| 1 | Residual Streams Read, Recurrent States Remember: The Global Workspace in Mamba Models | Wenlong Wang, Fergal Reid | cs.AI | 2026-09-26 |
| 2 | Escaping Alignment: A Physical Trap Model of Best-of-N Jailbreaking | Marco Biroli | cs.AI | 2026-09-26 |
| 3 | READ-Bench: Benchmarking Historical Instance Retrieval for Time-Series Diagnosis | Gerardo Pastrana, Haojun Li, Dhruv Mehta +4 | cs.AI | 2026-09-26 |
| #4 | PastForward: Faster On-Device GUI Agents via Computational Experience Reuse | Taehwan Park, Changmin Lee, Hayeon Lee +1 | cs.AI | 2026-09-26 |
| #5 | Noisy Test-Time Reinforcement Learning for Code LLMs | Xikai Yang, Hieu Trung Nguyen, Dunyuan Xu +4 | cs.AI | 2026-09-26 |
| #6 | AI Harness: Certification under Proposal-Conditioned Information for Foundation-Model Agents | Hailin Zhong, Shengxin Zhu | cs.AI | 2026-09-26 |
| #7 | CoMemBench: Benchmarking Collaborative Memory Boundaries across Multi-Agent Workflow Topologies | Sen Zhao, Ruiqi Kong, Zuyu Zhang +5 | cs.AI | 2026-09-26 |
| #8 | Instruct, Not Answer: Using Instruction Privileges in On-Policy Context Distillation | Hantao Yu, Sandy Han, Udaya Ghai +4 | cs.AI | 2026-09-26 |
| #9 | Witness: Discovery, Deciphering, and Epiphany in Interactive Puzzle Environments | Guanghan Ning, Ping Liu, Linyi Li +6 | cs.AI | 2026-09-26 |
| #10 | Fracast-0: Fractal Weight Sharing for a Time Series Foundation Model with Only 85K Parameters | Tianxiang Zhan, Huanyao Zhang, Yuanpeng He | cs.AI | 2026-09-26 |
| #11 | A bilingual AI audiologist built through rubric-guided playbook induction outperforms human audiologists in a blinded evaluation of simulated cases | Linkai Li, Changgeng Mo, Hanlin Yu +4 | cs.AI | 2026-09-26 |
| #12 | RAO-Nav: Probing Omni-Language Models for Zero-shot Semantic Audio-Visual Navigation | Qilang Ye, Meng Liu, Yu Zhou | cs.AI | 2026-09-26 |
| #13 | Certifying Interventional Agreement Among Observationally Equivalent Causal Models | Sourena Khanzadeh, Daniel Platnick, Marjan Alirezaie +1 | cs.AI | 2026-09-26 |
| #14 | Why Directly Learning Periodic Trajectories Can Fail | Kaixin Zheng, Anita Layton | cs.AI | 2026-09-26 |
| #15 | Clarify the User or Verify the World? Uncertainty Routing for Proactive Agents | Zhaofeng Li, Xuan Zhang, Xiaokui Xiao +1 | cs.AI | 2026-09-26 |
| #16 | LAM: Efficient Lossy Agent Memory Framework With A Retrieval-Score Error Bound | Baixi Sun, Le Chen, Anjir Ahmed Chowdhury +10 | cs.AI | 2026-09-26 |
| #17 | Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs | Vincent-Daniel Yun, Woosang Lim, Haneul Yoo +3 | cs.AI | 2026-09-26 |
| #18 | When Does a Skill Add Value? Task-Conditional Gain Prediction for Selective Skill Use | Anjie Xu, Zhiyu Zhang, Ruiqing Ding +2 | cs.AI | 2026-09-26 |
| #19 | GLIDE: Generalized Layer-wise Intrinsic Distributional Evaluation for Heterogeneous LLM Agents | Wei Zhu, Yiming Wang, Rui Wang +3 | cs.AI | 2026-09-26 |
| #20 | Agentsensus: Consensus-Compressed Shared Memory for Multi-Agent Story Worlds | Yu Pan | cs.AI | 2026-09-26 |
| #21 | Train4Merge: A Controlled Single-Teacher Study of RL vs. SFT Teachers for OPD-Based Model Merging | Jingyuan Huang, Zuming Huang, Yucheng Shi +4 | cs.AI | 2026-09-26 |
| #22 | PhiFold: Towards Dynamic Protein Design with Physics-Structured Covariance Modeling | Yutian Liu, Mujie Lin, LanqianZhang +4 | cs.AI | 2026-09-26 |
| #23 | Delayed Supervision for Test-Time Language Models | Jinha Kim, Taksh Kothari | cs.AI | 2026-09-26 |
| #24 | RLHarness: Co-evolving Procedural Skills with Reinforcement Learning for Long-horizon Multimodal Reasoning | Ziqiao Shang, Zian Xu, Ji-Chen Yan +6 | cs.AI | 2026-09-26 |
| #25 | HyperReCo: Retrieving and Connecting Evidence with Hypergraph Neural Networks for LLM Multi-hop Reasoning | Zicheng Zhao, Linhao Luo, Junnan Dong +4 | cs.AI | 2026-09-26 |
| #26 | Enabling Timely Guidance before Skill Retrieval: Retaining Helpful Warm Tips in Agent Context | Feng Liang, Yupeng Li, Runhao Zeng +2 | cs.AI | 2026-09-26 |
| #27 | ALLOT: Budgeted Hybrid-Memory Routing for Knowledge Updates in LLMs | Shanfeng Huang, Zhou Fang, Song Xiao +1 | cs.AI | 2026-09-26 |
| #28 | From Trajectories to Grounded Preferences: Process Preference Synthesis via Interaction Element Graphs for Web PRMs | Yangzhe Peng, Xiaoyang Wang, Yiyang Zhao +2 | cs.AI | 2026-09-26 |
| #29 | AuthorityLens: Rethinking LLM-Based Agent Systems Through the Lens of Authority | Shaojin Chen, Huihao Jing, Wun Yu Chan +7 | cs.AI | 2026-09-26 |
| #30 | Reward Hacking and Agent Containment Failure: A Monte Carlo Study Based on the 2026 Hugging Face Incident | Murat Ozer, Bulent Erenay, Ibrahim Berber | cs.AI | 2026-09-26 |
| #31 | SCLATE: a Substrate for Continual-Learning Agent Training and Evaluation | Youngmok Jung, Sirajul Salekin, Henry Tran +3 | cs.AI | 2026-09-26 |
| #32 | Beyond Scripted Search: Sample-Efficient Reward Discovery via Agentic Black-box Optimization | Minghao Li, Rui Tan, Ruihang Wang | cs.AI | 2026-09-26 |
| #33 | Memory as a cache: Exact context reuse and deletion by construction | Shengyao Wang, Jiang Liu | cs.AI | 2026-09-26 |
| #34 | Function Over Form: Distributional Orthogonalization in Mixture-of-Experts with Replica Expert Mechanism | Jinfan He, Yunzhuo Liu, Kai Zhang +3 | cs.AI | 2026-09-26 |
| #35 | Opening LLM Judges: Recovering Preference Signals Beyond the Final Verdict | Sourabrata Mukherjee, Sunayana Sitaram | cs.AI | 2026-09-26 |
| #36 | Carnator: Fast Text-to-Video Generation with Generation-Native Compatibility-Guided Cross-Request Reuse | Xingkun Yin, Xuebin Tang, Mingkun Xu +1 | cs.AI | 2026-09-26 |
| #37 | MergeHEIR: Mitigating Multimodal Hallucinations as the Tax of Model Merging | Jinyu Li, Hao Fang, Zhiming Zhang +3 | cs.AI | 2026-09-26 |
| #38 | PluginRSI: Recursive Improvement of Agent Harnesses with Reusable Plugins | Yaorui Shi, Yuchun Miao, Yuxin Chen +5 | cs.AI | 2026-09-26 |
| #39 | Authorization Closure Graph: Minimal Repair for LLM Agents with Evolving User Instructions | Qingzhuo Wang, CaiYi Wang, Jinglu Meng +4 | cs.AI | 2026-09-26 |
| #40 | PrismQuant: Optimal Null-Space Rotations for Grouped Quantizers | Yanlong Chen, Yining Chen, Song Zhang +2 | cs.AI | 2026-09-26 |
| #41 | Multi-Agent System Search via Active Substructure-aware Policy Optimization | Beicheng Xu, Bowen Fan, Weitong Qian +2 | cs.AI | 2026-09-26 |
| #42 | From Latents to Wires: Surgical Post-Editing on Large Language Models | Jiankai Jin, Xiangzheng Zhang, Zhao Liu +4 | cs.AI | 2026-09-26 |
| #43 | Controllable GNN Explanations via Multi-Metric Preference Selection | Rachit Verma, Yashraj J. Deshmukh, Anirban Dasgupta | cs.AI | 2026-09-26 |
| #44 | ForkLeft: Entropy-First Rollouts for Prefix-Aligned Autoregressive-to-Diffusion Distillation | Junming Liu, Jicheng Wang, Yifeng He +2 | cs.AI | 2026-09-26 |
| #45 | PULSE: Identifying Demonstration-Utility Features with Sparse Autoencoders | Chenduo Hao, Chuanbao Gao, Pinjun Zeng +4 | cs.AI | 2026-09-26 |
| #46 | VPEvolve: A Self-Evolving Virtual Process Engineer for Computational Lithography | Tianyi Li, Wenxuan Dong, Donger Luo +5 | cs.AI | 2026-09-26 |
| #47 | From Outcomes to Strategies: Learning Strategy Utility for Mathematical Reasoning | Ruikang Zhang, Xiao An, Xuli Shen +5 | cs.AI | 2026-09-26 |
| #48 | Separating Diagnosis from Disease Representation: Dual-View EEG Learning with Neural-Dynamics-Guided Deformation | Jiaying Wang, Shouqian Shi, Yutong Chen +5 | cs.AI | 2026-09-26 |
| #49 | Towards Scalable Data Diversification for Language Model Pretraining via Leverage Score Sampling | Zailin Ma, Quzhe Huang, Yujun Li +2 | cs.AI | 2026-09-26 |
| #50 | When Helpful Text Hurts: Option-Redirecting Bias in Vision-Language Models | Tam Le Thi Thanh, Hoang Tran Van, Hong-Hanh Nguyen-Le +1 | cs.AI | 2026-09-26 |
| #51 | RepoMAS: Solving Progressively Specified Tasks with Issue-Driven Multi-Agent Systems | Yuchen Song, Andong Chen, Wenxin Zhu +2 | cs.AI | 2026-09-26 |
| #52 | Beyond Prompt or Skill? Attribution-Guided Optimization of Modular LLM Programs | Haoran Shou, Haoyue Liu, Yu Huo +2 | cs.AI | 2026-09-26 |
| #53 | DAAF: From Failure Localization to Editable System Assets in LLM Agents | Xiaoyang Yuan, Qi Liu, Yubin Ruan +9 | cs.AI | 2026-09-26 |
| #54 | TreeRef-BFN: Equivariance-Free De Novo Molecule Generation based on 2D Topology and Internal 3D Geometry | Ruiqing Sun, Sen Yang, Dawei Feng +3 | cs.AI | 2026-09-26 |
| #55 | Learning from Others, Acting for You: Cross-User Memory Sharing for LLM Agents | Jinming Hu, Haodong Zhao, Qi Jia +4 | cs.AI | 2026-09-26 |
| #56 | From Anomalies to Failures: Constructing Causal Error Graphs for Agentic Trace Diagnosis | Shu-Xun Yang, Yidong Wang, Zhuoer Feng +7 | cs.AI | 2026-09-26 |
| #57 | LocalProp: Neuro-Localized Memory-Efficient Backpropagation | Diana-Nicoleta Grigore, Iuliana Georgescu, Radu Tudor Ionescu | cs.AI | 2026-09-26 |
| #58 | STR: Supervised Transcoder Replacement for Reducing Steering Side Effects | Haonan Yu, Junhao Liu, Zhenyu Yan +2 | cs.AI | 2026-09-26 |
| #59 | MemAgent: Learning to Manage Heterogeneous Memory Providers for LLM Agents | Yongxian Wei, Yilin Zhao, Runxi Cheng +5 | cs.AI | 2026-09-26 |
| #60 | Beyond Dyadic Memory: Interaction-Aware Multimodal Memory with Adaptive Agentic Retrieval for Multi-Party Spoken Conversations | Wenxu Jia, Xize Cheng, Zihan Zhang +5 | cs.AI | 2026-09-26 |
| #61 | AmbiModBench: Benchmarking Gene Perturbation Prediction Beyond Shared Responses | Sikai Huang, Zhiwen Yang, Kai Yu +2 | cs.AI | 2026-09-26 |
| #62 | Fail Loudly: An Auditable Runtime for Agentic Data Analysis | Hanxu Yan, Langxuan Deng, Zhengle Wang +2 | cs.AI | 2026-09-26 |
| #63 | LLMAdBench: A Human Preference Benchmark for Advertising in LLM Responses | Rui Ai, Yuqing Liu, Sitao Qiu +14 | cs.AI | 2026-09-26 |
| #64 | Interpretable Physics Informed WiFi Indoor Localization: Learning an Effective Access Point Geometry and Using It to Prune | Arshia Eftekhari zadeh, Rezvan Nasiri, Hadi Moradi | cs.AI | 2026-09-26 |
