional guidance: the noise estimate is integrated with the tortoise equation on the original, fine-grained timestep grid, while the additional guidance is integrated with the hare equation only on a coarse grid. We also introduce (i) an error-bound-aware timestep sampler that adaptively selects step sizes and (ii) a guidance-scale scheduler that stabilizes large extrapolation spans. THG reduces the number of function evaluations (NFE) by up to 30% with virtually no loss in generation fidelity ($Δ$ImageReward $\leq$ 0.032) and outperforms state-of-the-art CFG-based training-free accelerators under identical computation budgets. Our findings highlight the potential of multirate formulations for diffusion solvers, paving the way for real-time high-quality image synthesis without any model retraining. The source code is available at https://github.com/yhlee-add/THG.

Paperid: 1044, https://arxiv.org/pdf/2511.04084.pdf GitHub

Abstract:
Medical image segmentation is critical for accurate diagnostics and treatment planning, but remains challenging due to complex anatomical structures and limited annotated training data. CNN-based segmentation methods excel at local feature extraction, but struggle with modeling long-range dependencies. Transformers, on the other hand, capture global context more effectively, but are inherently data-hungry and computationally expensive. In this work, we introduce UKAST, a U-Net like architecture that integrates rational-function based Kolmogorov-Arnold Networks (KANs) into Swin Transformer encoders. By leveraging rational base functions and Group Rational KANs (GR-KANs) from the Kolmogorov-Arnold Transformer (KAT), our architecture addresses the inefficiencies of vanilla spline-based KANs, yielding a more expressive and data-efficient framework with reduced FLOPs and only a very small increase in parameter count compared to SwinUNETR. UKAST achieves state-of-the-art performance on four diverse 2D and 3D medical image segmentation benchmarks, consistently surpassing both CNN- and Transformer-based baselines. Notably, it attains superior accuracy in data-scarce settings, alleviating the data-hungry limitations of standard Vision Transformers. These results show the potential of KAN-enhanced Transformers to advance data-efficient medical image segmentation. Code is available at: https://github.com/nsapkota417/UKAST

Paperid: 1045, https://arxiv.org/pdf/2511.04083.pdf GitHub

Abstract:
We study CT image denoising in the unpaired and self-supervised regimes by evaluating two strong, training-data-efficient paradigms: a CycleGAN-based residual translator and a Noise2Score (N2S) score-matching denoiser. Under a common evaluation protocol, a configuration sweep identifies a simple standard U-Net backbone within CycleGAN (lambda_cycle = 30, lambda_iden = 2, ngf = ndf = 64) as the most reliable setting; we then train it to convergence with a longer schedule. The selected CycleGAN improves the noisy input from 34.66 dB / 0.9234 SSIM to 38.913 dB / 0.971 SSIM and attains an estimated score of 1.9441 and an unseen-set (Kaggle leaderboard) score of 1.9343. Noise2Score, while slightly behind in absolute PSNR / SSIM, achieves large gains over very noisy inputs, highlighting its utility when clean pairs are unavailable. Overall, CycleGAN offers the strongest final image quality, whereas Noise2Score provides a robust pair-free alternative with competitive performance. Source code is available at https://github.com/hanifsyarubany/CT-Scan-Image-Denoising-using-CycleGAN-and-Noise2Score.

Paperid: 1046, https://arxiv.org/pdf/2511.04076.pdf GitHub

Abstract:
Redistricting plays a central role in shaping how votes are translated into political power. While existing computational methods primarily aim to generate large ensembles of legally valid districting plans, they often neglect the strategic dynamics involved in the selection process. This oversight creates opportunities for partisan actors to cherry-pick maps that, while technically compliant, are politically advantageous. Simply satisfying formal constraints does not ensure fairness when the selection process itself can be manipulated. We propose \textbf{Agentmandering}, a framework that reimagines redistricting as a turn-based negotiation between two agents representing opposing political interests. Drawing inspiration from game-theoretic ideas, particularly the \textit{Choose-and-Freeze} protocol, our method embeds strategic interaction into the redistricting process via large language model (LLM) agents. Agents alternate between selecting and freezing districts from a small set of candidate maps, gradually partitioning the state through constrained and interpretable choices. Evaluation on post-2020 U.S. Census data across all states shows that Agentmandering significantly reduces partisan bias and unfairness, while achieving 2 to 3 orders of magnitude lower variance than standard baselines. These results demonstrate both fairness and stability, especially in swing-state scenarios. Our code is available at https://github.com/Lihaogx/AgentMandering.

Paperid: 1047, https://arxiv.org/pdf/2511.04063.pdf GitHub

Abstract:
Quantization plays a crucial role in accelerating the inference of large-scale models, and rotational matrices have been shown to effectively improve quantization performance by smoothing outliers. However, end-to-end fine-tuning of rotational optimization algorithms incurs high computational costs and is prone to overfitting. To address this challenge, we propose an efficient distribution-aware rotational calibration method, DartQuant, which reduces the complexity of rotational optimization by constraining the distribution of the activations after rotation. This approach also effectively reduces reliance on task-specific losses, thereby mitigating the risk of overfitting. Additionally, we introduce the QR-Orth optimization scheme, which replaces expensive alternating optimization with a more efficient solution. In a variety of model quantization experiments, DartQuant demonstrates superior performance. Compared to existing methods, it achieves 47$\times$ acceleration and 10$\times$ memory savings for rotational optimization on a 70B model. Furthermore, it is the first to successfully complete rotational calibration for a 70B model on a single 3090 GPU, making quantization of large language models feasible in resource-constrained environments. Code is available at https://github.com/CAS-CLab/DartQuant.git.

Paperid: 1048, https://arxiv.org/pdf/2511.04053.pdf GitHub

Abstract:
Although behavioral studies have documented numerical reasoning errors in large language models (LLMs), the underlying representational mechanisms remain unclear. We hypothesize that numerical attributes occupy shared latent subspaces and investigate two questions:(1) How do LLMs internally integrate multiple numerical attributes of a single entity? (2)How does irrelevant numerical context perturb these representations and their downstream outputs? To address these questions, we combine linear probing with partial correlation analysis and prompt-based vulnerability tests across models of varying sizes. Our results show that LLMs encode real-world numerical correlations but tend to systematically amplify them. Moreover, irrelevant context induces consistent shifts in magnitude representations, with downstream effects that vary by model size. These findings reveal a vulnerability in LLM decision-making and lay the groundwork for fairer, representation-aware control under multi-attribute entanglement.

Paperid: 1049, https://arxiv.org/pdf/2511.04014.pdf GitHub

Abstract:
Large language models (LLMs) have achieved remarkable progress in code understanding tasks. However, they demonstrate limited performance in vulnerability detection and struggle to distinguish vulnerable code from patched code. We argue that LLMs lack understanding of security specifications -- the expectations about how code should behave to remain safe. When code behavior differs from these expectations, it becomes a potential vulnerability. However, such knowledge is rarely explicit in training data, leaving models unable to reason about security flaws. We propose VulInstruct, a specification-guided approach that systematically extracts security specifications from historical vulnerabilities to detect new ones. VulInstruct constructs a specification knowledge base from two perspectives: (i) General specifications from high-quality patches across projects, capturing fundamental safe behaviors; and (ii) Domain-specific specifications from repeated violations in particular repositories relevant to the target code. VulInstruct retrieves relevant past cases and specifications, enabling LLMs to reason about expected safe behaviors rather than relying on surface patterns. We evaluate VulInstruct under strict criteria requiring both correct predictions and valid reasoning. On PrimeVul, VulInstruct achieves 45.0% F1-score (32.7% improvement) and 37.7% recall (50.8% improvement) compared to baselines, while uniquely detecting 24.3% of vulnerabilities -- 2.4x more than any baseline. In pair-wise evaluation, VulInstruct achieves 32.3% relative improvement. VulInstruct also discovered a previously unknown high-severity vulnerability (CVE-2025-56538) in production code, demonstrating practical value for real-world vulnerability discovery. All code and supplementary materials are available at https://github.com/zhuhaopku/VulInstruct-temp.

Paperid: 1050, https://arxiv.org/pdf/2511.03976.pdf GitHub

Abstract:
Since its emergence, SARS-CoV-2 has demonstrated a rapid and unpredictable evolutionary trajectory, characterized by the continual emergence of immune-evasive variants. This poses persistent challenges to public health and vaccine development. While large-scale generative pre-trained transformers (GPTs) have revolutionized the modeling of sequential data, their direct applications to noisy viral genomic sequences are limited. In this paper, we introduce PETRA(Pretrained Evolutionary TRAnsformer), a novel transformer approach based on evolutionary trajectories derived from phylogenetic trees rather than raw RNA sequences. This method effectively mitigates sequencing noise and captures the hierarchical structure of viral evolution. With a weighted training framework to address substantial geographical and temporal imbalances in global sequence data, PETRA excels in predicting future SARS-CoV-2 mutations, achieving a weighted recall@1 of 9.45% for nucleotide mutations and 17.10\% for spike amino-acid mutations, compared to 0.49% and 6.64% respectively for the best baseline. PETRA also demonstrates its ability to aid in the real-time mutation prediction of major clades like 24F(XEC) and 25A(LP.8.1). The code is open sourced on https://github.com/xz-keg/PETra

Paperid: 1051, https://arxiv.org/pdf/2511.03877.pdf GitHub

Abstract:
Social and collaborative platforms emit multivariate time-series traces in which early interactions-such as views, likes, or downloads-are followed, sometimes months or years later, by higher impact like citations, sales, or reviews. We formalize this setting as Lead-Lag Forecasting (LLF): given an early usage channel (the lead), predict a correlated but temporally shifted outcome channel (the lag). Despite the ubiquity of such patterns, LLF has not been treated as a unified forecasting problem within the time-series community, largely due to the absence of standardized datasets. To anchor research in LLF, here we present two high-volume benchmark datasets-arXiv (accesses -> citations of 2.3M papers) and GitHub (pushes/stars -> forks of 3M repositories)-and outline additional domains with analogous lead-lag dynamics, including Wikipedia (page views -> edits), Spotify (streams -> concert attendance), e-commerce (click-throughs -> purchases), and LinkedIn profile (views -> messages). Our datasets provide ideal testbeds for lead-lag forecasting, by capturing long-horizon dynamics across years, spanning the full spectrum of outcomes, and avoiding survivorship bias in sampling. We documented all technical details of data curation and cleaning, verified the presence of lead-lag dynamics through statistical and classification tests, and benchmarked parametric and non-parametric baselines for regression. Our study establishes LLF as a novel forecasting paradigm and lays an empirical foundation for its systematic exploration in social and usage data. Our data portal with downloads and documentation is available at https://lead-lag-forecasting.github.io/.

Paperid: 1052, https://arxiv.org/pdf/2511.03855.pdf GitHub

Abstract:
Deep learned (DL) models for image recognition have been shown to fail to generalize to data from different devices, populations, etc. COVID-19 detection from Chest X-rays (CXRs), in particular, has been shown to fail to generalize to out-of-distribution (OOD) data from new clinical sources not covered in the training set. This occurs because models learn to exploit shortcuts - source-specific artifacts that do not translate to new distributions - rather than reasonable biomarkers to maximize performance on in-distribution (ID) data. Rendering the models more robust to distribution shifts, our study investigates the use of fundamental noise injection techniques (Gaussian, Speckle, Poisson, and Salt and Pepper) during training. Our empirical results demonstrate that this technique can significantly reduce the performance gap between ID and OOD evaluation from 0.10-0.20 to 0.01-0.06, based on results averaged over ten random seeds across key metrics such as AUC, F1, accuracy, recall and specificity. Our source code is publicly available at https://github.com/Duongmai127/Noisy-ood

Paperid: 1053, https://arxiv.org/pdf/2511.03824.pdf GitHub GitHub

Abstract:
Graph Neural Networks learn on graph-structured data by iteratively aggregating local neighborhood information. While this local message passing paradigm imparts a powerful inductive bias and exploits graph sparsity, it also yields three key challenges: (i) oversquashing of long-range information, (ii) oversmoothing of node representations, and (iii) limited expressive power. In this work we inject randomized global embeddings of node features, which we term \textit{Sketched Random Features}, into standard GNNs, enabling them to efficiently capture long-range dependencies. The embeddings are unique, distance-sensitive, and topology-agnostic -- properties which we analytically and empirically show alleviate the aforementioned limitations when injected into GNNs. Experimental results on real-world graph learning tasks confirm that this strategy consistently improves performance over baseline GNNs, offering both a standalone solution and a complementary enhancement to existing techniques such as graph positional encodings. Our source code is available at \href{https://github.com/ryienh/sketched-random-features}{https://github.com/ryienh/sketched-random-features}.

Paperid: 1054, https://arxiv.org/pdf/2511.03725.pdf GitHub

Abstract:
Effective explanations of video action recognition models should disentangle how movements unfold over time from the surrounding spatial context. However, existing methods based on saliency produce entangled explanations, making it unclear whether predictions rely on motion or spatial context. Language-based approaches offer structure but often fail to explain motions due to their tacit nature -- intuitively understood but difficult to verbalize. To address these challenges, we propose Disentangled Action aNd Context concept-based Explainable (DANCE) video action recognition, a framework that predicts actions through disentangled concept types: motion dynamics, objects, and scenes. We define motion dynamics concepts as human pose sequences. We employ a large language model to automatically extract object and scene concepts. Built on an ante-hoc concept bottleneck design, DANCE enforces prediction through these concepts. Experiments on four datasets -- KTH, Penn Action, HAA500, and UCF-101 -- demonstrate that DANCE significantly improves explanation clarity with competitive performance. We validate the superior interpretability of DANCE through a user study. Experimental results also show that DANCE is beneficial for model debugging, editing, and failure analysis.

Paperid: 1055, https://arxiv.org/pdf/2511.03634.pdf GitHub

Abstract:
Tabular foundation models such as TabPFN have revolutionized predictive machine learning for tabular data. At the same time, the driving factors of this revolution are hard to understand. Existing open-source tabular foundation models are implemented in complicated pipelines boasting over 10,000 lines of code, lack architecture documentation or code quality. In short, the implementations are hard to understand, not beginner-friendly, and complicated to adapt for new experiments. We introduce nanoTabPFN, a simplified and lightweight implementation of the TabPFN v2 architecture and a corresponding training loop that uses pre-generated training data. nanoTabPFN makes tabular foundation models more accessible to students and researchers alike. For example, restricted to a small data setting it achieves a performance comparable to traditional machine learning baselines within one minute of pre-training on a single GPU (160,000x faster than TabPFN v2 pretraining). This eliminated requirement of large computational resources makes pre-training tabular foundation models accessible for educational purposes. Our code is available at https://github.com/automl/nanoTabPFN.

Paperid: 1056, https://arxiv.org/pdf/2511.03620.pdf GitHub

Abstract:
CLAX is a JAX-based library that implements classic click models using modern gradient-based optimization. While neural click models have emerged over the past decade, complex click models based on probabilistic graphical models (PGMs) have not systematically adopted gradient-based optimization, preventing practitioners from leveraging modern deep learning frameworks while preserving the interpretability of classic models. CLAX addresses this gap by replacing EM-based optimization with direct gradient-based optimization in a numerically stable manner. The framework's modular design enables the integration of any component, from embeddings and deep networks to custom modules, into classic click models for end-to-end optimization. We demonstrate CLAX's efficiency by running experiments on the full Baidu-ULTR dataset comprising over a billion user sessions in $\approx$ 2 hours on a single GPU, orders of magnitude faster than traditional EM approaches. CLAX implements ten classic click models, serving both industry practitioners seeking to understand user behavior and improve ranking performance at scale and researchers developing new click models. CLAX is available at: https://github.com/philipphager/clax

Paperid: 1057, https://arxiv.org/pdf/2511.03618.pdf GitHub

Abstract:
In this paper, we formalize the almost sure convergence of $Q$-learning and linear temporal difference (TD) learning with Markovian samples using the Lean 4 theorem prover based on the Mathlib library. $Q$-learning and linear TD are among the earliest and most influential reinforcement learning (RL) algorithms. The investigation of their convergence properties is not only a major research topic during the early development of the RL field but also receives increasing attention nowadays. This paper formally verifies their almost sure convergence in a unified framework based on the Robbins-Siegmund theorem. The framework developed in this work can be easily extended to convergence rates and other modes of convergence. This work thus makes an important step towards fully formalizing convergent RL results. The code is available at https://github.com/ShangtongZhang/rl-theory-in-lean.

Paperid: 1058, https://arxiv.org/pdf/2511.03610.pdf GitHub

Abstract:
This article presents a systematic review of relation extraction (RE) research since the advent of Transformer-based models. Using an automated framework to collect and annotate publications, we analyze 34 surveys, 64 datasets, and 104 models published between 2019 and 2024. The review highlights methodological advances, benchmark resources, and the integration of semantic web technologies. By consolidating results across multiple dimensions, the study identifies current trends, limitations, and open challenges, offering researchers and practitioners a comprehensive reference for understanding the evolution and future directions of RE.

Paperid: 1059, https://arxiv.org/pdf/2511.03589.pdf GitHub

Abstract:
Parametric body models are central to many human-centric tasks, yet existing models often rely on costly 3D scans and learned shape spaces that are proprietary and demographically narrow. We introduce Anny, a simple, fully differentiable, and scan-free human body model grounded in anthropometric knowledge from the MakeHuman community. Anny defines a continuous, interpretable shape space, where phenotype parameters (e.g. gender, age, height, weight) control blendshapes spanning a wide range of human forms -- across ages (from infants to elders), body types, and proportions. Calibrated using WHO population statistics, it provides realistic and demographically grounded human shape variation within a single unified model. Thanks to its openness and semantic control, Anny serves as a versatile foundation for 3D human modeling -- supporting millimeter-accurate scan fitting, controlled synthetic data generation, and Human Mesh Recovery (HMR). We further introduce Anny-One, a collection of 800k photorealistic humans generated with Anny, showing that despite its simplicity, HMR models trained with Anny can match the performance of those trained with scan-based body models, while remaining interpretable and broadly representative. The Anny body model and its code are released under the Apache 2.0 license, making Anny an accessible foundation for human-centric 3D modeling.

Paperid: 1060, https://arxiv.org/pdf/2511.03571.pdf GitHub GitHub

Abstract:
Robust 3D semantic occupancy is crucial for legged/humanoid robots, yet most semantic scene completion (SSC) systems target wheeled platforms with forward-facing sensors. We present OneOcc, a vision-only panoramic SSC framework designed for gait-introduced body jitter and 360° continuity. OneOcc combines: (i) Dual-Projection fusion (DP-ER) to exploit the annular panorama and its equirectangular unfolding, preserving 360° continuity and grid alignment; (ii) Bi-Grid Voxelization (BGV) to reason in Cartesian and cylindrical-polar spaces, reducing discretization bias and sharpening free/occupied boundaries; (iii) a lightweight decoder with Hierarchical AMoE-3D for dynamic multi-scale fusion and better long-range/occlusion reasoning; and (iv) plug-and-play Gait Displacement Compensation (GDC) learning feature-level motion correction without extra sensors. We also release two panoramic occupancy benchmarks: QuadOcc (real quadruped, first-person 360°) and Human360Occ (H3O) (CARLA human-ego 360° with RGB, Depth, semantic occupancy; standardized within-/cross-city splits). OneOcc sets new state-of-the-art (SOTA): on QuadOcc it beats strong vision baselines and popular LiDAR ones; on H3O it gains +3.83 mIoU (within-city) and +8.08 (cross-city). Modules are lightweight, enabling deployable full-surround perception for legged/humanoid robots. Datasets and code will be publicly available at https://github.com/MasterHow/OneOcc.

Paperid: 1061, https://arxiv.org/pdf/2511.03549.pdf GitHub

Abstract:
Understanding the purpose of source code is a critical task in software maintenance, onboarding, and modernization. While large language models (LLMs) have shown promise in generating code explanations, they often lack grounding in the broader software engineering context. We propose a novel approach that leverages natural language artifacts from GitHub -- such as pull request descriptions, issue descriptions and discussions, and commit messages -- to enhance LLM-based code understanding. Our system consists of three components: one that extracts and structures relevant GitHub context, another that uses this context to generate high-level explanations of the code's purpose, and a third that validates the explanation. We implemented this as a standalone tool, as well as a server within the Model Context Protocol (MCP), enabling integration with other AI-assisted development tools. Our main use case is that of enhancing a standard LLM-based code explanation with code insights that our system generates. To evaluate explanations' quality, we conducted a small scale user study, with developers of several open projects, as well as developers of proprietary projects. Our user study indicates that when insights are generated they often are helpful and non trivial, and are free from hallucinations.

Paperid: 1062, https://arxiv.org/pdf/2511.03542.pdf GitHub

Abstract:
Medical question answering systems face deployment challenges including hallucinations, bias, computational demands, privacy concerns, and the need for specialized expertise across diverse domains. Here, we present SOLVE-Med, a multi-agent architecture combining domain-specialized small language models for complex medical queries. The system employs a Router Agent for dynamic specialist selection, ten specialized models (1B parameters each) fine-tuned on specific medical domains, and an Orchestrator Agent that synthesizes responses. Evaluated on Italian medical forum data across ten specialties, SOLVE-Med achieves superior performance with ROUGE-1 of 0.301 and BERTScore F1 of 0.697, outperforming standalone models up to 14B parameters while enabling local deployment. Our code is publicly available on GitHub: https://github.com/PRAISELab-PicusLab/SOLVE-Med.

Paperid: 1063, https://arxiv.org/pdf/2511.03497.pdf GitHub

Abstract:
Agentic AI systems and Physical or Embodied AI systems have been two key research verticals at the forefront of Artificial Intelligence and Robotics, with Model Context Protocol (MCP) increasingly becoming a key component and enabler of agentic applications. However, the literature at the intersection of these verticals, i.e., Agentic Embodied AI, remains scarce. This paper introduces an MCP server for analyzing ROS and ROS 2 bags, allowing for analyzing, visualizing and processing robot data with natural language through LLMs and VLMs. We describe specific tooling built with robotics domain knowledge, with our initial release focused on mobile robotics and supporting natively the analysis of trajectories, laser scan data, transforms, or time series data. This is in addition to providing an interface to standard ROS 2 CLI tools ("ros2 bag list" or "ros2 bag info"), as well as the ability to filter bags with a subset of topics or trimmed in time. Coupled with the MCP server, we provide a lightweight UI that allows the benchmarking of the tooling with different LLMs, both proprietary (Anthropic, OpenAI) and open-source (through Groq). Our experimental results include the analysis of tool calling capabilities of eight different state-of-the-art LLM/VLM models, both proprietary and open-source, large and small. Our experiments indicate that there is a large divide in tool calling capabilities, with Kimi K2 and Claude Sonnet 4 demonstrating clearly superior performance. We also conclude that there are multiple factors affecting the success rates, from the tool description schema to the number of arguments, as well as the number of tools available to the models. The code is available with a permissive license at https://github.com/binabik-ai/mcp-rosbags.

Paperid: 1064, https://arxiv.org/pdf/2511.03475.pdf GitHub

Abstract:
Retrieval-augmented generation (RAG) enhances large language models (LLMs) with retrieved context but often suffers from downgraded prefill performance as modern applications demand longer and more complex inputs. Existing caching techniques either preserve accuracy with low cache reuse or improve reuse at the cost of degraded reasoning quality. We present RAGBoost, an efficient RAG system that achieves high cache reuse without sacrificing accuracy through accuracy-preserving context reuse. RAGBoost detects overlapping retrieved items across concurrent sessions and multi-turn interactions, using efficient context indexing, ordering, and de-duplication to maximize reuse, while lightweight contextual hints maintain reasoning fidelity. It integrates seamlessly with existing LLM inference engines and improves their prefill performance by 1.5-3X over state-of-the-art methods, while preserving or even enhancing reasoning accuracy across diverse RAG and agentic AI workloads. Our code is released at: https://github.com/Edinburgh-AgenticAI/RAGBoost.

Paperid: 1065, https://arxiv.org/pdf/2511.03441.pdf GitHub

Abstract:
Critical appraisal of scientific literature is an essential skill in the biomedical field. While large language models (LLMs) can offer promising support in this task, their reliability remains limited, particularly for critical reasoning in specialized domains. We introduce CareMedEval, an original dataset designed to evaluate LLMs on biomedical critical appraisal and reasoning tasks. Derived from authentic exams taken by French medical students, the dataset contains 534 questions based on 37 scientific articles. Unlike existing benchmarks, CareMedEval explicitly evaluates critical reading and reasoning grounded in scientific papers. Benchmarking state-of-the-art generalist and biomedical-specialized LLMs under various context conditions reveals the difficulty of the task: open and commercial models fail to exceed an Exact Match Rate of 0.5 even though generating intermediate reasoning tokens considerably improves the results. Yet, models remain challenged especially on questions about study limitations and statistical analysis. CareMedEval provides a challenging benchmark for grounded reasoning, exposing current LLM limitations and paving the way for future development of automated support for critical appraisal.

Paperid: 1066, https://arxiv.org/pdf/2511.03376.pdf GitHub

Abstract:
We present a framework that combines Large Language Models with computational image analytics for non-invasive, zero-shot prediction of IDH mutation status in brain gliomas. For each subject, coregistered multi-parametric MRI scans and multi-class tumor segmentation maps were processed to extract interpretable semantic (visual) attributes and quantitative features, serialized in a standardized JSON file, and used to query GPT 4o and GPT 5 without fine-tuning. We evaluated this framework on six publicly available datasets (N = 1427) and results showcased high accuracy and balanced classification performance across heterogeneous cohorts, even in the absence of manual annotations. GPT 5 outperformed GPT 4o in context-driven phenotype interpretation. Volumetric features emerged as the most important predictors, supplemented by subtype-specific imaging markers and clinical information. Our results demonstrate the potential of integrating LLM-based reasoning with computational image analytics for precise, non-invasive tumor genotyping, advancing diagnostic strategies in neuro-oncology. The code is available at https://github.com/ATPLab-LUMS/CIM-LLM.

Paperid: 1067, https://arxiv.org/pdf/2511.03368.pdf GitHub

Abstract:
The rise of the machine learning (ML) model economy has intertwined markets for training datasets and pre-trained models. However, most pricing approaches still separate data and model transactions or rely on broker-centric pipelines that favor one side. Recent studies of data markets with externalities capture buyer interactions but do not yield a simultaneous and symmetric mechanism across data sellers, model producers, and model buyers. We propose a unified data-model coupled market that treats dataset and model trading as a single system. A supply-side mapping transforms dataset payments into buyer-visible model quotations, while a demand-side mapping propagates buyer prices back to datasets through Shapley-based allocation. Together, they form a closed loop that links four interactions: supply-demand propagation in both directions and mutual coupling among buyers and among sellers. We prove that the joint operator is a standard interference function (SIF), guaranteeing existence, uniqueness, and global convergence of equilibrium prices. Experiments demonstrate efficient convergence and improved fairness compared with broker-centric and one-sided baselines. The code is available on https://github.com/HongrunRen1109/Triple-Win-Pricing.

