# Research Papers — 2025-11 · bundle page 94 of 197 > Full-text markdown of papers #4651–4700 of 9830 published in 2025-11, newest first. AI-readable mirrors of the full 9830-paper 2025-11 archive (50 papers per file). Canonical page: https://aipod.dev/papers/archive/2025-11/page/94 [← Previous bundle](https://aipod.dev/papers/archive/2025-11/page/93.md) [Next bundle →](https://aipod.dev/papers/archive/2025-11/page/95.md) ### PASE: Leveraging the Phonological Prior of WavLM for Low-Hallucination Generative Speech Enhancement Authors: Xiaobin Rong, Qinwen Hu, Mansur Yesilbursa, Kamil Wojcicki, Jing Lu Published: 2025-11-17 Categories: eess.AS, cs.AI, cs.SD arXiv: https://arxiv.org/abs/2511.13300v1 Generative models have shown remarkable performance in speech enhancement (SE), achieving superior perceptual quality over traditional discriminative approaches. However, existing generative SE approaches often overlook the risk of hallucination under severe noise, leading to incorrect spoken content or inconsistent speaker characteristics, which we term linguistic and acoustic hallucinations, respectively. We argue that linguistic hallucination stems from models' failure to constrain valid phonological structures and it is a more fundamental challenge. While language models (LMs) are well-suited for capturing the underlying speech structure through modeling the distribution of discrete tokens, existing approaches are limited in learning from noise-corrupted representations, which can lead to contaminated priors and hallucinations. To overcome these limitations, we propose the Phonologically Anchored Speech Enhancer (PASE), a generative SE framework that leverages the robust phonological prior embedded in the pre-trained WavLM model to mitigate hallucinations. First, we adapt WavLM into a denoising expert via representation distillation to clean its final-layer features. Guided by the model's intrinsic phonological prior, this process enables robust denoising while minimizing linguistic hallucinations. To further reduce acoustic hallucinations, we train the vocoder with a dual-stream representation: the high-level phonetic representation provides clean linguistic content, while a low-level acoustic representation retains speaker identity and prosody. Experimental results demonstrate that PASE not only surpasses state-of-the-art discriminative models in perceptual quality, but also significantly outperforms prior generative models with substantially lower linguistic and acoustic hallucinations. --- ### CorrectAD: A Self-Correcting Agentic System to Improve End-to-end Planning in Autonomous Driving Authors: Enhui Ma, Lijun Zhou, Tao Tang, Jiahuan Zhang, Junpeng Jiang, Zhan Zhang, Dong Han, Kun Zhan, Xueyang Zhang, XianPeng Lang, Haiyang Sun, Xia Zhou et al. Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13297v1 End-to-end planning methods are the de facto standard of the current autonomous driving system, while the robustness of the data-driven approaches suffers due to the notorious long-tail problem (i.e., rare but safety-critical failure cases). In this work, we explore whether recent diffusion-based video generation methods (a.k.a. world models), paired with structured 3D layouts, can enable a fully automated pipeline to self-correct such failure cases. We first introduce an agent to simulate the role of product manager, dubbed PM-Agent, which formulates data requirements to collect data similar to the failure cases. Then, we use a generative model that can simulate both data collection and annotation. However, existing generative models struggle to generate high-fidelity data conditioned on 3D layouts. To address this, we propose DriveSora, which can generate spatiotemporally consistent videos aligned with the 3D annotations requested by PM-Agent. We integrate these components into our self-correcting agentic system, CorrectAD. Importantly, our pipeline is an end-to-end model-agnostic and can be applied to improve any end-to-end planner. Evaluated on both nuScenes and a more challenging in-house dataset across multiple end-to-end planners, CorrectAD corrects 62.5% and 49.8% of failure cases, reducing collision rates by 39% and 27%, respectively. --- ### Causal Inference, Biomarker Discovery, Graph Neural Network, Feature Selection Authors: Chaowang Lan, Jingxin Wu, Yulong Yuan, Chuxun Liu, Huangyi Kang, Caihua Liu Published: 2025-11-17 Categories: q-bio.QM, cs.LG arXiv: https://arxiv.org/abs/2511.13295v1 Biomarker discovery from high-throughput transcriptomic data is crucial for advancing precision medicine. However, existing methods often neglect gene-gene regulatory relationships and lack stability across datasets, leading to conflation of spurious correlations with genuine causal effects. To address these issues, we develop a causal graph neural network (Causal-GNN) method that integrates causal inference with multi-layer graph neural networks (GNNs). The key innovation is the incorporation of causal effect estimation for identifying stable biomarkers, coupled with a GNN-based propensity scoring mechanism that leverages cross-gene regulatory networks. Experimental results demonstrate that our method achieves consistently high predictive accuracy across four distinct datasets and four independent classifiers. Moreover, it enables the identification of more stable biomarkers compared to traditional methods. Our work provides a robust, efficient, and biologically interpretable tool for biomarker discovery, demonstrating strong potential for broad application across medical disciplines. --- ### Grounded by Experience: Generative Healthcare Prediction Augmented with Hierarchical Agentic Retrieval Authors: Chuang Zhao, Hui Tang, Hongke Zhao, Xiaofang Zhou, Xiaomeng Li Published: 2025-11-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.13293v1 Accurate healthcare prediction is critical for improving patient outcomes and reducing operational costs. Bolstered by growing reasoning capabilities, large language models (LLMs) offer a promising path to enhance healthcare predictions by drawing on their rich parametric knowledge. However, LLMs are prone to factual inaccuracies due to limitations in the reliability and coverage of their embedded knowledge. While retrieval-augmented generation (RAG) frameworks, such as GraphRAG and its variants, have been proposed to mitigate these issues by incorporating external knowledge, they face two key challenges in the healthcare scenario: (1) identifying the clinical necessity to activate the retrieval mechanism, and (2) achieving synergy between the retriever and the generator to craft contextually appropriate retrievals. To address these challenges, we propose GHAR, a \underline{g}enerative \underline{h}ierarchical \underline{a}gentic \underline{R}AG framework that simultaneously resolves when to retrieve and how to optimize the collaboration between submodules in healthcare. Specifically, for the first challenge, we design a dual-agent architecture comprising Agent-Top and Agent-Low. Agent-Top acts as the primary physician, iteratively deciding whether to rely on parametric knowledge or to initiate retrieval, while Agent-Low acts as the consulting service, summarising all task-relevant knowledge once retrieval was triggered. To tackle the second challenge, we innovatively unify the optimization of both agents within a formal Markov Decision Process, designing diverse rewards to align their shared goal of accurate prediction while preserving their distinct roles. Extensive experiments on three benchmark datasets across three popular tasks demonstrate our superiority over state-of-the-art baselines, highlighting the potential of hierarchical agentic RAG in advancing healthcare systems. --- ### Dropouts in Confidence: Moral Uncertainty in Human-LLM Alignment Authors: Jea Kwon, Luiz Felipe Vecchietti, Sungwon Park, Meeyoung Cha Published: 2025-11-17 Categories: cs.AI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2511.13290v1 Humans display significant uncertainty when confronted with moral dilemmas, yet the extent of such uncertainty in machines and AI agents remains underexplored. Recent studies have confirmed the overly confident tendencies of machine-generated responses, particularly in large language models (LLMs). As these systems are increasingly embedded in ethical decision-making scenarios, it is important to understand their moral reasoning and the inherent uncertainties in building reliable AI systems. This work examines how uncertainty influences moral decisions in the classical trolley problem, analyzing responses from 32 open-source models and 9 distinct moral dimensions. We first find that variance