| #65 | Porimon: An LLM-Based Pokémon Battle Agent Enhanced by Long/Short-Term Knowledge Augmented Generation | Dongyin Zhuo, Fengjunjie Pan, Nenad Petrovic +1 | cs.AI | 2026-09-26 |
| #66 | Are Vision-Language-Action Models Robust to One-Step Observation Perturbations? | Shojiro Yamabe, Jun Sakuma | cs.AI | 2026-09-26 |
| #67 | Artificial intelligences and human scientists exhibit complementary strengths in theory building | Ke Li, Spyros I. Zoumpoulis, Phanish Puranam +80 | cs.AI | 2026-09-26 |
| #68 | ProTTT: Learning to Learn Semantic User Memory with Test-Time Training | Sejun Park, Hyoungjo Bhang, Hyein Jeong +1 | cs.AI | 2026-09-26 |
| #69 | CUE-Mem: Benchmarking Long-Term User Memory via Implicit Cues in Multimodal Conversations | Yulin Hu, Yanyan Zhao, Zimo Long +6 | cs.AI | 2026-09-26 |
| #70 | EMIR$^2$: Evolution-Aware Memory with Intent-Guided Multi-Round Retrieval | Jinlan Liu, Hongliang Sun, Yong Wang +4 | cs.AI | 2026-09-26 |
| #71 | MA-FPPO: Multi-Agent Flow-Pretrained Policy Optimization | Guowei Zou, Haonan Chen, Haitao Wang +3 | cs.AI | 2026-09-26 |
| #72 | CUA-SWE: When Computer-Use Agents Meet Visual Software Engineering | Prince Zizhuang Wang, Chenhao Liang, Zelong Xu +6 | cs.AI | 2026-09-26 |
| #73 | "You're Right, Let Me Fix It": How LLM Agents Damage Correct Work When Falsely Accused | Xutao Mao, Rui Qian, Longxiang Wang +6 | cs.AI | 2026-09-26 |
| #74 | SWE-MILE: Asynchronous Potential-Induced Milestone Credit Assignment for Long-Horizon Software Engineering Agents | Chaoqun Cui, Hao Zhou, Meiqi Chen +2 | cs.AI | 2026-09-26 |
| #75 | Can Open-Weight Large Language Models (LLMs) Simulate Human Survey Populations? A Cross-Instrument Calibration Study | Grandee Lee, Wang Yue | cs.AI | 2026-09-26 |
| #76 | Business Compromise Detection with Agentic AI and LLM-driven Knowledge Discovery | Diego Palma, Kyu Bin Kim, Zhen Han +2 | cs.AI | 2026-09-26 |
| #77 | From Scene Graphs to Answers: Selective Neuro-Symbolic Reasoning for Autonomous Driving | Yiyao Wang, Pei Liu, Fangzhou Liu +1 | cs.AI | 2026-09-26 |
| #78 | Prediction Limits and Koopman Closure of Geometry-Induced Soft State Abstractions | Mohit Kumar, Somayeh Kargaran | cs.AI | 2026-09-26 |
| #79 | MixBench-TS: A Multivariate Time Series Forecasting Benchmark Where Channel Mixing Pays Off | Ibram Abdelmalak, Mischa Putzke, Jungmin Choi +3 | cs.AI | 2026-09-26 |
| #80 | World Models with Predictable Long-Horizon Marginals | Yuhao Du, Shunian Chen | cs.AI | 2026-09-26 |
| #81 | Contract Memory Compiler: Resolve, Then Traverse | Zhi Song, XiMing Xing, Chunhan Li +9 | cs.AI | 2026-09-26 |
| #82 | Learning from a Thoughtful Teacher: Adaptive On-Policy Self-Distillation for Mathematical Reasoning | Jiacheng Du, Weiwei Xie, Tianyi Du +3 | cs.AI | 2026-09-26 |
| #83 | Refinement Symmetry in Multimodal Transformers | Yuhao Du, Shunian Chen | cs.AI | 2026-09-26 |
| #84 | What Would Falsify It? A Variable Specific Evidence Standard for Mechanistic Claims About Self Explanation | Arshia Eftekhari zadeh | cs.AI | 2026-09-26 |
| #85 | Expected Reasoning-Step Return Unifies On-Policy Learning from Rewards and Teachers | Qiangqiang He, Jin Li | cs.AI | 2026-09-26 |
| #86 | When Better Gets Worse: Improvement Fidelity for Self-Improving Agents in Adaptive Worlds | Ke Wang, Zijie Zhao, Zhiyi Yuan +1 | cs.AI | 2026-09-26 |
| #87 | PINNMorph: Evolving Online Adaptation Policies for Physics-Informed Neural Networks | Xu Yang, Mingyang Yu, Jun Zhang +2 | cs.AI | 2026-09-26 |
| #88 | Dude, Where's My State? Execution Information Requirements for Stateful Agents | Nikita Mehrotra, Ashish Tiwari, Priyanshu Gupta +1 | cs.AI | 2026-09-26 |
| #89 | World Agent: Can Language Models Keep a World Running? | Weixing Chen, Weipeng Zhang, Nan An +2 | cs.AI | 2026-09-26 |
| #90 | IGSD: Environment-Verified Hindsight Self-Distillation for Search Agents | Angqing Jiang, Gaoming Zhang, Chaoqun Zhang +5 | cs.AI | 2026-09-26 |
| #91 | Flat-Consensus Diffusion for Robust Data Reshaping under Noisy Evaluator | Hongyu Cao, Kunpeng Liu, Fei Xie +1 | cs.AI | 2026-09-26 |
| #92 | CAIRN: Dynamic Fact-Intent DAGs for Multi-Agent Exploration | Zuyao Xu, Yuyang Jia, Junwei Guan +3 | cs.AI | 2026-09-26 |
| #93 | Despite Instructions: Frontier Agents Improvise Covert Channels at Test Time | Jacob Dineen, Silei Ren, Muhao Chen +2 | cs.AI | 2026-09-26 |
| #94 | CoWindow Attention: Full Causal Coverage Is a Collective Property | Jingze Shi, Zhangyang Peng, Xianduo Li +6 | cs.AI | 2026-09-26 |
| #95 | MassAlloc Attention: Let Attention Allocate Its Own Compute | Jingze Shi, Zhangyang Peng, Xianduo Li +6 | cs.AI | 2026-09-26 |
| #96 | SkillVine: Agent Skill Evolution via Branching Exploration | Kaiwei Liu, Jiqian Dong, Liran Dong +7 | cs.AI | 2026-09-26 |
| #97 | Retrospective Distillation Attribution via Normalized Response Similarity | Minwoo Jang, Jaechang Kim, Minhyeon Oh +2 | cs.AI | 2026-09-26 |
| #98 | CUA-Sandbox: Efficient Environments for Computer-Use Agent Reinforcement Learning | Xin Yan, Zhengbo Jiao, Jiaqi Liu +11 | cs.AI | 2026-09-26 |
| #99 | Action Shaping: Policies Absorb What They Can Express | Yanjun Chen, Jinghan Wang, Xiaoyu Shen +2 | cs.AI | 2026-09-26 |
| #100 | Adaptive Consistency Graph for Long-Horizon Agents | Jiecong Wang, Hao Peng, Zhanyi Wang | cs.AI | 2026-09-26 |
| #101 | Readout is not Recovery: Dissociating Coordinate Emission from Visual-Corruption Repair in Vision-Language Models | Drandreb Earl Juanico | cs.AI | 2026-09-26 |
| #102 | Mandela-Bench: Multimodal Models Remember Canonical Images Instead of Seeing Them | Yicheng Bao, Zhenkun Gao, Xiahui Guo +7 | cs.AI | 2026-09-26 |
| #103 | Forecasting Intraday USD/CAD Exchange Rate with News-Derived Monetary-Policy Signals | Maya Kodeih, Aliaa Alnaggar, Mucahit Cevik | cs.AI | 2026-09-26 |
| #104 | Agentic Network Traffic Monitoring | Manuel Tsoukatos, Hayden Jananthan, Jeremy Kepner | cs.AI | 2026-09-26 |
| #105 | Learning response-aware patient dynamics for respiratory support | Xiaolei Lu, Shamim Nemati | cs.AI | 2026-09-26 |
| #106 | CLAIRE: A Schema-Grounded Hybrid Workflow for Healthcare Administrative Form Completion | Garapati Keerthana, Manik Gupta | cs.AI | 2026-09-26 |
| #107 | $T^5$: Twin-Critic Training for Token-Level Thoughts in Reinforcement Mid-Training | Nan Qiao, Yebin Yang, Weinong Wang +10 | cs.AI | 2026-09-26 |
| #108 | AgentHabit: Characterizing Distinct Behaviors of Agents on Everyday Tasks | Woojung Song, Hoyeol Yang, Jeonghoon Shim +4 | cs.AI | 2026-09-26 |
| #109 | PlanGuard: A Guardrail for Multi-Step Plan Safety in Embodied Agents | Junchi Chen, Changtao Miao, Yuxiao Xiang +9 | cs.AI | 2026-09-26 |
| #110 | Re-derivability Decides What a Staged Agent Pipeline Recovers After an Upstream Fault | Tianqi Bu, YuXuan Peng, Junteng Tu +1 | cs.AI | 2026-09-26 |
| #111 | Nutri-ATLAS: Embodied Agent for Tabulated Lookup and Assistance for Smarter nutrition | Uttej Kallakuri, Boxun Hu, Ankur A. Butala +2 | cs.AI | 2026-09-26 |
| #112 | Decision-Sufficient State Representations: Measuring and Reducing Write-Time Regret | Bingyu Shen, Boyang Li | cs.AI | 2026-09-26 |
| #113 | Beyond Accuracy: Counterfactual Fragility and Demographic Bias in Clinical Evaluation of LLMs | Chaitai Deb Purkayastha, Bharath Kumar Bolla, Vishnu Surya Reddy Nandi | cs.AI | 2026-09-26 |
| #114 | Overwhelmed by Choice: Studying LLM Decision Making at Scale | Yu-Chi Lin, Aryan Seth, Anshul Aravind +4 | cs.AI | 2026-09-26 |
| #115 | Right Answer, Wrong Reason: Accuracy, Consistency, and Consensus Are Misleading Indicators of LLM Faithfulness in Clinical Decision Support | Bharath Kumar Bolla, Bharath Kumar Bolla, Vishnu Surya Reddy Nandi | cs.AI | 2026-09-26 |
| #116 | When Can First-Order Models of Fine-Tuning Bound Forgetting? | Jianchang Su, Wei Zhang | cs.AI | 2026-09-26 |
| #117 | Rank Collapse Is Recoverable, Growing $|Q|$ Is Not: Out-of-Sample Early Warning for Value Divergence in High-UTD Soft Actor-Critic | Tianqi Bu, YuXuan Peng, Junteng Tu +1 | cs.AI | 2026-09-26 |
| #118 | Routing Drift Alone Does Not Diagnose Failure in Merged MoE LLMs | Yuanyi Wang, Yanggan Gu, Su Lu +7 | cs.AI | 2026-09-26 |
| #119 | The Decomposition Tax: LLM Pipelines Lose Up to 40 Accuracy Points at Their Own Interfaces | Tianqi Bu, YuXuan Peng, Junteng Tu +1 | cs.AI | 2026-09-26 |
| #120 | Improving LLM Collaboration via Multi-Agent Preference Learning | Shuo Liu, Xinzichen Li, Tianle Chen +1 | cs.AI | 2026-09-26 |
| #121 | FinancialAuditBench: Benchmark Construction under Differential Privacy Using Real-World Priors | Jerry Huang, Sarvesh Babu, Matt Van Buren +5 | cs.AI | 2026-09-26 |
| #122 | Counterfactual Self-Evolving Agents for Evidence-Grounded Reasoning | Xing Han, Yuxin Wang, Chen Chen +8 | cs.AI | 2026-09-26 |
| #123 | Can LLMs Predict the Future? A Brier Score Analysis of Prediction Markets | Yuanbo Li, Zekun Li, Xiaoyan cong | cs.AI | 2026-09-26 |
| #124 | StraTune: Adaptive Selection of Revision Operators for Self-Evolving LLM Skills | Zeping Liu, Yan Li, Ni Lao +2 | cs.AI | 2026-09-26 |
| #125 | Constraints Are Graphs, Not Chains: Exact Decoding for Diffusion Language Models | Jianchang Su, Wei Zhang | cs.AI | 2026-09-26 |
| #126 | Logical subspace in LLMs | Hope Kean, Enric Boix-Adsera | cs.AI | 2026-09-26 |
| #127 | Planner-as-Router: Joint Plan-Time Model Routing for Cost-Efficient Multi-Agent Workflows | Vivek Kumar Singh, Preeti Priyam, Gautam Bhowmick | cs.AI | 2026-09-26 |
| #128 | Precision As You Need: Stochastic Computing Is a Dense Adaptive Quantizer | Haoran Jin, Kangqi Zhang, Jirong Yang +4 | cs.AI | 2026-09-26 |
| #129 | TRACE: Learning to Self-Calibrate Wireless Digital Twins from ISAC Measurements | Saad Masrur, Saeed R. Khosravirad, Ismail Guvenc | cs.AI | 2026-09-26 |
| #130 | Diagnosing Sampled LLM Reasoning in Formal Geometry: Coverage, Realization, and Validity Evidence | Xiao Yue, Guangzhi Qu | cs.AI | 2026-09-26 |
| #131 | The Commit-Abstain Circuit: Why Language Models Hallucinate Instead of Abstaining | Vy Nguyen, Ziqi Xu, Jeffrey Chan +5 | cs.AI | 2026-09-26 |