Paperid: 1068, https://arxiv.org/pdf/2511.03367.pdf GitHub

Abstract:
Recent advances in large-scale vision and language models have led to significant progress in zero-shot learning tasks. Methods such as CoOp and CoCoOp have shown that replacing handcrafted prompts with learnable vectors, known as prompt learning, can result in improved performance. However, these models often struggle to generalize to entirely unseen categories. While traditional zero-shot learning techniques benefit from various data augmentation strategies, prompt learning has primarily focused on text-based modifications, leaving the potential of image-based augmentation largely unexplored. In this work, we explore how image-level augmentations, particularly those that introduce attribute-specific variations, can support and enhance prompt learning. Our analysis examines the interaction between these augmentations and soft prompt frameworks, revealing their potential to improve generalization. We also identify a limitation in existing methods, such as CoCoOp, which do not provide explicit guidance for learning prompts that focus on semantically meaningful visual features. To address this, we propose Adding Attributes to Prompt Learning, AAPL, a novel method that introduces adversarial token embeddings to decouple superficial visual variations introduced by augmentation from class-relevant semantic representations. This decoupling enables the learned prompts to concentrate on visually discriminative features that align with the target categories. We conduct comprehensive experiments on eleven benchmark datasets, and AAPL consistently outperforms existing methods across few-shot, zero-shot, cross-dataset, and domain generalization settings. Our source code is publicly available at: https://github.com/Gahyeonkim09/AAPL

Paperid: 1069, https://arxiv.org/pdf/2511.03325.pdf GitHub

Abstract:
Video Question Answering (VideoQA) in the surgical domain aims to enhance intraoperative understanding by enabling AI models to reason over temporally coherent events rather than isolated frames. Current approaches are limited to static image features, and available datasets often lack temporal annotations, ignoring the dynamics critical for accurate procedural interpretation. We propose SurgViVQA, a surgical VideoQA model that extends visual reasoning from static images to dynamic surgical scenes. It uses a Masked Video--Text Encoder to fuse video and question features, capturing temporal cues such as motion and tool--tissue interactions, which a fine-tuned large language model (LLM) then decodes into coherent answers. To evaluate its performance, we curated REAL-Colon-VQA, a colonoscopic video dataset that includes motion-related questions and diagnostic attributes, as well as out-of-template questions with rephrased or semantically altered formulations to assess model robustness. Experimental validation on REAL-Colon-VQA and the public EndoVis18-VQA dataset shows that SurgViVQA outperforms existing image-based VQA benchmark models, particularly in keyword accuracy, improving over PitVQA by +11\% on REAL-Colon-VQA and +9\% on EndoVis18-VQA. A perturbation study on the questions further confirms improved generalizability and robustness to variations in question phrasing. SurgViVQA and the REAL-Colon-VQA dataset provide a framework for temporally-aware understanding in surgical VideoQA, enabling AI models to interpret dynamic procedural contexts more effectively. Code and dataset available at https://github.com/madratak/SurgViVQA.

Paperid: 1070, https://arxiv.org/pdf/2511.03317.pdf GitHub GitHub

Abstract:
Text-to-image diffusion models deliver high-quality images, yet aligning them with human preferences remains challenging. We revisit diffusion-based Direct Preference Optimization (DPO) for these models and identify a critical pathology: enlarging the preference margin does not necessarily improve generation quality. In particular, the standard Diffusion-DPO objective can increase the reconstruction error of both winner and loser branches. Consequently, degradation of the less-preferred outputs can become sufficiently severe that the preferred branch is also adversely affected even as the margin grows. To address this, we introduce Diffusion-SDPO, a safeguarded update rule that preserves the winner by adaptively scaling the loser gradient according to its alignment with the winner gradient. A first-order analysis yields a closed-form scaling coefficient that guarantees the error of the preferred output is non-increasing at each optimization step. Our method is simple, model-agnostic, broadly compatible with existing DPO-style alignment frameworks and adds only marginal computational overhead. Across standard text-to-image benchmarks, Diffusion-SDPO delivers consistent gains over preference-learning baselines on automated preference, aesthetic, and prompt alignment metrics. Code is publicly available at https://github.com/AIDC-AI/Diffusion-SDPO.

Paperid: 1071, https://arxiv.org/pdf/2511.03256.pdf GitHub

Abstract:
Entropy Minimization (EM) is beneficial to reducing class overlap, bridging domain gap, and restricting uncertainty for various tasks in machine learning, yet its potential is limited. To study the internal mechanism of EM, we reformulate and decouple the classical EM into two parts with opposite effects: cluster aggregation driving factor (CADF) rewards dominant classes and prompts a peaked output distribution, while gradient mitigation calibrator (GMC) penalizes high-confidence classes based on predicted probabilities. Furthermore, we reveal the limitations of classical EM caused by its coupled formulation: 1) reward collapse impedes the contribution of high-certainty samples in the learning process, and 2) easy-class bias induces misalignment between output distribution and label distribution. To address these issues, we propose Adaptive Decoupled Entropy Minimization (AdaDEM), which normalizes the reward brought from CADF and employs a marginal entropy calibrator (MEC) to replace GMC. AdaDEM outperforms DEM*, an upper-bound variant of classical EM, and achieves superior performance across various imperfectly supervised learning tasks in noisy and dynamic environments.

Paperid: 1072, https://arxiv.org/pdf/2511.03243.pdf GitHub

Abstract:
Climate change will cause an increase in the frequency and severity of flood events, prompting the need for cohesive adaptation policymaking. Designing effective adaptation policies, however, depends on managing the uncertainty of long-term climate impacts. Meanwhile, such policies can feature important normative choices that are not always made explicit. We propose that Reinforcement Learning (RL) can be a useful tool to both identify adaptation pathways under uncertain conditions while it also allows for the explicit modelling (and consequent comparison) of different adaptation priorities (e.g. economic vs. wellbeing). We use an Integrated Assessment Model (IAM) to link together a rainfall and flood model, and compute the impacts of flooding in terms of quality of life (QoL), transportation, and infrastructure damage. Our results show that models prioritising QoL over economic impacts results in more adaptation spending as well as a more even distribution of spending over the study area, highlighting the extent to which such normative assumptions can alter adaptation policy. Our framework is publicly available: https://github.com/MLSM-at-DTU/maat_qol_framework.

Paperid: 1073, https://arxiv.org/pdf/2511.03238.pdf GitHub

Abstract:
Urban flooding is expected to increase in frequency and severity as a consequence of climate change, causing wide-ranging impacts that include a decrease in urban Quality of Life (QoL). Meanwhile, policymakers must devise adaptation strategies that can cope with the uncertain nature of climate change and the complex and dynamic nature of urban flooding. Reinforcement Learning (RL) holds significant promise in tackling such complex, dynamic, and uncertain problems. Because of this, we use RL to identify which climate adaptation pathways lead to a higher QoL in the long term. We do this using an Integrated Assessment Model (IAM) which combines a rainfall projection model, a flood model, a transport accessibility model, and a quality of life index. Our preliminary results suggest that this approach can be used to learn optimal adaptation measures and it outperforms other realistic and real-world planning strategies. Our framework is publicly available: https://github.com/MLSM-at-DTU/maat_qol_framework.

Paperid: 1074, https://arxiv.org/pdf/2511.03196.pdf GitHub

Abstract:
Various data modalities are common in real-world applications (e.g., electronic health records, medical images and clinical notes in healthcare). It is essential to develop multimodal learning methods to aggregate various information from multiple modalities. The main challenge is how to appropriately align and fuse the representations of different modalities into a joint distribution. Existing methods mainly rely on concatenation or the Kronecker product, oversimplifying the interaction structure between modalities and indicating a need to model more complex interactions. Additionally, the joint distribution of latent representations with higher-order interactions is underexplored. Copula is a powerful statistical structure for modelling the interactions among variables, as it naturally bridges the joint distribution and marginal distributions of multiple variables. We propose a novel copula-driven multimodal learning framework, which focuses on learning the joint distribution of various modalities to capture the complex interactions among them. The key idea is to interpret the copula model as a tool to align the marginal distributions of the modalities efficiently. By assuming a Gaussian mixture distribution for each modality and a copula model on the joint distribution, our model can generate accurate representations for missing modalities. Extensive experiments on public MIMIC datasets demonstrate the superior performance of our model over other competitors. The code is available at https://github.com/HKU-MedAI/CMCM.

Paperid: 1075, https://arxiv.org/pdf/2511.03187.pdf GitHub

Abstract:
Unsupervised skill discovery in reinforcement learning (RL) aims to learn diverse behaviors without relying on external rewards. However, current methods often overlook the periodic nature of learned skills, focusing instead on increasing the mutual dependence between states and skills or maximizing the distance traveled in latent space. Considering that many robotic tasks - particularly those involving locomotion - require periodic behaviors across varying timescales, the ability to discover diverse periodic skills is essential. Motivated by this, we propose Periodic Skill Discovery (PSD), a framework that discovers periodic behaviors in an unsupervised manner. The key idea of PSD is to train an encoder that maps states to a circular latent space, thereby naturally encoding periodicity in the latent representation. By capturing temporal distance, PSD can effectively learn skills with diverse periods in complex robotic tasks, even with pixel-based observations. We further show that these learned skills achieve high performance on downstream tasks such as hurdling. Moreover, integrating PSD with an existing skill discovery method offers more diverse behaviors, thus broadening the agent's repertoire. Our code and demos are available at https://jonghaepark.github.io/psd/

Paperid: 1076, https://arxiv.org/pdf/2511.03168.pdf GitHub

Abstract:
Uncovering cause-effect relationships from observational time series is fundamental to understanding complex systems. While many methods infer static causal graphs, real-world systems often exhibit dynamic causality-where relationships evolve over time. Accurately capturing these temporal dynamics requires time-resolved causal graphs. We propose UnCLe, a novel deep learning method for scalable dynamic causal discovery. UnCLe employs a pair of Uncoupler and Recoupler networks to disentangle input time series into semantic representations and learns inter-variable dependencies via auto-regressive Dependency Matrices. It estimates dynamic causal influences by analyzing datapoint-wise prediction errors induced by temporal perturbations. Extensive experiments demonstrate that UnCLe not only outperforms state-of-the-art baselines on static causal discovery benchmarks but, more importantly, exhibits a unique capability to accurately capture and represent evolving temporal causality in both synthetic and real-world dynamic systems (e.g., human motion). UnCLe offers a promising approach for revealing the underlying, time-varying mechanisms of complex phenomena.

Paperid: 1077, https://arxiv.org/pdf/2511.03128.pdf GitHub

Abstract:
LLMs can provide substantial zero-shot performance on diverse tasks using a simple task prompt, eliminating the need for training or fine-tuning. However, when applying these models to sensitive tasks, it is crucial to thoroughly assess their robustness against adversarial inputs. In this work, we introduce Static Deceptor (StaDec) and Dynamic Deceptor (DyDec), two innovative attack frameworks designed to systematically generate dynamic and adaptive adversarial examples by leveraging the understanding of the LLMs. We produce subtle and natural-looking adversarial inputs that preserve semantic similarity to the original text while effectively deceiving the target LLM. By utilizing an automated, LLM-driven pipeline, we eliminate the dependence on external heuristics. Our attacks evolve with the advancements in LLMs and demonstrate strong transferability across models unknown to the attacker. Overall, this work provides a systematic approach for the self-assessment of an LLM's robustness. We release our code and data at https://github.com/Shukti042/AdversarialExample.

Paperid: 1078, https://arxiv.org/pdf/2511.03114.pdf GitHub

Abstract:
Recently, self-supervised contrastive learning has achieved great success on various tasks. However, its underlying working mechanism is yet unclear. In this paper, we first provide the tightest bounds based on the widely adopted assumption of conditional independence. Further, we relax the conditional independence assumption to a more practical assumption of augmentation overlap and derive the asymptotically closed bounds for the downstream performance. Our proposed augmentation overlap theory hinges on the insight that the support of different intra-class samples will become more overlapped under aggressive data augmentations, thus simply aligning the positive samples (augmented views of the same sample) could make contrastive learning cluster intra-class samples together. Moreover, from the newly derived augmentation overlap perspective, we develop an unsupervised metric for the representation evaluation of contrastive learning, which aligns well with the downstream performance almost without relying on additional modules. Code is available at https://github.com/PKU-ML/GARC.

Paperid: 1079, https://arxiv.org/pdf/2511.03108.pdf GitHub

Abstract:
We perform a thorough analysis of the formal and informal statements in the miniF2F benchmark from the perspective of an AI system that is tasked to participate in a math Olympiad consisting of the problems in miniF2F. In such setting, the model has to read and comprehend the problems in natural language, formalize them in Lean language, then proceed with proving the problems, and it will get credit for each problem if the formal proof corresponds to the original informal statement presented to the model. Our evaluation results reveal that the best accuracy of such pipeline can be about 36% using the SoTA models in the literature, considerably lower than the individual SoTA accuracies, 97% and 69% reported in the autoformalization and theorem proving literature. Analyzing the failure modes, we trace back a considerable portion of this drop to discrepancies between the formal and informal statements for more than half of the problems in miniF2F. We proceed with correcting all the errors, discrepancies and simplifications in formal and informal statements, and present the miniF2F-v2 with fully verified formal and informal statements and proofs. Evaluating the full theorem proving pipeline on miniF2F-v2 leads to the best accuracy of 70%, a significant improvement from the 40% on the original miniF2F, yet indicating considerable misalignment between the autoformalization models and theorem provers. Our deep analysis suggests that a higher quality benchmark can help the community better evaluate progress in the field of formal reasoning and also better diagnose the failure and success modes of autoformalization and theorem proving models. Our dataset is available at https://github.com/roozbeh-yz/miniF2F_v2.

Paperid: 1080, https://arxiv.org/pdf/2511.03104.pdf GitHub

Abstract:
This paper introduces D2-UC, a quantum-ready framework for the unit commitment (UC) problem that prepares UC for near-term hybrid quantum-classical solvers by combining distributed classical decomposition with distributed quantum execution. We reformulate deterministic and stochastic UC into a three-block alternating direction method of multipliers (ADMM): (i) a convex quadratic subproblem for dispatch and reserves, (ii) a binary subproblem expressed as a quadratic unconstrained binary optimization (QUBO), and (iii) a proximal slack update for consensus. The core contributions are fivefold. First, we demonstrate how the full UC problem can be expressed as a single monolithic QUBO, establishing a direct interface to quantum solvers. Second, we decompose this large binary block into three type-specific QUBOs for commitment, startup, and shutdown, making the problem more tractable but revealing slower ADMM convergence. Third, we restore local logical couplings through per-unit-time micro-QUBOs, which accelerate convergence. Fourth, we batch micro-QUBOs into K non-overlapping block-diagonal problems, reducing many subproblems to a fixed number of solver-ready QUBOs per iteration, compatible with distributed variational quantum eigensolvers (DVQE). Fifth, we integrate an accept-if-better safeguard with DVQE to stabilize hybrid updates and prevent oscillations. Case studies confirm that the proposed methods deliver feasible schedules, faster convergence, and QUBO sizes aligned with current and near-term quantum hardware capabilities. All detailed data, codes, and parameter values are available at https://github.com/LSU-RAISE-LAB/3B-ADMM-UC-DVQE .

Paperid: 1081, https://arxiv.org/pdf/2511.03014.pdf GitHub

Abstract:
We present a foundation model for brain MRI that can work with different combinations of imaging sequences. The model uses one encoder with learnable modality embeddings, conditional layer normalization, and a masked autoencoding objective that accounts for missing modalities. A variance-covariance regularizer is applied to stabilize feature learning and improve representation diversity. This design removes the need for separate models for each modality and allows the network to adapt when some sequences are missing or unseen. It is trained on about 60,000 multi-center MRIs using self-supervised reconstruction and modality imputation to learn flexible representations. A learnable modality embedding guides feature extraction so the encoder can adjust to different inputs. We describe our planned evaluation on brain tumor and multiple sclerosis segmentation, as well as lesion classification, under various modality settings. Preliminary results show that the method works feasibly, and further experiments are planned to study its performance in more detail. All code and pretrained models are available at https://github.com/BrainFM/brainfm

Paperid: 1082, https://arxiv.org/pdf/2511.03002.pdf GitHub

Abstract:
We address the design of a model predictive control (MPC) scheme for large-scale linear systems using reduced-order models (ROMs). Our approach uses a ROM, leverages tools from robust control, and integrates them into an MPC framework to achieve computational tractability with robust constraint satisfaction. Our key contribution is a method to obtain guaranteed bounds on the predicted outputs of the full-order system by predicting a (scalar) error-bounding system alongside the ROM. This bound is then used to formulate a robust ROM-based MPC that guarantees constraint satisfaction and robust performance. Our method is developed step-by-step by (i) analysing the error, (ii) bounding the peak-to-peak gain, an (iii) using filtered signals. We demonstrate our method on a 100-dimensional mass-spring-damper system, achieving over four orders of magnitude reduction in conservatism relative to existing approaches.

Paperid: 1083, https://arxiv.org/pdf/2511.02986.pdf GitHub

Abstract:
Computational modeling of single-cell gene expression is crucial for understanding cellular processes, but generating realistic expression profiles remains a major challenge. This difficulty arises from the count nature of gene expression data and complex latent dependencies among genes. Existing generative models often impose artificial gene orderings or rely on shallow neural network architectures. We introduce a scalable latent diffusion model for single-cell gene expression data, which we refer to as scLDM, that respects the fundamental exchangeability property of the data. Our VAE uses fixed-size latent variables leveraging a unified Multi-head Cross-Attention Block (MCAB) architecture, which serves dual roles: permutation-invariant pooling in the encoder and permutation-equivariant unpooling in the decoder. We enhance this framework by replacing the Gaussian prior with a latent diffusion model using Diffusion Transformers and linear interpolants, enabling high-quality generation with multi-conditional classifier-free guidance. We show its superior performance in a variety of experiments for both observational and perturbational single-cell data, as well as downstream tasks like cell-level classification.

Paperid: 1084, https://arxiv.org/pdf/2511.02946.pdf GitHub

Abstract:
We introduce ProM3E, a probabilistic masked multimodal embedding model for any-to-any generation of multimodal representations for ecology. ProM3E is based on masked modality reconstruction in the embedding space, learning to infer missing modalities given a few context modalities. By design, our model supports modality inversion in the embedding space. The probabilistic nature of our model allows us to analyse the feasibility of fusing various modalities for given downstream tasks, essentially learning what to fuse. Using these features of our model, we propose a novel cross-modal retrieval approach that mixes inter-modal and intra-modal similarities to achieve superior performance across all retrieval tasks. We further leverage the hidden representation from our model to perform linear probing tasks and demonstrate the superior representation learning capability of our model. All our code, datasets and model will be released at https://vishu26.github.io/prom3e.

Paperid: 1085, https://arxiv.org/pdf/2511.02888.pdf GitHub

Abstract:
Nucleotide sequence variation can induce significant shifts in functional fitness. Recent nucleotide foundation models promise to predict such fitness effects directly from sequence, yet heterogeneous datasets and inconsistent preprocessing make it difficult to compare methods fairly across DNA and RNA families. Here we introduce NABench, a large-scale, systematic benchmark for nucleic acid fitness prediction. NABench aggregates 162 high-throughput assays and curates 2.6 million mutated sequences spanning diverse DNA and RNA families, with standardized splits and rich metadata. We show that NABench surpasses prior nucleotide fitness benchmarks in scale, diversity, and data quality. Under a unified evaluation suite, we rigorously assess 29 representative foundation models across zero-shot, few-shot prediction, transfer learning, and supervised settings. The results quantify performance heterogeneity across tasks and nucleic-acid types, demonstrating clear strengths and failure modes for different modeling choices and establishing strong, reproducible baselines. We release NABench to advance nucleic acid modeling, supporting downstream applications in RNA/DNA design, synthetic biology, and biochemistry. Our code is available at https://github.com/mrzzmrzz/NABench.

Paperid: 1086, https://arxiv.org/pdf/2511.02866.pdf GitHub

Abstract:
This paper presents LM-Fix, a lightweight detection and rapid recovery framework for faults in large language models (LLMs). Existing integrity approaches are often heavy or slow for modern LLMs. LM-Fix runs a short test-vector pass and uses hash-guided checks to detect bit-flip faults, then repairs them locally without a full reload. Across multiple models, it detects over 94% of single-bit flips at TVL=200 and nearly 100% of multi-bit flips with approximately 1% to 7.7% runtime overhead; recovery is more than 100x faster than reloading. These results show a practical, low-overhead solution to keep LLMs reliable in production

Paperid: 1087, https://arxiv.org/pdf/2511.02830.pdf GitHub

Abstract:
We propose DenseMarks - a new learned representation for human heads, enabling high-quality dense correspondences of human head images. For a 2D image of a human head, a Vision Transformer network predicts a 3D embedding for each pixel, which corresponds to a location in a 3D canonical unit cube. In order to train our network, we collect a dataset of pairwise point matches, estimated by a state-of-the-art point tracker over a collection of diverse in-the-wild talking heads videos, and guide the mapping via a contrastive loss, encouraging matched points to have close embeddings. We further employ multi-task learning with face landmarks and segmentation constraints, as well as imposing spatial continuity of embeddings through latent cube features, which results in an interpretable and queryable canonical space. The representation can be used for finding common semantic parts, face/head tracking, and stereo reconstruction. Due to the strong supervision, our method is robust to pose variations and covers the entire head, including hair. Additionally, the canonical space bottleneck makes sure the obtained representations are consistent across diverse poses and individuals. We demonstrate state-of-the-art results in geometry-aware point matching and monocular head tracking with 3D Morphable Models. The code and the model checkpoint will be made available to the public.

Paperid: 1088, https://arxiv.org/pdf/2511.02818.pdf GitHub

Abstract:
Tabular data remain the predominant format for real-world applications. Yet, developing effective neural models for tabular data remains challenging due to heterogeneous feature types and complex interactions occurring at multiple scales. Recent advances in tabular in-context learning (ICL), such as TabPFN and TabICL, have achieved state-of-the-art performance comparable to gradient-boosted trees (GBTs) without task-specific fine-tuning. However, current architectures exhibit key limitations: (1) single-scale feature processing that overlooks hierarchical dependencies, (2) dense attention with quadratic scaling in table width, and (3) strictly sequential component processing that prevents iterative representation refinement and cross-component communication. To address these challenges, we introduce Orion-MSP, a tabular ICL architecture featuring three key innovations: (1) multi-scale processing to capture hierarchical feature interactions; (2) block-sparse attention combining windowed, global, and random patterns for scalable efficiency and long-range connectivity; and (3) a Perceiver-style memory enabling safe bidirectional information flow across components. Across diverse benchmarks, Orion-MSP matches or surpasses state-of-the-art performance while scaling effectively to high-dimensional tables, establishing a new standard for efficient tabular in-context learning. The model is publicly available at https://github.com/Lexsi-Labs/Orion-MSP .

Paperid: 1089, https://arxiv.org/pdf/2511.02805.pdf GitHub

Abstract:
Typical search agents concatenate the entire interaction history into the LLM context, preserving information integrity but producing long, noisy contexts, resulting in high computation and memory costs. In contrast, using only the current turn avoids this overhead but discards essential information. This trade-off limits the scalability of search agents. To address this challenge, we propose MemSearcher, an agent workflow that iteratively maintains a compact memory and combines the current turn with it. At each turn, MemSearcher fuses the user's question with the memory to generate reasoning traces, perform search actions, and update memory to retain only information essential for solving the task. This design stabilizes context length across multi-turn interactions, improving efficiency without sacrificing accuracy. To optimize this workflow, we introduce multi-context GRPO, an end-to-end RL framework that jointly optimize reasoning, search strategies, and memory management of MemSearcher Agents. Specifically, multi-context GRPO samples groups of trajectories under different contexts and propagates trajectory-level advantages across all conversations within them. Trained on the same dataset as Search-R1, MemSearcher achieves significant improvements over strong baselines on seven public benchmarks: +11% on Qwen2.5-3B-Instruct and +12% on Qwen2.5-7B-Instruct relative average gains. Notably, the 3B-based MemSearcher even outperforms 7B-based baselines, demonstrating that striking a balance between information integrity and efficiency yields both higher accuracy and lower computational overhead. The code and models will be publicly available at https://github.com/icip-cas/MemSearcher

Paperid: 1090, https://arxiv.org/pdf/2511.02802.pdf GitHub

Abstract:
Tabular foundation models represent a growing paradigm in structured data learning, extending the benefits of large-scale pretraining to tabular domains. However, their adoption remains limited due to heterogeneous preprocessing pipelines, fragmented APIs, inconsistent fine-tuning procedures, and the absence of standardized evaluation for deployment-oriented metrics such as calibration and fairness. We present TabTune, a unified library that standardizes the complete workflow for tabular foundation models through a single interface. TabTune provides consistent access to seven state-of-the-art models supporting multiple adaptation strategies, including zero-shot inference, meta-learning, supervised fine-tuning (SFT), and parameter-efficient fine-tuning (PEFT). The framework automates model-aware preprocessing, manages architectural heterogeneity internally, and integrates evaluation modules for performance, calibration, and fairness. Designed for extensibility and reproducibility, TabTune enables consistent benchmarking of adaptation strategies of tabular foundation models.

Paperid: 1091, https://arxiv.org/pdf/2511.02778.pdf GitHub GitHub GitHub

Abstract:
Code has emerged as a precise and executable medium for reasoning and action in the agent era. Yet, progress has largely focused on language-centric tasks such as program synthesis and debugging, leaving visual-centric coding underexplored. Inspired by how humans reason over sketches, we advocate SVG code as a compact, interpretable, and executable visual representation. We introduce VCode, a benchmark that reframes multimodal understanding as code generation: given an image, a model must produce SVG that preserves symbolic meaning for downstream reasoning. VCode covers three domains - general commonsense (MM-Vet), professional disciplines (MMMU), and visual-centric perception (CV-Bench). To assess symbolic fidelity, we propose CodeVQA, a novel evaluation protocol in which a policy model answers questions over rendered SVGs; correct answers indicate faithful symbolic preservation. Empirically, frontier VLMs struggle to generate faithful SVGs, revealing a persistent gap between language-centric and visual-centric coding. To close this gap, we introduce VCoder, an agentic framework that augments VLMs along two axes: (i) Thinking with Revision, which iteratively analyzes discrepancies and refines SVG code; and (ii) Acting with Visual Tools, where detectors and parsers supply structured cues such as objects, shapes, and text beyond the model's intrinsic capacity. Across benchmarks, frontier VLMs with strong reasoning capabilities score well overall yet remain limited in professional knowledge and 3D reasoning. VCoder delivers a 12.3-point overall gain over the top-performing Claude-4-Opus. Human studies show that both humans and VLMs perform worse on rendered SVGs, their consistency reveals the promise of symbolic visual representation. The benchmark and code are available at https://github.com/CSU-JPG/VCode.

Paperid: 1092, https://arxiv.org/pdf/2511.02777.pdf GitHub GitHub

Abstract:
We present PercHead, a method for single-image 3D head reconstruction and semantic 3D editing - two tasks that are inherently challenging due to severe view occlusions, weak perceptual supervision, and the ambiguity of editing in 3D space. We develop a unified base model for reconstructing view-consistent 3D heads from a single input image. The model employs a dual-branch encoder followed by a ViT-based decoder that lifts 2D features into 3D space through iterative cross-attention. Rendering is performed using Gaussian Splatting. At the heart of our approach is a novel perceptual supervision strategy based on DINOv2 and SAM2.1, which provides rich, generalized signals for both geometric and appearance fidelity. Our model achieves state-of-the-art performance in novel-view synthesis and, furthermore, exhibits exceptional robustness to extreme viewing angles compared to established baselines. Furthermore, this base model can be seamlessly extended for semantic 3D editing by swapping the encoder and finetuning the network. In this variant, we disentangle geometry and style through two distinct input modalities: a segmentation map to control geometry and either a text prompt or a reference image to specify appearance. We highlight the intuitive and powerful 3D editing capabilities of our model through a lightweight, interactive GUI, where users can effortlessly sculpt geometry by drawing segmentation maps and stylize appearance via natural language or image prompts. Project Page: https://antoniooroz.github.io/PercHead Video: https://www.youtube.com/watch?v=4hFybgTk4kE

Paperid: 1093, https://arxiv.org/pdf/2511.02776.pdf GitHub

Abstract:
Recent progress in large-scale robotic datasets and vision-language models (VLMs) has advanced research on vision-language-action (VLA) models. However, existing VLA models still face two fundamental challenges: (i) producing precise low-level actions from high-dimensional observations, (ii) bridging domain gaps across heterogeneous data sources, including diverse robot embodiments and human demonstrations. Existing methods often encode latent variables from either visual dynamics or robotic actions to guide policy learning, but they fail to fully exploit the complementary multi-modal knowledge present in large-scale, heterogeneous datasets. In this work, we present X Robotic Model 1 (XR-1), a novel framework for versatile and scalable VLA learning across diverse robots, tasks, and environments. XR-1 introduces the \emph{Unified Vision-Motion Codes (UVMC)}, a discrete latent representation learned via a dual-branch VQ-VAE that jointly encodes visual dynamics and robotic motion. UVMC addresses these challenges by (i) serving as an intermediate representation between the observations and actions, and (ii) aligning multimodal dynamic information from heterogeneous data sources to capture complementary knowledge. To effectively exploit UVMC, we propose a three-stage training paradigm: (i) self-supervised UVMC learning, (ii) UVMC-guided pretraining on large-scale cross-embodiment robotic datasets, and (iii) task-specific post-training. We validate XR-1 through extensive real-world experiments with more than 14,000 rollouts on six different robot embodiments, spanning over 120 diverse manipulation tasks. XR-1 consistently outperforms state-of-the-art baselines such as $π_{0.5}$, $π_0$, RDT, UniVLA, and GR00T-N1.5 while demonstrating strong generalization to novel objects, background variations, distractors, and illumination changes. Our project is at https://xr-1-vla.github.io/.