in model confidence is greater across models than within moral dimensions, suggesting that moral uncertainty is predominantly shaped by model architecture and training method. To quantify uncertainty, we measure binary entropy as a linear combination of total entropy, conditional entropy, and mutual information. To examine its effects, we introduce stochasticity into models via "dropout" at inference time. Our findings show that our mechanism increases total entropy, mainly through a rise in mutual information, while conditional entropy remains largely unchanged. Moreover, this mechanism significantly improves human-LLM moral alignment, with correlations in mutual information and alignment score shifts. Our results highlight the potential to better align model-generated decisions and human preferences by deliberately modulating uncertainty and reducing LLMs' confidence in morally complex scenarios. --- ### Multi-Agent Deep Research: Training Multi-Agent Systems with M-GRPO Authors: Haoyang Hong, Jiajun Yin, Yuan Wang, Jingnan Liu, Zhe Chen, Ailing Yu, Ji Li, Zhiling Ye, Hansong Xiao, Yefei Chen, Hualei Zhou, Yun Yue et al. Published: 2025-11-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.13288v2 Multi-agent systems perform well on general reasoning tasks. However, the lack of training in specialized areas hinders their accuracy. Current training methods train a unified large language model (LLM) for all agents in the system. This may limit the performances due to different distributions underlying for different agents. Therefore, training multi-agent systems with distinct LLMs should be the next step to solve. However, this approach introduces optimization challenges. For example, agents operate at different frequencies, rollouts involve varying sub-agent invocations, and agents are often deployed across separate servers, disrupting end-to-end gradient flow. To address these issues, we propose M-GRPO, a hierarchical extension of Group Relative Policy Optimization designed for vertical Multi-agent systems with a main agent (planner) and multiple sub-agents (multi-turn tool executors). M-GRPO computes group-relative advantages for both main and sub-agents, maintaining hierarchical credit assignment. It also introduces a trajectory-alignment scheme that generates fixed-size batches despite variable sub-agent invocations. We deploy a decoupled training pipeline in which agents run on separate servers and exchange minimal statistics via a shared store. This enables scalable training without cross-server backpropagation. In experiments on real-world benchmarks (e.g., GAIA, XBench-DeepSearch, and WebWalkerQA), M-GRPO consistently outperforms both single-agent GRPO and multi-agent GRPO with frozen sub-agents, demonstrating improved stability and sample efficiency. These results show that aligning heterogeneous trajectories and decoupling optimization across specialized agents enhances tool-augmented reasoning tasks. --- ### SkyReels-Text: Fine-Grained Font-Controllable Text Editing for Poster Design Authors: Yunjie Yu, Jingchen Wu, Junchen Zhu, Chunze Lin, Guibin Chen Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13285v2 Artistic design, particularly poster design, often demands rapid yet precise modification of textual content while preserving visual harmony and typographic intent, especially across diverse font styles. Although modern image editing models have grown increasingly powerful, they still fall short in fine-grained, font-aware text manipulation, limiting their utility in professional workflows. To address this issue, we present SkyReels-Text, a novel font-controllable framework for precise poster text editing. Our method enables simultaneous editing of multiple text regions, each rendered in distinct typographic styles, while preserving the visual appearance of non-edited regions. Notably, our model requires neither font labels nor test-time fine-tuning: users can simply provide cropped glyph patches corresponding to their desired typography - even if the font is not included in any standard library. Extensive experiments on multiple benchmarks demonstrate that SkyReels-Text achieves state-of-the-art performance in both text fidelity and visual realism, offering unprecedented control over font families and stylistic nuances. This work bridges the gap between general-purpose image editing and professional-grade typographic design. Code and models are publicly available at https://github.com/SkyworkAI/SkyReels-Text. --- ### TabFlash: Efficient Table Understanding with Progressive Question Conditioning and Token Focusing Authors: Jongha Kim, Minseong Bae, Sanghyeok Lee, Jinsung Yoon, Hyunwoo J. Kim Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13283v1 Table images present unique challenges for effective and efficient understanding due to the need for question-specific focus and the presence of redundant background regions. Existing Multimodal Large Language Model (MLLM) approaches often overlook these characteristics, resulting in uninformative and redundant visual representations. To address these issues, we aim to generate visual features that are both informative and compact to improve table understanding. We first propose progressive question conditioning, which injects the question into Vision Transformer layers with gradually increasing frequency, considering each layer's capacity to handle additional information, to generate question-aware visual features. To reduce redundancy, we introduce a pruning strategy that discards background tokens, thereby improving efficiency. To mitigate information loss from pruning, we further propose token focusing, a training strategy that encourages the model to concentrate essential information in the retained tokens. By combining these approaches, we present TabFlash, an efficient and effective MLLM for table understanding. TabFlash achieves state-of-the-art performance, outperforming both open-source and proprietary MLLMs, while requiring 27% less FLOPs and 30% less memory usage compared to the second-best MLLM. --- ### Towards Metric-Aware Multi-Person Mesh Recovery by Jointly Optimizing Human Crowd in Camera Space Authors: Kaiwen Wang, Kaili Zheng, Yiming Shi, Chenyi Guo, Ji Wu Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13282v2 Multi-person human mesh recovery from a single image is a challenging task, hindered by the scarcity of in-the-wild training data. Prevailing in-the-wild human mesh pseudo-ground-truth (pGT) generation pipelines are single-person-centric, where each human is processed individually without joint optimization. This oversight leads to a lack of scene-level consistency, producing individuals with conflicting depths and scales within the same image. To address this, we introduce Depth-conditioned Translation Optimization (DTO), a novel optimization-based method that jointly refines the camera-space translations of all individuals in a crowd. By leveraging anthropometric priors on human height and depth cues from a monocular depth estimator, DTO solves for a scene-consistent placement of all subjects within a principled Maximum a posteriori (MAP) framework. Applying DTO to the 4D-Humans dataset, we construct DTO-Humans, a new large-scale pGT dataset of 0.56M high-quality, scene-consistent multi-person images, featuring dense crowds with an average of 4.8 persons per image. Furthermore, we propose Metric-Aware HMR, an end-to-end network that directly estimates human mesh and camera parameters in metric scale. This is enabled by a camera branch and a relative metric loss that enforces plausible relative scales. Extensive experiments demonstrate that our method achieves state-of-the-art performance on relative depth reasoning and human mesh recovery. Code is available at: https://github.com/gouba2333/MA-HMR. --- ### SF-Recon: Simplification-Free Lightweight Building Reconstruction via 3D Gaussian Splatting Authors: Zihan Li, Tengfei Wang, Wentian Gan, Hao Zhan, Xin Wang, Zongqian Zhan Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13278v2 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/ --- ### Recognition of Abnormal Events in Surveillance Videos using Weakly Supervised Dual-Encoder Models Authors: Noam Tsfaty, Avishai Weizman, Liav Cohen, Moshe Tshuva, Yehudit Aperstein Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13276v1 We address the challenge of detecting rare and diverse anomalies in surveillance videos using only video-level supervision. Our dual-backbone framework combines convolutional and transformer representations through top-k pooling, achieving 90.7% area under the curve (AUC) on the UCF-Crime dataset. --- ### KForge: Program