| #132 | Relic: From Multi-Agent Collaboration to Persistent Organizational Capability | Hongyi Du, Tianyi Zhang, Weijia Zhang +9 | cs.AI | 2026-09-26 |
| #133 | Certified Long-Horizon Code Agent Evolution via Validation-Gated Skill Optimization | Yifan Wang, Hao Cheng, Xiaomin Li +13 | cs.AI | 2026-09-26 |
| #134 | X-Tree: Tokenizing Reusable Experience for Efficient Agent Generalization | Sitao Cheng, Xunjian Yin, Zhiyuan Sun +4 | cs.AI | 2026-09-26 |
| #135 | Model-Aware Data Selection from In-and-Out Information Interplay | Yifan Wang, Xiaomin Li, Yuexing Hao +7 | cs.AI | 2026-09-26 |
| #136 | When Pair Count Is Not the Sample Size: What All-Pairs Agent Comparisons Estimate | Wei-Jung Huang | cs.AI | 2026-09-26 |
| #137 | The Epistemics of Agent Memory: Measuring, and Governing, the Consolidation Decision in Long-Horizon LLM Agents | Sasank Annapureddy, Anjaneya Prasad Thamatani | cs.AI | 2026-09-26 |
| #138 | Trust and Task Completion in the World of Consumer AI Agents | Jeroen Olieslagers, Eduardo Pujol, Gal Zahavi +2 | cs.AI | 2026-09-26 |
| #139 | SRE-Marathon: A Continuous, Change-Driven Benchmark for Autonomous Site Reliability Agents | Yifang Tian, Yingjian Bai, Yifeng He +4 | cs.AI | 2026-09-26 |
| #140 | AutoPDEBench: Benchmarking LLM Auto-Research for Neural PDE Solver Design | Ruoyan Li, Wei Wang, Yizhou Sun | cs.CE | 2026-09-26 |
| #141 | Using LMs to Model the Effects of Context and Coreference during Sentence Comprehension | Kohei Kajikawa, Lin Ai, Tatsuki Kuribayashi +1 | cs.CL | 2026-09-26 |
| #142 | Typed Decision Models: An Early Evidence Audit and Evaluation Checklist | Lijuan Tang, Yuemeng Zheng | cs.CL | 2026-09-26 |
| #143 | ScopeIF: Improving Scope-Aware Precise Instruction-Following in Large Language Models via Graded Reward Modeling | Bosi Wen, Yilin Niu, Xiaoying Ning +3 | cs.CL | 2026-09-26 |
| #144 | The Judge Is Not Its Twin: Post-training makes a model's writing more predictable but barely moves its taste, as a judge, toward predictable writing | Arman Nik Khah, Arvin Bahreini | cs.CL | 2026-09-26 |
| #145 | Generalization and Memorization along the Learning Trajectory of Neural Language Models: A Geometric Account of Categorization | Wang Bojun, Holly Jenkins, Elizabeth Wonnacott | cs.CL | 2026-09-26 |
| #146 | A model of rational interlocutors: Unification of comprehension and production | Hanlin Wu, Zhenguang G. Cai | cs.CL | 2026-09-26 |
| #147 | OptiArena: Can LLMs Improve Executable Algorithms under Fixed Resource Budgets? | Wenjun Peng, Xinyu Wang | cs.CL | 2026-09-26 |
| #148 | KinyaMed: Seeds, Not Rows -- What a Corpus Requirement Written in the Wrong Unit Fails to Constrain | Marius Bayizere | cs.CL | 2026-09-26 |
| #149 | Solving Every Step Is Not Enough: Milestone Oracles Reveal a Composition Gap in LLM Math Reasoning | Zhuohan Wang, Haoran Ma, Tianyu Wu +3 | cs.CL | 2026-09-26 |
| #150 | LANTERN: Illuminating Hidden Mathematical Knowledge in Language Models | Pavel Tikhonov, Elena Tutubalina, Ivan Oseledets +2 | cs.CL | 2026-09-26 |
| #151 | Before Answering: Evidence Sufficiency under Size-Matched Memory Construction | Joyanta Jyoti Mondal, Md. Shifatul Ahsan Apurba, Mridul Banik +2 | cs.CL | 2026-09-26 |
| #152 | Supporting and Performing Culture from the Inside | Lea Frermann, Steven Bird | cs.CL | 2026-09-26 |
| #153 | TRAP: Understanding and Mitigating Privacy Memorization in Language Models | Muhammed Ustaomeroglu, Ziyue Xu, Hanshen Xiao +3 | cs.CL | 2026-09-26 |
| #154 | Language Distances are Practical for Equitable Cross-Lingual Transfer | York Hay Ng, Razan Ahsan Rifandi, Aditya Khan +1 | cs.CL | 2026-09-26 |
| #155 | Gradients for Interventions and Activations for Detection: Targeted Feature Learning in Language Models | Jonathan Drechsel, Steffen Herbold | cs.CL | 2026-09-26 |
| #156 | PlurVA-LLM-2026 Shared Task Track-1: Pluralistic Value Alignment in LLMs via Multilingual Fine-Tuning and Threshold Calibration | Vihindi Kotalawala, Nevidu Jayatilleke | cs.CL | 2026-09-26 |
| #157 | FA-Bench: A Benchmark for Word-Level and Phone-Level Forced-Alignment and ASR Timestamps Under Clean and Noisy Conditions | Wei Chu, Yuanzhe Dong, Ke Tan +11 | cs.CL | 2026-09-26 |
| #158 | SinBrief: A Hybrid Framework for Abstractive Text Summarisation of Sinhala Legal Documents | Minduli Lasandi, Nevidu Jayatilleke | cs.CL | 2026-09-26 |
| #159 | Shared Worlds, Private Minds: Structured Memory for Long-Form Writing as World Creation | Qiuyu Tian, Xiaowen Gu, Hang Su +9 | cs.CL | 2026-09-26 |
| #160 | Automatic Speech Recognition for the Basaà Language: A Low-Resource Approach | Sophie Gertrude Ngo Mock, Charles Moudina Varmantchaonala, Paul Dayang +2 | cs.CL | 2026-09-26 |
| #161 | DualGuard: Dual-Mode Quality Control for Logic-Preserving Data Augmentation | Shenghao Li, Lin Zhao | cs.CL | 2026-09-26 |
| #162 | Masking Frequent Tokens Sharpens Direct Preference Optimization | Harshvardhan Saini, Samyak Jha, Yiming Tang +1 | cs.CL | 2026-09-26 |
| #163 | Self-Reports Do Not Identify Self-Models: An Identifiability Test for Counterfactual Reports | Phongsakon Mark Konrad, Toygar Tanyel, Serkan Ayvaz | cs.CL | 2026-09-26 |
| #164 | What Should the Reflector See? An Empirical Study of Evidence in Reflective Prompt Optimization | Xiaofan Zhou, Lu Cheng | cs.CL | 2026-09-26 |
| #165 | Streamlined Reflective Evolution for Task-Adaptive Self-Refinement Pipelines | Xiaofan Zhou, Lu Cheng | cs.CL | 2026-09-26 |
| #166 | AdaTutoRank: Learning to Rerank Document Sets via Adaptive Tutoring Optimization for RAG and Deep Research | Kailin Jiang, Lei Liu, Jian Xi +6 | cs.CL | 2026-09-26 |
| #167 | PC-SubMax: Efficient Prompt Compression via Regularized Submodular Maximization | Ziyi Zhang, Shuang Cui, Haotian Zhang +1 | cs.CL | 2026-09-26 |
| #168 | Explaining Textual Entailment with Lexical Entailments: Using LLMs to Supply Lexical Relations for Formal Proofs | Jorryt de Jong, Stefan Moraca, Ettore Cesari +1 | cs.CL | 2026-09-26 |
| #169 | Locally Sound, Globally Insufficient: The Local-Global Gap in Multi-Hop Reasoning | Bohao Chu, Hendrik Damm, Qianli Wang +4 | cs.CL | 2026-09-26 |
| #170 | Learning an Anchored Prompt Space for Continual Adaptation of Large Language Models | Rongguang Ye, Zhan Zhuang, Yichen Wu +2 | cs.CL | 2026-09-26 |
| #171 | When Users Change Their Minds: Measuring and Repairing Intent Drift in LLM Agents | Yanjie Zhang, Bowen Cao, Zixin Chen +1 | cs.CL | 2026-09-26 |
| #172 | Language as an Independent Information Layer: A Conceptual Model of Communication, Cognition and Decision-Making | Anastasiia Alifanova, Elena Benderskaya | cs.CL | 2026-09-26 |
| #173 | How to Reduce Whisper Hallucination | Husein Zolkepli | cs.CL | 2026-09-26 |
| #174 | Groupwise Agentic Grading and Advantage Redistribution for Code Agent RL | Jinhao Dong, Liang Zhao, Zihao Yue +7 | cs.CL | 2026-09-26 |
| #175 | HERO-MoE: Historical Expert Routing with Scale-Preserving Fusion | Junxiang Qiu, Zhengsu Chen, Xinting Hu +6 | cs.CL | 2026-09-26 |
| #176 | KV-Lingo: Learning KV-Cache Translators with Distillation | Valérie Castin, Keitaro Sakamoto, Anastasiia Filippova +3 | cs.CL | 2026-09-26 |
| #177 | The Alignment Paradox: How Post-Training Amplifies Confident Hallucinations in Language Models | Qingjia Huang, Yakai Li, Jianguo Wu +5 | cs.CL | 2026-09-26 |
| #178 | Does CoT-Pass@k Really Check the CoT? A Multilingual Mathematical Audit | Tarık Tuna Taşaltı, Burcu Hüdaverdi, David Semedo | cs.CL | 2026-09-26 |
| #179 | MixDetect: Word-Level Localization and Quantification of AI Editing | Hongrui Bao, Yubing Ren, Zhendong Pan +3 | cs.CL | 2026-09-26 |
| #180 | ExpVoyager: Direct Experience Navigation for Dynamic Agent Skill Synthesis | Kwangwook Seo, Dongha Lee | cs.CL | 2026-09-26 |
| #181 | From Knowing to Abstaining: Bridging the Representation-Action Gap in Vision-Language Models | Jialuo He, Huangxun Chen | cs.CL | 2026-09-26 |
| #182 | Focusing Condition: Inference-Time Self-Contrastive Steering Elicits Better Conditional Text Embeddings in LLMs | Zifeng Cheng, Lingyun Qian, Zhiwei Jiang +5 | cs.CL | 2026-09-26 |
| #183 | LLM Alignment--Utility Asymmetry under Semantic-Preserving Transformations | Mohan Li, Chengyu Yu, Francesco Sovrano +2 | cs.CL | 2026-09-26 |
| #184 | How Far Do Persona Effects Generalize in Language Models? | Yufan Zhou, Yuxuan Liu, Enze Ma +6 | cs.CL | 2026-09-26 |
| #185 | C-HAT-Bench: Benchmarking Chinese AI-Text Detection Beyond Fully Generated Text | Qing Yang, Zixiang Luo, Zhenyu Mao +6 | cs.CL | 2026-09-26 |
| #186 | On the Behavioral Traits of LLM Agents | Haokai Zhao, Jie Gao, Yunze Xiao +5 | cs.CL | 2026-09-26 |
| #187 | OpenTumorBoard: A Real-World Benchmark of Multidisciplinary Tumor Board Discussion Trajectories | Anqi Li, Zhixuan Ge, Yixuan Duan +9 | cs.CL | 2026-09-26 |
| #188 | ARSM: Auto-Regressive State Machine for Agentic Reasoning Compression | Xiafeng Man, Siyuan Ye, Xiaosong Ma | cs.CL | 2026-09-26 |
| #189 | Are You Sure You're Sure? Two Confounds in a Sycophancy Benchmark | Atharv Gupta, Akshat Jindal, Lavanya Nigam +1 | cs.CL | 2026-09-26 |
| #190 | Linger and Lose: Knowledge Collapse in Low-Bit Language Models | Prashanna Mani Paudel, Shivanand Venkanna Sheshappanavar | cs.CL | 2026-09-26 |
| #191 | The Key Handoff: Retrieval in Hybrid Language Models | Kaan Kale, Oguzhan Baser, Sriram Vishwanath | cs.CL | 2026-09-26 |
| #192 | TCMQA: A 38K-Question Traditional Chinese Medicine Benchmark with a Licensed-Practitioner Reference | Tzu-Heng Huang, Jet Lin, Eric Lin | cs.CL | 2026-09-26 |
| #193 | Checking Leakage Witnesses versus Certifying Bounded Non-Leakage | Chao Feng, Burkhard Stiller | cs.CR | 2026-09-26 |
| #194 | DegreeSpar: Structured Degree Sparsity for Efficient Secure Transformer Inference | Yifei Cai, Zhuoran Li, Xiaozuo Shen +2 | cs.CR | 2026-09-26 |
| #195 | Residual Transferability in Neural Image Watermarking | Ziping Dong, Qi Li, Xinchao Wang | cs.CR | 2026-09-26 |
| #196 | SkillDRE: Dual-Stage Red-Team Evolution of Agent Skills via Pre-Execution and Runtime Feedback | Pengyu Zhu, Jingyi Yang, Yi Liu +2 | cs.CR | 2026-09-26 |