Paperid: 1094, https://arxiv.org/pdf/2511.02667.pdf GitHub

Abstract:
Compositional generalization-a key open challenge in modern machine learning-requires models to predict unknown combinations of known concepts. However, assessing compositional generalization remains a fundamental challenge due to the lack of standardized evaluation protocols and the limitations of current benchmarks, which often favor efficiency over rigor. At the same time, general-purpose vision architectures lack the necessary inductive biases, and existing approaches to endow them compromise scalability. As a remedy, this paper introduces: 1) a rigorous evaluation framework that unifies and extends previous approaches while reducing computational requirements from combinatorial to constant; 2) an extensive and modern evaluation on the status of compositional generalization in supervised vision backbones, training more than 5000 models; 3) Attribute Invariant Networks, a class of models establishing a new Pareto frontier in compositional generalization, achieving a 23.43% accuracy improvement over baselines while reducing parameter overhead from 600% to 16% compared to fully disentangled counterparts. Our code is available at https://github.com/IBM/scalable-compositional-generalization.

Paperid: 1095, https://arxiv.org/pdf/2511.02607.pdf GitHub

Abstract:
Change detection (CD) is a fundamental task for monitoring and analyzing land cover dynamics. While recent high performance models and high quality datasets have significantly advanced the field, a critical limitation persists. Current models typically acquire limited knowledge from single-type annotated data and cannot concurrently leverage diverse binary change detection (BCD) and semantic change detection (SCD) datasets. This constraint leads to poor generalization and limited versatility. The recent advancements in Multimodal Large Language Models (MLLMs) introduce new possibilities for a unified CD framework. We leverage the language priors and unification capabilities of MLLMs to develop UniChange, the first MLLM-based unified change detection model. UniChange integrates generative language abilities with specialized CD functionalities. Our model successfully unifies both BCD and SCD tasks through the introduction of three special tokens: [T1], [T2], and [CHANGE]. Furthermore, UniChange utilizes text prompts to guide the identification of change categories, eliminating the reliance on predefined classification heads. This design allows UniChange to effectively acquire knowledge from multi-source datasets, even when their class definitions conflict. Experiments on four public benchmarks (WHU-CD, S2Looking, LEVIR-CD+, and SECOND) demonstrate SOTA performance, achieving IoU scores of 90.41, 53.04, 78.87, and 57.62, respectively, surpassing all previous methods. The code is available at https://github.com/Erxucomeon/UniChange.

Paperid: 1096, https://arxiv.org/pdf/2511.02591.pdf GitHub

Abstract:
Multi-animal tracking is crucial for understanding animal ecology and behavior. However, it remains a challenging task due to variations in habitat, motion patterns, and species appearance. Traditional approaches typically require extensive model fine-tuning and heuristic design for each application scenario. In this work, we explore the potential of recent vision foundation models for zero-shot multi-animal tracking. By combining a Grounding Dino object detector with the Segment Anything Model 2 (SAM 2) tracker and carefully designed heuristics, we develop a tracking framework that can be applied to new datasets without any retraining or hyperparameter adaptation. Evaluations on ChimpAct, Bird Flock Tracking, AnimalTrack, and a subset of GMOT-40 demonstrate strong and consistent performance across diverse species and environments. The code is available at https://github.com/ecker-lab/SAM2-Animal-Tracking.

Paperid: 1097, https://arxiv.org/pdf/2511.02580.pdf GitHub

Abstract:
Despite the remarkable success of text-to-image diffusion models, their output of a single, flattened image remains a critical bottleneck for professional applications requiring layer-wise control. Existing solutions either rely on fine-tuning with large, inaccessible datasets or are training-free yet limited to generating isolated foreground elements, failing to produce a complete and coherent scene. To address this, we introduce the Training-free Noise Transplantation and Cultivation Diffusion Model (TAUE), a novel framework for zero-shot, layer-wise image generation. Our core technique, Noise Transplantation and Cultivation (NTC), extracts intermediate latent representations from both foreground and composite generation processes, transplanting them into the initial noise for subsequent layers. This ensures semantic and structural coherence across foreground, background, and composite layers, enabling consistent, multi-layered outputs without requiring fine-tuning or auxiliary datasets. Extensive experiments show that our training-free method achieves performance comparable to fine-tuned methods, enhancing layer-wise consistency while maintaining high image quality and fidelity. TAUE not only eliminates costly training and dataset requirements but also unlocks novel downstream applications, such as complex compositional editing, paving the way for more accessible and controllable generative workflows.

Paperid: 1098, https://arxiv.org/pdf/2511.02564.pdf GitHub

Abstract:
Video-based person re-identification (ReID) in cross-view domains (for example, aerial-ground surveillance) remains an open problem because of extreme viewpoint shifts, scale disparities, and temporal inconsistencies. To address these challenges, we propose MTF-CVReID, a parameter-efficient framework that introduces seven complementary modules over a ViT-B/16 backbone. Specifically, we include: (1) Cross-Stream Feature Normalization (CSFN) to correct camera and view biases; (2) Multi-Resolution Feature Harmonization (MRFH) for scale stabilization across altitudes; (3) Identity-Aware Memory Module (IAMM) to reinforce persistent identity traits; (4) Temporal Dynamics Modeling (TDM) for motion-aware short-term temporal encoding; (5) Inter-View Feature Alignment (IVFA) for perspective-invariant representation alignment; (6) Hierarchical Temporal Pattern Learning (HTPL) to capture multi-scale temporal regularities; and (7) Multi-View Identity Consistency Learning (MVICL) that enforces cross-view identity coherence using a contrastive learning paradigm. Despite adding only about 2 million parameters and 0.7 GFLOPs over the baseline, MTF-CVReID maintains real-time efficiency (189 FPS) and achieves state-of-the-art performance on the AG-VPReID benchmark across all altitude levels, with strong cross-dataset generalization to G2A-VReID and MARS datasets. These results show that carefully designed adapter-based modules can substantially enhance cross-view robustness and temporal consistency without compromising computational efficiency. The source code is available at https://github.com/MdRashidunnabi/MTF-CVReID

Paperid: 1099, https://arxiv.org/pdf/2511.02560.pdf GitHub

Abstract:
We introduce SigmaCollab, a dataset enabling research on physically situated human-AI collaboration. The dataset consists of a set of 85 sessions in which untrained participants were guided by a mixed-reality assistive AI agent in performing procedural tasks in the physical world. SigmaCollab includes a set of rich, multimodal data streams, such as the participant and system audio, egocentric camera views from the head-mounted device, depth maps, head, hand and gaze tracking information, as well as additional annotations performed post-hoc. While the dataset is relatively small in size (~ 14 hours), its application-driven and interactive nature brings to the fore novel research challenges for human-AI collaboration, and provides more realistic testing grounds for various AI models operating in this space. In future work, we plan to use the dataset to construct a set of benchmarks for physically situated collaboration in mixed-reality task assistive scenarios. SigmaCollab is available at https://github.com/microsoft/SigmaCollab.

Paperid: 1100, https://arxiv.org/pdf/2511.02505.pdf GitHub

Abstract:
Shot assembly is a crucial step in film production and video editing, involving the sequencing and arrangement of shots to construct a narrative, convey information, or evoke emotions. Traditionally, this process has been manually executed by experienced editors. While current intelligent video editing technologies can handle some automated video editing tasks, they often fail to capture the creator's unique artistic expression in shot assembly. To address this challenge, we propose an energy-based optimization method for video shot assembly. Specifically, we first perform visual-semantic matching between the script generated by a large language model and a video library to obtain subsets of candidate shots aligned with the script semantics. Next, we segment and label the shots from reference videos, extracting attributes such as shot size, camera motion, and semantics. We then employ energy-based models to learn from these attributes, scoring candidate shot sequences based on their alignment with reference styles. Finally, we achieve shot assembly optimization by combining multiple syntax rules, producing videos that align with the assembly style of the reference videos. Our method not only automates the arrangement and combination of independent shots according to specific logic, narrative requirements, or artistic styles but also learns the assembly style of reference videos, creating a coherent visual sequence or holistic visual expression. With our system, even users with no prior video editing experience can create visually compelling videos. Project page: https://sobeymil.github.io/esa.com

Paperid: 1101, https://arxiv.org/pdf/2511.02489.pdf GitHub

Abstract:
With the rapid growth of the low-altitude economy, UAVs have become crucial for measurement and tracking in patrol systems. However, in GNSS-denied areas, satellite-based localization methods are prone to failure. This paper presents a cross-view UAV localization framework that performs map matching via object detection, aimed at effectively addressing cross-temporal, cross-view, heterogeneous aerial image matching. In typical pipelines, UAV visual localization is formulated as an image-retrieval problem: features are extracted to build a localization map, and the pose of a query image is estimated by matching it to a reference database with known poses. Because publicly available UAV localization datasets are limited, many approaches recast localization as a classification task and rely on scene labels in these datasets to ensure accuracy. Other methods seek to reduce cross-domain differences using polar-coordinate reprojection, perspective transformations, or generative adversarial networks; however, they can suffer from misalignment, content loss, and limited realism. In contrast, we leverage modern object detection to accurately extract salient instances from UAV and satellite images, and integrate a graph neural network to reason about inter-image and intra-image node relationships. Using a fine-grained, graph-based node-similarity metric, our method achieves strong retrieval and localization performance. Extensive experiments on public and real-world datasets show that our approach handles heterogeneous appearance differences effectively and generalizes well, making it applicable to scenarios with larger modality gaps, such as infrared-visible image matching. Our dataset will be publicly available at the following URL: https://github.com/liutao23/ODGNNLoc.git.

Paperid: 1102, https://arxiv.org/pdf/2511.02454.pdf GitHub

Abstract:
The Dilated FAVOR Conformer (DF-Conformer) is an efficient variant of the Conformer architecture designed for speech enhancement (SE). It employs fast attention through positive orthogonal random features (FAVOR+) to mitigate the quadratic complexity associated with self-attention, while utilizing dilated convolution to expand the receptive field. This combination results in impressive performance across various SE models. In this paper, we propose replacing FAVOR+ with bidirectional selective structured state-space sequence models to achieve two main objectives:(1) enhancing global sequential modeling by eliminating the approximations inherent in FAVOR+, and (2) maintaining linear complexity relative to the sequence length. Specifically, we utilize Hydra, a bidirectional extension of Mamba, framed within the structured matrix mixer framework. Experiments conducted using a generative SE model on discrete codec tokens, known as Genhancer, demonstrate that the proposed method surpasses the performance of the DF-Conformer.

Paperid: 1103, https://arxiv.org/pdf/2511.02400.pdf GitHub

Abstract:
The development of clinically reliable artificial intelligence (AI) systems for mammography is hindered by profound heterogeneity in data quality, metadata standards, and population distributions across public datasets. This heterogeneity introduces dataset-specific biases that severely compromise the generalizability of the model, a fundamental barrier to clinical deployment. We present MammoClean, a public framework for standardization and bias quantification in mammography datasets. MammoClean standardizes case selection, image processing (including laterality and intensity correction), and unifies metadata into a consistent multi-view structure. We provide a comprehensive review of breast anatomy, imaging characteristics, and public mammography datasets to systematically identify key sources of bias. Applying MammoClean to three heterogeneous datasets (CBIS-DDSM, TOMPEI-CMMD, VinDr-Mammo), we quantify substantial distributional shifts in breast density and abnormality prevalence. Critically, we demonstrate the direct impact of data corruption: AI models trained on corrupted datasets exhibit significant performance degradation compared to their curated counterparts. By using MammoClean to identify and mitigate bias sources, researchers can construct unified multi-dataset training corpora that enable development of robust models with superior cross-domain generalization. MammoClean provides an essential, reproducible pipeline for bias-aware AI development in mammography, facilitating fairer comparisons and advancing the creation of safe, effective systems that perform equitably across diverse patient populations and clinical settings. The open-source code is publicly available from: https://github.com/Minds-R-Lab/MammoClean.

Paperid: 1104, https://arxiv.org/pdf/2511.02397.pdf GitHub

Abstract:
Color consistency correction for color point clouds is a fundamental yet important task in 3D rendering and compression applications. In the past, most previous color correction methods aimed at correcting color for color images. The purpose of this paper is to propose a grouping-based hybrid color correction algorithm for color point clouds. Our algorithm begins by estimating the overlapping rate between the aligned source and target point clouds, and then adaptively partitions the target points into two groups, namely the close proximity group Gcl and the moderate proximity group Gmod, or three groups, namely Gcl, Gmod, and the distant proximity group Gdist, when the estimated overlapping rate is low or high, respectively. To correct color for target points in Gcl, a K-nearest neighbors based bilateral interpolation (KBI) method is proposed. To correct color for target points in Gmod, a joint KBI and the histogram equalization (JKHE) method is proposed. For target points in Gdist, a histogram equalization (HE) method is proposed for color correction. Finally, we discuss the grouping-effect free property and the ablation study in our algorithm. The desired color consistency correction benefit of our algorithm has been justified through 1086 testing color point cloud pairs against the state-of-the-art methods. The C++ source code of our algorithm can be accessed from the website: https://github.com/ivpml84079/Point-cloud-color-correction.

Paperid: 1105, https://arxiv.org/pdf/2511.02376.pdf GitHub

Abstract:
Large Language Models (LLMs) remain vulnerable to jailbreaking attacks where adversarial prompts elicit harmful outputs, yet most evaluations focus on single-turn interactions while real-world attacks unfold through adaptive multi-turn conversations. We present AutoAdv, a training-free framework for automated multi-turn jailbreaking that achieves up to 95% attack success rate on Llama-3.1-8B within six turns a 24 percent improvement over single turn baselines. AutoAdv uniquely combines three adaptive mechanisms: a pattern manager that learns from successful attacks to enhance future prompts, a temperature manager that dynamically adjusts sampling parameters based on failure modes, and a two-phase rewriting strategy that disguises harmful requests then iteratively refines them. Extensive evaluation across commercial and open-source models (GPT-4o-mini, Qwen3-235B, Mistral-7B) reveals persistent vulnerabilities in current safety mechanisms, with multi-turn attacks consistently outperforming single-turn approaches. These findings demonstrate that alignment strategies optimized for single-turn interactions fail to maintain robustness across extended conversations, highlighting an urgent need for multi-turn-aware defenses.

Paperid: 1106, https://arxiv.org/pdf/2511.02349.pdf GitHub

Abstract:
Portable physiological monitoring is essential for early detection and management of cardiovascular disease, but current methods often require specialized equipment that limits accessibility or impose impractical postures that patients cannot maintain. Video-based photoplethysmography on smartphones offers a convenient noninvasive alternative, yet it still faces reliability challenges caused by motion artifacts, lighting variations, and single-view constraints. Few studies have demonstrated reliable application to cardiovascular patients, and no widely used open datasets exist for cross-device accuracy. To address these limitations, we introduce the M3PD dataset, the first publicly available dual-view mobile photoplethysmography dataset, comprising synchronized facial and fingertip videos captured simultaneously via front and rear smartphone cameras from 60 participants (including 47 cardiovascular patients). Building on this dual-view setting, we further propose F3Mamba, which fuses the facial and fingertip views through Mamba-based temporal modeling. The model reduces heart-rate error by 21.9 to 30.2 percent over existing single-view baselines while improving robustness in challenging real-world scenarios. Data and code: https://github.com/Health-HCI-Group/F3Mamba.

Paperid: 1107, https://arxiv.org/pdf/2511.02280.pdf GitHub

Abstract:
We introduce SAIL-RL, a reinforcement learning (RL) post-training framework that enhances the reasoning capabilities of multimodal large language models (MLLMs) by teaching them when and how to think. Existing approaches are limited by outcome-only supervision, which rewards correct answers without ensuring sound reasoning, and by uniform thinking strategies, which often lead to overthinking on simple tasks and underthinking on complex ones. SAIL-RL addresses these challenges with a dual reward system: the Thinking Reward, which evaluates reasoning quality through factual grounding, logical coherence, and answer consistency, and the Judging Reward, which adaptively determines whether deep reasoning or direct answering is appropriate. Experiments on the state-of-the-art SAIL-VL2 show that SAIL-RL improves reasoning and multimodal understanding benchmarks at both 4B and 8B scales, achieving competitive performance against commercial closed-source models such as GPT-4o, and substantially reduces hallucinations, establishing it as a principled framework for building more reliable and adaptive MLLMs. The code will be available at https://github.com/BytedanceDouyinContent/SAIL-RL.

Paperid: 1108, https://arxiv.org/pdf/2511.02256.pdf GitHub

Abstract:
Motion artifacts in magnetic resonance imaging (MRI) remain a major challenge, as they degrade image quality and compromise diagnostic reliability. Score-based generative models (SGMs) have recently shown promise for artifact removal. However, existing 3D SGM-based approaches are limited in two key aspects: (1) their strong dependence on known forward operators makes them ineffective for correcting MRI motion artifacts, and (2) their slow inference speed hinders clinical translation. To overcome these challenges, we propose a wavelet-optimized end-to-end framework for 3D MRI motion correct using pre-trained 2D score priors (3D-WMoCo). Specifically, two orthogonal 2D score priors are leveraged to guide the 3D distribution prior, while a mean-reverting stochastic differential equation (SDE) is employed to model the restoration process of motion-corrupted 3D volumes to motion-free 3D distribution. Furthermore, wavelet diffusion is introduced to accelerate inference, and wavelet convolution is applied to enhance feature extraction. We validate the effectiveness of our approach through both simulated motion artifact experiments and real-world clinical motion artifact correction tests. The proposed method achieves robust performance improvements over existing techniques. Implementation details and source code are available at: https://github.com/ZG-yuan/3D-WMoCo.

Paperid: 1109, https://arxiv.org/pdf/2511.02247.pdf GitHub

Abstract:
Monocular depth estimation (MDE) is a critical task to guide autonomous medical robots. However, obtaining absolute (metric) depth from an endoscopy camera in surgical scenes is difficult, which limits supervised learning of depth on real endoscopic images. Current image-level unsupervised domain adaptation methods translate synthetic images with known depth maps into the style of real endoscopic frames and train depth networks using these translated images with their corresponding depth maps. However a domain gap often remains between real and translated synthetic images. In this paper, we present a latent feature alignment method to improve absolute depth estimation by reducing this domain gap in the context of endoscopic videos of the central airway. Our methods are agnostic to the image translation process and focus on the depth estimation itself. Specifically, the depth network takes translated synthetic and real endoscopic frames as input and learns latent domain-invariant features via adversarial learning and directional feature consistency. The evaluation is conducted on endoscopic videos of central airway phantoms with manually aligned absolute depth maps. Compared to state-of-the-art MDE methods, our approach achieves superior performance on both absolute and relative depth metrics, and consistently improves results across various backbones and pretrained weights. Our code is available at https://github.com/MedICL-VU/MDE.

Paperid: 1110, https://arxiv.org/pdf/2511.02246.pdf GitHub

Abstract:
Recent research has shown that hallucinations, omissions, and biases are prevalent in everyday use-cases of LLMs. However, chatbots used in medical contexts must provide consistent advice in situations where non-medical factors are involved, such as when demographic information is present. In order to understand the conditions under which medical chatbots fail to perform as expected, we develop an infrastructure that 1) automatically generates queries to probe LLMs and 2) evaluates answers to these queries using multiple LLM-as-a-judge setups and prompts. For 1), our prompt creation pipeline samples the space of patient demographics, histories, disorders, and writing styles to create realistic questions that we subsequently use to prompt LLMs. In 2), our evaluation pipeline provides hallucination and omission detection using LLM-as-a-judge as well as agentic workflows, in addition to LLM-as-a-judge treatment category detectors. As a baseline study, we perform two case studies on inter-LLM agreement and the impact of varying the answering and evaluation LLMs. We find that LLM annotators exhibit low agreement scores (average Cohen's Kappa $κ=0.118$), and only specific (answering, evaluation) LLM pairs yield statistically significant differences across writing styles, genders, and races. We recommend that studies using LLM evaluation use multiple LLMs as evaluators in order to avoid arriving at statistically significant but non-generalizable results, particularly in the absence of ground-truth data. We also suggest publishing inter-LLM agreement metrics for transparency. Our code and dataset are available here: https://github.com/BBN-E/medic-neurips-2025-demo.

Paperid: 1111, https://arxiv.org/pdf/2511.02239.pdf GitHub

Abstract:
Learning generalizable policies for robotic manipulation increasingly relies on large-scale models that map language instructions to actions (L2A). However, this one-way paradigm often produces policies that execute tasks without deeper contextual understanding, limiting their ability to generalize or explain their behavior. We argue that the complementary skill of mapping actions back to language (A2L) is essential for developing more holistic grounding. An agent capable of both acting and explaining its actions can form richer internal representations and unlock new paradigms for self-supervised learning. We introduce LACY (Language-Action Cycle), a unified framework that learns such bidirectional mappings within a single vision-language model. LACY is jointly trained on three synergistic tasks: generating parameterized actions from language (L2A), explaining observed actions in language (A2L), and verifying semantic consistency between two language descriptions (L2C). This enables a self-improving cycle that autonomously generates and filters new training data through an active augmentation strategy targeting low-confidence cases, thereby improving the model without additional human labels. Experiments on pick-and-place tasks in both simulation and the real world show that LACY improves task success rates by 56.46% on average and yields more robust language-action grounding for robotic manipulation. Project page: https://vla2026.github.io/LACY/

Paperid: 1112, https://arxiv.org/pdf/2511.02238.pdf GitHub

Abstract:
Novel research ideas play a critical role in advancing scientific inquiries. Recent advancements in Large Language Models (LLMs) have demonstrated their potential to generate novel research ideas by leveraging large-scale scientific literature. However, previous work in research ideation has primarily relied on simplistic methods, such as keyword co-occurrence or semantic similarity. These approaches focus on identifying statistical associations in the literature but overlook the complex, contextual relationships between scientific concepts, which are essential to effectively leverage knowledge embedded in human literature. For instance, papers that simultaneously mention "keyword A" and "keyword B" often present research ideas that integrate both concepts. Additionally, some LLM-driven methods propose and refine research ideas using the model's internal knowledge, but they fail to effectively utilize the scientific concept network, limiting the grounding of ideas in established research. To address these challenges, we propose the Deep Ideation framework to address these challenges, integrating a scientific network that captures keyword co-occurrence and contextual relationships, enriching LLM-driven ideation. The framework introduces an explore-expand-evolve workflow to iteratively refine research ideas, using an Idea Stack to track progress. A critic engine, trained on real-world reviewer feedback, guides the process by providing continuous feedback on the novelty and feasibility of ideas. Our experiments show that our approach improves the quality of generated ideas by 10.67% compared to other methods, with ideas surpassing top conference acceptance levels. Human evaluation highlights their practical value in scientific research, and ablation studies confirm the effectiveness of each component in the workflow. Code repo is available at https://github.com/kyZhao-1/Deep-Ideation.

Paperid: 1113, https://arxiv.org/pdf/2511.02230.pdf GitHub

Abstract:
Agentic LLM applications interleave LLM generation requests with tool calls. These tool calls break the continuity of the workflow by creating pauses between LLM requests, bringing many challenges for the serving system, especially under multi-turn scenarios. Each pause potentially causes KV cache eviction and extra waiting time before entering the continuous batch for the following LLM request. Since these pauses happen for each call, this problem becomes increasingly severe as turn number grow for agentic programs. Previous works either fail to incorporate information from the tool call, evicting KV cache that leads to repetitive prefill or loading, or ignore the continuity of a multi-turn program, creating waiting time between turns that increases per-request latency. We present Continuum, a serving system to optimize job completion time for multi-turn agent workloads by combining tool-aware KV cache timeout with program-level scheduling. By predicting tool call durations in agentic workflows, Continuum selectively pins the KV cache in GPU memory with a time-to-live value based on total turn number. When combined with program-level first-come-first-serve, Continuum prevents scheduling bubbles, preserves multi-turn continuity, and optimizes for throughput for complex agentic workflows. By modeling the variability of tool call and agent program continuity, Continuum outperforms state-of-the-art baselines. Our evaluation on real-world agentic workloads (SWE-Bench and BFCL) with Llama-3.1 8B/70B models shows that Continuum significantly improves the average job completion times, and remains performant across different hardware setups and DRAM offloading schemes. Preview code is available at: https://github.com/Hanchenli/vllm-continuum

Paperid: 1114, https://arxiv.org/pdf/2511.02213.pdf GitHub

Abstract:
With the growing computational demands of large language models (LLMs), efficient inference has become increasingly critical for practical deployment. Depth pruning has emerged as a promising approach for reducing the computational costs of large language models by removing transformer layers. However, existing methods typically rely on fixed block masks, which can lead to suboptimal performance across different tasks and inputs. In this paper, we propose IG-Pruning, a novel input-aware block-wise pruning method that dynamically selects layer masks at inference time. Our approach consists of two stages: (1) Discovering diverse mask candidates through semantic clustering and L0 optimization, and (2) Implementing efficient dynamic pruning without the need for extensive training. Experimental results demonstrate that our method consistently outperforms state-of-the-art static depth pruning methods, making it particularly suitable for resource-constrained deployment scenarios.

Paperid: 1115, https://arxiv.org/pdf/2511.02194.pdf GitHub

Abstract:
Decision-making models for individuals, particularly in high-stakes scenarios like vaccine uptake, often diverge from population optimal predictions. This gap arises from the uniqueness of the individual decision-making process, shaped by numerical attributes (e.g., cost, time) and linguistic influences (e.g., personal preferences and constraints). Developing upon Utility Theory and leveraging the textual-reasoning capabilities of Large Language Models (LLMs), this paper proposes an Adaptive Textual-symbolic Human-centric Reasoning framework (ATHENA) to address the optimal information integration. ATHENA uniquely integrates two stages: First, it discovers robust, group-level symbolic utility functions via LLM-augmented symbolic discovery; Second, it implements individual-level semantic adaptation, creating personalized semantic templates guided by the optimal utility to model personalized choices. Validated on real-world travel mode and vaccine choice tasks, ATHENA consistently outperforms utility-based, machine learning, and other LLM-based models, lifting F1 score by at least 6.5% over the strongest cutting-edge models. Further, ablation studies confirm that both stages of ATHENA are critical and complementary, as removing either clearly degrades overall predictive performance. By organically integrating symbolic utility modeling and semantic adaptation, ATHENA provides a new scheme for modeling human-centric decisions. The project page can be found at https://yibozh.github.io/Athena.