Synthesis for Diverse AI Hardware Accelerators Authors: Taras Sereda, Tom St. John, Burak Bartan, Natalie Serrino, Sachin Katti, Zain Asgar Published: 2025-11-17 Categories: cs.LG, cs.AI, cs.MA, cs.PF, cs.SE arXiv: https://arxiv.org/abs/2511.13274v1 GPU kernels are critical for ML performance but difficult to optimize across diverse accelerators. We present KForge, a platform-agnostic framework built on two collaborative LLM-based agents: a generation agent that produces and iteratively refines programs through compilation and correctness feedback, and a performance analysis agent that interprets profiling data to guide optimization. This agent-based architecture requires only a single-shot example to target new platforms. We make three key contributions: (1) introducing an iterative refinement system where the generation agent and performance analysis agent collaborate through functional and optimization passes, interpreting diverse profiling data (from programmatic APIs to GUI-based tools) to generate actionable recommendations that guide program synthesis for arbitrary accelerators; (2) demonstrating that the generation agent effectively leverages cross-platform knowledge transfer, where a reference implementation from one architecture substantially improves generation quality for different hardware targets; and (3) validating the platform-agnostic nature of our approach by demonstrating effective program synthesis across fundamentally different parallel computing platforms: NVIDIA CUDA and Apple Metal. --- ### AudioMotionBench: Evaluating Auditory Motion Perception in Audio LLMs Authors: Zhe Sun, Yujun Cai, Jiayu Yao, Yiwei Wang Published: 2025-11-17 Categories: cs.SD, cs.AI arXiv: https://arxiv.org/abs/2511.13273v2 Large Audio-Language Models (LALMs) have recently shown impressive progress in speech recognition, audio captioning, and auditory question answering. Yet, whether these models can perceive spatial dynamics, particularly the motion of sound sources, remains unclear. In this work, we uncover a systematic motion perception deficit in current ALLMs. To investigate this issue, we introduce AudioMotionBench, the first benchmark explicitly designed to evaluate auditory motion understanding. AudioMotionBench introduces a controlled question-answering benchmark designed to evaluate whether Audio-Language Models (LALMs) can infer the direction and trajectory of moving sound sources from binaural audio. Comprehensive quantitative and qualitative analyses reveal that current models struggle to reliably recognize motion cues or distinguish directional patterns. The average accuracy remains below 50\%, underscoring a fundamental limitation in auditory spatial reasoning. Our study highlights a fundamental gap between human and model auditory spatial reasoning, providing both a diagnostic tool and new insight for enhancing spatial cognition in future Audio-Language Models. --- ### Examining the Usage of Generative AI Models in Student Learning Activities for Software Programming Authors: Rufeng Chen, Shuaishuai Jiang, Jiyun Shen, AJung Moon, Lili Wei Published: 2025-11-17 Categories: cs.SE, cs.AI, cs.IR arXiv: https://arxiv.org/abs/2511.13271v2 The rise of Generative AI (GenAI) tools like ChatGPT has created new opportunities and challenges for computing education. Existing research has primarily focused on GenAI's ability to complete educational tasks and its impact on student performance, often overlooking its effects on knowledge gains. In this study, we investigate how GenAI assistance compares to conventional online resources in supporting knowledge gains across different proficiency levels. We conducted a controlled user experiment with 24 undergraduate students of two different levels of programming experience (beginner, intermediate) to examine how students interact with ChatGPT while solving programming tasks. We analyzed task performance, conceptual understanding, and interaction behaviors. Our findings reveal that generating complete solutions with GenAI significantly improves task performance, especially for beginners, but does not consistently result in knowledge gains. Importantly, usage strategies differ by experience: beginners tend to rely heavily on GenAI toward task completion often without knowledge gain in the process, while intermediates adopt more selective approaches. We find that both over-reliance and minimal use result in weaker knowledge gains overall. Based on our results, we call on students and educators to adopt GenAI as a learning rather than a problem solving tool. Our study highlights the urgent need for guidance when integrating GenAI into programming education to foster deeper understanding. --- ### Is your VLM Sky-Ready? A Comprehensive Spatial Intelligence Benchmark for UAV Navigation Authors: Lingfeng Zhang, Yuchen Zhang, Hongsheng Li, Haoxiang Fu, Yingbo Tang, Hangjun Ye, Long Chen, Xiaojun Liang, Xiaoshuai Hao, Wenbo Ding Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13269v1 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. --- ### SymGS : Leveraging Local Symmetries for 3D Gaussian Splatting Compression Authors: Keshav Gupta, Akshat Sanghvi, Shreyas Reddy Palley, Astitva Srivastava, Charu Sharma, Avinash Sharma Published: 2025-11-17 Categories: cs.CV, cs.GR arXiv: https://arxiv.org/abs/2511.13264v2 3D Gaussian Splatting has emerged as a transformative technique in novel view synthesis, primarily due to its high rendering speed and photorealistic fidelity. However, its memory footprint scales rapidly with scene complexity, often reaching several gigabytes. Existing methods address this issue by introducing compression strategies that exploit primitive-level redundancy through similarity detection and quantization. We aim to surpass the compression limits of such methods by incorporating symmetry-aware techniques, specifically targeting mirror symmetries to eliminate redundant primitives. We propose a novel compression framework, SymGS, introducing learnable mirrors into the scene, thereby eliminating local and global reflective redundancies for compression. Our framework functions as a plug-and-play enhancement to state-of-the-art compression methods, (e.g. HAC) to achieve further compression. Compared to HAC, we achieve $1.66 \times$ compression across benchmark datasets (upto $3\times$ on large-scale scenes). On an average, SymGS enables $\bf{108\times}$ compression of a 3DGS scene, while preserving rendering quality. The project page and supplementary can be found at symgs.github.io --- ### Case study of a differentiable heterogeneous multiphysics solver for a nuclear fusion application Authors: Jack B. Coughlin, Archis Joglekar, Jonathan Brodrick, Alexander Lavin Published: 2025-11-17 Categories: physics.comp-ph, cs.CE, cs.LG, cs.MS, physics.plasm-ph arXiv: https://arxiv.org/abs/2511.13262v1 This work presents a case study of a heterogeneous multiphysics solver from the nuclear fusion domain. At the macroscopic scale, an auto-differentiable ODE solver in JAX computes the evolution of the pulsed power circuit and bulk plasma parameters for a compressing Z Pinch. The ODE solver requires a closure for the impedance of the plasma load obtained via root-finding at every timestep, which we solve efficiently using gradient-based Newton iteration. However, incorporating non-differentiable production-grade plasma solvers like Gkeyll (a C/CUDA plasma simulation suite) into a gradient-based workflow is non-trivial. The ''Tesseract'' software addresses this challenge by providing a multi-physics differentiable abstraction layer made fully compatible with JAX (through the `tesseract_jax` adapter). This architecture ensures end-to-end differentiability while allowing seamless interchange between high-fidelity solvers (Gkeyll), neural surrogates, and analytical approximations for rapid, progressive prototyping. --- ### Building Egocentric Procedural AI Assistant: Methods, Benchmarks, and Challenges Authors: Junlong Li, Huaiyuan Xu, Sijie Cheng, Kejun Wu, Kim-Hui Yap, Lap-Pui Chau, Yi Wang Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13261v2 Driven by recent advances in vision-language models (VLMs) and egocentric perception research, the emerging topic of an egocentric procedural AI assistant (EgoProceAssist) is introduced to step-by-step support daily procedural tasks in a first-person view. In this paper, we start by identifying three core tasks in EgoProceAssist: egocentric procedural error detection, egocentric procedural learning, and egocentric procedural question answering, then introduce two enabling dimensions: real-time and streaming video understanding, and proactive interaction in procedural