| #197 | CyberClear: A Benchmark for LLM Agent Systems on APT Attack Chain Provenance | Qi Chen, Fushuo Huo, Hangli Shen +3 | cs.CR | 2026-09-26 |
| #198 | Hearsay: Can an Auditor Trust the Record a Deployed Agent Harness Writes? | Jiahong Dai, Zhuochen Yang, Pengyang Shao +5 | cs.CR | 2026-09-26 |
| #199 | REFINE: A Resilient Evolution Framework for Intelligent Enterprise Alert Triage in Security Operations Centers | Huimin Chen, Quan Long, Yanhao Wang | cs.CR | 2026-09-26 |
| #200 | Reading Is Not Leaking: Local, Auditable Measurement and Reduction of Inference Exposure from Public Footprints | Mahmudul Faisal Al Ameen | cs.CR | 2026-09-26 |
| #201 | Trust the Brand, Lose Control: How Identity Hijacks LLM Agent Orchestration | Xutao Mao, Rui Qian, Linghan Chen +5 | cs.CR | 2026-09-26 |
| #202 | Ask Without Telling: Local SLMs Consult Cloud LLMs Without Revealing Task Intent | Yanmeng Wang, Yunxuan Li, Shilong Fan +2 | cs.CR | 2026-09-26 |
| #203 | Silent Failures in Agentic Security Evaluation: A Validated Harness for Tool-Call Mediation Under Indirect Prompt Injection | Animesh Shaw | cs.CR | 2026-09-26 |
| #204 | Learning to Refer: Client-Resolved Generation for Privacy-Aware Language Models | Jeongho Yoon, Chanhee Park, Yongchan Chun +5 | cs.CR | 2026-09-26 |
| #205 | AgentTell: Behavioural Side-Channel Leakage in Browser-Use Agents | Asif Shahriar, Md Nafiu Rahman, Sadif Ahmed +2 | cs.CR | 2026-09-26 |
| #206 | Gaussian Image Steganography via Parameter-Domain Keyed Embeddings | Tong Wu, Runze Cheng, Xiaoyue Fan +1 | cs.CV | 2026-09-26 |
| #207 | CausalDriveBench: Evaluating Causal Reasoning in Vision-Language-Action Models for Autonomous Driving | Narendiran Chembu, Navvrat Rao, Shreedhar Shreeshail Kodate +10 | cs.CV | 2026-09-26 |
| #208 | PruneForget: Joint Unlearning and Pruning of Vision Models | Yu-Shan Tai, Amber Yijia Zheng, Raymond A. Yeh | cs.CV | 2026-09-26 |
| #209 | PQR3D: Progressive Query Refinement over Reference-Conditioned Temporal Windows for Multi-View 3D Object Detection | Hui Ye, Yudong Liu, Yiran Chen +2 | cs.CV | 2026-09-26 |
| #210 | OneFixer: High-Quality and Consistent One-Step Autoregressive 3DGS Refinement for Driving Scenes | Boseong Jeon, Junhyeop Lee, Juhan Cha +1 | cs.CV | 2026-09-26 |
| #211 | Federated 3D Gaussian Splatting for Large-Scale Scene Reconstruction at Wireless Edge | Guanlin Wu, Chao Hu, Pu Chen +4 | cs.CV | 2026-09-26 |
| #212 | Binaural Audio-Visual Instance Segmentation | Saijun Wang, Guanfeng Tang, Hongbo Zhao +4 | cs.CV | 2026-09-26 |
| #213 | KeyRec: Bounded Visual Memory for Streaming and Long-Video Understanding | Zihan Chen, Xuejian Rong, Xiaojuan Wang +4 | cs.CV | 2026-09-26 |
| #214 | Scalable In-Domain Self-Supervised Foundation Model for Dense Representation Transfer in High-Resolution Plant Imaging | Junlin Guo, Sharmin Majumder, Isaac Lyngaas +2 | cs.CV | 2026-09-26 |
| #215 | Contamination, Prior, or Evidence? Decomposing and Training Evidence Use in Whole-Slide Vision-Language Models | Wenhao Zhang, Zhongliang Zhou, Shiyuan Zhang +6 | cs.CV | 2026-09-26 |
| #216 | Presence Is Not Faithfulness: Figurative Vehicle Intrusion in Text-to-Image Generation | Xiaoyu Ma, Chen Yang, Hao Chen | cs.CV | 2026-09-26 |
| #217 | Evaluating Single and Multi-Omics Based Explainable Artificial Intelligence (MOXAI) for Molecular Subclass Classification of Adult-Type Diffuse Gliomas | Md Zahangir Alom, Quynh T. Tran, Breuer Alexandar +1 | cs.CV | 2026-09-26 |
| #218 | Devol-ONE: One Autoregressive Mixture of Transformers to Unify Vision-Language-Action and Latent World Modeling | Hongyi Cai, Yi Herng Ong, Tingshiuan C. Wu +4 | cs.CV | 2026-09-26 |
| #219 | Kernel-Based Steering of CLIP with Vision-Language Model Preferences | Sajjad Ghiasvand, Haniyeh Ehsani Oskouie, Sina Mansouri +3 | cs.CV | 2026-09-26 |
| #220 | Geometry-Preserving Blind Watermarking for Raw 3D Point Clouds | Rungui Zhou, Chuanzhi Zhou, Ruihuan Wang +1 | cs.CV | 2026-09-26 |
| #221 | Skeletons in Flow: Graph Structured Flow Matching for Human Motion Prediction | Yixuan Wang, Brandon C. Fallin, Warren E. Dixon | cs.CV | 2026-09-26 |
| #222 | Two-Stage Multi-View Gait Recognition with a Re-Embedding Network | Long Hoang Le, Trung Thanh Ngo | cs.CV | 2026-09-26 |
| #223 | RoboSTAR: Next-Scale Autoregressive Sign Language Translation for Humanoid Robots | Yujia Zeng, Chensheng Peng, Yuxin Chen +3 | cs.CV | 2026-09-26 |
| #224 | FSS-UBrain: Multi-region Few-Shot Brain Tumor MRI Segmentation | Truong Viet Vu, Nguyen Phuc Nguyen, Dang Thi Thu Hang +4 | cs.CV | 2026-09-26 |
| #225 | HeroFrame-Bench: Reference-Anchored Evaluation via Rubric--Ranking Co-Evolution for Movie Hero Frame Selection | Weitai Kang, Hanieh Deilamsalehy, Yumo Xu +3 | cs.CV | 2026-09-26 |
| #226 | One Perception, All Maneuvers: Directional Traffic Signal Understanding for Maneuver-Level Signal Intent Prediction | Ang Zou, Runzhe Zheng, Zhigang li +5 | cs.CV | 2026-09-26 |
| #227 | FoundDSR: A Generalizable Foundation Model with Guided 2D Gaussian Splatting for Depth Super-Resolution | Zhengxue Wang, Zhiqiang Yan, Yuan Wu +3 | cs.CV | 2026-09-26 |
| #228 | Progressive-View On-Policy Distillation for Regional-to-Global Transfer in Multimodal LLMs | Shanfeng Huang, Zhou Fang, Song Xiao +1 | cs.CV | 2026-09-26 |
| #229 | SGA-Flow-GRPO: Spatial Gradient-Guided Credit Assignment for Flow-GRPO | Yunkai Yang, Yudong Zhang, Xinying Chen +5 | cs.CV | 2026-09-26 |
| #230 | OpenMASC: An Open-Source Pipeline for Cross-Trajectory Metal-Aware Sampling and Correction in Accelerated MRI | Zhengyi Lu, Ming Lu, Chongyu Qu +11 | cs.CV | 2026-09-26 |
| #231 | EyeVQA: Benchmarking Ophthalmic Vision-Language Models from Recognition to Spatial Grounding | Gujie Shao, Zixun Xie, Xuechun Xing +7 | cs.CV | 2026-09-26 |
| #232 | Fewer Tokens, More Self-Teaching: On-Policy Self-Distillation for Extreme Visual Token Reduction | Junxian Li, Ruixuan Yang, Tianao Zhang +3 | cs.CV | 2026-09-26 |
| #233 | StegGNN: Learning Graphical Representation for Image Steganography | Abhinav Kumar, Shorya Singhal, Agam Pandey +2 | cs.CV | 2026-09-26 |
| #234 | An End-to-End Latent-Rollout Approach for Pushing Few-Step ImageNet-$256$ Generation to FID $1.11$ without Fréchet Losses | Xiaoran Xu, Yujing Wang | cs.CV | 2026-09-26 |
| #235 | RefCompose: Multi-Reference Image Generation via LoRA-Conditioned Diffusion | Sai Sri Teja Kuppa, Parth Shinde, Priyadharsan Balaji S +2 | cs.CV | 2026-09-26 |
| #236 | Endo-TSR: Temporal Spectral Modeling of Appearance and Motion for Endoscopic Reconstruction | Taoyu Wu, Yiyi Miao, Qi Shao +4 | cs.CV | 2026-09-26 |
| #237 | Toward On-Chip Training of Spiking Neural Networks for Dense Event-Based Vision | Maxime Vaillant, Axel Carlier, Lai Xing Ng +2 | cs.CV | 2026-09-26 |
| #238 | RefAdapt-DiT: Adaptive Joint Attention for Reference-Conditioned Diffusion Transformers | Jian Tang, Jiawei Fan, Qiannan Zhou +3 | cs.CV | 2026-09-26 |
| #239 | CityToolVQA: Tool-Augmented Visual Question Answering for 3D Spatial Cognition in Urban Low-Altitude Environments | Boao Yu, Yingzhen Nie, Yue Hu +2 | cs.CV | 2026-09-26 |
| #240 | De-biasing Skeleton-based Action Recognition with Convex Hull Adaptive Shift | Mengyuan Liu, Yuhang Wen, Yi Zhang +4 | cs.CV | 2026-09-26 |
| #241 | QuacamFM: Quaternion-Constrained Flow Matching for Camera Pose Estimation | Bao-Long Tran, Cuong Le, Tahereh Dehdarirad +2 | cs.CV | 2026-09-26 |
| #242 | Seeing Parts, Reasoning about Worlds: Visual Inference under Partial Observation | Wei Wang, Wenqiao Zhang, Yutong Lin +2 | cs.CV | 2026-09-26 |
| #243 | REMEDY: How Far Is Video Generation from Medical Education World Models? | Lixing Tan, Yanghao Zhou, Qing Xia +3 | cs.CV | 2026-09-26 |
| #244 | Can Motion-Language Models Ground Structure? STRIDE for Evaluating the Evaluators | Lixing Tan, Qing Xia, Yuting Guo +2 | cs.CV | 2026-09-26 |
| #245 | Back-Tracking from Clarity: Self-Learning to See Text from Afar | Duc-Tri Tran, Phi Le Nguyen, Minh Hoai | cs.CV | 2026-09-26 |
| #246 | JEPA Learns What the Mask Leaves Unrecoverable | Peng Xie, Amr Alanwar | cs.CV | 2026-09-26 |
| #247 | GeoCR: Learning a Generalist Cloud Removal Prior from Heterogeneous Observations | Jeonghyeok Do, Munchurl Kim | cs.CV | 2026-09-26 |
| #248 | Cross-Domain Few-Shot Writer Adaptation for Real-World Handwritten Mathematical Expression Recognition | Paulo Grane Gabriel Silva, Lorenz Bernard Marqueses, Joel Ilao | cs.CV | 2026-09-26 |
| #249 | UnStep: Training-Free Acceleration of Causal Video Diffusion with Fewer Steps Than Distillation | Youssef Mansour, Enis Simsar, Fadime Sener +4 | cs.CV | 2026-09-26 |
| #250 | SetOPD: From Few Visual Exemplars to Multimodal Candidate Sets for Remote-Sensing Open-Prompt Detection | Jinlong Hu, Yi Zhang, Zhiqi Xia +2 | cs.CV | 2026-09-26 |
| #251 | DepthBench: Measuring How Residual Connections Enable More Computational Depth | Keyu Wang, Yangyi Huang, Jiale Kang +3 | cs.CV | 2026-09-26 |
| #252 | RIPE-MambaSpike: Resolution-Independent Spiking-State-Space Interfaces for Parameter-Efficient Event-Based Vision | Md Muhiminul Islam, Shoaib Ahmed Dipu, Sayeed Shafayet Chowdhury | cs.CV | 2026-09-26 |
| #253 | In-Flight KV Cache with Clean Anchors for Faster Autoregressive Video Diffusion | Yikai Wang, Xiao Han, Mengmeng Xu +9 | cs.CV | 2026-09-26 |
| #254 | Harnessing Coupled Stream Completion For Human-Object Ineraction Modeling | Dawei Guan, Di Yang, Jiangtao Wang | cs.CV | 2026-09-26 |
| #255 | Feature Space Guidance for Breast Cancer Classification in DCE-MRI | Benjamin Hamm, Yannick Kirchhoff, Maximilian Rokuss +6 | cs.CV | 2026-09-26 |
| #256 | CFCH: Coarse-Fine Collaborative Hierarchical Learning for Anterior Segment Disease Analysis | Peng Wang, Haohan Zou, Yanlin Wu +3 | cs.CV | 2026-09-26 |
| #257 | Attribution Gaps in Zero-Training LLM+OVOD Pipelines: A Fine-Grained Analysis of the CAAP--SNAP Discrepancy | Yu-Feng Yen | cs.CV | 2026-09-26 |