Paperid: 1116, https://arxiv.org/pdf/2511.02193.pdf GitHub

Abstract:
Accurate detection of retinal vessels plays a critical role in reflecting a wide range of health status indicators in the clinical diagnosis of ocular diseases. Recently, advances in deep learning have led to a surge in retinal vessel segmentation methods, which have significantly contributed to the quantitative analysis of vascular morphology. However, retinal vasculature differs significantly from conventional segmentation targets in that it consists of extremely thin and branching structures, whose global morphology varies greatly across images. These characteristics continue to pose challenges to segmentation precision and robustness. To address these issues, we propose MM-UNet, a novel architecture tailored for efficient retinal vessel segmentation. The model incorporates Morph Mamba Convolution layers, which replace pointwise convolutions to enhance branching topological perception through morph, state-aware feature sampling. Additionally, Reverse Selective State Guidance modules integrate reverse guidance theory with state-space modeling to improve geometric boundary awareness and decoding efficiency. Extensive experiments conducted on two public retinal vessel segmentation datasets demonstrate the superior performance of the proposed method in segmentation accuracy. Compared to the existing approaches, MM-UNet achieves F1-score gains of 1.64 % on DRIVE and 1.25 % on STARE, demonstrating its effectiveness and advancement. The project code is public via https://github.com/liujiawen-jpg/MM-UNet.

Paperid: 1117, https://arxiv.org/pdf/2511.02136.pdf GitHub

Abstract:
Agent-based modelling (ABM) approaches for high-frequency financial markets are difficult to calibrate and validate, partly due to the large parameter space created by defining fixed agent policies. Multi-agent reinforcement learning (MARL) enables more realistic agent behaviour and reduces the number of free parameters, but the heavy computational cost has so far limited research efforts. To address this, we introduce JaxMARL-HFT (JAX-based Multi-Agent Reinforcement Learning for High-Frequency Trading), the first GPU-accelerated open-source multi-agent reinforcement learning environment for high-frequency trading (HFT) on market-by-order (MBO) data. Extending the JaxMARL framework and building on the JAX-LOB implementation, JaxMARL-HFT is designed to handle a heterogeneous set of agents, enabling diverse observation/action spaces and reward functions. It is designed flexibly, so it can also be used for single-agent RL, or extended to act as an ABM with fixed-policy agents. Leveraging JAX enables up to a 240x reduction in end-to-end training time, compared with state-of-the-art reference implementations on the same hardware. This significant speed-up makes it feasible to exploit the large, granular datasets available in high-frequency trading, and to perform the extensive hyperparameter sweeps required for robust and efficient MARL research in trading. We demonstrate the use of JaxMARL-HFT with independent Proximal Policy Optimization (IPPO) for a two-player environment, with an order execution and a market making agent, using one year of LOB data (400 million orders), and show that these agents learn to outperform standard benchmarks. The code for the JaxMARL-HFT framework is available on GitHub.

Paperid: 1118, https://arxiv.org/pdf/2511.02135.pdf GitHub GitHub

Abstract:
Large language models (LLMs) are increasingly used to simulate humans, with applications ranging from survey prediction to decision-making. However, are LLMs strictly necessary, or can smaller, domain-grounded models suffice? We identify a large class of simulation problems in which individuals make choices among discrete options, where a graph neural network (GNN) can match or surpass strong LLM baselines despite being three orders of magnitude smaller. We introduce Graph-basEd Models for human Simulation (GEMS), which casts discrete choice simulation tasks as a link prediction problem on graphs, leveraging relational knowledge while incorporating language representations only when needed. Evaluations across three key settings on three simulation datasets show that GEMS achieves comparable or better accuracy than LLMs, with far greater efficiency, interpretability, and transparency, highlighting the promise of graph-based modeling as a lightweight alternative to LLMs for human simulation. Our code is available at https://github.com/schang-lab/gems.

Paperid: 1119, https://arxiv.org/pdf/2511.02133.pdf GitHub GitHub

Abstract:
Designing multi-functional alloys requires exploring high-dimensional composition-structure-property spaces, yet current tools are limited to low-dimensional projections and offer limited support for sensitivity or multi-objective tradeoff reasoning. We introduce AlloyLens, an interactive visual analytics system combining a coordinated scatterplot matrix (SPLOM), dynamic parameter sliders, gradient-based sensitivity curves, and nearest neighbor recommendations. This integrated approach reveals latent structure in simulation data, exposes the local impact of compositional changes, and highlights tradeoffs when exact matches are absent. We validate the system through case studies co-developed with domain experts spanning structural, thermal, and electrical alloy design.

Paperid: 1120, https://arxiv.org/pdf/2511.01999.pdf GitHub

Abstract:
Vision-Language Models (VLMs) struggle to translate high-level instructions into the precise spatial affordances required for robotic manipulation. While visual Chain-of-Thought (CoT) methods exist, they are often computationally intensive. In this work, we introduce TRACE (Textual Reasoning for Affordance Coordinate Extraction), a novel methodology that integrates a textual Chain of Reasoning (CoR) into the affordance prediction process. We use this methodology to create the TRACE dataset, a large-scale collection created via an autonomous pipeline that pairs instructions with explicit textual rationales. By fine-tuning a VLM on this data, our model learns to externalize its spatial reasoning before acting. Our experiments show that our TRACE-tuned model achieves state-of-the-art performance, reaching 48.1% accuracy on the primary Where2Place (W2P) benchmark (a 9.6% relative improvement) and 55.0% on the more challenging W2P(h) subset. Crucially, an ablation study demonstrates that performance scales directly with the amount of reasoning data used, confirming the CoR's effectiveness. Furthermore, analysis of the model's attention maps reveals an interpretable reasoning process where focus shifts dynamically across reasoning steps. This work shows that training VLMs to generate a textual CoR is an effective and robust strategy for enhancing the precision, reliability, and interpretability of VLM-based robot control. Our dataset and code are available at https://github.com/jink-ucla/TRACE

Paperid: 1121, https://arxiv.org/pdf/2511.01952.pdf GitHub

Abstract:
Large vision-language models (LVLMs) derive their capabilities from extensive training on vast corpora of visual and textual data. Empowered by large-scale parameters, these models often exhibit strong memorization of their training data, rendering them susceptible to membership inference attacks (MIAs). Existing MIA methods for LVLMs typically operate under white- or gray-box assumptions, by extracting likelihood-based features for the suspected data samples based on the target LVLMs. However, mainstream LVLMs generally only expose generated outputs while concealing internal computational features during inference, limiting the applicability of these methods. In this work, we propose the first black-box MIA framework for LVLMs, based on a prior knowledge-calibrated memory probing mechanism. The core idea is to assess the model memorization of the private semantic information embedded within the suspected image data, which is unlikely to be inferred from general world knowledge alone. We conducted extensive experiments across four LVLMs and three datasets. Empirical results demonstrate that our method effectively identifies training data of LVLMs in a purely black-box setting and even achieves performance comparable to gray-box and white-box methods. Further analysis reveals the robustness of our method against potential adversarial manipulations, and the effectiveness of the methodology designs. Our code and data are available at https://github.com/spmede/KCMP.

Paperid: 1122, https://arxiv.org/pdf/2511.01937.pdf GitHub GitHub GitHub

Abstract:
Large language models (LLMs) trained for step-by-step reasoning often become excessively verbose, raising inference cost. Standard Reinforcement Learning with Verifiable Rewards (RLVR) pipelines filter out ``easy'' problems for training efficiency, leaving the model to train primarily on harder problems that require longer reasoning chains. This skews the output length distribution upward, resulting in a \textbf{model that conflates ``thinking longer'' with ``thinking better''}. In this work, we show that retaining and modestly up-weighting moderately easy problems acts as an implicit length regularizer. Exposing the model to solvable short-chain tasks constrains its output distribution and prevents runaway verbosity. The result is \textbf{\emph{emergent brevity for free}}: the model learns to solve harder problems without inflating the output length, \textbf{ despite the absence of any explicit length penalization}. RLVR experiments using this approach on \textit{Qwen3-4B-Thinking-2507} (with a 16k token limit) achieve baseline pass@1 AIME25 accuracy while generating solutions that are, on average, nearly twice as short. The code is available at \href{https://github.com/MBZUAI-Paris/Frugal-AI}{GitHub}, with datasets and models on \href{https://huggingface.co/collections/MBZUAI-Paris/k2-think-mini-68dcfa8b114686a4bd3dc2bc}{Hugging Face}.

Paperid: 1123, https://arxiv.org/pdf/2511.01891.pdf GitHub

Abstract:
Multi-personality generation for LLMs, enabling simultaneous embodiment of multiple personalization attributes, is a fundamental challenge. Existing retraining-based approaches are costly and poorly scalable, while decoding-time methods often rely on external models or heuristics, limiting flexibility and robustness. In this paper, we propose a novel Multi-Personality Generation (MPG) framework under the decoding-time combination paradigm. It flexibly controls multi-personality without relying on scarce multi-dimensional models or extra training, leveraging implicit density ratios in single-dimensional models as a "free lunch" to reformulate the task as sampling from a target strategy aggregating these ratios. To implement MPG efficiently, we design Speculative Chunk-level based Rejection sampling (SCR), which generates responses in chunks and parallelly validates them via estimated thresholds within a sliding window. This significantly reduces computational overhead while maintaining high-quality generation. Experiments on MBTI personality and Role-Playing demonstrate the effectiveness of MPG, showing improvements up to 16%-18%. Code and data are available at https://github.com/Libra117/MPG .

Paperid: 1124, https://arxiv.org/pdf/2511.01885.pdf GitHub

Abstract:
As artificial intelligence (AI) advances toward superhuman capabilities, aligning these systems with human values becomes increasingly critical. Current alignment strategies rely largely on externally specified constraints that may prove insufficient against future super-intelligent AI capable of circumventing top-down controls. This research investigates whether artificial neural networks (ANNs) can develop patterns analogous to biological mirror neurons cells that activate both when performing and observing actions, and how such patterns might contribute to intrinsic alignment in AI. Mirror neurons play a crucial role in empathy, imitation, and social cognition in humans. The study therefore asks: (1) Can simple ANNs develop mirror-neuron patterns? and (2) How might these patterns contribute to ethical and cooperative decision-making in AI systems? Using a novel Frog and Toad game framework designed to promote cooperative behaviors, we identify conditions under which mirror-neuron patterns emerge, evaluate their influence on action circuits, introduce the Checkpoint Mirror Neuron Index (CMNI) to quantify activation strength and consistency, and propose a theoretical framework for further study. Our findings indicate that appropriately scaled model capacities and self/other coupling foster shared neural representations in ANNs similar to biological mirror neurons. These empathy-like circuits support cooperative behavior and suggest that intrinsic motivations modeled through mirror-neuron dynamics could complement existing alignment techniques by embedding empathy-like mechanisms directly within AI architectures.

Paperid: 1125, https://arxiv.org/pdf/2511.01884.pdf GitHub

Abstract:
Developing efficient CUDA kernels is increasingly critical for AI applications such as large-scale LLM training. However, manual kernel design is both costly and time-consuming, motivating automatic approaches that leverage LLMs for code generation. Existing methods for automatic kernel generation, however, often produce low-efficiency kernels, incur high computational overhead, and fail to generalize across settings. In this work, we propose CudaForge, a training-free multi-agent workflow for CUDA kernel generation and optimization. Our workflow is inspired by the iterative workflow of human experts, which contains steps such as developing initial kernels, testing correctness, analyzing hardware feedback, and iterative improvement. More specifically, CudaForge employs two LLM agents: a Coder and a Judge, that iteratively generate, correct, and optimize CUDA kernels, while integrating hardware feedback such as Nsight Compute (NCU) metrics. In extensive evaluations, we show that CudaForge, by leveraging base models like OpenAI-o3, achieves 97.6\% correctness of generated kernels and an average 1.68$\times$ speedup over PyTorch baselines, substantially surpassing state-of-the-art models including OpenAI-o3 and Kevin on KernelBench.Beyond accuracy and speed, CudaForge demonstrates strong generalization across GPUs (A100, RTX 6000, 4090, 3090) and base models (OpenAI-o3, GPT-5, gpt-oss-120B, Claude-Sonnet-4, QwQ-32B), while maintaining high efficiency. In particular, generating an optimized kernel takes about 26.5 minutes on one RTX6000 and incurs about \$ 0.3 API cost, which is significantly cheaper than existing agentic work that costs 6 H100 hours and \$ 5 API cost per kernel. Our results highlight that multi-agent, training-free workflows can enable cost-effective, generalizable, and high-performance CUDA kernel optimization. Code available at https://github.com/OptimAI-Lab/CudaForge

Paperid: 1126, https://arxiv.org/pdf/2511.01846.pdf GitHub

Abstract:
Finding the right north-star metrics is highly critical for advancing the mathematical reasoning capabilities of foundation models, especially given that existing evaluations are either too easy or only focus on getting correct short answers. To address these issues, we present IMO-Bench, a suite of advanced reasoning benchmarks, vetted by a panel of top specialists and that specifically targets the level of the International Mathematical Olympiad (IMO), the most prestigious venue for young mathematicians. IMO-AnswerBench first tests models on 400 diverse Olympiad problems with verifiable short answers. IMO-Proof Bench is the next-level evaluation for proof-writing capabilities, which includes both basic and advanced IMO level problems as well as detailed grading guidelines to facilitate automatic grading. These benchmarks played a crucial role in our historic achievement of the gold-level performance at IMO 2025 with Gemini Deep Think (Luong and Lockhart, 2025). Our model achieved 80.0% on IMO-AnswerBench and 65.7% on the advanced IMO-Proof Bench, surpassing the best non-Gemini models by large margins of 6.9% and 42.4% respectively. We also showed that autograders built with Gemini reasoning correlate well with human evaluations and construct IMO-GradingBench, with 1000 human gradings on proofs, to enable further progress in automatic evaluation of long-form answers. We hope that IMO-Bench will help the community towards advancing robust mathematical reasoning and release it at https://imobench.github.io/.

Paperid: 1127, https://arxiv.org/pdf/2511.01819.pdf GitHub

Abstract:
Ultra-wideband (UWB) localization delivers centimeter-scale accuracy but is vulnerable to jamming attacks, creating security risks for asset tracking and intrusion detection in smart buildings. Although machine learning (ML) and deep learning (DL) methods have improved tag localization, localizing malicious jammers within a single room and across changing indoor layouts remains largely unexplored. Two novel UWB datasets, collected under original and modified room configurations, are introduced to establish comprehensive ML/DL baselines. Performance is rigorously evaluated using a variety of classification and regression metrics. On the source dataset with the collected UWB features, Random Forest achieves the highest F1-macro score of 0.95 and XGBoost achieves the lowest mean Euclidean error of 20.16 cm. However, deploying these source-trained models in the modified room layout led to severe performance degradation, with XGBoost's mean Euclidean error increasing tenfold to 207.99 cm, demonstrating significant domain shift. To mitigate this degradation, a domain-adversarial ConvNeXt autoencoder (A-CNT) is proposed that leverages a gradient-reversal layer to align CIR-derived features across domains. The A-CNT framework restores localization performance by reducing the mean Euclidean error to 34.67 cm. This represents a 77 percent improvement over non-adversarial transfer learning and an 83 percent improvement over the best baseline, restoring the fraction of samples within 30 cm to 0.56. Overall, the results demonstrate that adversarial feature alignment enables robust and transferable indoor jammer localization despite environmental changes. Code and dataset available at https://github.com/afbf4c8996f/Jammer-Loc

Paperid: 1128, https://arxiv.org/pdf/2511.01791.pdf GitHub

Abstract:
Data scarcity remains a fundamental bottleneck for embodied intelligence. Existing approaches use large language models (LLMs) to automate gripper-based simulation generation, but they transfer poorly to dexterous manipulation, which demands more specialized environment design. Meanwhile, dexterous manipulation tasks are inherently more difficult due to their higher degrees of freedom. Massively generating feasible and trainable dexterous hand tasks remains an open challenge. To this end, we present GenDexHand, a generative simulation pipeline that autonomously produces diverse robotic tasks and environments for dexterous manipulation. GenDexHand introduces a closed-loop refinement process that adjusts object placements and scales based on vision-language model (VLM) feedback, substantially improving the average quality of generated environments. Each task is further decomposed into sub-tasks to enable sequential reinforcement learning, reducing training time and increasing success rates. Our work provides a viable path toward scalable training of diverse dexterous hand behaviors in embodied intelligence by offering a simulation-based solution to synthetic data generation. Our website: https://winniechen2002.github.io/GenDexHand/.

Paperid: 1129, https://arxiv.org/pdf/2511.01768.pdf GitHub

Abstract:
Although transformers have demonstrated remarkable capabilities across various domains, their quadratic attention mechanisms introduce significant computational overhead when processing long-sequence data. In this paper, we present a unified autonomous driving model, UniLION, which efficiently handles large-scale LiDAR point clouds, high-resolution multi-view images, and even temporal sequences based on the linear group RNN operator (i.e., performs linear RNN for grouped features). Remarkably, UniLION serves as a single versatile architecture that can seamlessly support multiple specialized variants (i.e., LiDAR-only, temporal LiDAR, multi-modal, and multi-modal temporal fusion configurations) without requiring explicit temporal or multi-modal fusion modules. Moreover, UniLION consistently delivers competitive and even state-of-the-art performance across a wide range of core tasks, including 3D perception (e.g., 3D object detection, 3D object tracking, 3D occupancy prediction, BEV map segmentation), prediction (e.g., motion prediction), and planning (e.g., end-to-end planning). This unified paradigm naturally simplifies the design of multi-modal and multi-task autonomous driving systems while maintaining superior performance. Ultimately, we hope UniLION offers a fresh perspective on the development of 3D foundation models in autonomous driving. Code is available at https://github.com/happinesslz/UniLION

Paperid: 1130, https://arxiv.org/pdf/2511.01767.pdf GitHub

Abstract:
In this work, we introduce \textbf{Wonder3D++}, a novel method for efficiently generating high-fidelity textured meshes from single-view images. Recent methods based on Score Distillation Sampling (SDS) have shown the potential to recover 3D geometry from 2D diffusion priors, but they typically suffer from time-consuming per-shape optimization and inconsistent geometry. In contrast, certain works directly produce 3D information via fast network inferences, but their results are often of low quality and lack geometric details. To holistically improve the quality, consistency, and efficiency of single-view reconstruction tasks, we propose a cross-domain diffusion model that generates multi-view normal maps and the corresponding color images. To ensure the consistency of generation, we employ a multi-view cross-domain attention mechanism that facilitates information exchange across views and modalities. Lastly, we introduce a cascaded 3D mesh extraction algorithm that drives high-quality surfaces from the multi-view 2D representations in only about $3$ minute in a coarse-to-fine manner. Our extensive evaluations demonstrate that our method achieves high-quality reconstruction results, robust generalization, and good efficiency compared to prior works. Code available at https://github.com/xxlong0/Wonder3D/tree/Wonder3D_Plus.

Paperid: 1131, https://arxiv.org/pdf/2511.01758.pdf GitHub

Abstract:
Open-ended generation tasks require outputs to satisfy diverse and often implicit task-specific evaluation rubrics. The sheer number of relevant rubrics leads to prohibitively high verification costs and incomplete assessments of a response, making reinforcement learning (RL) post-training with rubric-based rewards difficult to scale. This problem is exacerbated by the fact that often the best way to combine these rubrics into one single reward is also highly prompt-specific. We propose Reinforcement Learning with Adversarial Critic (RLAC), a post-training approach that addresses these challenges via dynamic rubric verification. Our approach employs a large language model (LLM) as a critic that dynamically identifies only the most likely failure modes (e.g., a factual error or unhandled edge case), which are then verified by an external validator to optimize both generator and critic jointly. By training both the generator and the critic, this game enhances the critic's error detection and the generator's output quality while reducing required verifications. Our experiments demonstrate that RLAC improves factual accuracy in text generation and correctness in code generation, while also outperforming exhaustive verification and reward model methods. We show that dynamic critics are more effective than fixed critics, showcasing the potential of RLAC for scaling RL post-training to free-form generation tasks.

Paperid: 1132, https://arxiv.org/pdf/2511.01737.pdf GitHub

Abstract:
Federated learning (FL) has emerged as a transformative paradigm for edge intelligence, enabling collaborative model training while preserving data privacy across distributed personal devices. However, the inherent volatility of edge environments, characterized by dynamic resource availability and heterogeneous client capabilities, poses significant challenges for achieving high accuracy and fairness in client participation. This paper investigates the fundamental trade-off between model accuracy and fairness in highly volatile edge environments. This paper provides an extensive empirical evaluation of fairness-based client selection algorithms such as RBFF and RBCSF against random and greedy client selection regarding fairness, model performance, and time, in three benchmarking datasets (CIFAR10, FashionMNIST, and EMNIST). This work aims to shed light on the fairness-performance and fairness-speed trade-offs in a volatile edge environment and explore potential future research opportunities to address existing pitfalls in \textit{fair client selection} strategies in FL. Our results indicate that more equitable client selection algorithms, while providing a marginally better opportunity among clients, can result in slower global training in volatile environments\footnote{The code for our experiments can be found at https://github.com/obaidullahzaland/FairFL_FLTA.

Paperid: 1133, https://arxiv.org/pdf/2511.01724.pdf GitHub

Abstract:
Deep learning models are notoriously vulnerable to imperceptible perturbations. Most existing research centers on adversarial robustness (AR), which evaluates models under worst-case scenarios by examining the existence of deterministic adversarial examples (AEs). In contrast, probabilistic robustness (PR) adopts a statistical perspective, measuring the probability that predictions remain correct under stochastic perturbations. While PR is widely regarded as a practical complement to AR, dedicated training methods for improving PR are still relatively underexplored, albeit with emerging progress. Among the few PR-targeted training methods, we identify three limitations: i non-comparable evaluation protocols; ii limited comparisons to strong AT baselines despite anecdotal PR gains from AT; and iii no unified framework to compare the generalization of these methods. Thus, we introduce PRBench, the first benchmark dedicated to evaluating improvements in PR achieved by different robustness training methods. PRBench empirically compares most common AT and PR-targeted training methods using a comprehensive set of metrics, including clean accuracy, PR and AR performance, training efficiency, and generalization error (GE). We also provide theoretical analysis on the GE of PR performance across different training methods. Main findings revealed by PRBench include: AT methods are more versatile than PR-targeted training methods in terms of improving both AR and PR performance across diverse hyperparameter settings, while PR-targeted training methods consistently yield lower GE and higher clean accuracy. A leaderboard comprising 222 trained models across 7 datasets and 10 model architectures is publicly available at https://tmpspace.github.io/PRBenchLeaderboard/.

Paperid: 1134, https://arxiv.org/pdf/2511.01720.pdf GitHub

Abstract:
We present a multi-expert system for creating Non-Player Characters (NPCs) capable of both natural dialogue and contextual action execution in interactive environments. Using Qwen3 as the base model and Low-Rank Adaptation (LoRA) adapters, we instantiate three specialists: tool calling, tool-response interpretation, and direct dialogue. Our system comfortably meets the computational efficiency requirements, delivering fast responses and maintaining modest resource usage on L40S GPUs. In the Commonsense Persona-Grounded Dialogue Challenge 2025, our method ranked second overall. Code available at: https://github.com/MahammadNuriyev62/CPDC-challenge-2025-solution/

Paperid: 1135, https://arxiv.org/pdf/2511.01718.pdf GitHub

Abstract:
Vision-language-action (VLA) models aim to understand natural language instructions and visual observations and to execute corresponding actions as an embodied agent. Recent work integrates future images into the understanding-acting loop, yielding unified VLAs that jointly understand, generate, and act -- reading text and images and producing future images and actions. However, these models either rely on external experts for modality unification or treat image generation and action prediction as separate processes, limiting the benefits of direct synergy between these tasks. Our core philosophy is to optimize generation and action jointly through a synchronous denoising process, where the iterative refinement enables actions to evolve from initialization, under constant and sufficient visual guidance. We ground this philosophy in our proposed Unified Diffusion VLA and Joint Discrete Denoising Diffusion Process (JD3P), which is a joint diffusion process that integrates multiple modalities into a single denoising trajectory to serve as the key mechanism enabling understanding, generation, and acting to be intrinsically synergistic. Our model and theory are built on a unified tokenized space of all modalities and a hybrid attention mechanism. We further propose a two-stage training pipeline and several inference-time techniques that optimize performance and efficiency. Our approach achieves state-of-the-art performance on benchmarks such as CALVIN, LIBERO, and SimplerEnv with 4$\times$ faster inference than autoregressive methods, and we demonstrate its effectiveness through in-depth analysis and real-world evaluations. Our project page is available at https://irpn-eai.github.io/UD-VLA.github.io/.

Paperid: 1136, https://arxiv.org/pdf/2511.01706.pdf GitHub

Abstract:
Natural Language Explanations (NLEs) describe how Large Language Models (LLMs) make decisions, drawing on both external Context Knowledge (CK) and Parametric Knowledge (PK) stored in model weights. Understanding their interaction is key to assessing the grounding of NLEs, yet it remains underexplored. Prior work has largely examined only single-step generation, typically the final answer, and has modelled PK and CK interaction only as a binary choice in a rank-1 subspace. This overlooks richer forms of interaction, such as complementary or supportive knowledge. We propose a novel rank-2 projection subspace that disentangles PK and CK contributions more accurately and use it for the first multi-step analysis of knowledge interactions across longer NLE sequences. Experiments on four QA datasets and three open-weight instruction-tuned LLMs show that diverse knowledge interactions are poorly represented in a rank-1 subspace but are effectively captured in our rank-2 formulation. Our multi-step analysis reveals that hallucinated NLEs align strongly with the PK direction, context-faithful ones balance PK and CK, and Chain-of-Thought prompting for NLEs shifts generated NLEs toward CK by reducing PK reliance. This work provides the first framework for systematic studies of multi-step knowledge interactions in LLMs through a richer rank-2 subspace disentanglement. Code and data: https://github.com/copenlu/pk-ck-knowledge-disentanglement.

Paperid: 1137, https://arxiv.org/pdf/2511.01704.pdf GitHub

Abstract:
Under-display ToF imaging aims to achieve accurate depth sensing through a ToF camera placed beneath a screen panel. However, transparent OLED (TOLED) layers introduce severe degradations-such as signal attenuation, multi-path interference (MPI), and temporal noise-that significantly compromise depth quality. To alleviate this drawback, we propose Learnable Fractional Reaction-Diffusion Dynamics (LFRD2), a hybrid framework that combines the expressive power of neural networks with the interpretability of physical modeling. Specifically, we implement a time-fractional reaction-diffusion module that enables iterative depth refinement with dynamically generated differential orders, capturing long-term dependencies. In addition, we introduce an efficient continuous convolution operator via coefficient prediction and repeated differentiation to further improve restoration quality. Experiments on four benchmark datasets demonstrate the effectiveness of our approach. The code is publicly available at https://github.com/wudiqx106/LFRD2.

Paperid: 1138, https://arxiv.org/pdf/2511.01689.pdf GitHub

Abstract:
The character of the "AI assistant" persona generated by modern chatbot large language models influences both surface-level behavior and apparent values, beliefs, and ethics. These all affect interaction quality, perceived intelligence, and alignment with both developer and user intentions. The shaping of this persona, known as character training, is a critical component of industry post-training, yet remains effectively unstudied in the academic literature. We introduce the first open implementation of character training, leveraging Constitutional AI and a new data pipeline using synthetic introspective data to shape the assistant persona in a more effective and controlled manner than alternatives such as constraining system prompts or activation steering. Specifically, we fine-tune three popular open-weights models using 11 example personas, such as humorous, deeply caring, or even malevolent. To track the effects of our approach, we introduce a method which analyzes revealed preferences, uncovering clear and holistic changes in character. We find these changes are more robust to adversarial prompting than the above two alternatives, while also leading to more coherent and realistic generations. Finally, we demonstrate this fine-tuning has little to no effect on general capabilities as measured by common benchmarks. We describe and open-source our full post-training method, the implementation of which can be found at https://github.com/maiush/OpenCharacterTraining.