contexts. We define these tasks within a new taxonomy as the EgoProceAssist's essential functions and illustrate how they can be deployed in real-world scenarios for daily activity assistants. Specifically, our work encompasses a comprehensive review of current techniques, relevant datasets, and evaluation metrics across these five core areas. To clarify the gap between the proposed EgoProceAssist and existing VLM-based assistants, we conduct novel experiments to provide a comprehensive evaluation of representative VLM-based methods. Through 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. --- ### GeoX-Bench: Benchmarking Cross-View Geo-Localization and Pose Estimation Capabilities of Large Multimodal Models Authors: Yushuo Zheng, Jiangyong Ying, Huiyu Duan, Chunyi Li, Zicheng Zhang, Jing Liu, Xiaohong Liu, Guangtao Zhai Published: 2025-11-17 Categories: cs.CV, cs.AI arXiv: https://arxiv.org/abs/2511.13259v1 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}. --- ### Souper-Model: How Simple Arithmetic Unlocks State-of-the-Art LLM Performance Authors: Shalini Maiti, Amar Budhiraja, Bhavul Gauri, Gaurav Chaurasia, Anton Protopopov, Alexis Audran-Reiss, Michael Slater, Despoina Magka, Tatiana Shavrina, Roberta Raileanu, Yoram Bachrach Published: 2025-11-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.13254v2 Large Language Models (LLMs) have displayed remarkable capabilities across diverse domains, but their training remains resource- and time-intensive, requiring massive computational resources and careful orchestration of training procedures. Model souping-the practice of averaging weights from multiple models of the same architecture-has emerged as a promising pre- and post-training technique that can enhance performance without expensive retraining. We observe that previous souping approaches can lead to collapse in precision-sensitive LLM capabilities. In this paper, we introduce SoCE, a principled approach for model souping to overcome this shortcoming. The proposed method utilizes benchmark composition to identify optimal model candidates and applies non-uniform weighted averaging to maximize performance. Contrary to previous approaches, our method leverages the observation that different clusters (or categories) of points within a benchmark often exhibit low inter-correlations in model performance. SoCE identifies "expert" models for each weakly-correlated category cluster and combines them using optimized weighted averaging rather than uniform weights. We demonstrate that SoCE improves performance and robustness across multiple domains and achieves state-of-the-art results on the Berkeley Function Calling Leaderboard. --- ### Edge-aware baselines for ogbn-proteins in PyTorch Geometric: species-wise normalization, post-hoc calibration, and cost-accuracy trade-offs Authors: Aleksandar Stanković, Dejan Lisica Published: 2025-11-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.13250v1 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. --- ### Referring Camouflaged Object Detection With Multi-Context Overlapped Windows Cross-Attention Authors: Yu Wen, Shuyong Gao, Shuping Zhang, Miao Huang, Lili Tao, Han Yang, Haozhe Xing, Lihe Zhang, Boxue Hou Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13249v1 Referring camouflaged object detection (Ref-COD) aims to identify hidden objects by incorporating reference information such as images and text descriptions. Previous research has transformed reference images with salient objects into one-dimensional prompts, yielding significant results. We explore ways to enhance performance through multi-context fusion of rich salient image features and camouflaged object features. Therefore, we propose RFMNet, which utilizes features from multiple encoding stages of the reference salient images and performs interactive fusion with the camouflage features at the corresponding encoding stages. Given that the features in salient object images contain abundant object-related detail information, performing feature fusion within local areas is more beneficial for detecting camouflaged objects. Therefore, we propose an Overlapped Windows Cross-attention mechanism to enable the model to focus more attention on the local information matching based on reference features. Besides, we propose the Referring Feature Aggregation (RFA) module to decode and segment the camouflaged objects progressively. Extensive experiments on the Ref-COD benchmark demonstrate that our method achieves state-of-the-art performance. --- ### Proceedings Seventh International Workshop on Formal Methods for Autonomous Systems Authors: Matt Luckcuck, Maike Schwammberger, Mengwei Xu Published: 2025-11-17 Categories: cs.LO, cs.AI, cs.RO arXiv: https://arxiv.org/abs/2511.13245v1 This EPTCS volume contains the papers from the Seventh International Workshop on Formal Methods for Autonomous Systems (FMAS 2025), which was held between the 17th and 19th of November 2025. The goal of the FMAS workshop series is to bring together leading researchers who are using formal methods to tackle the unique challenges that autonomous systems present, so that they can publish and discuss their work with a growing community of researchers. FMAS 2025 was co-located with the 20th International Conference on integrated Formal Methods (iFM'25), hosted by Inria Paris, France at the Inria Paris Center. In total, FMAS 2025 received 16 submissions from researchers at institutions in: Canada, China, France, Germany, Ireland, Italy, Japan, the Netherlands, Portugal, Sweden, the United States of America, and the United Kingdom. Though we received fewer submissions than last year, we are encouraged to see the submissions being sent from a wide range of countries. Submissions come from both past and new FMAS authors, which shows us that the existing community appreciates the network that FMAS has built over the past 7 years, while new authors also show the FMAS community's great potential of growth. --- ### Seek and You Shall Fold Authors: Nadav Bojan Sellam, Meital Bojan, Paul Schanda, Alex Bronstein Published: 2025-11-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.13244v1 Accurate protein structures are essential for understanding biological function, yet incorporating experimental data into protein generative models remains a major challenge. Most predictors of experimental observables are non-differentiable, making them incompatible with gradient-based conditional sampling. This is especially limiting in nuclear magnetic resonance, where rich data such as chemical shifts are hard to directly integrate into generative modeling. We introduce a framework for non-differentiable guidance of protein generative models, coupling a continuous diffusion-based generator with any black-box objective via a tailored genetic algorithm. We demonstrate its effectiveness across three modalities: pairwise distance constraints, nuclear Overhauser effect restraints, and for the first time chemical shifts. These results establish chemical shift guided structure generation as feasible, expose key weaknesses in current predictors, and showcase a general strategy for incorporating diverse experimental signals. Our work points toward automated, data-conditioned protein modeling beyond the limits of differentiability. --- ### Uncovering and Mitigating Transient Blindness in Multimodal Model Editing Authors: Xiaoqi Han, Ru Li, Ran Yi, Hongye Tan, Zhuomin Liang, Víctor Gutiérrez-Basulto, Jeff Z. Pan Published: 2025-11-17 Categories: cs.LG, cs.AI, cs.CV arXiv: https://arxiv.org/abs/2511.13243v1 Multimodal Model Editing (MMED) aims to correct erroneous knowledge in multimodal models. Existing evaluation methods, adapted from textual model editing, overstate success by relying on low-similarity or random inputs, obscure overfitting. We propose a comprehensive locality evaluation framework, covering three key dimensions: random-image locality, no-image locality, and consistent-image locality, operationalized through seven distinct data types, enabling a detailed and structured analysis of multimodal edits. We introduce De-VQA, a dynamic evaluation for visual question answering, uncovering a phenomenon we term transient blindness, overfitting to edit-similar text while ignoring visuals. Token analysis shows edits disproportionately affect textual tokens. We propose locality-aware adversarial losses to balance cross-modal representations. Empirical results demonstrate that our approach consistently outperforms existing baselines, reducing transient blindness and improving locality by 17% on average. --- ### MMD-Thinker: Adaptive Multi-Dimensional Thinking for Multimodal