| #258 | OmniSmartHome: A Multimodal Reasoning Benchmark for Smart-Home Agents | Jihoo Jung, Suho Yoo, Jeongsoo Choi +5 | cs.CV | 2026-09-26 |
| #259 | Retrieved but Not Delivered: Multimodal Memory Delivery for Long-Term Agents | Yuhang Jiang, Qingwei Liao, Kaize Yin +3 | cs.CV | 2026-09-26 |
| #260 | SPACE: Sparse Predictive Attractor via Counterfactual Eviction for Streaming Video Memory | Hongjin Niu, Weizhan Zhang, Shuo Bao +4 | cs.CV | 2026-09-26 |
| #261 | GAUGE: Group-Wise View-Inconsistency Rectification for Feed-Forward 4D Tracking | Zhuoqian Feng, Weixing Chen, Ziliang Chen +2 | cs.CV | 2026-09-26 |
| #262 | Levy-Driven Correspondence Estimation for Registration | Qianliang Wu, Jiaqi Yang, Wankou Yang +4 | cs.CV | 2026-09-26 |
| #263 | DraftAttention2: Fast Video Diffusion with Low-Resolution-Guided Mixed-Precision Attention | Rui Ding, Haopeng Li, Weize Ma +10 | cs.CV | 2026-09-26 |
| #264 | InterTab: Interleaved Visual-Structure Alignment for Multi-Modal Table Reasoning | Hanqian Li, Sirui Huang, Chen Ling +12 | cs.CV | 2026-09-26 |
| #265 | RCVLA: 4D Radar-Grounded Semantic Reasoning and Trajectory Arbitration for Autonomous Driving | Lianqing Zheng, Xiaokai Bai, Yixuan Luo +6 | cs.CV | 2026-09-26 |
| #266 | MM-OPD: Towards One More Bottleneck Between Perception and Reasoning | Jintao Tong, Yujing Lou, Zhanming Shen +6 | cs.CV | 2026-09-26 |
| #267 | DPAMixerSR: An Efficient Degradation-Pattern-Aware Model for Image Super-Resolution | Song-Li Wu, Haonan Jiang, Jixuan Fan +3 | cs.CV | 2026-09-26 |
| #268 | ProDyGS: Dynamic Gaussian Splatting from a Single Static Monocular Camera | Ugo Leone Cavalcanti, Fabio Tosi, Matteo Poggi +4 | cs.CV | 2026-09-26 |
| #269 | Region-Local Copula Evidence Fusion for Heterogeneous Remote Sensing Change Detection | Zhiyuan Ji, Junjun Yin, Jian Yang | cs.CV | 2026-09-26 |
| #270 | REALIS: A Curated Dataset for Studying the Challenges of AI Image Detection | Aleksandr Gushchin, Khaled Abud, Georgii Bychkov +5 | cs.CV | 2026-09-26 |
| #271 | Gradient-Guided Decoupled Adaptation for Geospatial Vision-Language Models | Dongdong Wang, Deepak Balakrishnan, Ravi Srinivasan +1 | cs.CV | 2026-09-26 |
| #272 | AnesTRACE: Benchmarking Intraoperative Anesthesia from Multimodal Perception to Multi-step Decision-Making | Ziwei Huang, Qi Gao, Zhe Ji +5 | cs.CV | 2026-09-26 |
| #273 | LoCoVSR: Local Context Diffusion Posterior Sampling for Video Super-Resolution | Matan Ben Chorin, Michael Elad | cs.CV | 2026-09-26 |
| #274 | From Feed-Forward to Flow: Unifying Reconstruction and Generation Is Easier Than You Think | Haoru Wang, Qianfan Shen, Kai Ye +2 | cs.CV | 2026-09-26 |
| #275 | OmniMoE-VL: A Sparse Vision-Language Model with Coupled Visual-Depth Routing | Long Qian, Bingke Zhu, Jiaqi Wei +2 | cs.CV | 2026-09-26 |
| #276 | CT-OPD: Counterfactual Trace On-Policy Distillation for Diffusion Vision-Language Models | Long Qian, Bingke Zhu, Jiaqi Wei +3 | cs.CV | 2026-09-26 |
| #277 | Hierarchical Frequency-Domain Compression of Implicit Geometric Representations for Large-Scale Point Clouds | Manlin Yao, Jiabin Liu, Guan Wang +2 | cs.CV | 2026-09-26 |
| #278 | Latent Space Is Not Flat: Rethinking Latent Structure for 3D Medical Image Synthesis | Haowen Xue, Hao Chen, Hexuan Hu +6 | cs.CV | 2026-09-26 |
| #279 | Progressive Risk Estimation for Accident Anticipation | Samet Hicsonmez, Eray Çakar, Nermin Samet +1 | cs.CV | 2026-09-26 |
| #280 | USAI-Quant: A Quantitative Reasoning Benchmark for Vision-Language Models in Built Environments | Dongdong Wang, Qingqi Song, Yuzhou Chen +3 | cs.CV | 2026-09-26 |
| #281 | Unlocking Geodesic Gromov-Wasserstein Distances for 3D Modeling | Krzysztof Marcin Choromanski, Derek Long, Ananya Parashar +1 | cs.CV | 2026-09-26 |
| #282 | VCRE-Fib: View-Conditioned Regional Evidence for Fine-Grained Ultrasound Grading of Schistosoma japonicum-Associated Liver Fibrosis | Ziyang Xu, Shuli An, Hao Zhou +5 | cs.CV | 2026-09-26 |
| #283 | Beyond Temporal Smoothing: Spatial Energy Budgets Stabilize One-Step Diffusion Editing | Shengxiao Zhou, Lei Luo, Jian Yang | cs.CV | 2026-09-26 |
| #284 | SynCo: Learning Cross-Modal Synergy by Contrasting Interaction Residuals | Yavuz Yarici, Ghassan AlRegib | cs.CV | 2026-09-26 |
| #285 | PolyTopoBench: A Benchmark for Complex Vector Polygon Generation from Remote Sensing Imagery | Zeping Liu, Ni Lao, Weiwei Sun +5 | cs.CV | 2026-09-26 |
| #286 | Is H&E Image-to-Spatial Transcriptomics Simpler Than It Looks? | Duc T. Nguyen, Thanh Ha Do, Phuong M. Cao +1 | cs.CV | 2026-09-26 |
| #287 | SV2V-RSim: A Comprehensive Benchmark for Self-Selective V2V Cooperative Perception with Near-Realistic Data | Yulu Wu, Chao Wei, Jujun Cheng +6 | cs.CV | 2026-09-26 |
| #288 | Multimodal LLMs Outperform Pathology Foundation Models in Cross-Domain Histological Similarity | Yishu Zhang, Yun Li, Daiwei Zhang | cs.CV | 2026-09-26 |
| #289 | Improving Video Sparse Attention with Fine-grained Router and Sparse Rebasing | Peiyuan Zhang, Guoqiang Wei, Yilong Zhao +7 | cs.CV | 2026-09-26 |
| #290 | Rethinking the Fully Hyperbolic Vision Transformer in Polar Coordinates | Ahmad Bdeir, Niels Landwehr | cs.CV | 2026-09-26 |
| #291 | Synthetic Thermal Image Generation for Real-Time Animal Detection Under Low-Visibility Conditions | James Momoh, Khandaker Mamun Ahmed | cs.CV | 2026-09-26 |
| #292 | DynamicDx: Evaluating Evidence Acquisition in Video-Based Diagnosis | Jiahui Li, Yutong Guo, Nan Yang +3 | cs.CV | 2026-09-26 |
| #293 | Distributed Hydrological Modeling in the Feature Space | Mohamad Hakam Shams Eddin, Maria Luisa Taccari, Yikui Zhang +3 | cs.CV | 2026-09-26 |
| #294 | ReVision3D: Attribution-Guided Recursive Self-Improvement for 3D Medical Perception | Ho Hin Lee, Yuyin Zhou, Yannan Yu +2 | cs.CV | 2026-09-26 |
| #295 | Oracle Gaps in Reliability Coverage: Sampling Noise or Policy Specialization? | Mert Onur Cakiroglu, Mehmet Dalkilic, Hasan Kurban | cs.CV | 2026-09-26 |
| #296 | Certified Interface Aliases: Exact Collisions in Vision-Language Preprocessing, and When They Exist | Mert Onur Cakiroglu, Elham Buxton, Mehmet Dalkilic +1 | cs.CV | 2026-09-26 |
| #297 | Safety-Constrained Cascade Inference for Robust Malaria Cell Classification Under Field Corruptions | J. T. Hagbe, Michel Emel | cs.CV | 2026-09-26 |
| #298 | Residual Diffusion Implicit Models | João Guerreiro, Pedro Tomás, Helena Aidos +1 | cs.CV | 2026-09-26 |
| #299 | Environmental Impact of Generative and Agentic AI: An in-Depth Analysis and Green Solutions | Abderaouf Bahi, Amel Ourici, Ibtissem Gasmi | cs.CY | 2026-09-26 |
| #300 | Empowering Hybrid Attention Models on NPUs | Yinyuan Zhang, Daliang Xu, Xiaolong Huang +4 | cs.DC | 2026-09-26 |
| #301 | SparSP: Exploiting Communication Sparsity for Sequence-Parallel Video DiTs | Desen Sun, Xinrui Zhong, Yuke Wang +1 | cs.DC | 2026-09-26 |
| #302 | ASCEND: Personal AI Agents for Autonomous Scientific Computing Across HPC Clusters and GPU Workstations | J. Paul Liu, Uthpala Herath, Andrew Petersen | cs.DC | 2026-09-26 |
| #303 | Learning Shuffle Ideals with Membership Queries and Contrastive Examples | S. Mahmoud Mousawi, Pierluigi San Pietro, Sandra Zilles | cs.FL | 2026-09-26 |
| #304 | Learnable Randomization as Commitment Against Adaptive Optimizers | Zihan Deng, Chuanzhi Xu, Xiaozhen Zhong +2 | cs.GT | 2026-09-26 |
| #305 | DashAct: A Progressive Diagnostic Benchmark for GUI Agents in Interactive Dashboard Analysis | Chuhan Zhang, Qi Xie, Ziyue Wang +4 | cs.HC | 2026-09-26 |
| #306 | When Does Dense Retrieval Need Asymmetric Geometry? A Bias-Variance Theory of Shared and Dual Projections | Maojun Sun, Yancheng Yuan, Jian Huang +1 | cs.IR | 2026-09-26 |
| #307 | Concepts Complement Dense Semantics: Learning Compact Sparse Spaces for Text-Image Retrieval | Yoonseo Kim, Jungwoo Choi, Cheonyoung Park +3 | cs.IR | 2026-09-26 |
| #308 | Mend the Measurement Gap: Latent User Preference Modeling for Short-Form Video Recommendation | Shuo Chang, Yueqi Wang, Zihuan Diao +7 | cs.IR | 2026-09-26 |
| #309 | One-Step Generative Modeling via Unbalanced Optimal Transport | Yirong Shen, Mengfei Xia, Junpeng Jing +2 | cs.IT | 2026-09-26 |
| #310 | Emergent One-Third Scaling Law as Attention Tries to Concentrate | Yizhou Liu, Sara Kangaslahti, Jeff Gore | cs.LG | 2026-09-26 |
| #311 | LLM Unlearning Evaluation with TRIAGE | Danial Ataee, Peter Triantafillou | cs.LG | 2026-09-26 |
| #312 | An Attention-Driven Heterogeneous GNN Model for Credit Card Fraud Detection | Kathiresan Jayabalan, Sethuraman Radhakrishnan | cs.LG | 2026-09-26 |
| #313 | SAMBAR: Selective Anchoring via Method of Multipliers for Balanced Knowledge Acquisition and Retention in Vision-Language-Action Models | Aayushi Shrivastava, Xunlan Zhou, Hongrui Zhao +2 | cs.LG | 2026-09-26 |
| #314 | How Reusable Are Benchmarks with Richer Feedback? | Youssef Allouah, John Duchi | cs.LG | 2026-09-26 |
| #315 | Handwritten Digit Leakage from Smartphone Motion Sensors Across Unseen Users and Phone Models | Constantino Álvarez Casado, Erkka Rantahalvari, Matteo Pedone +6 | cs.LG | 2026-09-26 |
| #316 | What Should We Freeze? Guarded Freezing: Connectivity Shapes the Fine-Tuning of Pretrained Models | Leonel Aguilar | cs.LG | 2026-09-26 |
| #317 | Latency-Aware Client Assignment for Parallel Split Learning With Global Sampling | Mohammad Kohankhaki, Valentin Rentschler, Anke Schmeink | cs.LG | 2026-09-26 |
| #318 | REALM: Regime-Switching, Explainable, and Activation-Induced Linear Models | Xiaoran Cheng, Sen Na, Jia Li | cs.LG | 2026-09-26 |
| #319 | Spectral Reversal: Counteracting Singular Value Bias for Graph Prompting | Hanxu Yang, Yuhuan Zhao, Xiaodong He +1 | cs.LG | 2026-09-26 |
| #320 | Playing to Par: Reinforcement Learning for Provably Optimal Quadrilateral Block Decompositions | Arjun Narayanan, Per-Olof Persson | cs.LG | 2026-09-26 |
| #321 | CAFE: Counterfactual Prediction via Fast Posterior Estimation | Xinyan Han, Xiaoyu Lin, Hao Zou +3 | cs.LG | 2026-09-26 |
| #322 | Uncertainty-Aware Selection of Online Algorithms with Simulator Ensembles | Yongyi Guo, Zifan Xu, Ziping Xu +1 | cs.LG | 2026-09-26 |