Paperid: 1139, https://arxiv.org/pdf/2511.01678.pdf GitHub

Abstract:
Relighting is a crucial task with both practical demand and artistic value, and recent diffusion models have shown strong potential by enabling rich and controllable lighting effects. However, as they are typically optimized in semantic latent space, where proximity does not guarantee physical correctness in visual space, they often produce unrealistic results, such as overexposed highlights, misaligned shadows, and incorrect occlusions. We address this with UniLumos, a unified relighting framework for both images and videos that brings RGB-space geometry feedback into a flow matching backbone. By supervising the model with depth and normal maps extracted from its outputs, we explicitly align lighting effects with the scene structure, enhancing physical plausibility. Nevertheless, this feedback requires high-quality outputs for supervision in visual space, making standard multi-step denoising computationally expensive. To mitigate this, we employ path consistency learning, allowing supervision to remain effective even under few-step training regimes. To enable fine-grained relighting control and supervision, we design a structured six-dimensional annotation protocol capturing core illumination attributes. Building upon this, we propose LumosBench, a disentangled attribute-level benchmark that evaluates lighting controllability via large vision-language models, enabling automatic and interpretable assessment of relighting precision across individual dimensions. Extensive experiments demonstrate that UniLumos achieves state-of-the-art relighting quality with significantly improved physical consistency, while delivering a 20x speedup for both image and video relighting. Code is available at https://github.com/alibaba-damo-academy/Lumos-Custom.

Paperid: 1140, https://arxiv.org/pdf/2511.01617.pdf GitHub

Abstract:
In the retrieval domain, candidates' fusion from heterogeneous retrievers is a long-standing challenge, particularly for complex, multi-modal data such as videos. While typical fusion techniques are training-free, they rely solely on rank or score signals, disregarding candidates' representations. This work introduces Vote-in-Context (ViC), a generalized, training-free framework that re-thinks list-wise reranking and fusion as a zero-shot reasoning task for a Vision-Language Model (VLM). The core insight is to serialize both content evidence and retriever metadata directly within the VLM's prompt, allowing the model to adaptively weigh retriever consensus against visual-linguistic content. We demonstrate the generality of this framework by applying it to the challenging domain of cross-modal video retrieval. To this end, we introduce the S-Grid, a compact serialization map that represents each video as an image grid, optionally paired with subtitles to enable list-wise reasoning over video candidates. ViC is evaluated both as a single-list reranker, where it dramatically improves the precision of individual retrievers, and as an ensemble fuser, where it consistently outperforms strong baselines like CombSUM. Across video retrieval benchmarks including ActivityNet and VATEX, the framework establishes new state-of-the-art zero-shot retrieval performance, demonstrating its effectiveness in handling complex visual and temporal signals alongside text. In zero-shot settings, ViC achieves Recall@1 scores of 87.1% (t2v) / 89.0% (v2t) on MSR-VTT and 99.6% (v2t) on VATEX, representing massive gains of up to +40 Recall@1 over previous state-of-the-art baselines. We present ViC as a simple, reproducible, and highly effective recipe for turning modern VLMs into powerful zero-shot rerankers and fusers. Code and resources are publicly available at: https://github.com/mohammad2012191/ViC

Paperid: 1141, https://arxiv.org/pdf/2511.01613.pdf GitHub

Abstract:
Progress in anatomical 3D shape classification is limited by the complexity of mesh data and the lack of standardized benchmarks, highlighting the need for robust learning methods and reproducible evaluation. We introduce two key steps toward clinically and benchmark-ready anatomical shape classification via self-supervised graph autoencoding. We propose Precomputed Structural Pooling (PSPooling), a non-learnable mesh pooling operator designed for efficient and structure-preserving graph coarsening in 3D anatomical shape analysis. PSPooling precomputes node correspondence sets based on geometric proximity, enabling parallelizable and reversible pooling and unpooling operations with guaranteed support structure. This design avoids the sparsity and reconstruction issues of selection-based methods and the sequential overhead of edge contraction approaches, making it particularly suitable for high-resolution medical meshes. To demonstrate its effectiveness, we integrate PSPooling into a self-supervised graph autoencoder that learns anatomy-aware representations from unlabeled surface meshes. We evaluate the downstream benefits on MedShapeNet19, a new curated benchmark dataset we derive from MedShapeNet, consisting of 19 anatomical classes with standardized training, validation, and test splits. Experiments show that PSPooling significantly improves reconstruction fidelity and classification accuracy in low-label regimes, establishing a strong baseline for medical 3D shape learning. We hope that MedShapeNet19 will serve as a widely adopted benchmark for anatomical shape classification and further research in medical 3D shape analysis. Access the complete codebase, model weights, and dataset information here: https://github.com/TomasKrsicka/MedShapeNet19-PSPooling.

Paperid: 1142, https://arxiv.org/pdf/2511.01555.pdf GitHub

Abstract:
Introduction: Epigenomic datasets from high-throughput sequencing experiments are commonly summarized as genomic intervals. As the volume of this data grows, so does interest in analyzing it through deep learning. However, the heterogeneity of genomic interval data, where each dataset defines its own regions, creates barriers for machine learning methods that require consistent, discrete vocabularies. Methods: We introduce gtars-tokenizers, a high-performance library that maps genomic intervals to a predefined universe or vocabulary of regions, analogous to text tokenization in natural language processing. Built in Rust with bindings for Python, R, CLI, and WebAssembly, gtars-tokenizers implements two overlap methods (BITS and AIList) and integrates seamlessly with modern ML frameworks through Hugging Face-compatible APIs. Results: The gtars-tokenizers package achieves top efficiency for large-scale datasets, while enabling genomic intervals to be processed using standard ML workflows in PyTorch and TensorFlow without ad hoc preprocessing. This token-based approach bridges genomics and machine learning, supporting scalable and standardized analysis of interval data across diverse computational environments. Availability: PyPI and GitHub: https://github.com/databio/gtars.

Paperid: 1143, https://arxiv.org/pdf/2511.01541.pdf GitHub

Abstract:
Rare and challenging driving scenarios are critical for autonomous vehicle development. Since they are difficult to encounter, simulating or generating them using generative models is a popular approach. Following previous efforts to structure driving scenario representations in a layer model, we propose a structured five-layer model to improve the evaluation and generation of rare scenarios. We use this model alongside large foundational models to generate new driving scenarios using a data augmentation strategy. Unlike previous representations, our structure introduces subclasses and characteristics for every agent of the scenario, allowing us to compare them using an embedding specific to our layer-model. We study and adapt two metrics to evaluate the relevance of a synthetic dataset in the context of a structured representation: the diversity score estimates how different the scenarios of a dataset are from one another, while the originality score calculates how similar a synthetic dataset is from a real reference set. This paper showcases both metrics in different generation setup, as well as a qualitative evaluation of synthetic videos generated from structured scenario descriptions. The code and extended results can be found at https://github.com/Valgiz/5LMSG.

Paperid: 1144, https://arxiv.org/pdf/2511.01527.pdf GitHub

Abstract:
Large language model (LLM) agents have exhibited strong problem-solving competence across domains like research and coding. Yet, it remains underexplored whether LLM agents can tackle compounding real-world problems that require a diverse set of tools to complete. Given a broad, heterogeneous tool repository, LLM agents must not only select appropriate tools based on task planning analysis but also strategically schedule the execution order to ensure efficiency. This paper introduces TPS-Bench to benchmark the ability of LLM agents in solving such problems that demand Tool Planning and Scheduling. TPS-Bench collects 200 compounding tasks of two difficulty levels, based on a tool repository containing hundreds of model context protocol (MCP) tools. In particular, each task is composed of multiple subtasks, such as web search, map navigation, calendar checking, etc., and each subtask can be completed by a basic tool. Our evaluation emphasizes both task completion rate and efficiency. The empirical studies on popular closed-source and open-source LLMs indicate that most models can perform reasonable tool planning, but differ in scheduling. For example, GLM-4.5 achieves an outperforming task completion rate of 64.72% with extensive sequential tool calls, hence suffering from significantly long execution time. By contrast, GPT-4o prioritizes parallel tool calls but achieves only a 45.08% completion rate. Considering reinforcement learning (RL) can be a viable way to improve the scheduling efficiency without compromising performance, we perform an initial study on Qwen3-1.7B and witness a 14% reduction in execution time alongside a 6% gain in task completion rate based on rarely 100 RL training samples. Our code is available https://github.com/hanwenxu1/mcp-agent.

Paperid: 1145, https://arxiv.org/pdf/2511.01517.pdf GitHub

Abstract:
Current text conditioned image generation methods output realistic looking images, but they fail to capture specific styles. Simply finetuning them on the target style datasets still struggles to grasp the style features. In this work, we present a novel contrastive learning framework to improve the stylization capability of large text-to-image diffusion models. Motivated by the astonishing advance in image generation models that makes synthetic data an intrinsic part of model training in various computer vision tasks, we exploit synthetic image generation in our approach. Usually, the generated synthetic data is dependent on the task, and most of the time it is used to enlarge the available real training dataset. With NSYNC, alternatively, we focus on generating negative synthetic sets to be used in a novel contrastive training scheme along with real positive images. In our proposed training setup, we forward negative data along with positive data and obtain negative and positive gradients, respectively. We then refine the positive gradient by subtracting its projection onto the negative gradient to get the orthogonal component, based on which the parameters are updated. This orthogonal component eliminates the trivial attributes that are present in both positive and negative data and directs the model towards capturing a more unique style. Experiments on various styles of painters and illustrators show that our approach improves the performance over the baseline methods both quantitatively and qualitatively. Our code is available at https://github.com/giddyyupp/NSYNC.

Paperid: 1146, https://arxiv.org/pdf/2511.01498.pdf GitHub

Abstract:
Person re-identification (ReID) plays a pivotal role in computer vision, particularly in surveillance and security applications within IoT-enabled smart environments. This study introduces the Enhanced Pedestrian Alignment Network (EPAN), tailored for robust ReID across diverse IoT surveillance conditions. EPAN employs a dual-branch architecture to mitigate the impact of perspective and environmental changes, extracting alignment information under varying scales and viewpoints. Here, we demonstrate EPAN's strong feature extraction capabilities, achieving outstanding performance on the Inspection-Personnel dataset with a Rank-1 accuracy of 90.09% and a mean Average Precision (mAP) of 78.82%. This highlights EPAN's potential for real-world IoT applications, enabling effective and reliable person ReID across diverse cameras in surveillance and security systems. The code and data are available at: https://github.com/ggboy2580/EPAN

Paperid: 1147, https://arxiv.org/pdf/2511.01468.pdf GitHub

Abstract:
Data Assimilation is a cornerstone of atmospheric system modeling, tasked with reconstructing system states by integrating sparse, noisy observations with prior estimation. While traditional approaches like variational and ensemble Kalman filtering have proven effective, recent advances in deep learning offer more scalable, efficient, and flexible alternatives better suited for complex, real-world data assimilation involving large-scale and multi-modal observations. However, existing deep learning-based DA research suffers from two critical limitations: (1) reliance on oversimplified scenarios with synthetically perturbed observations, and (2) the absence of standardized benchmarks for fair model comparison. To address these gaps, in this work, we introduce DAMBench, the first large-scale multi-modal benchmark designed to evaluate data-driven DA models under realistic atmospheric conditions. DAMBench integrates high-quality background states from state-of-the-art forecasting systems and real-world multi-modal observations (i.e., real-world weather stations and satellite imagery). All data are resampled to a common grid and temporally aligned to support systematic training, validation, and testing. We provide unified evaluation protocols and benchmark representative data assimilation approaches, including latent generative models and neural process frameworks. Additionally, we propose a lightweight multi-modal plugin to demonstrate how integrating realistic observations can enhance even simple baselines. Through comprehensive experiments, DAMBench establishes a rigorous foundation for future research, promoting reproducibility, fair comparison, and extensibility to real-world multi-modal scenarios. Our dataset and code are publicly available at https://github.com/figerhaowang/DAMBench.

Paperid: 1148, https://arxiv.org/pdf/2511.01458.pdf GitHub

Abstract:
Safety and reliability are essential for deploying Visual Question Answering (VQA) in surgery, where incorrect or ambiguous responses can harm the patient. Most surgical VQA research focuses on accuracy or linguistic quality while overlooking safety behaviors such as ambiguity awareness, referral to human experts, or triggering a second opinion. Inspired by Automatic Failure Detection (AFD), we study uncertainty estimation as a key enabler of safer decision making. We introduce Question Aligned Semantic Nearest Neighbor Entropy (QA-SNNE), a black box uncertainty estimator that incorporates question semantics into prediction confidence. It measures semantic entropy by comparing generated answers with nearest neighbors in a medical text embedding space, conditioned on the question. We evaluate five models, including domain specific Parameter-Efficient Fine-Tuned (PEFT) models and zero-shot Large Vision-Language Models (LVLMs), on EndoVis18-VQA and PitVQA. PEFT models degrade under mild paraphrasing, while LVLMs are more resilient. Across three LVLMs and two PEFT baselines, QA-SNNE improves AUROC in most in-template settings and enhances hallucination detection. The Area Under the ROC Curve (AUROC) increases by 15-38% for zero-shot models, with gains maintained under out-of-template stress. QA-SNNE offers a practical and interpretable step toward AFD in surgical VQA by linking semantic uncertainty to question context. Combining LVLM backbones with question aligned uncertainty estimation can improve safety and clinician trust. The code and model are available at https://github.com/DennisPierantozzi/QASNNE

Paperid: 1149, https://arxiv.org/pdf/2511.01448.pdf GitHub

Abstract:
Large Language Model (LLM) agents exhibit remarkable conversational and reasoning capabilities but remain constrained by limited context windows and the lack of persistent memory. Recent efforts address these limitations via external memory architectures, often employing graph-based representations, yet most adopt flat, entangled structures that intertwine semantics with topology, leading to redundant representations, unstructured retrieval, and degraded efficiency and accuracy. To resolve these issues, we propose LiCoMemory, an end-to-end agentic memory framework for real-time updating and retrieval, which introduces CogniGraph, a lightweight hierarchical graph that utilizes entities and relations as semantic indexing layers, and employs temporal and hierarchy-aware search with integrated reranking for adaptive and coherent knowledge retrieval. Experiments on long-term dialogue benchmarks, LoCoMo and LongMemEval, show that LiCoMemory not only outperforms established baselines in temporal reasoning, multi-session consistency, and retrieval efficiency, but also notably reduces update latency. Our official code and data are available at https://github.com/EverM0re/LiCoMemory.

Paperid: 1150, https://arxiv.org/pdf/2511.01417.pdf GitHub

Abstract:
Operational Design Domains (ODDs) define the conditions under which an Automated Driving System (ADS) is allowed to operate, while Current Operational Domains (CODs) capture the actual runtime situation. Ensuring that a COD instance lies within the ODD is a crucial step in safety assurance. Today, ODD and COD specifications are frequently expressed in YAML to remain accessible for stakeholders, but such descriptions are not directly suitable for solver-based verification. Manual translation into formal languages such as SMT-LIB is slow and error-prone. We present VeriODD, a tool that automates this translation. VeriODD uses ANTLR-based compiler technology to transform YAML-based ODD/COD specifications into both human-readable propositional logic, for lightweight review on a simple basis, and solver-ready SMT-LIB. The tool integrates with SMT solvers such as Z3 to provide automated consistency checks of ODD specifications and verification of COD conformance. A graphical user interface supports editing specifications, inspecting generated formulas, and performing verification with a single click. VeriODD thereby closes the gap between stakeholder-friendly ODD/COD notations and formal verification, enabling scalable and automated assurance of operational boundaries in autonomous driving. Video demonstration: https://youtu.be/odRacNoL_Pk Tool available at: https://github.com/BasselRafie/VeriODD

Paperid: 1151, https://arxiv.org/pdf/2511.01390.pdf GitHub

Abstract:
Fine-grained cross-modal alignment aims to establish precise local correspondences between vision and language, forming a cornerstone for visual question answering and related multimodal applications. Current approaches face challenges in addressing patch redundancy and ambiguity, which arise from the inherent information density disparities across modalities. Recently, Multimodal Large Language Models (MLLMs) have emerged as promising solutions to bridge this gap through their robust semantic generation capabilities. However, the dense textual outputs from MLLMs may introduce conflicts with the original sparse captions. Furthermore, accurately quantifying semantic relevance between rich visual patches and concise textual descriptions remains a core challenge. To overcome these limitations, we introduce the Semantic-Enhanced Patch Slimming (SEPS) framework, which systematically addresses patch redundancy and ambiguity. Our approach employs a two-stage mechanism to integrate unified semantics from both dense and sparse texts, enabling the identification of salient visual patches. Additionally, it leverages relevance-aware selection with mean value computation to highlight crucial patch-word correspondences, thereby improving cross-modal similarity assessment. Comprehensive experiments on Flickr30K and MS-COCO datasets validate that SEPS achieves superior performance, surpassing existing approaches by 23\%-86\% in rSum across diverse model architectures, with notable enhancements in text-to-image retrieval scenarios. Our implementation is available at https://github.com/Sweet4tars/seps.git.

Paperid: 1152, https://arxiv.org/pdf/2511.01376.pdf GitHub

Abstract:
The mode of a collection of values (i.e., the most frequent value in the collection) is a key summary statistic. Finding the mode in a given range of an array of values is thus of great importance, and constructing a data structure to solve this problem is in fact the well-known Range Mode problem. In this work, we introduce the Subtree Mode (SM) problem, the analogous problem in a leaf-colored tree, where the task is to compute the most frequent color in the leaves of the subtree of a given node. SM is motivated by several applications in domains such as text analytics and biology, where the data are hierarchical and can thus be represented as a (leaf-colored) tree. Our central contribution is a time-optimal algorithm for SM that computes the answer for every node of an input $N$-node tree in $O(N)$ time. We further show how our solution can be adapted for node-colored trees, or for computing the $k$ most frequent colors, in the optimal $O(N)$ time, for any given $k=O(1)$. Moreover, we prove that a similarly fast solution for when the input is a sink-colored directed acyclic graph instead of a leaf-colored tree is highly unlikely. Our experiments on real datasets with trees of up to 7.3 billion nodes demonstrate that our algorithm is faster than baselines by at least one order of magnitude and much more space efficient. Last, we present case studies showing the effectiveness of our approach in pattern mining and sequence-to-database search applications.

Paperid: 1153, https://arxiv.org/pdf/2511.01374.pdf GitHub

Abstract:
Traditional continuous deep reinforcement learning (RL) algorithms employ deterministic or unimodal Gaussian actors, which cannot express complex multimodal decision distributions. This limitation can hinder their performance in diversity-critical scenarios. There have been some attempts to design online multimodal RL algorithms based on diffusion or amortized actors. However, these actors are intractable, making existing methods struggle with balancing performance, decision diversity, and efficiency simultaneously. To overcome this challenge, we first reformulate existing intractable multimodal actors within a unified framework, and prove that they can be directly optimized by policy gradient via reparameterization. Then, we propose a distance-based diversity regularization that does not explicitly require decision probabilities. We identify two diversity-critical domains, namely multi-goal achieving and generative RL, to demonstrate the advantages of multimodal policies and our method, particularly in terms of few-shot robustness. In conventional MuJoCo benchmarks, our algorithm also shows competitive performance. Moreover, our experiments highlight that the amortized actor is a promising policy model class with strong multimodal expressivity and high performance. Our code is available at https://github.com/PneuC/DrAC

Paperid: 1154, https://arxiv.org/pdf/2511.01359.pdf GitHub

Abstract:
Natural Language Inference (NLI) models have been used in various ways to improve the factuality of LLM outputs. This is typically done by applying an NLI model to judge whether the model output is entailed from the supposed evidence, triggering some corrective actions, such as beam reranking at inference time or RL rewards during training. While NLI models are trained to detect factual inconsistencies over complete sentences, decisions in the common autoregressive generation architecture are made for each evolving text prefix, during decoding. Addressing this setting, we generalize the entailment detection task to apply over arbitrary text prefixes, and suggest its utility for improving generation faithfulness. Providing suitable evaluation and training datasets for this task, we train MiniTruePrefixes, a novel specialized model that better detects factual inconsistencies over text prefixes, outperforming comparable baseline NLI models by 5-14 F1 points in prefix-level entailment. We further demonstrate that integrating MiniTruePrefixes into a controlled decoding framework substantially improves factual consistency in abstractive summarization. When guided by MiniTruePrefixes, LLaMA-3.2-3B-Instruct matches the faithfulness and runtime of the 8B model from the same model family, while using only half the memory.

Paperid: 1155, https://arxiv.org/pdf/2511.01357.pdf GitHub

Abstract:
Medical visual question answering (Med-VQA) is a crucial multimodal task in clinical decision support and telemedicine. Recent self-attention based methods struggle to effectively handle cross-modal semantic alignments between vision and language. Moreover, classification-based methods rely on predefined answer sets. Treating this task as a simple classification problem may make it unable to adapt to the diversity of free-form answers and overlook the detailed semantic information of free-form answers. In order to tackle these challenges, we introduce a Cross-Mamba Interaction based Multi-Task Learning (CMI-MTL) framework that learns cross-modal feature representations from images and texts. CMI-MTL comprises three key modules: fine-grained visual-text feature alignment (FVTA), cross-modal interleaved feature representation (CIFR), and free-form answer-enhanced multi-task learning (FFAE). FVTA extracts the most relevant regions in image-text pairs through fine-grained visual-text feature alignment. CIFR captures cross-modal sequential interactions via cross-modal interleaved feature representation. FFAE leverages auxiliary knowledge from open-ended questions through free-form answer-enhanced multi-task learning, improving the model's capability for open-ended Med-VQA. Experimental results show that CMI-MTL outperforms the existing state-of-the-art methods on three Med-VQA datasets: VQA-RAD, SLAKE, and OVQA. Furthermore, we conduct more interpretability experiments to prove the effectiveness. The code is publicly available at https://github.com/BioMedIA-repo/CMI-MTL.

Paperid: 1156, https://arxiv.org/pdf/2511.01318.pdf GitHub

Abstract:
The stock market is a complex and dynamic system, where it is non-trivial for researchers and practitioners to uncover underlying patterns and forecast stock movements. The existing studies for stock market analysis rely on leveraging various types of information to extract useful factors, which are highly conditional on the quality of the data used. However, the currently available resources are mainly based on the U.S. stock market in English, which is inapplicable to adapt to other countries. To address these issues, we propose CSMD, a multimodal dataset curated specifically for analyzing the Chinese stock market with meticulous processing for validated quality. In addition, we develop a lightweight and user-friendly framework LightQuant for researchers and practitioners with expertise in financial domains. Experimental results on top of our datasets and framework with various backbone models demonstrate their effectiveness compared with using existing datasets. The datasets and code are publicly available at the link: https://github.com/ECNU-CILAB/LightQuant.

Paperid: 1157, https://arxiv.org/pdf/2511.01315.pdf GitHub

Abstract:
Robust feature representations are essential for learning-based Multi-View Stereo (MVS), which relies on accurate feature matching. Recent MVS methods leverage Transformers to capture long-range dependencies based on local features extracted by conventional feature pyramid networks. However, the quadratic complexity of Transformer-based MVS methods poses challenges to balance performance and efficiency. Motivated by the global modeling capability and linear complexity of the Mamba architecture, we propose MVSMamba, the first Mamba-based MVS network. MVSMamba enables efficient global feature aggregation with minimal computational overhead. To fully exploit Mamba's potential in MVS, we propose a Dynamic Mamba module (DM-module) based on a novel reference-centered dynamic scanning strategy, which enables: (1) Efficient intra- and inter-view feature interaction from the reference to source views, (2) Omnidirectional multi-view feature representations, and (3) Multi-scale global feature aggregation. Extensive experimental results demonstrate MVSMamba outperforms state-of-the-art MVS methods on the DTU dataset and the Tanks-and-Temples benchmark with both superior performance and efficiency. The source code is available at https://github.com/JianfeiJ/MVSMamba.

Paperid: 1158, https://arxiv.org/pdf/2511.01307.pdf GitHub

Abstract:
Recent advances in diffusion models have enabled high-quality synthesis of specific subjects, such as identities or objects. This capability, while unlocking new possibilities in content creation, also introduces significant privacy risks, as personalization techniques can be misused by malicious users to generate unauthorized content. Although several studies have attempted to counter this by generating adversarially perturbed samples designed to disrupt personalization, they rely on unrealistic assumptions and become ineffective in the presence of even a few clean images or under simple image transformations. To address these challenges, we shift the protection target from the images to the diffusion model itself to hinder the personalization of specific subjects, through our novel framework called Anti-Personalized Diffusion Models (APDM). We first provide a theoretical analysis demonstrating that a naive approach of existing loss functions to diffusion models is inherently incapable of ensuring convergence for robust anti-personalization. Motivated by this finding, we introduce Direct Protective Optimization (DPO), a novel loss function that effectively disrupts subject personalization in the target model without compromising generative quality. Moreover, we propose a new dual-path optimization strategy, coined Learning to Protect (L2P). By alternating between personalization and protection paths, L2P simulates future personalization trajectories and adaptively reinforces protection at each step. Experimental results demonstrate that our framework outperforms existing methods, achieving state-of-the-art performance in preventing unauthorized personalization. The code is available at https://github.com/KU-VGI/APDM.

Paperid: 1159, https://arxiv.org/pdf/2511.01304.pdf GitHub

Abstract:
Multiple instance learning (MIL) has been widely used for representing whole-slide pathology images. However, spatial, semantic, and decision entanglements among instances limit its representation and interpretability. To address these challenges, we propose a latent factor grouping-boosted cluster-reasoning instance disentangled learning framework for whole-slide image (WSI) interpretable representation in three phases. First, we introduce a novel positive semi-definite latent factor grouping that maps instances into a latent subspace, effectively mitigating spatial entanglement in MIL. To alleviate semantic entanglement, we employs instance probability counterfactual inference and optimization via cluster-reasoning instance disentangling. Finally, we employ a generalized linear weighted decision via instance effect re-weighting to address decision entanglement. Extensive experiments on multicentre datasets demonstrate that our model outperforms all state-of-the-art models. Moreover, it attains pathologist-aligned interpretability through disentangled representations and a transparent decision-making process.

Paperid: 1160, https://arxiv.org/pdf/2511.01295.pdf GitHub

Abstract:
Recent advances in multi-modal generative models have driven substantial improvements in image editing. However, current generative models still struggle with handling diverse and complex image editing tasks that require implicit reasoning, underscoring the need for a comprehensive benchmark to systematically assess their performance across various reasoning scenarios. Existing benchmarks primarily focus on single-object attribute transformation in realistic scenarios, which, while effective, encounter two key challenges: (1) they largely overlook multi-object interactions as well as game-world scenarios that involve human-defined rules, which are common in real-life applications; (2) they only rely on textual references to evaluate the generated images, potentially leading to systematic misjudgments, especially in complex reasoning scenarios. To this end, this work proposes UniREditBench, a unified benchmark for reasoning-based image editing evaluation. It comprises 2,700 meticulously curated samples, covering both real- and game-world scenarios across 8 primary dimensions and 18 sub-dimensions. To improve evaluation reliability, we introduce multimodal dual-reference evaluation, providing both textual and ground-truth image references for each sample assessment. Furthermore, we design an automated multi-scenario data synthesis pipeline and construct UniREdit-Data-100K, a large-scale synthetic dataset with high-quality chain-of-thought (CoT) reasoning annotations. We fine-tune Bagel on this dataset and develop UniREdit-Bagel, demonstrating substantial improvements in both in-domain and out-of-distribution settings. Through thorough benchmarking of both open-source and closed-source image editing models, we reveal their strengths and weaknesses across various aspects.