Misinformation Detection Authors: Junjie Wu, Guohong Fu Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13242v1 Multimodal misinformation floods on various social media, and continues to evolve in the era of AI-generated content (AIGC). The emerged misinformation with low creation cost and high deception poses significant threats to society. While recent studies leverage general-purpose multimodal large language models (MLLMs) to achieve remarkable results in detection, they encounter two critical limitations: (1) Insufficient reasoning, where general-purpose MLLMs often follow the uniform reasoning paradigm but generate inaccurate explanations and judgments, due to the lack of the task-specific knowledge of multimodal misinformation detection. (2) Reasoning biases, where a single thinking mode make detectors a suboptimal path for judgment, struggling to keep pace with the fast-growing and intricate multimodal misinformation. In this paper, we propose MMD-Thinker, a two-stage framework for multimodal misinformation detection through adaptive multi-dimensional thinking. First, we develop tailor-designed thinking mode for multimodal misinformation detection. Second, we adopt task-specific instruction tuning to inject the tailored thinking mode into general-purpose MLLMs. Third, we further leverage reinforcement learning strategy with a mixed advantage function, which incentivizes the reasoning capabilities in trajectories. Furthermore, we construct the multimodal misinformation reasoning (MMR) dataset, encompasses more than 8K image-text pairs with both reasoning processes and classification labels, to make progress in the relam of multimodal misinformation detection. Experimental results demonstrate that our proposed MMD-Thinker achieves state-of-the-art performance on both in-domain and out-of-domain benchmark datasets, while maintaining flexible inference and token usage. Code will be publicly available at Github. --- ### Knowing What You Know Is Not Enough: Large Language Model Confidences Don't Align With Their Actions Authors: Arka Pal, Teo Kitanovski, Arthur Liang, Akilesh Potti, Micah Goldblum Published: 2025-11-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.13240v3 Large language models (LLMs) are increasingly deployed in agentic and multi-turn workflows where they are tasked to perform actions of significant consequence. In order to deploy them reliably and manage risky outcomes in these settings, it is helpful to access model uncertainty estimates. However, confidence elicitation methods for LLMs are typically not evaluated directly in agentic settings; instead, they are evaluated on static datasets, such as Q&A benchmarks. In this work we investigate the relationship between confidence estimates elicited in static settings and the behavior of LLMs in interactive settings. We uncover a significant action-belief gap -- LLMs frequently take actions that contradict their elicited confidences. In a prediction market setting, we find that models often bet against their own high-confidence predictions; in a tool-use setting, models fail to reliably invoke information-seeking tools when their internal confidence is low; and in a user-challenge setting, models change their answers when they have high confidence in them, whilst sticking to answers they have low confidence in. Crucially, we show that static calibration is an insufficient predictor of consistency in the above dynamic settings, as stronger, better calibrated models are somtimes less consistent than their smaller and weaker open-source counterparts. Our results highlight a critical blind spot in current evaluation methodologies: ensuring that a model knows what it knows does not guarantee that it will act rationally on that knowledge. --- ### Computational Measurement of Political Positions: A Review of Text-Based Ideal Point Estimation Algorithms Authors: Patrick Parschan, Charlott Jakob Published: 2025-11-17 Categories: cs.LG, cs.AI, cs.CL, cs.CY arXiv: https://arxiv.org/abs/2511.13238v1 This article presents the first systematic review of unsupervised and semi-supervised computational text-based ideal point estimation (CT-IPE) algorithms, methods designed to infer latent political positions from textual data. These algorithms are widely used in political science, communication, computational social science, and computer science to estimate ideological preferences from parliamentary speeches, party manifestos, and social media. Over the past two decades, their development has closely followed broader NLP trends -- beginning with word-frequency models and most recently turning to large language models (LLMs). While this trajectory has greatly expanded the methodological toolkit, it has also produced a fragmented field that lacks systematic comparison and clear guidance for applied use. To address this gap, we identified 25 CT-IPE algorithms through a systematic literature review and conducted a manual content analysis of their modeling assumptions and development contexts. To compare them meaningfully, we introduce a conceptual framework that distinguishes how algorithms generate, capture, and aggregate textual variance. On this basis, we identify four methodological families -- word-frequency, topic modeling, word embedding, and LLM-based approaches -- and critically assess their assumptions, interpretability, scalability, and limitations. Our review offers three contributions. First, it provides a structured synthesis of two decades of algorithm development, clarifying how diverse methods relate to one another. Second, it translates these insights into practical guidance for applied researchers, highlighting trade-offs in transparency, technical requirements, and validation strategies that shape algorithm choice. Third, it emphasizes that differences in estimation outcomes across algorithms are themselves informative, underscoring the need for systematic benchmarking. --- ### Counterfactual Explainable AI (XAI) Method for Deep Learning-Based Multivariate Time Series Classification Authors: Alan G. Paredes Cetina, Kaouther Benguessoum, Raoni Lourenço, Sylvain Kubler Published: 2025-11-17 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.13237v2 Recent advances in deep learning have improved multivariate time series (MTS) classification and regression by capturing complex patterns, but their lack of transparency hinders decision-making. Explainable AI (XAI) methods offer partial insights, yet often fall short of conveying the full decision space. Counterfactual Explanations (CE) provide a promising alternative, but current approaches typically prioritize either accuracy, proximity or sparsity -- rarely all -- limiting their practical value. To address this, we propose CONFETTI, a novel multi-objective CE method for MTS. CONFETTI identifies key MTS subsequences, locates a counterfactual target, and optimally modifies the time series to balance prediction confidence, proximity and sparsity. This method provides actionable insights with minimal changes, improving interpretability, and decision support. CONFETTI is evaluated on seven MTS datasets from the UEA archive, demonstrating its effectiveness in various domains. CONFETTI consistently outperforms state-of-the-art CE methods in its optimization objectives, and in six other metrics from the literature, achieving $\geq10\%$ higher confidence while improving sparsity in $\geq40\%$. --- ### MorphBoost: Self-Organizing Universal Gradient Boosting with Adaptive Tree Morphing Authors: Boris Kriuk Published: 2025-11-17 Categories: cs.LG arXiv: https://arxiv.org/abs/2511.13234v1 Traditional gradient boosting algorithms employ static tree structures with fixed splitting criteria that remain unchanged throughout training, limiting their ability to adapt to evolving gradient distributions and problem-specific characteristics across different learning stages. This work introduces MorphBoost, a new gradient boosting framework featuring self-organizing tree structures that dynamically morph their splitting behavior during training. The algorithm implements adaptive split functions that evolve based on accumulated gradient statistics and iteration-dependent learning pressures, enabling automatic adjustment to problem complexity. Key innovations include: (1) morphing split criterion combining gradient-based scores with information-theoretic metrics weighted by training progress; (2) automatic problem fingerprinting for intelligent parameter configuration across binary/multiclass/regression tasks; (3) vectorized tree prediction achieving significant computational speedups; (4) interaction-aware feature importance detecting multiplicative