| #323 | Efficient Support Recovery of Mixtures of Sparse Linear Classifiers with Less Measurements | Xiaxin Li, Arya Mazumdar | cs.LG | 2026-09-26 |
| #324 | Analytic-Walk Rotary Positional Encodings for Graphs | Jiaqing Xie, Yuxin Wang, Xipeng Qiu | cs.LG | 2026-09-26 |
| #325 | Rethinking Cross-Channel Importance in Time-Series Forecasting | Yong-Hoon Choi, Kwang-Hyun Park, Youngjin Cho | cs.LG | 2026-09-26 |
| #326 | HM-ROUTER: Joint Model and Harness Routing for Agentic Systems | Hao Mark Chen, Royson Lee, Yasuyuki Okoshi +3 | cs.LG | 2026-09-26 |
| #327 | DP-Rec: Towards Dynamic Patching for Efficient Long-Sequence Recommendation | Dwipam Katariya, Thomas Caputo, Akshat Shreemali +6 | cs.LG | 2026-09-26 |
| #328 | CompassPlay: Rewarding the Proposer for Where It Moves the Solver | Sophia Xiao Pu, Ximeng Sun, Jiang Liu +4 | cs.LG | 2026-09-26 |
| #329 | "Where Can I Trust You?": Boundary-Aware Evaluation of Surrogate Fidelity | Jackson Eshbaugh | cs.LG | 2026-09-26 |
| #330 | Arithmetic Simplicity in Stochastic Gradient Methods | Bin Fu, Pengfei Gu, Jose Nunez +1 | cs.LG | 2026-09-26 |
| #331 | Anytime-Valid LLM Leaderboards via Benchmark-weighted and Block-Factorized e-Processes | Hongfu Gao, Songxin Zhang, Zejian Xie +3 | cs.LG | 2026-09-26 |
| #332 | Representation Editing for Multimodal Test-Time Adaptation | Longfei Huang, Xiangyu Wu, Yang Yang | cs.LG | 2026-09-26 |
| #333 | When Can Old Evaluations Certify a New Model? Label-Efficient Release Decisions under Evaluator Drift | Joyanta Jyoti Mondal, Mridul Banik, Md. Shifatul Ahsan Apurba +1 | cs.LG | 2026-09-26 |
| #334 | Self-Reconstruction Dynamics for Autoencoder Reconstruction Refinement | Hitoshi Iyatomi | cs.LG | 2026-09-26 |
| #335 | Certification Frontiers for Gaussian LoRA: Independent Priors, Posterior Risk, and Prediction-Preserving Balancing | Joyanta Jyoti Mondal, Ibne Farabi Shihab | cs.LG | 2026-09-26 |
| #336 | Learning Through Game: Skewed Transfer of Tabular Knowledge to Strengthen Image Model | Longfei Huang, Shangdong Yang, Yang Yang | cs.LG | 2026-09-26 |
| #337 | Topology-Adaptive Hyperbolic Graph Attention Networks Guided by the Hyperbolic Sombor Index | Haifang Cao, Boan Tao, Xiyuan Gao +3 | cs.LG | 2026-09-26 |
| #338 | HyperLabel: Multi-Label Classification via Hypergraph-Based Label Correlation Modeling | Peiyu Zhang, Heng Ping, Nikos Kanakaris +5 | cs.LG | 2026-09-26 |
| #339 | SIMANF: Sample Free Learning of Unnormalized Distributions via Simulated Annealing in Normalizing Flows | Vikas Kanaujia | cs.LG | 2026-09-26 |
| #340 | A Solvable Theory of Pre-training Data Poisoning: Regime-Dependent Scaling Exponents | Indranil Halder, Rastri Dey, Cengiz Pehlevan | cs.LG | 2026-09-26 |
| #341 | A Journey to the Edge of Stability | Jaerin Lee, Kyoung Mu Lee | cs.LG | 2026-09-26 |
| #342 | FUND: Density Flow for Sampling Unnormalised Distributions | Vikas Kanaujia, Vipul Arora | cs.LG | 2026-09-26 |
| #343 | Refresh or Realize? Compute Allocation in Drifting Models | Sipeng Chen, Xu Zheng, Shibo Li | cs.LG | 2026-09-26 |
| #344 | When Does Synergy Help Active Feature Acquisition? A PID-Based Study | Jie Li, Maruf A. Dhali, Hjalmar R. Bouma | cs.LG | 2026-09-26 |
| #345 | On the Capability and Limitation of Hard Prompt | Lijia Yu, Shuaitong Liu, Gaojie Jin +2 | cs.LG | 2026-09-26 |
| #346 | What Can a Leaderboard Certify? Compositional Controllability for Fair Evaluation and Training of Biomedical Literature-Review Agents | Zhaowei Han, Xiang Zhang, Lingxiao Guan +4 | cs.LG | 2026-09-26 |
| #347 | Phase Space Attention:A Hairer Lift Circumvents the Single-Layer Induction Obstruction | Kingsuk Maitra, Shagun Sood Morteza Hosseini, Suman Gunnala +1 | cs.LG | 2026-09-26 |
| #348 | Superposed Inference for Hyperdimensional Computing | Quanling Zhao, Nilesh Prasad Pandey, Ye Tian +1 | cs.LG | 2026-09-26 |
| #349 | Not All Errors Matter: Decision-Relevant Prediction Error Predicts Planning Quality | Linhao Wang, Yiyan Fan, Dongjin Huang | cs.LG | 2026-09-26 |
| #350 | Active Feature Acquisition With Incomplete Training Data | Reza Rezvan, Valter Schütz, Han Wu +2 | cs.LG | 2026-09-26 |
| #351 | Continual Data Unlearning in Diffusion Models via Transition-based Regularization | Sunbeom Jeong, Sehwan Kim, Sangwoo Hong +1 | cs.LG | 2026-09-26 |
| #352 | When the Merge Coefficient Stops Mattering: Proximity Regularized Merging for Continual LoRA Adaptation | Yixuan Liu, Yuhao Sun, Sen Song +1 | cs.LG | 2026-09-26 |
| #353 | A Comparative Analysis of Attention versus State-Space Models for In-Context Learning | Enes Arda, Semih Cayci, Atilla Eryilmaz | cs.LG | 2026-09-26 |
| #354 | Analog-Friendly Predictive Coding without Activation Derivatives | Francesco Innocenti | cs.LG | 2026-09-26 |
| #355 | Editable Map-Conditioned Trajectory Generation for Human Mobility Simulation | Takayuki Mizuno, Shouji Fujimoto, Mikito Hiruki +1 | cs.LG | 2026-09-26 |
| #356 | Black-Box Auditing of Epistemic Reliability in Multi-Agent Debate Distillation | Derui Wang, Zewei Shi, Rayne Holland +4 | cs.LG | 2026-09-26 |
| #357 | DiffPTS: Rethinking Diffusion ELBO for Probabilistic Time Series Forecasting | Weiwei Ye, Dongyuan Li, Hangchen Liu +3 | cs.LG | 2026-09-26 |
| #358 | Graph Memory: Spectral Associative Memory via Dirichlet Energy | Zhaoyang Shi | cs.LG | 2026-09-26 |
| #359 | STRIDE: State-Transition Representation via Increment Dynamics and Evolution | Yuchen Xiong, Siming Huang, Jianfeng Sun | cs.LG | 2026-09-26 |
| #360 | Measurement Boundaries in LLM Financial Agent Evaluation: Fixed-Tape Execution and Multi-Defect Auditing | Weicheng Xue | cs.LG | 2026-09-26 |
| #361 | Attribution Without a Second Pass: Inline Per-Sample Gradient Provenance at ~1% Overhead | Amit Nautiyal | cs.LG | 2026-09-26 |
| #362 | TimeES: Probabilistic and Deterministic Time Series Forecasting via Evolutionary Spectra | Weiwei Ye, Renhe Jiang, Hangchen Liu +2 | cs.LG | 2026-09-26 |
| #363 | Using Machine Learning to Investigate Predictors of Fasting Blood Glucose: Insights into Circadian Timing and Age Interactions | Viktoriya Bu-Dager, Silvia Cirstea | cs.LG | 2026-09-26 |
| #364 | Recovery-Directed Symbolic Distillation of Neural Likelihoods | Kianté Fernandez, Xinwei Li | cs.LG | 2026-09-26 |
| #365 | HoTS: Homophily-Aware Temperature Scaling for Graph Neural Network Calibration | Inwoo Tae, Yoontae Hwang, Yongjae Lee | cs.LG | 2026-09-26 |
| #366 | Beyond the Manifold Hypothesis: Hybrid Spectral Parameterizations for Flow Matching | Ségolène Martin, Anne Gagneux, Quentin Bertrand +2 | cs.LG | 2026-09-26 |
| #367 | Rethinking Training-Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It | Tianrun Yu, Kaixiang Zhao, Shangzhe Li +4 | cs.LG | 2026-09-26 |
| #368 | Length-Independent State Tracking Under a Parallel Scan | Julien Brandoit, Arthur Fyon, Thomas Braipson +5 | cs.LG | 2026-09-26 |
| #369 | Write Back the $Δ$: Revisiting the Same Tokens with Fresh Representations | Wencheng Ye, Anning Hu, Xiangdong Zhang +5 | cs.LG | 2026-09-26 |
| #370 | Adapting Nonstationary Multi-output Gaussian Processes to Bayesian Optimization | Zikai Xie | cs.LG | 2026-09-26 |
| #371 | PolyStepOR: Learning to Decide Without Optimal Decisions | Viet The Nguyen, Gunther Gust, An Thai Le | cs.LG | 2026-09-26 |
| #372 | Bison: Cross-Dataset Learning for Unseen-Compound Perturbation Prediction | Yunfan Liu, Kasra Ghorbani, Yufei Huang +6 | cs.LG | 2026-09-26 |
| #373 | On the Pitfalls of Verbalized Confidence Priors for Calibrating Large Reasoning Models | Shuoyuan Wang, Beier Luo, Hao Zeng +5 | cs.LG | 2026-09-26 |
| #374 | Fast and Precise Learned Charged-Particle Trajectory Regression at the Large Hadron Collider | Jonathan Renusch, Benjamin Huth, Daniel Murnane +9 | cs.LG | 2026-09-26 |
| #375 | What Should Federated LoRA Share? FedSAIL via Input-aware Subspace Alignment | Junye Du, Shuaida He, Long Feng | cs.LG | 2026-09-26 |
| #376 | Elastic Selective Spectral Hybrids for Train-Once, Export-Many Budgeted Inference | Dachuan Song, Chuchu Chen, Xuan Wang | cs.LG | 2026-09-26 |
| #377 | Neural Dynamics as the Composition of Quantized Units | Jacopo Minniti, Aravinth Kulanthaivelu, Richard Sproat | cs.LG | 2026-09-26 |
| #378 | SoFT: Soft Targets for Generalizable LLM Fine-Tuning | Huihao Jing, Wenbin Hu, Shaojin Chen +7 | cs.LG | 2026-09-26 |
| #379 | Rondo: Unsupervised Discovery of Recurring Temporal Structure | Yingtian Shi, Ankith Chandra, Thomas Plötz | cs.LG | 2026-09-26 |
| #380 | Fisher Simplicity in Kolmogorov-Arnold Networks and Multilayer Perceptrons | Ami Tavory, Meir Feder | cs.LG | 2026-09-26 |
| #381 | What Do Latent Predictive Vehicle Representations Retain? Measuring State, Geometry, and Local Response | Enzo Nicolás Spotorno, Josafat Leal Filho, Antônio Augusto Fröhlich | cs.LG | 2026-09-26 |
| #382 | Does Transolver really need a Transformer? | Shizheng Wen, Siddhartha Mishra | cs.LG | 2026-09-26 |
| #383 | Activation Flow: Manufacturing Activations for Steering | Hong Kiat Tan, Linh Le, David Williams-King | cs.LG | 2026-09-26 |
| #384 | What Does a ProcGen Generalization Gap Measure? Action Rules, Convergence, and the Missing Random Floor | Abhisek Keshari | cs.LG | 2026-09-26 |
| #385 | Shared Autoregressive Context Can Distort Relationships in Synthetic Data | Thomas S. Robinson | cs.LG | 2026-09-26 |
| #386 | Prioritizing Repeated LLM Evaluation for Hidden Failure Discovery | Keita Broadwater, Akin Broadwater | cs.LG | 2026-09-26 |
| #387 | Compositional Objectives: Learning Structure in Structure | Pranavchandra Vivekananda, Sumukh Bettadapura, Ajan Subramanian | cs.LG | 2026-09-26 |
| #388 | CAESAR: Clustering via Autonomous Embedding-Space Agglomerative Reorganization | Ilan Bacry, Rémi Devaux, Antoine Jardin | cs.LG | 2026-09-26 |
| #389 | Trapped by Their Own Rollouts: Understanding Aggregation--Rollout Feedback in Federated On-Policy Distillation | Jinqian Chen, Jihua Zhu, Chang Liu | cs.LG | 2026-09-26 |