Paperid: 1161, https://arxiv.org/pdf/2511.01293.pdf GitHub

Abstract:
The increasing realism of generated images has raised significant concerns about their potential misuse, necessitating robust detection methods. Current approaches mainly rely on training binary classifiers, which depend heavily on the quantity and quality of available generated images. In this work, we propose a novel framework that exploits geometric differences between the data manifolds of natural and generated images. To exploit this difference, we employ a pair of functions engineered to yield consistent outputs for natural images but divergent outputs for generated ones, leveraging the property that their gradients reside in mutually orthogonal subspaces. This design enables a simple yet effective detection method: an image is identified as generated if a transformation along its data manifold induces a significant change in the loss value of a self-supervised model pre-trained on natural images. Further more, to address diminishing manifold disparities in advanced generative models, we leverage normalizing flows to amplify detectable differences by extruding generated images away from the natural image manifold. Extensive experiments demonstrate the efficacy of this method. Code is available at https://github.com/tmlr-group/ConV.

Paperid: 1162, https://arxiv.org/pdf/2511.01265.pdf GitHub

Abstract:
This paper investigates the impact of domain specificity on abstractive summarisation of Arabic financial texts using large language models (LLMs). We introduce AraFinNews, the largest publicly available Arabic financial news dataset to date, comprising 212,500 article-headline pairs spanning nearly a decade of reporting from October 2015 to July 2025. Designed as the Arabic equivalent of major English summarisation corpora such as CNN/DailyMail, AraFinNews provides a robust benchmark for evaluating domain-specific language understanding and generation in financial contexts. Using this resource, we evaluate transformer-based models -- including mT5, AraT5, and the domain-adapted FinAraT5 -- to examine how financial-domain pretraining influences factual accuracy, numerical reliability, and stylistic alignment with professional reporting. Experimental results show that domain-adapted models generate more faithful and coherent summaries, particularly in handling quantitative and entity-centric information. The findings highlight the importance of domain-specific adaptation for improving factual consistency and narrative fluency in Arabic financial summarisation. The dataset is freely available for non-commercial research at https://github.com/ArabicNLP-UK/AraFinNews.

Paperid: 1163, https://arxiv.org/pdf/2511.01252.pdf GitHub

Abstract:
In modern software ecosystems, 1-day vulnerabilities pose significant security risks due to extensive code reuse. Identifying vulnerable functions in target binaries alone is insufficient; it is also crucial to determine whether these functions have been patched. Existing methods, however, suffer from limited usability and accuracy. They often depend on the compilation process to extract features, requiring substantial manual effort and failing for certain software. Moreover, they cannot reliably differentiate between code changes caused by patches or compilation variations. To overcome these limitations, we propose Lares, a scalable and accurate method for patch presence testing. Lares introduces Code Slice Semantic Search, which directly extracts features from the patch source code and identifies semantically equivalent code slices in the pseudocode of the target binary. By eliminating the need for the compilation process, Lares improves usability, while leveraging large language models (LLMs) for code analysis and SMT solvers for logical reasoning to enhance accuracy. Experimental results show that Lares achieves superior precision, recall, and usability. Furthermore, it is the first work to evaluate patch presence testing across optimization levels, architectures, and compilers. The datasets and source code used in this article are available at https://github.com/Siyuan-Li201/Lares.

Paperid: 1164, https://arxiv.org/pdf/2511.01203.pdf GitHub

Abstract:
The performance of Large Language Models (LLMs) and the associated dollar costs of API calls can fluctuate over time, potentially invalidating conclusions drawn in prior research. To address this, we propose a Fair Evaluation protocol for Test-Time Compute (FEval-TTC), designed to ensure consistent assessment of test-time compute (TTC) methods, regardless of such fluctuations. FEval-TTC focuses on the evaluation of TTC methods that utilize underlying Chains-of-Thought (CoT). It supports evaluations across multiple LLMs on a diverse set of mathematical and commonsense reasoning datasets. The few-shot prompting and answer extraction processes are standardized across datasets, reducing both time and monetary overhead for researchers. Furthermore, we provide a cost modelling procedure that estimates both the token and dollar cost per query, facilitating equitable comparisons of prevalent TTC methods. We open-source FEval-TTC for public use at https://github.com/networkslab/feval_ttc .

Paperid: 1165, https://arxiv.org/pdf/2511.01200.pdf GitHub

Abstract:
We introduce MoSa, a novel hierarchical motion generation framework for text-driven 3D human motion generation that enhances the Vector Quantization-guided Generative Transformers (VQ-GT) paradigm through a coarse-to-fine scalable generation process. In MoSa, we propose a Multi-scale Token Preservation Strategy (MTPS) integrated into a hierarchical residual vector quantization variational autoencoder (RQ-VAE). MTPS employs interpolation at each hierarchical quantization to effectively retain coarse-to-fine multi-scale tokens. With this, the generative transformer supports Scalable Autoregressive (SAR) modeling, which predicts scale tokens, unlike traditional methods that predict only one token at each step. Consequently, MoSa requires only 10 inference steps, matching the number of RQ-VAE quantization layers. To address potential reconstruction degradation from frequent interpolation, we propose CAQ-VAE, a lightweight yet expressive convolution-attention hybrid VQ-VAE. CAQ-VAE enhances residual block design and incorporates attention mechanisms to better capture global dependencies. Extensive experiments show that MoSa achieves state-of-the-art generation quality and efficiency, outperforming prior methods in both fidelity and speed. On the Motion-X dataset, MoSa achieves an FID of 0.06 (versus MoMask's 0.20) while reducing inference time by 27 percent. Moreover, MoSa generalizes well to downstream tasks such as motion editing, requiring no additional fine-tuning. The code is available at https://mosa-web.github.io/MoSa-web

Paperid: 1166, https://arxiv.org/pdf/2511.01197.pdf GitHub

Abstract:
Private large language model (LLM) inference based on cryptographic primitives offers a promising path towards privacy-preserving deep learning. However, existing frameworks only support dense LLMs like LLaMA-1 and struggle to scale to mixture-of-experts (MoE) architectures. The key challenge comes from securely evaluating the dynamic routing mechanism in MoE layers, which may reveal sensitive input information if not fully protected. In this paper, we propose CryptoMoE, the first framework that enables private, efficient, and accurate inference for MoE-based models. CryptoMoE balances expert loads to protect expert routing information and proposes novel protocols for secure expert dispatch and combine. CryptoMoE also develops a confidence-aware token selection strategy and a batch matrix multiplication protocol to improve accuracy and efficiency further. Extensive experiments on DeepSeekMoE-16.4B, OLMoE-6.9B, and QWenMoE-14.3B show that CryptoMoE achieves $2.8\sim3.5\times$ end-to-end latency reduction and $2.9\sim4.3\times$ communication reduction over a dense baseline with minimum accuracy loss. We also adapt CipherPrune (ICLR'25) for MoE inference and demonstrate CryptoMoE can reduce the communication by up to $4.3 \times$. Code is available at: https://github.com/PKU-SEC-Lab/CryptoMoE.

Paperid: 1167, https://arxiv.org/pdf/2511.01169.pdf GitHub

Abstract:
Computer vision for animals holds great promise for wildlife research but often depends on large-scale data, while existing collection methods rely on controlled capture setups. Recent data-driven approaches show the potential of single-view, non-invasive analysis, yet current animal video datasets are limited--offering as few as 2.4K 15-frame clips and lacking key processing for animal-centric 3D/4D tasks. We introduce an automated pipeline that mines YouTube videos and processes them into object-centric clips, along with auxiliary annotations valuable for downstream tasks like pose estimation, tracking, and 3D/4D reconstruction. Using this pipeline, we amass 30K videos (2M frames)--an order of magnitude more than prior works. To demonstrate its utility, we focus on the 4D quadruped animal reconstruction task. To support this task, we present Animal-in-Motion (AiM), a benchmark of 230 manually filtered sequences with 11K frames showcasing clean, diverse animal motions. We evaluate state-of-the-art model-based and model-free methods on Animal-in-Motion, finding that 2D metrics favor the former despite unrealistic 3D shapes, while the latter yields more natural reconstructions but scores lower--revealing a gap in current evaluation. To address this, we enhance a recent model-free approach with sequence-level optimization, establishing the first 4D animal reconstruction baseline. Together, our pipeline, benchmark, and baseline aim to advance large-scale, markerless 4D animal reconstruction and related tasks from in-the-wild videos. Code and datasets are available at https://github.com/briannlongzhao/Animal-in-Motion.

Paperid: 1168, https://arxiv.org/pdf/2511.01166.pdf GitHub

Abstract:
Large Language Models (LLMs) integrated with agent-based reasoning frameworks have recently shown strong potential for autonomous decision-making and system-level operations. One promising yet underexplored direction is microservice remediation, where the goal is to automatically recover faulty microservice systems. Existing approaches, however, still rely on human-crafted prompts from Site Reliability Engineers (SREs), with LLMs merely converting textual instructions into executable code. To advance research in this area, we introduce MicroRemed, the first benchmark for evaluating LLMs in end-to-end microservice remediation, where models must directly generate executable Ansible playbooks from diagnosis reports to restore system functionality. We further propose ThinkRemed, a multi-agent framework that emulates the reflective and perceptive reasoning of SREs. Experimental results show that MicroRemed presents substantial challenges to current LLMs, while ThinkRemed improves end-to-end remediation performance through iterative reasoning and system reflection. The benchmark is available at https://github.com/LLM4AIOps/MicroRemed.

Paperid: 1169, https://arxiv.org/pdf/2511.01143.pdf GitHub

Abstract:
Early and accurate segmentation of colorectal polyps is critical for reducing colorectal cancer mortality, which has been extensively explored by academia and industry. However, current deep learning-based polyp segmentation models either compromise clinical decision-making by providing ambiguous polyp margins in segmentation outputs or rely on heavy architectures with high computational complexity, resulting in insufficient inference speeds for real-time colorectal endoscopic applications. To address this problem, we propose MicroAUNet, a light-weighted attention-based segmentation network that combines depthwise-separable dilated convolutions with a single-path, parameter-shared channel-spatial attention block to strengthen multi-scale boundary features. On the basis of it, a progressive two-stage knowledge-distillation scheme is introduced to transfer semantic and boundary cues from a high-capacity teacher. Extensive experiments on benchmarks also demonstrate the state-of-the-art accuracy under extremely low model complexity, indicating that MicroAUNet is suitable for real-time clinical polyp segmentation. The code is publicly available at https://github.com/JeremyXSC/MicroAUNet.

Paperid: 1170, https://arxiv.org/pdf/2511.01104.pdf GitHub

Abstract:
Existing LLM-based automatic test generation methods mainly produce input and expected output pairs to categorize the intended behavior of correct programs. Although straightforward, these methods have limited diversity in generated tests and cannot provide enough debugging information. We propose HarnessLLM, a two-stage training pipeline that enables LLMs to write harness code for testing. Particularly, LLMs generate code that synthesizes inputs and validates the observed outputs, allowing complex test cases and flexible output validation such as invariant checking. To achieve this, we train LLMs with SFT followed by RLVR with a customized reward design. Experiments show that HarnessLLM outperforms input-output-based testing in bug finding and testing strategy diversity. HarnessLLM further benefits the code generation performance through test-time scaling with our generated test cases as inference-phase validation. Our code is available at https://github.com/UCSB-NLP-Chang/HarnessLLM.git.

Paperid: 1171, https://arxiv.org/pdf/2511.01082.pdf GitHub

Abstract:
Image geolocalization, the task of determining an image's geographic origin, poses significant challenges, largely due to visual similarities across disparate locations and the large search space. To address these issues, we propose a hierarchical sequence prediction approach inspired by how humans narrow down locations from broad regions to specific addresses. Analogously, our model predicts geographic tokens hierarchically, first identifying a general region and then sequentially refining predictions to increasingly precise locations. Rather than relying on explicit semantic partitions, our method uses S2 cells, a nested, multiresolution global grid, and sequentially predicts finer-level cells conditioned on visual inputs and previous predictions. This procedure mirrors autoregressive text generation in large language models. Much like in language modeling, final performance depends not only on training but also on inference-time strategy. We investigate multiple top-down traversal methods for autoregressive sampling, incorporating techniques from test-time compute scaling used in language models. Specifically, we integrate beam search and multi-sample inference while exploring various selection strategies to determine the final output. This enables the model to manage uncertainty by exploring multiple plausible paths through the hierarchy. We evaluate our method on the Im2GPS3k and YFCC4k datasets against two distinct sets of baselines: those that operate without a Multimodal Large Language Model (MLLM) and those that leverage one. In the MLLM-free setting, our model surpasses other comparable baselines on nearly all metrics, achieving state-of-the-art performance with accuracy gains of up to 13.9%. When augmented with an MLLM, our model outperforms all baselines, setting a new state-of-the-art across all metrics. The source code is available at https://github.com/NNargesNN/GeoToken.

Paperid: 1172, https://arxiv.org/pdf/2511.01017.pdf GitHub

Abstract:
This study develops a SARIMAX-based prediction system for short-term power outage forecasting during extreme weather events. Using hourly data from Michigan counties with outage counts and comprehensive weather features, we implement a systematic two-stage feature engineering pipeline: data cleaning to remove zero-variance and unknown features, followed by correlation-based filtering to eliminate highly correlated predictors. The selected features are augmented with temporal embeddings, multi-scale lag features, and weather variables with their corresponding lags as exogenous inputs to the SARIMAX model. To address data irregularity and numerical instability, we apply standardization and implement a hierarchical fitting strategy with sequential optimization methods, automatic downgrading to ARIMA when convergence fails, and historical mean-based fallback predictions as a final safeguard. The model is optimized separately for short-term (24 hours) and medium-term (48 hours) forecast horizons using RMSE as the evaluation metric. Our approach achieves an RMSE of 177.2, representing an 8.4\% improvement over the baseline method (RMSE = 193.4), thereby validating the effectiveness of our feature engineering and robust optimization strategy for extreme weather-related outage prediction.

Paperid: 1173, https://arxiv.org/pdf/2511.01016.pdf GitHub

Abstract:
Recently, advanced large language models (LLMs) have emerged at an increasingly rapid pace. However, when faced with complex problems, most users are often unable to provide accurate and effective prompts to interact with LLMs, thus limiting the performance of LLMs. To address this challenge, we propose Prompt-R1, an end-to-end reinforcement learning framework that uses a small-scale LLM to collaborate with large-scale LLMs, replacing user interaction to solve problems better. This collaboration is cast as a multi-turn prompt interaction, where the small-scale LLM thinks and generates prompts, and the large-scale LLM performs complex reasoning. A dual-constrained reward is designed to optimize for correctness, generation quality, and reasoning accuracy. Prompt-R1 provides a plug-and-play framework that supports both inference and training with various large-scale LLMs. Experiments on multiple public datasets show that Prompt-R1 significantly outperforms baseline models across tasks. Our code is publicly available at https://github.com/QwenQKing/Prompt-R1.

Paperid: 1174, https://arxiv.org/pdf/2511.01008.pdf GitHub

Abstract:
Translating natural language to SQL remains difficult for complex queries. Such queries often need environmental interaction and self-correction. To address this, we introduce MARS-SQL, a novel multi-agent framework that combines principled task decomposition and interactive reinforcement learning (RL). Our system comprises three specialized agents: a Grounding Agent for schema linking, a Generation Agent for query generation, and a Validation Agent for final selection. The core of our framework is the Generation agent, which is trained via a multi-turn RL policy. Adopting a ReAct-style Think-Act-Observe loop, the agent iteratively generates thoughts, executes SQL actions against a live database, and revises its strategy based on execution feedback, enabling dynamic, stateful reasoning and self-correction. At inference time, we generate multiple interaction trajectories to explore diverse reasoning paths. The Validation agent, then selects the optimal trajectory by modeling verification as a next-token prediction task and choosing the solution with the highest generation probability. This structured workflow pipelines specialized agents. It combines interactive RL for generation with generative modeling for verification. The approach proves highly effective for robust and accurate SQL generation. Experiments show that MARS-SQL achieves state-of-the-art Execution Accuracy of 77.84% on the BIRD dev set and 89.75% on the Spider test set. Our code is available at https://github.com/YangHaolin0526/MARS-SQL.

Paperid: 1175, https://arxiv.org/pdf/2511.00998.pdf GitHub

Abstract:
Recently, effective coordination in embodied multi-agent systems has remained a fundamental challenge, particularly in scenarios where agents must balance individual perspectives with global environmental awareness. Existing approaches often struggle to balance fine-grained local control with comprehensive scene understanding, resulting in limited scalability and compromised collaboration quality. In this paper, we present GauDP, a novel Gaussian-image synergistic representation that facilitates scalable, perception-aware imitation learning in multi-agent collaborative systems. Specifically, GauDP constructs a globally consistent 3D Gaussian field from decentralized RGB observations, then dynamically redistributes 3D Gaussian attributes to each agent's local perspective. This enables all agents to adaptively query task-critical features from the shared scene representation while maintaining their individual viewpoints. This design facilitates both fine-grained control and globally coherent behavior without requiring additional sensing modalities (e.g., 3D point cloud). We evaluate GauDP on the RoboFactory benchmark, which includes diverse multi-arm manipulation tasks. Our method achieves superior performance over existing image-based methods and approaches the effectiveness of point-cloud-driven methods, while maintaining strong scalability as the number of agents increases.

Paperid: 1176, https://arxiv.org/pdf/2511.00988.pdf GitHub

Abstract:
Existing machine-generated text (MGT) detection methods implicitly assume labels as the "golden standard". However, we reveal boundary ambiguity in MGT detection, implying that traditional training paradigms are inexact. Moreover, limitations of human cognition and the superintelligence of detectors make inexact learning widespread and inevitable. To this end, we propose an easy-to-hard enhancement framework to provide reliable supervision under such inexact conditions. Distinct from knowledge distillation, our framework employs an easy supervisor targeting relatively simple longer-text detection tasks (despite weaker capabilities), to enhance the more challenging target detector. Firstly, longer texts targeted by supervisors theoretically alleviate the impact of inexact labels, laying the foundation for reliable supervision. Secondly, by structurally incorporating the detector into the supervisor, we theoretically model the supervisor as a lower performance bound for the detector. Thus, optimizing the supervisor indirectly optimizes the detector, ultimately approximating the underlying "golden" labels. Extensive experiments across diverse practical scenarios, including cross-LLM, cross-domain, mixed text, and paraphrase attacks, demonstrate the framework's significant detection effectiveness. The code is available at: https://github.com/tmlr-group/Easy2Hard.

Paperid: 1177, https://arxiv.org/pdf/2511.00962.pdf GitHub

Abstract:
Most video-anomaly research stops at frame-wise detection, offering little insight into why an event is abnormal, typically outputting only frame-wise anomaly scores without spatial or semantic context. Recent video anomaly localization and video anomaly understanding methods improve explainability but remain data-dependent and task-specific. We propose a unified reasoning framework that bridges the gap between temporal detection, spatial localization, and textual explanation. Our approach is built upon a chained test-time reasoning process that sequentially connects these tasks, enabling holistic zero-shot anomaly analysis without any additional training. Specifically, our approach leverages intra-task reasoning to refine temporal detections and inter-task chaining for spatial and semantic understanding, yielding improved interpretability and generalization in a fully zero-shot manner. Without any additional data or gradients, our method achieves state-of-the-art zero-shot performance across multiple video anomaly detection, localization, and explanation benchmarks. The results demonstrate that careful prompt design with task-wise chaining can unlock the reasoning power of foundation models, enabling practical, interpretable video anomaly analysis in a fully zero-shot manner. Project Page: https://rathgrith.github.io/Unified_Frame_VAA/.

Paperid: 1178, https://arxiv.org/pdf/2511.00924.pdf GitHub

Abstract:
Large language models (LLMs) show promise for supporting clinicians in diagnostic communication by generating explanations and guidance for patients. Yet their ability to produce outputs that are both understandable and empathetic remains uncertain. We evaluate two leading LLMs on medical diagnostic scenarios, assessing understandability using readability metrics as a proxy and empathy through LLM-as-a-Judge ratings compared to human evaluations. The results indicate that LLMs adapt explanations to socio-demographic variables and patient conditions. However, they also generate overly complex content and display biased affective empathy, leading to uneven accessibility and support. These patterns underscore the need for systematic calibration to ensure equitable patient communication. The code and data are released: https://github.com/Jeffateth/Biased_Oracle

Paperid: 1179, https://arxiv.org/pdf/2511.00859.pdf GitHub

Abstract:
In autonomous driving, transparency in the decision-making of perception models is critical, as even a single misperception can be catastrophic. Yet with multi-sensor inputs, it is difficult to determine how each modality contributes to a prediction because sensor information becomes entangled within the fusion network. We introduce Layer-Wise Modality Decomposition (LMD), a post-hoc, model-agnostic interpretability method that disentangles modality-specific information across all layers of a pretrained fusion model. To our knowledge, LMD is the first approach to attribute the predictions of a perception model to individual input modalities in a sensor-fusion system for autonomous driving. We evaluate LMD on pretrained fusion models under camera-radar, camera-LiDAR, and camera-radar-LiDAR settings for autonomous driving. Its effectiveness is validated using structured perturbation-based metrics and modality-wise visual decompositions, demonstrating practical applicability to interpreting high-capacity multimodal architectures. Code is available at https://github.com/detxter-jvb/Layer-Wise-Modality-Decomposition.

Paperid: 1180, https://arxiv.org/pdf/2511.00833.pdf GitHub

Abstract:
Vision Transformers (ViTs) have become a universal backbone for both image recognition and image generation. Yet their Multi-Head Self-Attention (MHSA) layer still performs a quadratic query-key interaction for every token pair, spending the bulk of computation on visually weak or redundant correlations. We introduce Visual-Contrast Attention (VCA), a drop-in replacement for MHSA that injects an explicit notion of discrimination while reducing the theoretical complexity from O(N N C) to O(N n C) with n << N. VCA first distils each head's dense query field into a handful of spatially pooled visual-contrast tokens, then splits them into a learnable positive and negative stream whose differential interaction highlights what truly separates one region from another. The module adds fewer than 0.3M parameters to a DeiT-Tiny backbone, requires no extra FLOPs, and is wholly architecture-agnostic. Empirically, VCA lifts DeiT-Tiny top-1 accuracy on ImageNet-1K from 72.2% to 75.6% (+3.4) and improves three strong hierarchical ViTs by up to 3.1%, while in class-conditional ImageNet generation it lowers FID-50K by 2.1 to 5.2 points across both diffusion (DiT) and flow (SiT) models. Extensive ablations confirm that (i) spatial pooling supplies low-variance global cues, (ii) dual positional embeddings are indispensable for contrastive reasoning, and (iii) combining the two in both stages yields the strongest synergy. VCA therefore offers a simple path towards faster and sharper Vision Transformers. The source code is available at https://github.com/LeapLabTHU/LinearDiff.

Paperid: 1181, https://arxiv.org/pdf/2511.00810.pdf GitHub

Abstract:
Graphical user interface (GUI) grounding is a key function of computer-use agents, which maps natural-language instructions to actionable screen regions. Existing approaches based on Multimodal Large Language Models (MLLMs) typically formulate it as a text-based coordinate generation task, yet directly generating precise coordinates from visual inputs remains challenging and computationally intensive. An intuitive way to implement GUI grounding is to first select visual patches relevant to the instructions and then determine the precise click location within those patches. Based on the observations that general MLLMs have some native grounding capability, nested within their attentions, we propose GUI-AIMA, an attention-based and coordinate-free supervised fine-tuning framework for efficient GUI grounding. GUI-AIMA aligns the intrinsic multimodal attention of MLLMs with patch-wise grounding signals. These signals are calculated adaptively for diverse user instructions by multi-head aggregation on simplified query-visual attention matrices. Besides, its coordinate-free manner can easily integrate a plug-and-play zoom-in stage. GUI-AIMA-3B was trained with only 85k screenshots, demonstrating exceptional data efficiency and verifying that light training can trigger the native grounding capability of MLLMs. It achieves state-of-the-art performance among 3B models, attaining an average accuracy of 59.6% on ScreenSpot-Pro, 63.8% on OSWorld-G and 91.5% on ScreenSpot-v2. Project page: https://github.com/sjz5202/GUI-AIMA

Paperid: 1182, https://arxiv.org/pdf/2511.00807.pdf GitHub

Abstract:
The ever-increasing computation and energy demand for LLM and AI agents call for holistic and efficient optimization of LLM serving systems. In practice, heterogeneous GPU clusters can be deployed in a geographically distributed manner, while LLM load also observes diversity in terms of both query traffic and serving patterns. LLM queries running on advanced GPUs during a high-emission hour at one location can lead to significantly higher carbon footprints versus same queries running on mid-level GPUs at a low-emission time and location. By observing LLM serving requirements and leveraging spatiotemporal computation flexibility, we consider the joint routing and scheduling problem, and propose FREESH to cooperatively run a group of data centers while minimizing user-specified carbon or energy objectives. FREESH identifies the optimal configurations of balanced load serving by matching distinct GPU instance's power-throughput characteristics with predictable LLM query length and workloads. To ensure both latency and fairness requirements, FREESH identifies optimized parallelism and query routing schedules together with dynamic GPU frequency scaling for power saving, and Least-Laxity-First (LLF) serving strategy for query scheduling. During the 1-hour serving on production workloads, FREESH reduces energy by 28.6% and emissions by 45.45% together with improvements in SLO attainment and fairness.

Paperid: 1183, https://arxiv.org/pdf/2511.00801.pdf GitHub

Abstract:
Medical image editing has emerged as a pivotal technology with broad applications in data augmentation, model interpretability, medical education, and treatment simulation. However, the lack of large-scale, high-quality, and openly accessible datasets tailored for medical contexts with strict anatomical and clinical constraints has significantly hindered progress in this domain. To bridge this gap, we introduce Med-Banana-50K, a comprehensive dataset of over 50k medically curated image edits spanning chest X-ray, brain MRI, and fundus photography across 23 diseases. Each sample supports bidirectional lesion editing (addition and removal) and is constructed using Gemini-2.5-Flash-Image based on real clinical images. A key differentiator of our dataset is the medically grounded quality control protocol: we employ an LLM-as-Judge evaluation framework with criteria such as instruction compliance, structural plausibility, image realism, and fidelity preservation, alongside iterative refinement over up to five rounds. Additionally, Med-Banana-50K includes around 37,000 failed editing attempts with full evaluation logs to support preference learning and alignment research. By offering a large-scale, medically rigorous, and fully documented resource, Med-Banana-50K establishes a critical foundation for developing and evaluating reliable medical image editing systems. Our dataset and code are publicly available. [https://github.com/richardChenzhihui/med-banana-50k].

Paperid: 1184, https://arxiv.org/pdf/2511.00792.pdf GitHub

Abstract:
Eigenvalue problems have a distinctive forward-inverse structure and are fundamental to characterizing a system's thermal response, stability, and natural modes. Physics-Informed Neural Networks (PINNs) offer a mesh-free alternative for solving such problems but are often orders of magnitude slower than classical numerical schemes. In this paper, we introduce a reformulated PINN approach that casts the search for eigenpairs as a biconvex optimization problem, enabling fast and provably convergent alternating convex search (ACS) over eigenvalues and eigenfunctions using analytically optimal updates. Numerical experiments show that PINN-ACS attains high accuracy with convergence speeds up to 500$\times$ faster than gradient-based PINN training. We release our codes at https://github.com/NeurIPS-ML4PS-2025/PINN_ACS_CODES.

Paperid: 1185, https://arxiv.org/pdf/2511.00782.pdf GitHub

Abstract:
Structured electronic health records (EHR) are essential for clinical prediction. While count-based learners continue to perform strongly on such data, no benchmarking has directly compared them against more recent mixture-of-agents LLM pipelines, which have been reported to outperform single LLMs in various NLP tasks. In this study, we evaluated three categories of methodologies for EHR prediction using the EHRSHOT dataset: count-based models built from ontology roll-ups with two time bins, based on LightGBM and the tabular foundation model TabPFN; a pretrained sequential transformer (CLMBR); and a mixture-of-agents pipeline that converts tabular histories to natural-language summaries followed by a text classifier. We assessed eight outcomes using the EHRSHOT dataset. Across the eight evaluation tasks, head-to-head wins were largely split between the count-based and the mixture-of-agents methods. Given their simplicity and interpretability, count-based models remain a strong candidate for structured EHR benchmarking. The source code is available at: https://github.com/cristea-lab/Structured_EHR_Benchmark.