relationships; and (5) fast-mode optimization balancing speed and accuracy. Comprehensive benchmarking across 10 diverse datasets against competitive models (XGBoost, LightGBM, GradientBoosting, HistGradientBoosting, ensemble methods) demonstrates that MorphBoost achieves state-of-the-art performance, outperforming XGBoost by 0.84% on average. MorphBoost secured the overall winner position with 4/10 dataset wins (40% win rate) and 6/30 top-3 finishes (20%), while maintaining the lowest variance (σ=0.0948) and highest minimum accuracy across all models, revealing superior consistency and robustness. Performance analysis across difficulty levels shows competitive results on easy datasets while achieving notable improvements on advanced problems due to higher adaptation levels. --- ### MRIQT: Physics-Aware Diffusion Model for Image Quality Transfer in Neonatal Ultra-Low-Field MRI Authors: Malek Al Abed, Sebiha Demir, Anne Groteklaes, Elodie Germani, Shahrooz Faghihroohi, Hemmen Sabir, Shadi Albarqouni Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13232v4 Portable ultra-low-field MRI (uLF-MRI, 0.064 T) offers accessible neuroimaging for neonatal care but suffers from low signal-to-noise ratio and poor diagnostic quality compared to high-field (HF) MRI. We propose MRIQT, a 3D conditional diffusion framework for image quality transfer (IQT) from uLF to HF MRI. MRIQT combines realistic K-space degradation for physics-consistent uLF simulation, v-prediction with classifier-free guidance for stable image-to-image generation, and an SNR-weighted 3D perceptual loss for anatomical fidelity. The model denoises from a noised uLF input conditioned on the same scan, leveraging volumetric attention-UNet architecture for structure-preserving translation. Trained on a neonatal cohort with diverse pathologies, MRIQT surpasses recent GAN and CNN baselines in PSNR 15.3% with 1.78% over the state of the art, while physicians rated 85% of its outputs as good quality with clear pathology present. MRIQT enables high-fidelity, diffusion-based enhancement of portable ultra-low-field (uLF) MRI for deliable neonatal brain assessment. --- ### Laplace Learning in Wasserstein Space Authors: Mary Chriselda Antony Oliver, Michael Roberts, Carola-Bibiane Schönlieb, Matthew Thorpe Published: 2025-11-17 Categories: cs.LG, stat.ML arXiv: https://arxiv.org/abs/2511.13229v1 The manifold hypothesis posits that high-dimensional data typically resides on low-dimensional sub spaces. In this paper, we assume manifold hypothesis to investigate graph-based semi-supervised learning methods. In particular, we examine Laplace Learning in the Wasserstein space, extending the classical notion of graph-based semi-supervised learning algorithms from finite-dimensional Euclidean spaces to an infinite-dimensional setting. To achieve this, we prove variational convergence of a discrete graph p- Dirichlet energy to its continuum counterpart. In addition, we characterize the Laplace-Beltrami operator on asubmanifold of the Wasserstein space. Finally, we validate the proposed theoretical framework through numerical experiments conducted on benchmark datasets, demonstrating the consistency of our classification performance in high-dimensional settings. --- ### Informative Communication of Robot Plans Authors: Michele Persiani, Thomas Hellstrom Published: 2025-11-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.13226v1 When a robot is asked to verbalize its plan it can do it in many ways. For example, a seemingly natural strategy is incremental, where the robot verbalizes its planned actions in plan order. However, an important aspect of this type of strategy is that it misses considerations on what is effectively informative to communicate, because not considering what the user knows prior to explanations. In this paper we propose a verbalization strategy to communicate robot plans informatively, by measuring the information gain that verbalizations have against a second-order theory of mind of the user capturing his prior knowledge on the robot. As shown in our experiments, this strategy allows to understand the robot's goal much quicker than by using strategies such as increasing or decreasing plan order. In addition, following our formulation we hint to what is informative and why when a robot communicates its plan. --- ### Seeing isn't Hearing: Benchmarking Vision Language Models at Interpreting Spectrograms Authors: Tyler Loakman, Joseph James, Chenghua Lin Published: 2025-11-17 Categories: cs.CL arXiv: https://arxiv.org/abs/2511.13225v1 With the rise of Large Language Models (LLMs) and their vision-enabled counterparts (VLMs), numerous works have investigated their capabilities in tasks that fuse the modalities of vision and language. In this work, we benchmark the extent to which VLMs are able to act as highly-trained phoneticians, interpreting spectrograms and waveforms of speech. To do this, we synthesise a novel dataset containing 4k+ English words spoken in isolation alongside stylistically consistent spectrogram and waveform figures. We test the ability of VLMs to understand these representations of speech through a multiple-choice task whereby models must predict the correct phonemic or graphemic transcription of a spoken word when presented amongst 3 distractor transcriptions that have been selected based on their phonemic edit distance to the ground truth. We observe that both zero-shot and finetuned models rarely perform above chance, demonstrating the requirement for specific parametric knowledge of how to interpret such figures, rather than paired samples alone. --- ### TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs Authors: Yuxiang Zhang, Zhengxu Yu, Weihang Pan, Zhongming Jin, Qiang Fu, Deng Cai, Binbin Lin, Jieping Ye Published: 2025-11-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.13223v1 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. --- ### Hybrid-Domain Adaptative Representation Learning for Gaze Estimation Authors: Qida Tan, Hongyu Yang, Wenchao Du Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13222v1 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. --- ### Likelihood-guided Regularization in Attention Based Models Authors: Mohamed Salem, Inyoung Kim Published: 2025-11-17 Categories: stat.ML, cs.LG arXiv: https://arxiv.org/abs/2511.13221v1 The transformer architecture has demonstrated strong performance in classification tasks involving structured and high-dimensional data. However, its success often hinges on large- scale training data and careful regularization to prevent overfitting. In this paper, we intro- duce a novel likelihood-guided variational Ising-based regularization framework for Vision Transformers (ViTs), which simultaneously enhances model generalization and dynamically prunes redundant parameters. The proposed variational Ising-based regularization approach leverages Bayesian sparsification techniques to impose structured sparsity on model weights, allowing for adaptive architecture search during training. Unlike traditional dropout-based methods, which enforce fixed sparsity patterns, the variational Ising-based regularization method learns task-adaptive regularization, improving both efficiency and interpretability. We evaluate our approach on benchmark vision datasets, including MNIST, Fashion-MNIST, CIFAR-10, and CIFAR-100, demonstrating improved generalization under sparse, complex data and allowing for principled uncertainty quantification on both weights and selection parameters. Additionally, we show that the Ising regularizer leads to better-calibrated probability estimates and structured feature selection through uncertainty-aware attention mechanisms. Our results highlight the effectiveness of structured Bayesian sparsification in enhancing transformer-based architectures, offering a principled alternative to standard regularization techniques. --- ### FoleyBench: A Benchmark For Video-to-Audio Models Authors: Satvik Dixit, Koichi Saito, Zhi Zhong, Yuki Mitsufuji, Chris Donahue Published: 2025-11-17 Categories: cs.SD, cs.AI, eess.AS arXiv: https://arxiv.org/abs/2511.13219v2 Video-to-audio generation (V2A) is of increasing importance in domains such as film post-production, AR/VR, and sound design, particularly for the creation of Foley sound effects synchronized with on-screen actions. Foley requires generating audio that is both semantically aligned with visible events and temporally aligned with their timing. Yet, there is a mismatch between evaluation and downstream applications due to the absence of a benchmark tailored to Foley-style scenarios. We find that 74% of videos from past evaluation datasets have