001 LAVIFT: Latent-Action-Guided Vision Fine-Tuning for Surgical Interaction Recognition arXiv Paper Jiajun Cheng, Subarna Tripathi et al. Jul 22 002 Model Merging for Medical LVLMs: A Benchmark and a Winner-Take-All Approach arXiv Paper Lichao Mou, Shilan Zhang et al. Jul 17 003 Learning Anatomy-Grounded CT Vision-Language Representations with Organ-Hierarchical Report Knowledge arXiv Paper Guoliang You, Hongming Li et al. Jul 12 004 SHTA: Semantic Hard Token Correction and Center Alignment for Semi-Supervised Medical Image Segmentation arXiv Paper Zhuo Zhang, Yiheng Zhong et al. Jul 8 005 TACoS: Weakly Supervised Learning of Two-Dimensional Materials from Scribble Annotations to Precise Segmentation arXiv Paper Jiabei Chen, Liping Zhang et al. Jul 8 006 ProxyUp: Training-Free Proxy-Conditioned Video Generation for Controllable Dynamics arXiv Paper Zanwei Zhou, Jiazhong Cen et al. Jul 4 007 Beyond Confidence in AI-Assisted Colonoscopy: A Spatial, Temporal and Quality-Aware Audit Framework for Endoscopic AI Review arXiv Paper Roberto Alcaraz Machado, Ana Lucía Rodríguez Blanco Jul 1 008 CoPersona: Collaborative Persona Graphs for Robust LLM Personalization arXiv Paper Yangtian Zhang, Leyao Wang et al. Jul 1 009 Emergence of Preferential Attachment and Glass-Ceiling Effects in Autonomous Networks of LLMs arXiv Paper Yiming Zhang, Vikram Krishnamurthy Jul 1 010 GeoSearcher: Anchor-Guided Progressive Reasoning for Remote Sensing Visual Grounding with Process Supervision arXiv Paper Di Wang, Peirong Zhang et al. Jul 1 011 Anchoring on Reality: Breaking the Pseudo-Target Ceiling in Makeup Transfer arXiv Paper B. Wei, Xianhui Lin et al. Jun 30 012 Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination Mitigation arXiv Paper Xin Zou, Hao Deng et al. Jun 29 013 Progressive Pixel-Neighborhood Deformable Cross-Attention for Multispectral Object Detection arXiv Paper Tian Qiu, Jifeng Shen et al. Jun 23 014 FoleyGenEx: Unified Video-to-Audio Generation with Multi-Modal Control, Temporal Alignment, and Semantic Precision arXiv Paper Shiyao Wang, Xijuan Zeng et al. Jun 12 015 Benchmarking stereo reconstruction for 3D printable Martian terrain models arXiv Paper Joseph Wang Jun 9 016 The Consistency Illusion: How Multi-Agent Debate Hides Reasoning Misalignment arXiv Paper Xiaoyang Wang, Christopher C. Yang Jun 7 017 Discrete-WAM: Unified Discrete Vision-Action Token Editing for World-Policy Learning arXiv Paper Ziyang Yao, Haochen Liu et al. Jun 4 018 How is Latin America engaging with responsible metrics? A systematic review comparing regional and global scientific production arXiv Paper Daniela Oyarz'un-Cristi, 'Alvaro Cabezas-Clavijo et al. Jun 1 019 Lattice Aggregation in Distributed Verification under Crash and Byzantine Failures arXiv Paper Gilde Valeria Rodríguez, B. Bonakdarpour et al. Jun 1 020 Mind Companion: An Embodied Conversational Agent for Process-Based Psychotherapy arXiv Paper Sofie Kamber, Lukas Diebold et al. Jun 1 021 Multi-LLM Systems Exhibit Robust Semantic Collapse arXiv Paper Weiyi Kong, Shiyang Lai et al. May 16 022 WOW-Seg: A Word-free Open World Segmentation Model arXiv Paper Danyang Li, Tianhao Wu et al. May 16 023 Towards Continuous Sign Language Conversation from Isolated Signs arXiv Paper Young Min Kim, K. Choo et al. May 14 024 Pareto-Guided Optimal Transport for Multi-Reward Alignment arXiv Paper Ying Ba, Tianyu Zhang et al. May 13 025 HSUGA: LLM-Enhanced Recommendation with Hierarchical Semantic Understanding and Group-Aware Alignment arXiv Paper Guorui Li, Dugang Liu et al. May 12 026 Filtering Memorization from Parameter-Space in Diffusion Models arXiv Paper Yu Zhe, Jiayan Yang et al. May 11 027 Alignment as Jurisprudence arXiv Paper Nicholas Caputo May 8 028 Change My View? The Dynamics of Persuasion and Polarization in Online Discourse arXiv Paper D. Freeborn, M. Alikani et al. May 8 029 Implicit Preference Alignment for Human Image Animation arXiv Paper Yuanzhi Wang, Xuhua Ren et al. May 8 030 The Endogeneity of Miscalibration: Impossibility and Escape in Scored Reporting arXiv Paper Lauri Lov'en, Sasu Tarkoma May 8 031 A Testable Certificate for Constant Collapse in Teacher-Guided VAEs arXiv Paper Zegu Zhang, Jian Peng et al. May 7 032 Arena as Offline Reward: Efficient Fine-Grained Preference Optimization for Diffusion Models arXiv Paper Zhikai Li, Yue Zhao et al. May 7 033 Automated alignment is harder than you think arXiv Paper Aleksandr Bowkis, Marie Davidsen Buhl et al. May 7 034 Behavior Cue Reasoning: Monitorable Reasoning Improves Efficiency and Safety through Oversight arXiv Paper Christopher Z. Cui, Taylor W. Killian et al. May 7 035 G-SHARE: A Guideline-Based Structured Reasoning Framework for Human-Factor Event Diagnosis arXiv Paper Xingyu Xiao, Mao Du et al. May 7 036 I'm Sorry, but I Can't Help with Braille: Revealing Accessibility Failures in State-of-the-Art LLMs arXiv Paper Abdullah Nazhat Abdullah May 7 037 Memory Inception: Latent-Space KV Cache Manipulation for Steering LLMs arXiv Paper A. Liu, Michael Zhang et al. May 7 038 Misrouter: Exploiting Routing Mechanisms for Input-Only Attacks on Mixture-of-Experts LLMs arXiv Paper Zekun Fei, Zihao Wang et al. May 6 039 Towards General Preference Alignment: Diffusion Models at Nash Equilibrium arXiv Paper Jiaming Hu, Jiamu Bai et al. May 6 040 Explaining and Preventing Alignment Collapse in Iterative RLHF arXiv Paper Etienne Gauthier, Francis Bach et al. May 5 041 Bolek: A Multimodal Language Model for Molecular Reasoning arXiv Paper Frederic Grabowski, Jacek Szczerbi'nski et al. May 4 042 Combining Trained Models in Reinforcement Learning arXiv Paper Ujjwal Patil, Javad Ghofrani May 4 043 Gradient-Gated DPO: Stabilizing Preference Optimization in Language Models arXiv Paper Inoussa Mouiche May 4 044 Verifiable Counterfactual Supervision for Process Reward Models arXiv Paper Yinghui Chi, Lu Wang May 4 045 12 Angry AI Agents: Evaluating Multi-Agent LLM Decision-Making Through Cinematic Jury Deliberation arXiv Paper A. Ersoz May 3 046 RMGAP: Benchmarking the Generalization of Reward Models across Diverse Preferences arXiv Paper Yangyang Zhou, Yicao Li May 3 047 Rethinking Model Selection in VLM Through the Lens of Gromov-Wasserstein Distance arXiv Paper Muyang Li, Yuchen Liu et al. May 2 048 Common-agency Games for Multi-Objective Test-Time Alignment arXiv Paper Baiting Chen, Tong Zhu et al. May 1 049 Evaluating the Temporal Detection Capability of Integrated Gradients Applied on Sound Classifier arXiv Paper Martynas Dumpis, Tuomas Virtanen May 1 050 PERSA: Reinforcement Learning for Professor-Style Personalized Feedback with LLMs arXiv Paper Ravi Ranjan, Utkarsh Grover et al. May 1 051 StepAudio 2.5 Technical Report arXiv Paper Bin Lin, Bo Zhao et al. May 1 052 Estimating LLM Grading Ability and Response Difficulty in Automatic Short Answer Grading via Item Response Theory arXiv Paper Longwei Cong, Sonja Hahn et al. Apr 30 053 Learning from Disagreement: Clinician Overrides as Implicit Preference Signals for Clinical AI in Value-Based Care arXiv Paper Prabhjot Singh, Abhishek Gupta et al. Apr 30 054 Mapping how LLMs debate societal issues when shadowing human personality traits, sociodemographics and social media behavior arXiv Paper Alì Aghazadeh Ardebili, M. Stella Apr 30 055 Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking arXiv Paper D. Singha Apr 29 056 BARRED: Synthetic Training of Custom Policy Guardrails via Asymmetric Debate arXiv Paper A.J. Mazza, Elad Levi Apr 28 057 Evaluating Risks in Weak-to-Strong Alignment: A Bias-Variance Perspective arXiv Paper Hamid Osooli, Kareema Batool et al. Apr 28 058 EvoSelect: Data-Efficient LLM Evolution for Targeted Task Adaptation arXiv Paper Ting-Wei Li, Sirui Chen et al. Apr 28 059 LongSumEval: Question-Answering Based Evaluation and Feedback-Driven Refinement for Long Document Summarization arXiv Paper Huyen Nguyen, Haoxuan Zhang et al. Apr 28 060 Dual-Track CoT: Budget-Aware Stepwise Guidance for Small LMs arXiv Paper Sagnik Chatterjee, Atharva Patil et al. Apr 27