Paperid: 1186, https://arxiv.org/pdf/2511.00716.pdf GitHub

Abstract:
The increasing frequency of heavy rainfall events, which are a major cause of urban flooding, underscores the urgent need for accurate precipitation forecasting - particularly in urban areas where localized events often go undetected by ground-based sensors. In Germany, only 17.3% of hourly heavy rain events between 2001 and 2018 were recorded by rain gauges, highlighting the limitations of traditional monitoring systems. Radar data are another source that effectively tracks ongoing precipitation; however, forecasting the development of heavy rain using radar alone remains challenging due to the brief and unpredictable nature of such events. Our focus is on evaluating the effectiveness of fusing satellite and radar data for nowcasting. We develop a multimodal nowcasting model that combines both radar and satellite imagery for predicting precipitation at lead times of 5, 15, and 30 minutes. We demonstrate that this multimodal strategy significantly outperforms radar-only approaches. Experimental results show that integrating satellite data improves prediction accuracy, particularly for intense precipitation. The proposed model increases the Critical Success Index for heavy rain by 4% and for violent rain by 3% at a 5-minute lead time. Moreover, it maintains higher predictive skill at longer lead times, where radar-only performance declines. A qualitative analysis of the severe flooding event in the state of North Rhine-Westphalia, Germany in 2021 further illustrates the superior performance of the multimodal model. Unlike the radar-only model, which captures general precipitation patterns, the multimodal model yields more detailed and accurate forecasts for regions affected by heavy rain. This improved precision enables timely, reliable, life-saving warnings. Implementation available at https://github.com/RamaKassoumeh/Multimodal_heavy_rain

Paperid: 1187, https://arxiv.org/pdf/2511.00702.pdf GitHub

Abstract:
Doctors and researchers routinely use diffusion tensor imaging (DTI) and tractography to visualize the fibrous structure of tissues in the human body. This paper explores the connection of these techniques to the painterly rendering of images. Using a tractography algorithm the presented method can place brush strokes that mimic the painting process of human artists, analogously to how fibres are tracked in DTI. The analogue to the diffusion tensor for image orientation is the structural tensor, which can provide better local orientation information than the gradient alone. I demonstrate this technique in portraits and general images, and discuss the parallels between fibre tracking and brush stroke placement, and frame it in the language of tractography. This work presents an exploratory investigation into the cross-domain application of diffusion tensor imaging techniques to painterly rendering of images. All the code is available at https://github.com/tito21/st-python

Paperid: 1188, https://arxiv.org/pdf/2511.00663.pdf GitHub

Abstract:
Sensitivity analysis is a cornerstone of climate science, essential for understanding phenomena ranging from storm intensity to long-term climate feedbacks. However, computing these sensitivities using traditional physical models is often prohibitively expensive in terms of both computation and development time. While modern AI-based generative models are orders of magnitude faster to evaluate, computing sensitivities with them remains a significant bottleneck. This work addresses this challenge by applying the adjoint state method for calculating gradients in generative flow models. We apply this method to the cBottle generative model, trained on ERA5 and ICON data, to perform sensitivity analysis of any atmospheric variable with respect to sea surface temperatures. We quantitatively validate the computed sensitivities against the model's own outputs. Our results provide initial evidence that this approach can produce reliable gradients, reducing the computational cost of sensitivity analysis from weeks on a supercomputer with a physical model to hours on a GPU, thereby simplifying a critical workflow in climate science. The code can be found at https://github.com/Kwartzl8/cbottle_adjoint_sensitivity.

Paperid: 1189, https://arxiv.org/pdf/2511.00657.pdf GitHub

Abstract:
Most multilingual question-answering benchmarks, while covering a diverse pool of languages, do not factor in regional diversity in the information they capture and tend to be Western-centric. This introduces a significant gap in fairly evaluating multilingual models' comprehension of factual information from diverse geographical locations. To address this, we introduce XNationQA for investigating the cultural literacy of multilingual LLMs. XNationQA encompasses a total of 49,280 questions on the geography, culture, and history of nine countries, presented in seven languages. We benchmark eight standard multilingual LLMs on XNationQA and evaluate them using two novel transference metrics. Our analyses uncover a considerable discrepancy in the models' accessibility to culturally specific facts across languages. Notably, we often find that a model demonstrates greater knowledge of cultural information in English than in the dominant language of the respective culture. The models exhibit better performance in Western languages, although this does not necessarily translate to being more literate for Western countries, which is counterintuitive. Furthermore, we observe that models have a very limited ability to transfer knowledge across languages, particularly evident in open-source models.

Paperid: 1190, https://arxiv.org/pdf/2511.00635.pdf GitHub

Abstract:
As various 3D light detection and ranging (LiDAR) sensors have been introduced to the market, research on multi-session simultaneous localization and mapping (MSS) using heterogeneous LiDAR sensors has been actively conducted. Existing MSS methods mostly rely on loop closure detection for inter-session alignment; however, the performance of loop closure detection can be potentially degraded owing to the differences in the density and field of view (FoV) of the sensors used in different sessions. In this study, we challenge the existing paradigm that relies heavily on loop detection modules and propose a novel MSS framework, called Multi-Mapcher, that employs large-scale map-to-map registration to perform inter-session initial alignment, which is commonly assumed to be infeasible, by leveraging outlier-robust 3D point cloud registration. Next, after finding inter-session loops by radius search based on the assumption that the inter-session initial alignment is sufficiently precise, anchor node-based robust pose graph optimization is employed to build a consistent global map. As demonstrated in our experiments, our approach shows substantially better MSS performance for various LiDAR sensors used to capture the sessions and is faster than state-of-the-art approaches. Our code is available at https://github.com/url-kaist/multi-mapcher.

Paperid: 1191, https://arxiv.org/pdf/2511.00624.pdf GitHub

Abstract:
The rapid development of Large Language Models (LLMs) has transformed software engineering, showing promise in tasks like code generation, bug detection, and compliance checking. However, current models struggle to detect compliance violations in Android applications across diverse legal frameworks. We propose \emph{CompliBench}, a novel evaluation framework for assessing LLMs' ability to detect compliance violations under regulations like LGPD, PDPA, and PIPEDA. The framework defines two tasks: Task 1 evaluates \emph{retrieval and localization} at file, module, and line granularities, and Task 2 assesses \emph{multi-label judgment} for code snippets. These tasks mirror the audit process, where auditors locate problematic code and determine implicated provisions. Traditional metrics fail to capture important aspects like cross-granularity stability and jurisdictional consistency. Thus, we introduce stability-aware composites (SGS, RCS, CRGS, and OCS) for a more comprehensive assessment. Experiments with six models, including GPT-4O and Claude-3.5, show \emph{CompliBench} improves compliance detection, with Claude-3.5-sonnet-20241022 achieving the highest OCS score (0.3295), and Gemini-2.5-pro the lowest (0.0538). This work demonstrates \emph{CompliBench}'s potential for improving LLM performance in compliance tasks and provides a foundation for future tools aligned with data protection standards. Our project is available at https://github.com/Haoyi-Zhang/CompliBench.

Paperid: 1192, https://arxiv.org/pdf/2511.00619.pdf GitHub

Abstract:
Automating the detection of EU General Data Protection Regulation (GDPR) violations in source code is a critical but underexplored challenge. We introduce \textbf{GDPR-Bench-Android}, the first comprehensive benchmark for evaluating diverse automated methods for GDPR compliance detection in Android applications. It contains \textbf{1951} manually annotated violation instances from \textbf{15} open-source repositories, covering 23 GDPR articles at file-, module-, and line-level granularities. To enable a multi-paradigm evaluation, we contribute \textbf{Formal-AST}, a novel, source-code-native formal method that serves as a deterministic baseline. We define two tasks: (1) \emph{multi-granularity violation localization}, evaluated via Accuracy@\textit{k}; and (2) \emph{snippet-level multi-label classification}, assessed by macro-F1 and other classification metrics. We benchmark 11 methods, including eight state-of-the-art LLMs, our Formal-AST analyzer, a retrieval-augmented (RAG) method, and an agentic (ReAct) method. Our findings reveal that no single paradigm excels across all tasks. For Task 1, the ReAct agent achieves the highest file-level Accuracy@1 (17.38%), while the Qwen2.5-72B LLM leads at the line level (61.60%), in stark contrast to the Formal-AST method's 1.86%. For the difficult multi-label Task 2, the Claude-Sonnet-4.5 LLM achieves the best Macro-F1 (5.75%), while the RAG method yields the highest Macro-Precision (7.10%). These results highlight the task-dependent strengths of different automated approaches and underscore the value of our benchmark in diagnosing their capabilities. All resources are available at: https://github.com/Haoyi-Zhang/GDPR-Bench-Android.

Paperid: 1193, https://arxiv.org/pdf/2511.00598.pdf GitHub

Abstract:
Registration of optical and synthetic aperture radar (SAR) remote sensing images serves as a critical foundation for image fusion and visual navigation tasks. This task is particularly challenging because of their modal discrepancy, primarily manifested as severe nonlinear radiometric differences (NRD), geometric distortions, and noise variations. Under large geometric transformations, existing classical template-based and sparse keypoint-based strategies struggle to achieve reliable registration results for optical-SAR image pairs. To address these limitations, we propose GDROS, a geometry-guided dense registration framework leveraging global cross-modal image interactions. First, we extract cross-modal deep features from optical and SAR images through a CNN-Transformer hybrid feature extraction module, upon which a multi-scale 4D correlation volume is constructed and iteratively refined to establish pixel-wise dense correspondences. Subsequently, we implement a least squares regression (LSR) module to geometrically constrain the predicted dense optical flow field. Such geometry guidance mitigates prediction divergence by directly imposing an estimated affine transformation on the final flow predictions. Extensive experiments have been conducted on three representative datasets WHU-Opt-SAR dataset, OS dataset, and UBCv2 dataset with different spatial resolutions, demonstrating robust performance of our proposed method across different imaging resolutions. Qualitative and quantitative results show that GDROS significantly outperforms current state-of-the-art methods in all metrics. Our source code will be released at: https://github.com/Zi-Xuan-Sun/GDROS.

Paperid: 1194, https://arxiv.org/pdf/2511.00574.pdf GitHub

Abstract:
Understanding probabilistic relationships among variables is crucial for analyzing complex systems. Traditional structure learning methods often require extensive observational data and incur high computational costs. Recent studies have explored using large language models (LLMs) for structure learning, but most treat LLMs as auxiliary tools for pre-processing or post-processing, leaving the core learning process data-driven. In this work, we propose a unified framework for Bayesian network structure discovery that places LLMs at the center, supporting both data-free and data-aware settings. In the data-free case, we introduce \textbf{PromptBN} to query LLMs with metadata and efficiently uncover valid probabilistic relationships. When observational data are available, we introduce \textbf{ReActBN}, which integrates the ReAct reasoning paradigm with structure scores such as the Bayesian Information Criterion (BIC) for iterative refinement. Unlike prior methods that offload refinement to external algorithms, our framework maintains the LLM actively in the loop throughout the discovery process. Experiments demonstrate that our method significantly outperforms both existing LLM-based approaches and traditional data-driven algorithms, particularly in the low- or no-data scenario. Code is publicly available at {\texttt{\textcolor{magenta}{https://github.com/sherryzyh/prompt2bn}}}.

Paperid: 1195, https://arxiv.org/pdf/2511.00556.pdf GitHub

Abstract:
Large language models (LLMs) remain vulnerable to jailbreaking attacks despite their impressive capabilities. Investigating these weaknesses is crucial for robust safety mechanisms. Existing attacks primarily distract LLMs by introducing additional context or adversarial tokens, leaving the core harmful intent unchanged. In this paper, we introduce ISA (Intent Shift Attack), which obfuscates LLMs about the intent of the attacks. More specifically, we establish a taxonomy of intent transformations and leverage them to generate attacks that may be misperceived by LLMs as benign requests for information. Unlike prior methods relying on complex tokens or lengthy context, our approach only needs minimal edits to the original request, and yields natural, human-readable, and seemingly harmless prompts. Extensive experiments on both open-source and commercial LLMs show that ISA achieves over 70% improvement in attack success rate compared to direct harmful prompts. More critically, fine-tuning models on only benign data reformulated with ISA templates elevates success rates to nearly 100%. For defense, we evaluate existing methods and demonstrate their inadequacy against ISA, while exploring both training-free and training-based mitigation strategies. Our findings reveal fundamental challenges in intent inference for LLMs safety and underscore the need for more effective defenses. Our code and datasets are available at https://github.com/NJUNLP/ISA.

Paperid: 1196, https://arxiv.org/pdf/2511.00555.pdf GitHub

Abstract:
Integrating generative models with action chunking has shown significant promise in imitation learning for robotic manipulation. However, the existing diffusion-based paradigm often struggles to capture strong temporal dependencies across multiple steps, particularly when incorporating proprioceptive input. This limitation can lead to task failures, where the policy overfits to proprioceptive cues at the expense of capturing the visually derived features of the task. To overcome this challenge, we propose the Deep Koopman-boosted Dual-branch Diffusion Policy (D3P) algorithm. D3P introduces a dual-branch architecture to decouple the roles of different sensory modality combinations. The visual branch encodes the visual observations to indicate task progression, while the fused branch integrates both visual and proprioceptive inputs for precise manipulation. Within this architecture, when the robot fails to accomplish intermediate goals, such as grasping a drawer handle, the policy can dynamically switch to execute action chunks generated by the visual branch, allowing recovery to previously observed states and facilitating retrial of the task. To further enhance visual representation learning, we incorporate a Deep Koopman Operator module that captures structured temporal dynamics from visual inputs. During inference, we use the test-time loss of the generative model as a confidence signal to guide the aggregation of the temporally overlapping predicted action chunks, thereby enhancing the reliability of policy execution. In simulation experiments across six RLBench tabletop tasks, D3P outperforms the state-of-the-art diffusion policy by an average of 14.6\%. On three real-world robotic manipulation tasks, it achieves a 15.0\% improvement. Code: https://github.com/dianyeHuang/D3P.

Paperid: 1197, https://arxiv.org/pdf/2511.00542.pdf GitHub

Abstract:
This paper proposes a method for precise learning and synthesizing multi-instance semantics from a single image. The difficulty of this problem lies in the limited training data, and it becomes even more challenging when the instances to be learned have similar semantics or appearance. To address this, we propose a penalty-based attention optimization to disentangle similar semantics during the learning stage. Then, in the synthesis, we introduce and optimize box control in attention layers to further mitigate semantic leakage while precisely controlling the output layout. Experimental results demonstrate that our method achieves disentangled and high-quality semantic learning and synthesis, strikingly balancing editability and instance consistency. Our method remains robust when dealing with semantically or visually similar instances or rare-seen objects. The code is publicly available at https://github.com/Kareneveve/MIFO

Paperid: 1198, https://arxiv.org/pdf/2511.00536.pdf GitHub

Abstract:
Large Reasoning Models (LRMs) are often bottlenecked by the high cost of output tokens. We show that a significant portion of these tokens are useless self-repetitions - what we call "word salad" - that exhaust the decoding budget without adding value. Interestingly, we observe that LRMs are self-aware when trapped in these loops: the hidden states of <\n\n> tokens trailing each reasoning chunk exhibit patterns that allow us to detect word salad behavior on-the-fly via a single-layer linear classifier. Once detected, a simple chop appended by a straightforward regeneration prompt yields substantial length savings with minimal quality loss. Our work offers WordSaladChopper (WSC) - a lightweight, turnkey component for LRM that is minimally invasive to its reasoning trajectory by only removing semantically redundant tokens. Given its low overhead, strong savings, and the lack of semantic value of word salad tokens, we believe it is not too far-fetched to argue that WSC - or a similar component - is a must-have for all LRM applications with user experience in mind. Our code is publicly available at https://github.com/wenyaxie023/WordSaladChopper.

Paperid: 1199, https://arxiv.org/pdf/2511.00521.pdf GitHub

Abstract:
Selecting an appropriate reasoning method for a given query remains a key challenge in language model generation. Existing approaches typically generate multiple candidate responses and use an aggregation strategy to select the output answer, often assuming that more candidate answers yield higher accuracy. We revisit this assumption through a rigorous theoretical analysis, deriving accuracy bounds for standard aggregation methods under fixed generation distributions and candidate sizes. Building on these insights, we introduce EPIC, an Ensemble Planning with Contrastive learning framework to learn a shared representation space that captures both model reasoning abilities and query-method compatibility. EPIC incorporates our probability bounds as a regularizer in a utility-driven optimization that balances accuracy and computational cost. Experiments on diverse mathematical reasoning tasks show that EPIC consistently selects optimal reasoning methods, improving accuracy while reducing computational overhead. Our code can be found at https://github.com/nguyenngocbaocmt02/EPIC.

Paperid: 1200, https://arxiv.org/pdf/2511.00510.pdf GitHub GitHub

Abstract:
This paper investigates Multi-Object Tracking (MOT) in panoramic imagery, which introduces unique challenges including a 360° Field of View (FoV), resolution dilution, and severe view-dependent distortions. Conventional MOT methods designed for narrow-FoV pinhole cameras generalize unsatisfactorily under these conditions. To address panoramic distortion, large search space, and identity ambiguity under a 360° FoV, OmniTrack++ adopts a feedback-driven framework that progressively refines perception with trajectory cues. A DynamicSSM block first stabilizes panoramic features, implicitly alleviating geometric distortion. On top of normalized representations, FlexiTrack Instances use trajectory-informed feedback for flexible localization and reliable short-term association. To ensure long-term robustness, an ExpertTrack Memory consolidates appearance cues via a Mixture-of-Experts design, enabling recovery from fragmented tracks and reducing identity drift. Finally, a Tracklet Management module adaptively switches between end-to-end and tracking-by-detection modes according to scene dynamics, offering a balanced and scalable solution for panoramic MOT. To support rigorous evaluation, we establish the EmboTrack benchmark, a comprehensive dataset for panoramic MOT that includes QuadTrack, captured with a quadruped robot, and BipTrack, collected with a bipedal wheel-legged robot. Together, these datasets span wide-angle environments and diverse motion patterns, providing a challenging testbed for real-world panoramic perception. Extensive experiments on JRDB and EmboTrack demonstrate that OmniTrack++ achieves state-of-the-art performance, yielding substantial HOTA improvements of +25.5% on JRDB and +43.07% on QuadTrack over the original OmniTrack. Datasets and code will be made publicly available at https://github.com/xifen523/OmniTrack.

Paperid: 1201, https://arxiv.org/pdf/2511.00508.pdf GitHub GitHub

Abstract:
Reconstruction of an object from points cloud is essential in prosthetics, medical imaging, computer vision, etc. We present an effective algorithm for an Allen--Cahn-type model of reconstruction, employing the Lagrange multiplier approach. Utilizing scattered data points from an object, we reconstruct a narrow shell by solving the governing equation enhanced with an edge detection function derived from the unsigned distance function. The specifically designed edge detection function ensures the energy stability. By reformulating the governing equation through the Lagrange multiplier technique and implementing a Crank--Nicolson time discretization, we can update the solutions in a stable and decoupled manner. The spatial operations are approximated using the finite difference method, and we analytically demonstrate the unconditional stability of the fully discrete scheme. Comprehensive numerical experiments, including reconstructions of complex 3D volumes such as characters from \textit{Star Wars}, validate the algorithm's accuracy, stability, and effectiveness. Additionally, we analyze how specific parameter selections influence the level of detail and refinement in the reconstructed volumes. To facilitate the interested readers to understand our algorithm, we share the computational codes and data in https://github.com/cfdyang521/C-3PO/tree/main.

Paperid: 1202, https://arxiv.org/pdf/2511.00489.pdf GitHub

Abstract:
Large Language Models (LLMs), constrained by limited context windows, often face significant performance degradation when reasoning over long contexts. To address this, Retrieval-Augmented Generation (RAG) retrieves and reasons over chunks but frequently sacrifices logical coherence due to its reliance on similarity-based rankings. Similarly, divide-and-conquer frameworks (DCF) split documents into small chunks for independent reasoning and aggregation. While effective for local reasoning, DCF struggles to capture long-range dependencies and risks inducing conflicts by processing chunks in isolation. To overcome these limitations, we propose ToM, a novel Tree-oriented MapReduce framework for long-context reasoning. ToM leverages the inherent hierarchical structure of long documents (e.g., main headings and subheadings) by constructing a DocTree through hierarchical semantic parsing and performing bottom-up aggregation. Using a Tree MapReduce approach, ToM enables recursive reasoning: in the Map step, rationales are generated at child nodes; in the Reduce step, these rationales are aggregated across sibling nodes to resolve conflicts or reach consensus at parent nodes. Experimental results on 70B+ LLMs show that ToM significantly outperforms existing divide-and-conquer frameworks and retrieval-augmented generation methods, achieving better logical coherence and long-context reasoning. Our code is available at https://github.com/gjn12-31/ToM .

Paperid: 1203, https://arxiv.org/pdf/2511.00480.pdf GitHub

Abstract:
In this paper, we introduce FedMGP, a new paradigm for personalized federated prompt learning in vision-language models. FedMGP equips each client with multiple groups of paired textual and visual prompts, enabling the model to capture diverse, fine-grained semantic and instance-level cues. A diversity loss is introduced to drive each prompt group to specialize in distinct and complementary semantic aspects, ensuring that the groups collectively cover a broader range of local characteristics. During communication, FedMGP employs a dynamic prompt aggregation strategy based on similarity-guided probabilistic sampling: each client computes the cosine similarity between its prompt groups and the global prompts from the previous round, then samples s groups via a softmax-weighted distribution. This soft selection mechanism preferentially aggregates semantically aligned knowledge while still enabling exploration of underrepresented patterns effectively balancing the preservation of common knowledge with client-specific features. Notably, FedMGP maintains parameter efficiency by redistributing a fixed prompt capacity across multiple groups, achieving state-of-the-art performance with the lowest communication parameters among all federated prompt learning methods. Theoretical analysis shows that our dynamic aggregation strategy promotes robust global representation learning by reinforcing shared semantics while suppressing client-specific noise. Extensive experiments demonstrate that FedMGP consistently outperforms prior approaches in both personalization and domain generalization across diverse federated vision-language benchmarks. The code will be released on https://github.com/weihao-bo/FedMGP.git.

Paperid: 1204, https://arxiv.org/pdf/2511.00469.pdf GitHub

Abstract:
Federated optimization is a constrained form of distributed optimization that enables training a global model without directly sharing client data. Although existing algorithms can guarantee convergence in theory and often achieve stable training in practice, the reasons behind performance degradation under data heterogeneity remain unclear. To address this gap, the main contribution of this paper is to provide a theoretical perspective that explains why such degradation occurs. We introduce the assumption that heterogeneous client data lead to distinct local optima, and show that this assumption implies two key consequences: 1) the distance among clients' local optima raises the lower bound of the global objective, making perfect fitting of all client data impossible; and 2) in the final training stage, the global model oscillates within a region instead of converging to a single optimum, limiting its ability to fully fit the data. These results provide a principled explanation for performance degradation in non-iid settings, which we further validate through experiments across multiple tasks and neural network architectures. The framework used in this paper is open-sourced at: https://github.com/NPCLEI/fedtorch.

Paperid: 1205, https://arxiv.org/pdf/2511.00468.pdf GitHub

Abstract:
Recent advances in generative models have achieved high-fidelity in 3D human reconstruction, yet their utility for specific tasks (e.g., human 3D segmentation) remains constrained. We propose HumanCrafter, a unified framework that enables the joint modeling of appearance and human-part semantics from a single image in a feed-forward manner. Specifically, we integrate human geometric priors in the reconstruction stage and self-supervised semantic priors in the segmentation stage. To address labeled 3D human datasets scarcity, we further develop an interactive annotation procedure for generating high-quality data-label pairs. Our pixel-aligned aggregation enables cross-task synergy, while the multi-task objective simultaneously optimizes texture modeling fidelity and semantic consistency. Extensive experiments demonstrate that HumanCrafter surpasses existing state-of-the-art methods in both 3D human-part segmentation and 3D human reconstruction from a single image.

Paperid: 1206, https://arxiv.org/pdf/2511.00456.pdf GitHub

Abstract:
This study proposes a weakly supervised deep learning framework for pneumonia classification and localization from chest X-rays, utilizing Grad-CAM explanations. Instead of costly pixel-level annotations, our approach uses image-level labels to generate clinically meaningful heatmaps that highlight regions affected by pneumonia. We evaluate seven pre-trained architectures and the Vision Transformer under identical training conditions, using focal loss and patient-wise splits to prevent data leakage. Experimental results suggest that all models achieved high accuracy (96-98%), with ResNet-18 and EfficientNet-B0 showing the best overall performance and MobileNet-V2 providing an efficient lightweight alternative. Grad-CAM heatmap visualizations confirm that the proposed models focus on clinically relevant lung regions, supporting the use of interpretable AI for radiological diagnostics. This work highlights the potential of weakly supervised, explainable models that enhance the transparency of pneumonia screening and clinical trust in AI-assisted screening.

Paperid: 1207, https://arxiv.org/pdf/2511.00446.pdf GitHub

Abstract:
The Contrastive Language-Image Pretraining (CLIP) model has significantly advanced vision-language modeling by aligning image-text pairs from large-scale web data through self-supervised contrastive learning. Yet, its reliance on uncurated Internet-sourced data exposes it to data poisoning and backdoor risks. While existing studies primarily investigate image-based attacks, the text modality, which is equally central to CLIP's training, remains underexplored. In this work, we introduce ToxicTextCLIP, a framework for generating high-quality adversarial texts that target CLIP during the pre-training phase. The framework addresses two key challenges: semantic misalignment caused by background inconsistency with the target class, and the scarcity of background-consistent texts. To this end, ToxicTextCLIP iteratively applies: 1) a background-aware selector that prioritizes texts with background content aligned to the target class, and 2) a background-driven augmenter that generates semantically coherent and diverse poisoned samples. Extensive experiments on classification and retrieval tasks show that ToxicTextCLIP achieves up to 95.83% poisoning success and 98.68% backdoor Hit@1, while bypassing RoCLIP, CleanCLIP and SafeCLIP defenses. The source code can be accessed via https://github.com/xinyaocse/ToxicTextCLIP/.

Paperid: 1208, https://arxiv.org/pdf/2511.00423.pdf GitHub

Abstract:
Online planning has proven effective in reinforcement learning (RL) for improving sample efficiency and final performance. However, using planning for environment interaction inevitably introduces a divergence between the collected data and the policy's actual behaviors, degrading both model learning and policy improvement. To address this, we propose BOOM (Bootstrap Off-policy with WOrld Model), a framework that tightly integrates planning and off-policy learning through a bootstrap loop: the policy initializes the planner, and the planner refines actions to bootstrap the policy through behavior alignment. This loop is supported by a jointly learned world model, which enables the planner to simulate future trajectories and provides value targets to facilitate policy improvement. The core of BOOM is a likelihood-free alignment loss that bootstraps the policy using the planner's non-parametric action distribution, combined with a soft value-weighted mechanism that prioritizes high-return behaviors and mitigates variability in the planner's action quality within the replay buffer. Experiments on the high-dimensional DeepMind Control Suite and Humanoid-Bench show that BOOM achieves state-of-the-art results in both training stability and final performance. The code is accessible at https://github.com/molumitu/BOOM_MBRL.