poor audio-visual correspondence. Moreover, they are dominated by speech and music, domains that lie outside the use case for Foley. To address this gap, we introduce FoleyBench, the first large-scale benchmark explicitly designed for Foley-style V2A evaluation. FoleyBench contains 5,000 (video, ground-truth audio, text caption) triplets, each featuring visible sound sources with audio causally tied to on-screen events. The dataset is built using an automated, scalable pipeline applied to in-the-wild internet videos from YouTube-based and Vimeo-based sources. Compared to past datasets, we show that videos from FoleyBench have stronger coverage of sound categories from a taxonomy specifically designed for Foley sound. Each clip is further labeled with metadata capturing source complexity, UCS/AudioSet category, and video length, enabling fine-grained analysis of model performance and failure modes. We benchmark several state-of-the-art V2A models, evaluating them on audio quality, audio-video alignment, temporal synchronization, and audio-text consistency. Samples are available at: https://gclef-cmu.org/foleybench --- ### Learning to Solve Resource-Constrained Project Scheduling Problems with Duration Uncertainty using Graph Neural Networks Authors: Guillaume Infantes, Stéphanie Roussel, Antoine Jacquet, Emmanuel Benazera Published: 2025-11-17 Categories: cs.AI, cs.LG arXiv: https://arxiv.org/abs/2511.13214v1 The Resource-Constrained Project Scheduling Problem (RCPSP) is a classical scheduling problem that has received significant attention due to of its numerous applications in industry. However, in practice, task durations are subject to uncertainty that must be considered in order to propose resilient scheduling. In this paper, we address the RCPSP variant with uncertain tasks duration (modeled using known probabilities) and aim to minimize the overall expected project duration. Our objective is to produce a baseline schedule that can be reused multiple times in an industrial setting regardless of the actual duration scenario. We leverage Graph Neural Networks in conjunction with Deep Reinforcement Learning (DRL) to develop an effective policy for task scheduling. This policy operates similarly to a priority dispatch rule and is paired with a Serial Schedule Generation Scheme to produce a schedule. Our empirical evaluation on standard benchmarks demonstrates the approach's superiority in terms of performance and its ability to generalize. The developed framework, Wheatley, is made publicly available online to facilitate further research and reproducibility. --- ### 3DAlign-DAER: Dynamic Attention Policy and Efficient Retrieval Strategy for Fine-grained 3D-Text Alignment at Scale Authors: Yijia Fan, Jusheng Zhang, Kaitong Cai, Jing Yang, Jian Wang, Keze Wang Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13211v2 Despite recent advancements in 3D-text cross-modal alignment, existing state-of-the-art methods still struggle to align fine-grained textual semantics with detailed geometric structures, and their alignment performance degrades significantly when scaling to large-scale 3D databases. To overcome this limitation, we introduce 3DAlign-DAER, a unified framework designed to align text and 3D geometry via the proposed dynamic attention policy and the efficient retrieval strategy, capturing subtle correspondences for diverse cross-modal retrieval and classification tasks. Specifically, during the training, our proposed dynamic attention policy (DAP) employs the Hierarchical Attention Fusion (HAF) module to represent the alignment as learnable fine-grained token-to-point attentions. To optimize these attentions across different tasks and geometric hierarchies, our DAP further exploits the Monte Carlo tree search to dynamically calibrate HAF attention weights via a hybrid reward signal and further enhances the alignment between textual descriptions and local 3D geometry. During the inference, our 3DAlign-DAER introduces an Efficient Retrieval Strategy (ERS) to leverage efficient hierarchical searching in the large-scale embedding spaces, outperforming traditional methods (e.g., KNN) in accuracy and efficiency. Furthermore, to facilitate text-3D alignment research and train our 3DAlign-DAER, we construct Align3D-2M, a large-scale dataset featuring 2M text-3D pairs, to provide sufficient fine-grained cross-modal annotations. Extensive and comprehensive experiments demonstrate the superior performance of our 3DAlign-DAER on diverse benchmarks. We will release our codes, models, and datasets. Our code and updates are available at https://github.com/waltstephen/Cost-Effective-Communication. --- ### End-to-End Multi-Person Pose Estimation with Pose-Aware Video Transformer Authors: Yonghui Yu, Jiahang Cai, Xun Wang, Wenwu Yang Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13208v2 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 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. --- ### PIGEON: VLM-Driven Object Navigation via Points of Interest Selection Authors: Cheng Peng, Zhenzhe Zhang, Xiaobao Wei, Yanhao Zhang, Heng Wang, Pengwei Wang, Zhongyuan Wang, Cheng Chi, Shanghang Zhang, Jing Liu Published: 2025-11-17 Categories: cs.RO, cs.CV arXiv: https://arxiv.org/abs/2511.13207v2 Object navigation in unseen indoor environments requires agents to perform semantic search under partial observability. Vision-language models (VLMs) provide strong semantic-spatial priors for this task, but how to interface them with robot navigation remains challenging: dense VLM inference is expensive, while abstracting environments into symbolic memories often separates high-level reasoning from the raw visual evidence that supports it. We propose we propose PIGEON (Point of Interest Guided Exploration for Object Navigation), a VLM-driven framework that formulates object navigation as raw-observation-grounded sparse decision problem. PIGEON introduces Points of Interest (PoIs) as sparse visual decision units that couple geometrically executable waypoints with raw egocentric observations. Rather than using VLMs as dense controllers or restricting them to frontier ranking, PIGEON enables VLMs to select among task-critical PoIs, including exploration frontiers, suspected target objects, traversable stairs, and floor-level summaries, while low-level planners execute continuous motion between them. This PoI interface further makes high-level navigation decisions verifiable, allowing us to develop an RLVR pipeline that improves local VLMs without manual Chain-of-Thought annotations. Extensive experiments on Habitat ObjectNav benchmarks show that PIGEON achieves state-of-the-art zero-shot performance, scales consistently with foundation model capacity, and transfers to Active Embodied Question Answering with only prompt modifications. Real-world deployments on physical robots further demonstrate its robustness and efficiency. --- ### RefineVAD: Semantic-Guided Feature Recalibration for Weakly Supervised Video Anomaly Detection Authors: Junhee Lee, ChaeBeen Bang, MyoungChul Kim, MyeongAh Cho Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13204v2 Weakly-Supervised Video Anomaly Detection aims to identify anomalous events using only video-level labels, balancing annotation efficiency with practical applicability. However, existing methods often oversimplify the anomaly space by treating all abnormal events as a single category, overlooking the diverse semantic and temporal characteristics intrinsic to real-world anomalies. Inspired by how humans perceive anomalies, by jointly interpreting temporal motion patterns and semantic structures underlying different anomaly types, we propose RefineVAD, a novel framework that mimics this dual-process reasoning. Our framework integrates two core modules. The first, Motion-aware Temporal Attention and Recalibration (MoTAR), estimates motion salience and dynamically adjusts temporal focus via shift-based attention and global Transformer-based modeling. The second, Category-Oriented Refinement (CORE), injects soft anomaly category priors into the representation space by aligning segment-level features with learnable category prototypes through cross-attention. By jointly leveraging temporal dynamics and semantic structure, explicitly models both "how" motion evolves and "what" semantic category it resembles. Extensive experiments on WVAD benchmark validate the effectiveness of RefineVAD and highlight the importance of integrating semantic context to guide feature refinement toward anomaly-relevant patterns. --- ### Asymptotic confidence bands for centered purely random forests Authors: Natalie Neumeyer, Jan Rabe, Mathias Trabs