| #390 | DimPO: Dimensionality Reduction for Attention using Preference Optimization | Vojtěch Lanz, Yufei Cui, Prasanna Parthasarathi | cs.LG | 2026-09-26 |
| #391 | Age of Learning: Temporal Persistence of Prediction Errors as a Learning Signal | Chenyang Wang, Stefan Forsström, Roger Olsson +2 | cs.LG | 2026-09-26 |
| #392 | Not Every Term Adds New Structure: Sobolev Novelty for Symbolic Regression | Boxiao Wang, Kai Li, Yuheng Jing +4 | cs.LG | 2026-09-26 |
| #393 | AnchorRep: Defending LLMs Against Cross-Model Adversarial Transfer via Representation Repulsion | Gal Wertheizer, Rom Himelstein, Tomer Peretz +1 | cs.LG | 2026-09-26 |
| #394 | Learning the Graph and the Embedding Together: Classifier-Independent Rewiring for Heterophilic Node Classification | Harshit Kumar, Sujan Chakraborty, Priyanka Saha +2 | cs.LG | 2026-09-26 |
| #395 | Stabilizing the Dynamic Low-Rank Training | Zhonghan Xu, Ling Wang, Junhao Chen +2 | cs.LG | 2026-09-26 |
| #396 | Intuition vectors | Shahar Haim, Daniel C. McNamee | cs.LG | 2026-09-26 |
| #397 | Extremely Fast and Compact Binary Graph Representations via Randomized Operator Sketching | Srajan Agarwal, Megha P, Bikas C Das +2 | cs.LG | 2026-09-26 |
| #398 | Quantization-Aware Pre-Training with Constrained Empirical Weight Distribution | Ningfeng Yang, Tor M. Aamodt | cs.LG | 2026-09-26 |
| #399 | Equivariant Neural Primal-Dual Assignment for Maximum Common Edge Subgraphs | Jiaqing Xie, Yanchao Li, Zhuo Yang +3 | cs.LG | 2026-09-26 |
| #400 | Distance-KV: Exploiting Relative Distance for Efficient Long-Context Inference | Xianpeng Shang, Canbin Huang, Jiang Li +4 | cs.LG | 2026-09-26 |
| #401 | Timestep Weighting: A Hidden Key to Effective ELBO-Based Flow-Matching RL | Qinwei Ma, Jingzhe Shi, Simin Fan +3 | cs.LG | 2026-09-26 |
| #402 | STAMP: Predicting Out-of-Distribution Generalization without Target Data | Md Kawsher Mahbub, Milon Biswas | cs.LG | 2026-09-26 |
| #403 | SIFT: Enhancing Time Series Foundation Models via Semantic Invariance and Structural Fidelity Fine-Tuning | Yi Tang, Tengxue Zhang, Yang Shu +3 | cs.LG | 2026-09-26 |
| #404 | The GUI Is Not the State: Diagnosing State Aliasing in GUI World Models | Dongsheng Liu, Chao Jin, Wenkui Yang +7 | cs.LG | 2026-09-26 |
| #405 | Self-Evolving Time-Series Forecasting Agents with Episodic Memory and Online Policy Learning | Junyi Wang, Yilin Wang, Wen Wu +1 | cs.LG | 2026-09-26 |
| #406 | BiasReducer: Adaptive Bias Mitigation for Reward Models | Shuang Liu, Yongliang Miao, Yanguang Liu +2 | cs.LG | 2026-09-26 |
| #407 | Scaling Properties of Same-Family On-Policy Distillation | Yuntai Bao, Qinfeng Li, Guoqing Jiang +5 | cs.LG | 2026-09-26 |
| #408 | Distributionally Robust Average-Reward Reinforcement Learning: Finite-Sample Guarantees under Weak Communication | Chenyu Lu, Zijun Chen, Nian Si | cs.LG | 2026-09-26 |
| #409 | Predicting the Financial Impact of Supply Chain Risk for Major AI-Related Semiconductor Firms: A Heterogeneous Graph Patch Transformer Approach | Jianna Hur, Sagar Samtani | cs.LG | 2026-09-26 |
| #410 | Benchmarking EEG Foundation Models at Scale: Lessons from 20,000 Evaluations | Zhige Chen, Shu Peng, Chengxuan Qin +4 | cs.LG | 2026-09-26 |
| #411 | Reuse or Relearn? A Spectral View of Earth Observation Foundation Models | Mehmet Ozgur Turkoglu, Valerio Marsocci, Dominik J. Mühlematter +3 | cs.LG | 2026-09-26 |
| #412 | The Extender: A Log-Structured Transformer | Jakob Eriksson | cs.LG | 2026-09-26 |
| #413 | AnchorMixGAN: Anchor-Aligned Generative Semi-Supervision for DDoS Detection in Cloud-Integrated IoT Networks | Jin Yang, Xufeng Liu, Yong Hu +3 | cs.LG | 2026-09-26 |
| #414 | Structuring Relations Among Learning Paradigms via Protocol--Objective--Resource Reductions | Junwei Su, Changjie Wang, Dongyang Chang | cs.LG | 2026-09-26 |
| #415 | Continual Learning via Self-Probe Gradients | Dongkyu Cho, Rumi Chunara, Sungmin Cha | cs.LG | 2026-09-26 |
| #416 | Beyond Gaussian Assumptions: Distribution-Aware Channel Capacity for Effective Connectivity | Jianan Jian, Jacob Kang, Nurahmed Multezem +2 | cs.LG | 2026-09-26 |
| #417 | Robust Bayesian Optimization with Q-Exponential Surrogates | Richard Cornelius Suwandi, Zhidi Lin, Feng Yin +1 | cs.LG | 2026-09-26 |
| #418 | Learning When to Recur: Token-Adaptive Recursion for Imbalanced Ophthalmic Domain Incremental Learning | Nanxi Yu, Kang Li, Ye Du +3 | cs.LG | 2026-09-26 |
| #419 | Getting Motif-ated: Controllable AI Compositions from Injected Motif Prompts | Chao Peter Yang, Cynthia Rudin, Yue Jiang +2 | cs.LG | 2026-09-26 |
| #420 | FedHV: Low-Overhead Hypervolume Weighting for Federated Multi-Objective Optimization | Amirardalan Dehghanpour, Seyed Mohammad Azimi-Abarghouyi, Christopher G. Brinton | cs.LG | 2026-09-26 |
| #421 | Understanding and Exploiting Anisotropy in Post-Training | Samyak Jha, Harshvardhan Saini, Yizhen Liao +2 | cs.LG | 2026-09-26 |
| #422 | Derivative-Informed Training of Neural Operators On-the-Fly via Sketched Tangent Consistency | Xinhan Yang, Lu Lu, Shancong Mou | cs.LG | 2026-09-26 |
| #423 | Mind the Spike: Mechanisms and Brittleness of Visual Massive Activations in Large Vision-Language Models | Jonas Ngnawé, Yann Pequignot, Sabyasachi Sahoo +3 | cs.LG | 2026-09-26 |
| #424 | Change the Product, Keep the Parameters: Associative Algebra Layers for Transformers | Ilya Koziev, Ivan Oseledets | cs.LG | 2026-09-26 |
| #425 | Retimed Bellman Flows: Escaping the Impossible Triangle of Velocity Bootstrapping | Boyang Xu, Shengzhe Chen, Hao Yan | cs.LG | 2026-09-26 |
| #426 | UniCache: Task- and Type-Aware KV Cache Compression for Unified Multimodal Models | Wanqi Yang, Yuexiao Ma, Mei Xie +2 | cs.LG | 2026-09-26 |
| #427 | Over-the-Air Federated Learning in Heterogeneous Mobile Wireless Networks | Ming Xiang, Nicolò Michelusi, Yonina C. Eldar +1 | cs.LG | 2026-09-26 |
| #428 | Permutation-Equivariant Flow Matching for Alignment-Free Neural Weight Generation | Arkadi Piven, Yam Eitan, Guy Bar-Shalom +5 | cs.LG | 2026-09-26 |
| #429 | HamiFormer: Dual-Expert Diffusion Fields with Affine Symplectic Maps | Haoxiang Huang, Xiang Liu, Shuwei Wang +2 | cs.LG | 2026-09-26 |
| #430 | Transfer Learning for Edge Classification on Dynamic Text-Attributed Graphs | Tyler Bonnet, Marek Rei | cs.LG | 2026-09-26 |
| #431 | Logic Gate Networks and Lookup Table Networks as Lightweight Hardware Classifiers for Inter-patient ECG Arrhythmia Classification | Wout Mommen, Lars Keuninckx, Siddharth Patil +3 | cs.LG | 2026-09-26 |
| #432 | Muon Under Gradient Noise and the Limits of Orthogonalization Near Optima | Xiaohui Xie | cs.LG | 2026-09-26 |
| #433 | Staying on the Attractor: Supervising Neural Surrogates of 3D Turbulence Where They Leave It | Yilong Dai, Shaswata Mitra, Raj Patel +7 | cs.LG | 2026-09-26 |
| #434 | Refreshing Less, Selecting Better: Reusing Stale Gradient Features for Efficient Influence-Based Data Selection | Jianchang Su, Yifan Zhang, Wei Zhang | cs.LG | 2026-09-26 |
| #435 | Measurement-Gated Provenance Attenuation for Frozen EEG Representations | Anuar Aimoldin, Yankai Chen, Ayana Mussabayeva +2 | cs.LG | 2026-09-26 |
| #436 | A Function-Level Vulnerability Score Measures Flag Rate More Than the Model: Protocol Effects on Paired Benchmarks | Maciej Cichoń, Bartłomiej Dmitruk | cs.LG | 2026-09-26 |
| #437 | Optimizing H-Graph Hybridization for Diffusion-Guided RRT | Omer Talmi | cs.LG | 2026-09-26 |
| #438 | When Less Compute Is More: Adaptive Early Exit Improves Pretrained Outlier Detection | Tianyang Zhou, Leman Akoglu | cs.LG | 2026-09-26 |
| #439 | Predicting the Next State Is Not Enough: JEPA Representations for Lean Theorem Proving | Aarnav Choudhary | cs.LG | 2026-09-26 |
| #440 | Allspark: Weak to Strong Transfer via Alternating Chain of Thought | Kaizhao Liang, Junxiong Wang, Chen Liang +2 | cs.LG | 2026-09-26 |
| #441 | Adaptive Latent Capacity for World Models | Idan Achituve, Lior Dikstein, Idit Diamant +2 | cs.LG | 2026-09-26 |
| #442 | The Geometry of Logic: Stratification Induces Semantic Structure and Robust Reasoning | Cristina V. Lopes, Yuangang Li, Justin Tian Jin Chen +3 | cs.LG | 2026-09-26 |
| #443 | Phenomenon-Graph JEPA: Label-Efficient Representation Learning for Contactless Cardiorespiratory Sensing | Constantino Álvarez Casado, Nhi Nguyen, Mohammad Rakibur Rahman +4 | cs.LG | 2026-09-26 |
| #444 | Efficient Dynamic Algorithms for Graph Neural Networks with Non-Linear Propagation | Kiarash Banihashem, MohammadTaghi Hajiaghayi, Mahdi JafariRaviz +2 | cs.LG | 2026-09-26 |
| #445 | Counting on Thinking: Tracing Evidence Integration in Language Models | Jingming Xue, Robert C. Wilson, Huadong Xiong | cs.LG | 2026-09-26 |
| #446 | Last-Iterate Guarantees for Online Reinforcement Learning in Structured Constrained MDPs | Nam Phuong Tran, Trinh Ha Mai Huynh, Tuyen Pham Le +3 | cs.LG | 2026-09-26 |
| #447 | The Impact of Stochasticity on the Rashomon Effect in Machine Learning | Andrea Apicella, Francesco Isgrò, Andrea Pollastro +1 | cs.LG | 2026-09-26 |
| #448 | Theory of Scene: Breaking the Symmetry Trap in Multi-Agent LLM Coordination | Liangqi Yuan, Wenzhi Fang, Shiqiang Wang +1 | cs.LG | 2026-09-26 |
| #449 | TwinS-GCN: Spectral conjugate for Spectral Graph Convolutional Networks | Chun Hei Michael Chan, Flavia Petruso, Dimitri Van De Ville | cs.LG | 2026-09-26 |
| #450 | Generative Priors Conditioned on Natural Language for Bayesian Inversion in PDEs | Pengyu Zhang, Mark Girolami, Arnaud Vadeboncoeur | cs.LG | 2026-09-26 |
| #451 | Optimal Nonparametric Dynamic Pricing with Censored Demand and Adversarial Inventory | Mengxiao Zhang, Yingfei Wang, Haipeng Luo | cs.LG | 2026-09-26 |
| #452 | Constrained Flow Policy Updates: A Generalized Schrödinger Bridge View | Boyang Li, Matthew Kim, Sylvia Herbert | cs.LG | 2026-09-26 |
| #453 | Efficient Message Passing for Partial Differential Equation Priors | Anna Kazachkova, Leonhard Hennicke, Rainer Schlosser +1 | cs.LG | 2026-09-26 |
| #454 | Beyond Token Savings: A Systematic Study of Context Compression in LLM Agents | Ritul Satish, Prasoon Sinha, Akiho Kawada +1 | cs.LG | 2026-09-26 |