Paperid: 1209, https://arxiv.org/pdf/2511.00416.pdf GitHub

Abstract:
While AI-generated text (AIGT) detectors achieve over 90\% accuracy on direct LLM outputs, they fail catastrophically against iteratively-paraphrased content. We investigate why iteratively-paraphrased text -- itself AI-generated -- evades detection systems designed for AIGT identification. Through intrinsic mechanism analysis, we reveal that iterative paraphrasing creates an intermediate laundering region characterized by semantic displacement with preserved generation patterns, which brings up two attack categories: paraphrasing human-authored text (authorship obfuscation) and paraphrasing LLM-generated text (plagiarism evasion). To address these vulnerabilities, we introduce PADBen, the first benchmark systematically evaluating detector robustness against both paraphrase attack scenarios. PADBen comprises a five-type text taxonomy capturing the full trajectory from original content to deeply laundered text, and five progressive detection tasks across sentence-pair and single-sentence challenges. We evaluate 11 state-of-the-art detectors, revealing critical asymmetry: detectors successfully identify the plagiarism evasion problem but fail for the case of authorship obfuscation. Our findings demonstrate that current detection approaches cannot effectively handle the intermediate laundering region, necessitating fundamental advances in detection architectures beyond existing semantic and stylistic discrimination methods. For detailed code implementation, please see https://github.com/JonathanZha47/PadBen-Paraphrase-Attack-Benchmark.

Paperid: 1210, https://arxiv.org/pdf/2511.00411.pdf GitHub

Abstract:
Adversarial attacks present a critical challenge to deep neural networks' robustness, particularly in transfer scenarios across different model architectures. However, the transferability of adversarial attacks faces a fundamental dilemma between Exploitation (maximizing attack potency) and Exploration (enhancing cross-model generalization). Traditional momentum-based methods over-prioritize Exploitation, i.e., higher loss maxima for attack potency but weakened generalization (narrow loss surface). Conversely, recent methods with inner-iteration sampling over-prioritize Exploration, i.e., flatter loss surfaces for cross-model generalization but weakened attack potency (suboptimal local maxima). To resolve this dilemma, we propose a simple yet effective Gradient-Guided Sampling (GGS), which harmonizes both objectives through guiding sampling along the gradient ascent direction to improve both sampling efficiency and stability. Specifically, based on MI-FGSM, GGS introduces inner-iteration random sampling and guides the sampling direction using the gradient from the previous inner-iteration (the sampling's magnitude is determined by a random distribution). This mechanism encourages adversarial examples to reside in balanced regions with both flatness for cross-model generalization and higher local maxima for strong attack potency. Comprehensive experiments across multiple DNN architectures and multimodal large language models (MLLMs) demonstrate the superiority of our method over state-of-the-art transfer attacks. Code is made available at https://github.com/anuin-cat/GGS.

Paperid: 1211, https://arxiv.org/pdf/2511.00405.pdf GitHub

Abstract:
The remarkable success of multimodal large language models (MLLMs) has driven advances in multimodal embeddings, yet existing models remain inherently discriminative, limiting their ability to benefit from reasoning-driven generation paradigm. In this work, we pioneer the exploration of generative embeddings, unifying embedding tasks within a generative paradigm. We propose UME-R1, a universal multimodal embedding framework consisting of a two-stage training strategy: a cold-start supervised fine-tuning equips the model with reasoning capabilities and enables it to generate both discriminative and generative embeddings; a subsequent reinforcement learning enhances reasoning and further optimizes generative embedding quality. This pioneering work reveals four key insights: 1) generative embeddings unlock substantial performance gains over conventional discriminative embeddings by leveraging the powerful generative reasoning capabilities of MLLMs; 2) discriminative and generative embeddings are complementary, whose combined oracle performance far exceeding that of either alone; 3) RL can effectively enhance generative embeddings, establishing a scalable optimization paradigm.; 4) repeated sampling at inference boosts downstream task coverage (pass@k), highlighting the inference-time scalability potential of generative embeddings. Evaluated on the MMEB-V2 benchmark across 78 tasks spanning video, image, and visual documents, UME-R1 significantly outperforms conventional discriminative embedding models and offers a foundation for more interpretable, reasoning-driven generative multimodal embeddings. Our code, models, and datasets will be publicly available at https://github.com/XMUDeepLIT/UME-R1.

Paperid: 1212, https://arxiv.org/pdf/2511.00402.pdf GitHub

Abstract:
Emotion recognition from speech plays a vital role in the development of empathetic human-computer interaction systems. This paper presents a comparative analysis of lightweight transformer-based models, DistilHuBERT and PaSST, by classifying six core emotions from the CREMA-D dataset. We benchmark their performance against a traditional CNN-LSTM baseline model using MFCC features. DistilHuBERT demonstrates superior accuracy (70.64%) and F1 score (70.36%) while maintaining an exceptionally small model size (0.02 MB), outperforming both PaSST and the baseline. Furthermore, we conducted an ablation study on three variants of the PaSST, Linear, MLP, and Attentive Pooling heads, to understand the effect of classification head architecture on model performance. Our results indicate that PaSST with an MLP head yields the best performance among its variants but still falls short of DistilHuBERT. Among the emotion classes, angry is consistently the most accurately detected, while disgust remains the most challenging. These findings suggest that lightweight transformers like DistilHuBERT offer a compelling solution for real-time speech emotion recognition on edge devices. The code is available at: https://github.com/luckymaduabuchi/Emotion-detection-.

Paperid: 1213, https://arxiv.org/pdf/2511.00391.pdf GitHub

Abstract:
Multimodal code generation has garnered significant interest within the research community. Despite the notable success of recent vision-language models (VLMs) on specialized tasks like Chart-to-code generation, their reliance on single-task training regimens fosters a narrow paradigm that hinders the development of generalized \textbf{VI}sio\textbf{N} \textbf{C}ode \textbf{I}ntelligence. In this work, we introduce \textbf{VinciCoder}, a unified multimodal code generation model that addresses this limitation via a two-stage training framework. We begin by constructing a large-scale Supervised Finetuning (SFT) corpus comprising 1.6M image-code pairs for tasks involving direct code generation and visual-based code refinement. Subsequently, we introduce a Visual Reinforcement Learning (ViRL) strategy, which employs a coarse-to-fine reward mechanism to improve visual fidelity by calculating visual similarity across local and global image patches. Extensive experiments on various multimodal code generation benchmarks demonstrate that VinciCoder achieves state-of-the-art performance, underscoring the effectiveness of our coarse-to-fine ViRL strategy. The code and model will be available at https://github.com/DocTron-hub/VinciCoder.

Paperid: 1214, https://arxiv.org/pdf/2511.00351.pdf GitHub

Abstract:
Speculative Decoding (SD) ensures that the output matches the target model's distribution exactly. However, we argue that this distribution matching requirement is too stringent and results in unnecessarily low acceptance rates, limiting potential speedups. Instead, we advocate a reformulation of the decoding objective: the proposed decoding strategy should match the expected utility, i.e., the task-specific performance, of the target model. This perspective also aligns better with real-world use cases of LLMs, where utility (e.g., code correctness, factual accuracy) is often more important than sampling distribution. Based on this reformulation, we propose a novel decoding strategy: Pivot-Aware Speculative Decoding, which rejects only those tokens that would lead to a utility drop in the final output. We refer to these critical tokens as pivot tokens. We propose a method for labeling tokens as pivotal or non-pivotal and train a lightweight classifier to detect them. This method can be viewed as a relaxed version of standard SD, which offers much higher acceptance while preserving utility. We evaluate our method across various datasets, demonstrating that we can achieve up to $2.5\times$ speedup with comparable utility. Source code is available at https://github.com/amir-zsh/PAD.

Paperid: 1215, https://arxiv.org/pdf/2511.00345.pdf GitHub

Abstract:
Accurate and up-to-date geospatial data are essential for urban planning, infrastructure monitoring, and environmental management. Yet, automating urban monitoring remains difficult because curated datasets of specific urban features and their changes are scarce. We introduce OSMGen, a generative framework that creates realistic satellite imagery directly from raw OpenStreetMap (OSM) data. Unlike prior work that relies on raster tiles, OSMGen uses the full richness of OSM JSON, including vector geometries, semantic tags, location, and time, giving fine-grained control over how scenes are generated. A central feature of the framework is the ability to produce consistent before-after image pairs: user edits to OSM inputs translate into targeted visual changes, while the rest of the scene is preserved. This makes it possible to generate training data that addresses scarcity and class imbalance, and to give planners a simple way to preview proposed interventions by editing map data. More broadly, OSMGen produces paired (JSON, image) data for both static and changed states, paving the way toward a closed-loop system where satellite imagery can automatically drive structured OSM updates. Source code is available at https://github.com/amir-zsh/OSMGen.

Paperid: 1216, https://arxiv.org/pdf/2511.00318.pdf GitHub

Abstract:
Large Language Models (LLMs) offer a flexible means to generate synthetic tabular data, yet existing approaches often fail to preserve key causal parameters such as the average treatment effect (ATE). In this technical exploration, we first demonstrate that state-of-the-art synthetic data generators, both GAN- and LLM-based, can achieve high predictive fidelity while substantially misestimating causal effects. To address this gap, we propose a hybrid generation framework that combines model-based covariate synthesis (monitored via distance-to-closest-record filtering) with separately learned propensity and outcome models, thereby ensuring that (W, A, Y) triplets retain their underlying causal structure. We further introduce a synthetic pairing strategy to mitigate positivity violations and a realistic evaluation protocol that leverages unlimited synthetic samples to benchmark traditional estimators (IPTW, AIPW, substitution) under complex covariate distributions. This work lays the groundwork for LLM-powered data pipelines that support robust causal analysis. Our code is available at https://github.com/Xyc-arch/llm-synthetic-for-causal-inference.git.

Paperid: 1217, https://arxiv.org/pdf/2511.00306.pdf GitHub

Abstract:
Sliding window-factor graph optimization (SW-FGO) has gained more and more attention in navigation research due to its robust approximation to non-Gaussian noises and nonlinearity of measuring models. There are lots of works focusing on its application performance compared to extended Kalman filter (EKF) but there is still a myth at the theoretical relationship between the SW-FGO and EKF. In this paper, we find the necessarily fair condition to connect SW-FGO and Kalman filter variants (KFV) (e.g., EKF, iterative EKF (IEKF), robust EKF (REKF) and robust iterative EKF (RIEKF)). Based on the conditions, we propose a recursive FGO (Re-FGO) framework to represent KFV under SW-FGO formulation. Under explicit conditions (Markov assumption, Gaussian noise with L2 loss, and a one-state window), Re-FGO regenerates exactly to EKF/IEKF/REKF/RIEKF, while SW-FGO shows measurable benefits in nonlinear, non-Gaussian regimes at a predictable compute cost. Finally, after clarifying the connection between them, we highlight the unique advantages of SW-FGO in practical phases, especially on numerical estimation and deep learning integration. The code and data used in this work is open sourced at https://github.com/Baoshan-Song/KFV-FGO-Comparison.

Paperid: 1218, https://arxiv.org/pdf/2511.00143.pdf GitHub GitHub

Abstract:
Recent advances in text-to-image models have increased the exposure of powerful image editing techniques as a tool, raising concerns about their potential for malicious use. An emerging line of research to address such threats focuses on implanting "protective" adversarial noise into images before their public release, so future attempts to edit them using text-to-image models can be impeded. However, subsequent works have shown that these adversarial noises are often easily "reversed," e.g., with techniques as simple as JPEG compression, casting doubt on the practicality of the approach. In this paper, we argue that adversarial noise for image protection should not only be imperceptible, as has been a primary focus of prior work, but also irreversible, viz., it should be difficult to detect as noise provided that the original image is hidden. We propose a surprisingly simple method to enhance the robustness of image protection methods against noise reversal techniques. Specifically, it applies an adaptive per-region Gaussian blur on the noise to adjust the overall frequency spectrum. Through extensive experiments, we show that our method consistently improves the per-sample worst-case protection performance of existing methods against a wide range of reversal techniques on diverse image editing scenarios, while also reducing quality degradation due to noise in terms of perceptual metrics. Code is available at https://github.com/jsu-kim/BlurGuard.

Paperid: 1219, https://arxiv.org/pdf/2511.00136.pdf GitHub

Abstract:
Leveraging large language models (LLMs) in traffic signal control (TSC) improves optimization efficiency and interpretability compared to traditional reinforcement learning (RL) methods. However, existing LLM-based approaches are limited by fixed time signal durations and are prone to hallucination errors, while RL methods lack robustness in signal timing decisions and suffer from poor generalization. To address these challenges, this paper proposes HeraldLight, a dual LLMs architecture enhanced by Herald guided prompts. The Herald Module extracts contextual information and forecasts queue lengths for each traffic phase based on real-time conditions. The first LLM, LLM-Agent, uses these forecasts to make fine grained traffic signal control, while the second LLM, LLM-Critic, refines LLM-Agent's outputs, correcting errors and hallucinations. These refined outputs are used for score-based fine-tuning to improve accuracy and robustness. Simulation experiments using CityFlow on real world datasets covering 224 intersections in Jinan (12), Hangzhou (16), and New York (196) demonstrate that HeraldLight outperforms state of the art baselines, achieving a 20.03% reduction in average travel time across all scenarios and a 10.74% reduction in average queue length on the Jinan and Hangzhou scenarios. The source code is available on GitHub: https://github.com/BUPT-ANTlab/HeraldLight.

Paperid: 1220, https://arxiv.org/pdf/2511.00119.pdf GitHub

Abstract:
Spatial transcriptomics (ST) technologies can be used to align transcriptomes with histopathological morphology, presenting exciting new opportunities for biomolecular discovery. Using ST data, we construct a novel framework, GeneFlow, to map transcriptomics onto paired cellular images. By combining an attention-based RNA encoder with a conditional UNet guided by rectified flow, we generate high-resolution images with different staining methods (e.g. H&E, DAPI) to highlight various cellular/tissue structures. Rectified flow with high-order ODE solvers creates a continuous, bijective mapping between transcriptomics and image manifolds, addressing the many-to-one relationship inherent in this problem. Our method enables the generation of realistic cellular morphology features and spatially resolved intercellular interactions from observational gene expression profiles, provides potential to incorporate genetic/chemical perturbations, and enables disease diagnosis by revealing dysregulated patterns in imaging phenotypes. Our rectified flow-based method outperforms diffusion-based baseline method in all experiments. Code can be found at https://github.com/wangmengbo/GeneFlow.

Paperid: 1221, https://arxiv.org/pdf/2511.00103.pdf GitHub

Abstract:
Diffusion models have become state-of-the-art generative models for images, audio, and video, yet enabling fine-grained controllable generation, i.e., continuously steering specific concepts without disturbing unrelated content, remains challenging. Concept Sliders (CS) offer a promising direction by discovering semantic directions through textual contrasts, but they require per-concept training and architecture-specific fine-tuning (e.g., LoRA), limiting scalability to new modalities. In this work we introduce FreeSliders, a simple yet effective approach that is fully training-free and modality-agnostic, achieved by partially estimating the CS formula during inference. To support modality-agnostic evaluation, we extend the CS benchmark to include both video and audio, establishing the first suite for fine-grained concept generation control with multiple modalities. We further propose three evaluation properties along with new metrics to improve evaluation quality. Finally, we identify an open problem of scale selection and non-linear traversals and introduce a two-stage procedure that automatically detects saturation points and reparameterizes traversal for perceptually uniform, semantically meaningful edits. Extensive experiments demonstrate that our method enables plug-and-play, training-free concept control across modalities, improves over existing baselines, and establishes new tools for principled controllable generation. An interactive presentation of our benchmark and method is available at: https://azencot-group.github.io/FreeSliders/

Paperid: 1222, https://arxiv.org/pdf/2511.00101.pdf GitHub

Abstract:
Low-Rank Adaptation (LoRA) has become a widely adopted parameter-efficient fine-tuning (PEFT) technique for adapting large language models (LLMs) to downstream tasks. While prior work has explored strategies for integrating LLM training and serving, there still remains a gap in unifying fine-tuning and inference for LoRA-based models. We present Loquetier, a virtualized multi-LoRA framework that seamlessly integrates LoRA fine-tuning and serving within a single runtime. Loquetier introduces two key components: (1) a Virtualized Module that isolates PEFT-based modifications and supports multiple adapters on a shared base model, and (2) an optimized computation flow with a kernel design that merges fine-tuning and inference paths in forward propagation, enabling efficient batching and minimizing kernel invocation overhead. Extensive experiments across three task settings show that Loquetier consistently outperforms existing baselines in both performance and flexibility, achieving up to $3.0\times$ the throughput of the state-of-the-art co-serving system on inference-only tasks and $46.4\times$ higher SLO attainment than PEFT on unified fine-tuning and inference tasks. The implementation of Loquetier is publicly available at https://github.com/NJUDeepEngine/Loquetier.

Paperid: 1223, https://arxiv.org/pdf/2511.00096.pdf GitHub

Abstract:
Urban Artificial Intelligence (Urban AI) has advanced human-centered urban tasks such as perception prediction and human dynamics. Large Language Models (LLMs) can integrate multimodal inputs to address heterogeneous data in complex urban systems but often underperform on domain-specific tasks. Urban-MAS, an LLM-based Multi-Agent System (MAS) framework, is introduced for human-centered urban prediction under zero-shot settings. It includes three agent types: Predictive Factor Guidance Agents, which prioritize key predictive factors to guide knowledge extraction and enhance the effectiveness of compressed urban knowledge in LLMs; Reliable UrbanInfo Extraction Agents, which improve robustness by comparing multiple outputs, validating consistency, and re-extracting when conflicts occur; and Multi-UrbanInfo Inference Agents, which integrate extracted multi-source information across dimensions for prediction. Experiments on running-amount prediction and urban perception across Tokyo, Milan, and Seattle demonstrate that Urban-MAS substantially reduces errors compared to single-LLM baselines. Ablation studies indicate that Predictive Factor Guidance Agents are most critical for enhancing predictive performance, positioning Urban-MAS as a scalable paradigm for human-centered urban AI prediction. Code is available on the project website:https://github.com/THETUREHOOHA/UrbanMAS

Paperid: 1224, https://arxiv.org/pdf/2511.00095.pdf GitHub

Abstract:
The anatomical structure segmentation of the spine and adjacent structures from computed tomography (CT) images is a key step for spinal disease diagnosis and treatment. However, the segmentation of CT images is impeded by low contrast and complex vertebral boundaries. Although advanced models such as the Segment Anything Model (SAM) have shown promise in various segmentation tasks, their performance in spinal CT imaging is limited by high annotation requirements and poor domain adaptability. To address these limitations, we propose SpinalSAM-R1, a multimodal vision-language interactive system that integrates a fine-tuned SAM with DeepSeek-R1, for spine CT image segmentation. Specifically, our SpinalSAM-R1 introduces an anatomy-guided attention mechanism to improve spine segmentation performance, and a semantics-driven interaction protocol powered by DeepSeek-R1, enabling natural language-guided refinement. The SpinalSAM-R1 is fine-tuned using Low-Rank Adaptation (LoRA) for efficient adaptation. We validate our SpinalSAM-R1 on the spine anatomical structure with CT images. Experimental results suggest that our method achieves superior segmentation performance. Meanwhile, we develop a PyQt5-based interactive software, which supports point, box, and text-based prompts. The system supports 11 clinical operations with 94.3\% parsing accuracy and sub-800 ms response times. The software is released on https://github.com/6jm233333/spinalsam-r1.

Paperid: 1225, https://arxiv.org/pdf/2511.00090.pdf GitHub

Abstract:
We present LeMiCa, a training-free and efficient acceleration framework for diffusion-based video generation. While existing caching strategies primarily focus on reducing local heuristic errors, they often overlook the accumulation of global errors, leading to noticeable content degradation between accelerated and original videos. To address this issue, we formulate cache scheduling as a directed graph with error-weighted edges and introduce a Lexicographic Minimax Path Optimization strategy that explicitly bounds the worst-case path error. This approach substantially improves the consistency of global content and style across generated frames. Extensive experiments on multiple text-to-video benchmarks demonstrate that LeMiCa delivers dual improvements in both inference speed and generation quality. Notably, our method achieves a 2.9x speedup on the Latte model and reaches an LPIPS score of 0.05 on Open-Sora, outperforming prior caching techniques. Importantly, these gains come with minimal perceptual quality degradation, making LeMiCa a robust and generalizable paradigm for accelerating diffusion-based video generation. We believe this approach can serve as a strong foundation for future research on efficient and reliable video synthesis. Our code is available at :https://github.com/UnicomAI/LeMiCa

Paperid: 1226, https://arxiv.org/pdf/2511.00085.pdf GitHub

Abstract:
Stock trend prediction is crucial for profitable trading strategies and portfolio management yet remains challenging due to market volatility, complex temporal dynamics and multifaceted inter-stock relationships. Existing methods struggle to effectively capture temporal dependencies and dynamic inter-stock interactions, often neglecting cross-sectional market influences, relying on static correlations, employing uniform treatments of nodes and edges, and conflating diverse relationships. This work introduces MaGNet, a novel Mamba dual-hyperGraph Network for stock prediction, integrating three key innovations: (1) a MAGE block, which leverages bidirectional Mamba with adaptive gating mechanisms for contextual temporal modeling and integrates a sparse Mixture-of-Experts layer to enable dynamic adaptation to diverse market conditions, alongside multi-head attention for capturing global dependencies; (2) Feature-wise and Stock-wise 2D Spatiotemporal Attention modules enable precise fusion of multivariate features and cross-stock dependencies, effectively enhancing informativeness while preserving intrinsic data structures, bridging temporal modeling with relational reasoning; and (3) a dual hypergraph framework consisting of the Temporal-Causal Hypergraph (TCH) that captures fine-grained causal dependencies with temporal constraints, and Global Probabilistic Hypergraph (GPH) that models market-wide patterns through soft hyperedge assignments and Jensen-Shannon Divergence weighting mechanism, jointly disentangling localized temporal influences from instantaneous global structures for multi-scale relational learning. Extensive experiments on six major stock indices demonstrate MaGNet outperforms state-of-the-art methods in both superior predictive performance and exceptional investment returns with robust risk management capabilities. Codes available at: https://github.com/PeilinTime/MaGNet.

Paperid: 1227, https://arxiv.org/pdf/2511.00062.pdf GitHub GitHub

Authors:NVIDIA, :, Arslan Ali, Junjie Bai, Maciej Bala, Yogesh Balaji, Aaron Blakeman, Tiffany Cai, Jiaxin Cao, Tianshi Cao, Elizabeth Cha, Yu-Wei Chao, Prithvijit Chattopadhyay, Mike Chen, Yongxin Chen, Yu Chen, Shuai Cheng, Yin Cui, Jenna Diamond, Yifan Ding, Jiaojiao Fan, Linxi Fan, Liang Feng, Francesco Ferroni, Sanja Fidler, Xiao Fu, Ruiyuan Gao, Yunhao Ge, Jinwei Gu, Aryaman Gupta, Siddharth Gururani, Imad El Hanafi, Ali Hassani, Zekun Hao, Jacob Huffman, Joel Jang, Pooya Jannaty, Jan Kautz, Grace Lam, Xuan Li, Zhaoshuo Li, Maosheng Liao, Chen-Hsuan Lin, Tsung-Yi Lin, Yen-Chen Lin, Huan Ling, Ming-Yu Liu, Xian Liu, Yifan Lu, Alice Luo, Qianli Ma, Hanzi Mao, Kaichun Mo, Seungjun Nah, Yashraj Narang, Abhijeet Panaskar, Lindsey Pavao, Trung Pham, Morteza Ramezanali, Fitsum Reda, Scott Reed, Xuanchi Ren, Haonan Shao, Yue Shen, Stella Shi, Shuran Song, Bartosz Stefaniak, Shangkun Sun, Shitao Tang, Sameena Tasmeen, Lyne Tchapmi, Wei-Cheng Tseng, Jibin Varghese, Andrew Z. Wang, Hao Wang, Haoxiang Wang, Heng Wang, Ting-Chun Wang, Fangyin Wei, Jiashu Xu, Dinghao Yang, Xiaodong Yang, Haotian Ye, Seonghyeon Ye, Xiaohui Zeng, Jing Zhang, Qinsheng Zhang, Kaiwen Zheng, Andrew Zhu, Yuke Zhu

Abstract:
We introduce [Cosmos-Predict2.5], the latest generation of the Cosmos World Foundation Models for Physical AI. Built on a flow-based architecture, [Cosmos-Predict2.5] unifies Text2World, Image2World, and Video2World generation in a single model and leverages [Cosmos-Reason1], a Physical AI vision-language model, to provide richer text grounding and finer control of world simulation. Trained on 200M curated video clips and refined with reinforcement learning-based post-training, [Cosmos-Predict2.5] achieves substantial improvements over [Cosmos-Predict1] in video quality and instruction alignment, with models released at 2B and 14B scales. These capabilities enable more reliable synthetic data generation, policy evaluation, and closed-loop simulation for robotics and autonomous systems. We further extend the family with [Cosmos-Transfer2.5], a control-net style framework for Sim2Real and Real2Real world translation. Despite being 3.5$\times$ smaller than [Cosmos-Transfer1], it delivers higher fidelity and robust long-horizon video generation. Together, these advances establish [Cosmos-Predict2.5] and [Cosmos-Transfer2.5] as versatile tools for scaling embodied intelligence. To accelerate research and deployment in Physical AI, we release source code, pretrained checkpoints, and curated benchmarks under the NVIDIA Open Model License at https://github.com/nvidia-cosmos/cosmos-predict2.5 and https://github.com/nvidia-cosmos/cosmos-transfer2.5. We hope these open resources lower the barrier to adoption and foster innovation in building the next generation of embodied intelligence.

Paperid: 1228, https://arxiv.org/pdf/2511.00056.pdf GitHub

Abstract:
The substantial memory demands of pre-training and fine-tuning large language models (LLMs) require memory-efficient optimization algorithms. One promising approach is layer-wise optimization, which treats each transformer block as a single layer and optimizes it sequentially, while freezing the other layers to save optimizer states and activations. Although effective, these methods ignore the varying importance of the modules within each layer, leading to suboptimal performance. Moreover, layer-wise sampling provides only limited memory savings, as at least one full layer must remain active during optimization. To overcome these limitations, we propose Module-wise Importance SAmpling (MISA), a novel method that divides each layer into smaller modules and assigns importance scores to each module. MISA uses a weighted random sampling mechanism to activate modules, provably reducing gradient variance compared to layer-wise sampling. Additionally, we establish an $\mathcal{O}(1/\sqrt{K})$ convergence rate under non-convex and stochastic conditions, where $K$ is the total number of block updates, and provide a detailed memory analysis showcasing MISA's superiority over existing baseline methods. Experiments on diverse learning tasks validate the effectiveness of MISA. Source code is available at https://github.com/pkumelon/MISA.

Paperid: 1229, https://arxiv.org/pdf/2511.00051.pdf GitHub

Abstract:
Parameter-Efficient Fine-Tuning (PEFT) methods are crucial for adapting large pre-trained models. Among these, LoRA is considered a foundational approach. Building on this, the influential DoRA method enhances performance by decomposing weight updates into magnitude and direction. However, its underlying mechanism remains unclear, and it introduces significant computational overhead. In this work, we first identify that DoRA's success stems from its capacity to increase the singular value entropy of the weight update matrix, which promotes a more uniform update distribution akin to full fine-tuning. We then reformulate DoRA into a mathematically equivalent and more efficient matrix form, revealing it as a learnable weight conditioning method. Based on this insight, we propose a unified framework for designing advanced PEFT methods by exploring two orthogonal dimensions: the architectural placement and the transformation type of the conditioning matrix. Within this framework, we introduce two novel methods: (1) \textbf{Pre-Diag}, which applies a diagonal conditioning matrix before the LoRA update to efficiently calibrate the pre-trained weights, thereby enhancing performance while reducing training time; and (2) \textbf{S}kewed \textbf{O}rthogonal \textbf{R}otation \textbf{A}daptation (\textbf{SORA}), which employs a parameter-efficient orthogonal rotation to perform a more powerful, norm-preserving transformation of the feature space. Extensive experiments on natural language understanding and generation tasks demonstrate that our proposed methods achieve superior performance and efficiency compared to both LoRA and DoRA. The code is available at https://github.com/MaeChd/SORA.