Published: 2025-11-17 Categories: math.ST, stat.ML arXiv: https://arxiv.org/abs/2511.13199v1 In a multivariate nonparametric regression setting we construct explicit asymptotic uniform confidence bands for centered purely random forests. Since the most popular example in this class of random forests, namely the uniformly centered purely random forests, is well known to suffer from suboptimal rates, we propose a new type of purely random forests, called the Ehrenfest centered purely random forests, which achieve minimax optimal rates. Our main confidence band theorem applies to both random forests. The proof is based on an interpretation of random forests as generalized U-Statistics together with a Gaussian approximation of the supremum of empirical processes. Our theoretical findings are illustrated in simulation examples. --- ### ParaDySe: A Parallel-Strategy Switching Framework for Dynamic Sequence Lengths in Transformer Authors: Zhixin Ou, Peng Liang, Jianchen Han, Baihui Liu, Linbo Qiao Published: 2025-11-17 Categories: cs.LG, cs.AI arXiv: https://arxiv.org/abs/2511.13198v1 Dynamic sequences with varying lengths have been widely used in the training of Transformer-based large language models (LLMs). However, current training frameworks adopt a pre-defined static parallel strategy for these sequences, causing neither communication-parallelization cancellation on short sequences nor out-of-memory on long sequences. To mitigate these issues, we propose ParaDySe, a novel adaptive Parallel strategy switching framework for Dynamic Sequences. ParaDySe enables on-the-fly optimal strategy adoption according to the immediate input sequence. It first implements the modular function libraries for parallel strategies with unified tensor layout specifications, and then builds sequence-aware memory and time cost models with hybrid methods. Guided by cost models, ParaDySe selects optimal layer-wise strategies for dynamic sequences via an efficient heuristic algorithm. By integrating these techniques together, ParaDySe achieves seamless hot-switching of optimal strategies through its well-designed function libraries. We compare ParaDySe with baselines on representative LLMs under datasets with sequence lengths up to 624K. Experimental results indicate that ParaDySe addresses OOM and CPC bottlenecks in LLM training by systematically integrating long-sequence optimizations with existing frameworks. --- ### Fully Automatic Data Labeling for Ultrasound Screen Detection Authors: Alberto Gomez, Jorge Oliveira, Ramon Casero, Agis Chartsias Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13197v2 Ultrasound (US) machines display images on a built-in monitor, but routine transfer to hospital systems relies on DICOM. We propose a fully automatic method to generate labeled data that can be used to train a screen detector model, and a pipeline to use that model to extract and rectify the US image from a photograph of the monitor, without any need for human annotation. This removes the DICOM bottleneck and enables rapid testing and prototyping of new algorithms. In a proof-of-concept study, the rectified images retained enough visual fidelity to classify cardiac views with a balanced accuracy of 0.79 with respect to the native DICOMs., the rectified images retained enough visual fidelity to classify cardiac views with a balanced accuracy of 0.79 with respect to the native DICOMs. --- ### Difficulty-Aware Label-Guided Denoising for Monocular 3D Object Detection Authors: Soyul Lee, Seungmin Baek, Dongbo Min Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13195v1 Monocular 3D object detection is a cost-effective solution for applications like autonomous driving and robotics, but remains fundamentally ill-posed due to inherently ambiguous depth cues. Recent DETR-based methods attempt to mitigate this through global attention and auxiliary depth prediction, yet they still struggle with inaccurate depth estimates. Moreover, these methods often overlook instance-level detection difficulty, such as occlusion, distance, and truncation, leading to suboptimal detection performance. We propose MonoDLGD, a novel Difficulty-Aware Label-Guided Denoising framework that adaptively perturbs and reconstructs ground-truth labels based on detection uncertainty. Specifically, MonoDLGD applies stronger perturbations to easier instances and weaker ones into harder cases, and then reconstructs them to effectively provide explicit geometric supervision. By jointly optimizing label reconstruction and 3D object detection, MonoDLGD encourages geometry-aware representation learning and improves robustness to varying levels of object complexity. Extensive experiments on the KITTI benchmark demonstrate that MonoDLGD achieves state-of-the-art performance across all difficulty levels. --- ### Cost-Effective Communication: An Auction-based Method for Language Agent Interaction Authors: Yijia Fan, Jusheng Zhang, Kaitong Cai, Jing Yang, Chengpei Tang, Jian Wang, Keze Wang Published: 2025-11-17 Categories: cs.AI arXiv: https://arxiv.org/abs/2511.13193v2 Multi-agent systems (MAS) built on large language models (LLMs) often suffer from inefficient "free-for-all" communication, leading to exponential token costs and low signal-to-noise ratios that hinder their practical deployment. We challenge the notion that more communication is always beneficial, hypothesizing instead that the core issue is the absence of resource rationality. We argue that "free" communication, by ignoring the principle of scarcity, inherently breeds inefficiency and unnecessary expenses. To address this, we introduce the Dynamic Auction-based Language Agent (DALA), a novel framework that treats communication bandwidth as a scarce and tradable resource. Specifically, our DALA regards inter-agent communication as a centralized auction, where agents learn to bid for the opportunity to speak based on the predicted value density of their messages. Thus, our DALA intrinsically encourages agents to produce concise, informative messages while filtering out low-value communication. Extensive and comprehensive experiments demonstrate that our economically-driven DALA achieves new state-of-the-art performance across seven challenging reasoning benchmarks, including 84.32% on MMLU and a 91.21% pass@1 rate on HumanEval. Note that this is accomplished with remarkable efficiency, i.e., our DALA uses only 6.25 million tokens, a fraction of the resources consumed by current state-of-the-art methods on GSM8K. Further analysis reveals that our DALA cultivates the emergent skill of strategic silence, effectively adapting its communication strategies from verbosity to silence in a dynamical manner via resource constraints. Our code and updates are available at https://github.com/waltstephen/Cost-Effective-Communication. --- ### Birth of a Painting: Differentiable Brushstroke Reconstruction Authors: Ying Jiang, Jiayin Lu, Yunuo Chen, Yumeng He, Kui Wu, Yin Yang, Chenfanfu Jiang Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13191v1 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/. --- ### Video Spatial Reasoning with Object-Centric 3D Rollout Authors: Haoran Tang, Meng Cao, Ruyang Liu, Xiaoxi Liang, Linglong Li, Ge Li, Xiaodan Liang Published: 2025-11-17 Categories: cs.CV arXiv: https://arxiv.org/abs/2511.13190v1 Recent advances in Multi-modal Large Language Models (MLLMs) have showcased remarkable capabilities in vision-language understanding. However, enabling robust video spatial reasoning-the ability to comprehend object locations, orientations, and inter-object relationships in dynamic 3D scenes-remains a key unsolved challenge. Existing approaches primarily rely on spatially grounded supervised fine-tuning or reinforcement learning, yet we observe that such models often exhibit query-locked reasoning, focusing narrowly on objects explicitly mentioned in the prompt while ignoring critical contextual cues. To address this limitation, we propose Object-Centric 3D Rollout (OCR), a novel strategy that introduces structured perturbations to the 3D geometry of selected objects during training. By degrading object-specific visual cues and projecting the altered geometry into 2D space, OCR compels the model to reason holistically across the entire scene. We further design a rollout-based training pipeline that jointly leverages vanilla and region-noisy videos to optimize spatial reasoning trajectories. Experiments demonstrate state-of-the-art performance: our 3B-parameter model achieves 47.5% accuracy on VSI-Bench, outperforming several 7B baselines. Ablations confirm OCR's superiority over prior rollout strategies (e.g., T-GRPO, NoisyRollout). ---