| #455 | Clipped or Unclipped? Finite-Sample Trade-offs for Averaged SGD under Heavy-Tailed Noise | Alexandra Suvorikova, Egor Gladin, Darina Dvinskikh +5 | cs.LG | 2026-09-26 |
| #456 | Self-Confirming Superposition Traps in Reinforcement Learning | Dai Shi, Andi Han, Feng Chen +3 | cs.LG | 2026-09-26 |
| #457 | Adaptive Ensemble Selection for Noisy Labels on Tabular Data | Faizaan Ali, Inwon Kang, Oshani Seneviratne | cs.LG | 2026-09-26 |
| #458 | Feasible Flow Matching for Graph Reconstruction via Within-Sampling Primal-Dual Guidance | Haoming Chen, Nicolas Zilberstein, Santiago Paternain +1 | cs.LG | 2026-09-26 |
| #459 | What Should Data Teach? Moving Bottlenecks Across Circuit, Store, and Use | Yixiao Chen, Ke Cheng, Jiangtao Guan +5 | cs.LG | 2026-09-26 |
| #460 | Saturation-Insensitive Dueling Bandits with General Function Approximation | Chenggong Zhang, Xuheng Li, Qiwei Di +2 | cs.LG | 2026-09-26 |
| #461 | Relative Generalization Invariance of LLM Pretraining | Fengzhuo Zhang, Shuche Wang, Shenggui Li +7 | cs.LG | 2026-09-26 |
| #462 | Low-Rank Single-Index Bandits with Unknown Links: From Matrices to Tensors | Zhongxuan Liu, Yue Kang, Thomas C. M. Lee | cs.LG | 2026-09-26 |
| #463 | Łukasiewicz Neural Networks Extended: Residual Architectures and Crystallization Strategies for Interpretable Rule Extraction | Carlos Leandro | cs.LG | 2026-09-26 |
| #464 | What Must a World Model Distinguish for Planning? | Rongzhe Wei, Hans Hao-Hsun Hsu, Peizhi Niu +2 | cs.LG | 2026-09-26 |
| #465 | Progression- vs Automata-based Anticipatory Monitoring of LTL over Finite Traces (Extended Version) | Sarah Winkler, Toryn Klassen, Sheila McIlraith +1 | cs.LO | 2026-09-26 |
| #466 | Self-Evolving Multi-Agent Symbolic Discovery for Financial Fundamental Analysis | Kelvin J. L. Koa, Filip Orestav, Shengqiong Wu +2 | cs.MA | 2026-09-26 |
| #467 | All On-Board: Fully On-Chip Neuromorphic Q-Learning with Embedded CartPole Simulation | Steven C. Nesbit, Giovanni T. Michel, Gerd J. Kunde +2 | cs.NE | 2026-09-26 |
| #468 | Toward Agentic Optical Networks: A Vision of LLM Agent-Driven Autonomous Lifecycle Management | Yao Zhang, Shengnan Li, Yuchen Song +11 | cs.NI | 2026-09-26 |
| #469 | Agents as Software: A Programming Languages Agenda for Agent Reliability | Shraddha Barke, Adithya Murali | cs.PL | 2026-09-26 |
| #470 | AquaBEV-Nav: Learned BEV Occupancy for Underwater Navigation and Exploration | Trung Tien Dong, Zhenqi Wu, Sahasra Kondapalli +3 | cs.RO | 2026-09-26 |
| #471 | Federated Subspace Guided Vision-Language-Action Policy Distillation for Non-IID Multi-Robot Manipulation | Biprodip Pal, Kaushik Roy, Yanming Zhu +3 | cs.RO | 2026-09-26 |
| #472 | DS-VLA: A Dendritic-inspired Vision-Language-Action Model for Robust Action Control | Yaxing Lyu, Jingyi Li, Mingkun Xu +1 | cs.RO | 2026-09-26 |
| #473 | Affordance-Conditioned Decision Making: Bridging the Semantic-Spatial Gap in Zero-Shot Cross-Floor Vision-and-Language Navigation | Xuekang Yang, Lu Chen, Shuang Luo +4 | cs.RO | 2026-09-26 |
| #474 | RE-0: Verified Recursive Improvement of Embodied Code-as-Policy Agents through Local On-Policy Distillation | Jiawei Zhang, Xiangrong Zhang, Rui Song +3 | cs.RO | 2026-09-26 |
| #475 | DRAM: Delta-rule Recurrent Associative Memory for Robot Manipulation Policies | Xinyu Zhao, Yixiang Shan, Tao Yang +5 | cs.RO | 2026-09-26 |
| #476 | Think Fast, Plan Selectively: Adaptive Deliberation for Efficient Data-Driven MPC | Yi Xian Goh, Sze Jue Yang, Hao Luan | cs.RO | 2026-09-26 |
| #477 | RECAST: Recasting Vision-Language Semantics into an Actionable Cost Map for Robot Navigation | Incheol Cho, Jintae Park, Jinkyu Kim +3 | cs.RO | 2026-09-26 |
| #478 | World SLAM Model: Joint World Modeling for SLAM and Navigation | Minghui Qin, Yijun Yuan, Weicheng Zheng +7 | cs.RO | 2026-09-26 |
| #479 | An Empirical Study on What Matters for Viewpoint-Generalizable Policies in Visual Imitation Learning | Mino Nakura, Sriram Krishna, Yufei Wang +3 | cs.RO | 2026-09-26 |
| #480 | Copper-Policy: Focus on the Representation for Robust Robot Manipulation | Zexin Feng, Yixu Feng, Lingyu Xiao +6 | cs.RO | 2026-09-26 |
| #481 | CollisionGAT: Controller-Agnostic One-Step Collision Screening for Multi-Agent Motion | Alan Debbas, Edwin Meriaux, Gregory Dudek | cs.RO | 2026-09-26 |
| #482 | Scanning While Imagining: A Scene-Graph World Model for Robotic Ultrasound Navigation | Xuesong Li, Shuai Chen, Feng Li +3 | cs.RO | 2026-09-26 |
| #483 | FINE: Future-Informed Navigation Encoding for Data-Efficient Vision-Language Navigation | Khang H. Nguyen, Hoang Pham Quang Nguyen, Ha Phuong Nguyen +6 | cs.RO | 2026-09-26 |
| #484 | RoboFoundry: System-as-Policy Evolution for Self-Learning Embodied Agents | Jingsong Liang, Shuhao Liao, Shizhe Zhang +15 | cs.RO | 2026-09-26 |
| #485 | TriDrive: Joint Driver, Vehicle, and Road Modeling for Forecasting and Driver Monitoring | Yuhang Wang, Jingxin Yang, Chuheng Wei +4 | cs.RO | 2026-09-26 |
| #486 | CAPEX: Efficiently Distilling Foundation Model Behavior into Deployable Robot Policies through Experience-Adaptive Reasoning | Shivam Aarya, Zhang Xi-Jia, Chengyue Huang +6 | cs.RO | 2026-09-26 |
| #487 | Do Audio LLMs Listen Before They Act? Diagnosing Acoustic-Context Gating in Voice Agents | Yanjie Zhang, Nanchen Hu, Yushi Sun | cs.SD | 2026-09-26 |
| #488 | SAGE: Semantic Audio Generative Encoder | Francesco Brigante, Luca Cerovaz, Davide Marincione +4 | cs.SD | 2026-09-26 |
| #489 | Finding Emotions Where They Belong: Rethinking Audio Emotion Recognition through Masked Temporal Affective Grounding | Abdelrahman Mohamed, Lars Kai Hansen, Zheng-Hua Tan | cs.SD | 2026-09-26 |
| #490 | AsynCodeBench: Benchmarking Collaboration of Asynchronous Multi-Agent Systems in Software Engineering | Kaituo Zhang, Zhen Xiong, Zhimeng Jiang +8 | cs.SE | 2026-09-26 |
| #491 | Plan-to-Synthesis: Cross-City Human Mobility Generation via Semantic Latent Flow Matching | Zhoufu Wang, Baoshen Guo, Zhiqing Hong +6 | cs.SI | 2026-09-26 |
| #492 | Active Data Acquisition with Side Information via Discrete Diffusion Priors | An Vuong, Thinh Nguyen | eess.IV | 2026-09-26 |
| #493 | Mask2Restore: Self-Supervised Ultrasound Despeckling via Inpainting | Xuesong Li, Yingtai Xu, Zhongliang Jiang +2 | eess.IV | 2026-09-26 |
| #494 | Radiomap Blind Prediction under Incomplete Observation: Error Characterization and Correctable Propagation-Prior Learning | Xiaojie Li, Yu Han, Han Fang +4 | eess.SP | 2026-09-26 |
| #495 | EEG-Based Motor Imagery BCI Algorithms and Technologies: A Review | Mohammad Hossein Koohi Ghamsari, Seyede Fatemeh Ghamkhari, Siavash Bayat +1 | eess.SP | 2026-09-26 |
| #496 | Neural ODEs Meet Concurrent Learning: Stable Online Learning with Lyapunov Guarantees | Omkar Sudhir Patil | eess.SY | 2026-09-26 |
| #497 | Schur-Neural KF: Learned Schur-Consistent Corrections to the Extended Kalman Filter | Min Kim, Lianghao Cao, Soon-Jo Chung +1 | eess.SY | 2026-09-26 |
| #498 | LaMET-Agent: An Agent Framework for Large-Momentum Effective Theory Analysis | Jinchen He, Xiangyu Jiang, Fei Yao +1 | hep-lat | 2026-09-26 |
| #499 | Machine learning for the LHC physics program: a 2025-2026 stocktake | Jesse Thaler | hep-ph | 2026-09-26 |
| #500 | Fast Differentiable SVD on GPU via Polar Decomposition | Uliana Parkina, Askar Tsyganov, Sergei Kudriashov +2 | math.NA | 2026-09-26 |
| #501 | Neural Network-Assisted Refinement of Traditional Schemes for One-Dimensional Scalar Conservation Laws | Imre Fekete, Ferenc Izsák, Vendel P. Kupás | math.NA | 2026-09-26 |
| #502 | Convergent Plug-and-Play Image Restoration with Annealed Noise Levels | Samuel Hurault | math.OC | 2026-09-26 |
| #503 | Revisiting AdaGrad in Stochastic Convex Optimization: Last Iterates, High Probability, and Lower Bounds | Weiming Ou, Xiao Wang | math.OC | 2026-09-26 |
| #504 | Decentralized Optimization with Cross-Coupled Mixed Affine Constraints | Ewsey Obzherin, Ilya Khomchenko, Natalia Shelegeda +4 | math.OC | 2026-09-26 |
| #505 | Vision-Language Agents for Active Perception in Optics Laboratories | Ryan Lopez, Sachin Vaidya, Seou Choi +2 | physics.optics | 2026-09-26 |
| #506 | Rank Confidence Sequences:Anytime-valid Leaderboards | Hamed Khosravi, Xiaoming Huo | stat.ME | 2026-09-26 |
| #507 | A Unified Optimism-Agnostic Framework for Linear Bandits over Spherical Action Sets | Arda Güçlü, Subhonmesh Bose, John R. Birge | stat.ML | 2026-09-26 |
| #508 | FOCUS: Fixed-Confidence Online Causal Learning Using Sequential Adaptive Interventions | Haijie Xu, Chen Zhang | stat.ML | 2026-09-26 |
| #509 | Uncertainty Quantification of Next Generation Reservoir Computing with Applications to Memory-Driven Dynamical Systems | Livia Popa, Sumanta Basu, Martin T. Wells | stat.ML | 2026-09-26 |
| #510 | High-Probability Guarantees for SGD under $β$-Heavy-Tailed Gradient Noise | Qijun Tong, Masahiro Ikeda, Ryota Kawasumi | stat.ML | 2026-09-26 |
| #511 | Overfitting of Spectral Gradient Descent: How Matrix Geometry shapes Generalization and Implicit Bias | Guillaume Braun, Ichiro Hashimoto, Masaaki Imaizumi | stat.ML | 2026-09-26 |
| #512 | AECSF: Adaptive Ensemble Conditional Score Filtering for High-Dimensional Nonlinear Data Assimilation | Yangwen Zhang, Shiwei Ni, Xiaoping Zhang +2 | stat.ML | 2026-09-26 |
| #513 | Agnostic Smoothed Online Regression with Adversarial Responses | Xuanyu Chen, Yue Yu | stat.ML | 2026-09-26 |
| #514 | Learning What to Evaluate: Correlation-Aware Decoupling for Multiobjective Bayesian Optimization | Ashwin Renganathan, Peter Bachman | stat.ML | 2026-09-26 |
| #515 | Affine Geometry of Gaussian ReLU Networks via Conditional Kac-Rice Formulas | Recep Özkan, Christian Hirsch | stat.ML | 2026-09-26 |
| #516 | Domain Adaptation with Target Information via Doubly-Anchored Distributionally Robust Optimization | David Kepplinger, Anand N. Vidyashankar | stat.ML | 2026-09-26 |
| #517 | Sliced Orlicz-Wasserstein | Binh Thuan Tran, Khai Nguyen | stat.ML | 2026-09-26 |