PaperScope
LIVE · 2026-10-01 05:40 UTC

New Papers · 2026-09-30 669 submissions

cs.CL · cs.LG · cs.AI · cs.CV daily batch

#TitleAuthorsCatDate
1MAGiDiff: Sampling the Photospheric Vector Field from UV/EUV FiltergramsRuoyu Wang, David Fouheyastro-ph.SR2026-09-30
2Concept-Grounded Attention: A Controlled Evaluation of Graph-Injected Attention, Temporal Versioning, and Epistemic StatusSachin Dev Duggal, Pradyumna Swarnalatha Ramanna, Alexandros Vassiliadescs.AI2026-09-30
3GATE-ST: Gene-Aware Text-image Encoder for Spatial TranscriptomicsLucas Ni, Jian Luo, Wentao Huang +1cs.AI2026-09-30
#4Budget Boundary Effects in Test-Time Mathematical ReasoningGuilin Zhang, Ziqi Tan, Wulan Guo +5cs.AI2026-09-30
#5Staying on Task: Testing the Foundations of Long-Horizon Agent ReliabilityJeffrey Willette, Krishna C. Puvvada, Boris Ginsburgcs.AI2026-09-30
#6UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvementFang Wu, Da Xing, Yanjie Huang +16cs.AI2026-09-30
#7Code to Control: Synthesizing Parameterized Reactive ControllersZergham Ahmed, Joshua B. Tenenbaum, Chris Bates +1cs.AI2026-09-30
#8Learning to Route in Visual Space via Multi-Step Embedding RetrievalTianyu Chen, Mingyuan Zhou, Jiaxing Wucs.AI2026-09-30
#9Self-Evolving Algorithm-Design Agents: Escaping In-Context Evolutionary Stagnation via Population-Curated Policy OptimizationChen Lu, Ke Xue, Siyuan Xu +2cs.AI2026-09-30
#10PathAnchor: Path-Structured Evidence for Scientific AgentsQiuhui Chen, Jiafan Lu, Shuaimin Tang +5cs.AI2026-09-30
#11Action Conditioned Bisimulation For GUI Agent MemoryHongbo Zhang, Liuyang Song, Quanquan Li +3cs.AI2026-09-30
#12Persona and Persuasive Framing in AI Voice Agents: A $2\times2$ Field Experiment with ChildrenThilo Tamme, David Steck, Anton Hantelcs.AI2026-09-30
#13Positive Ratings, Hidden Concerns: Employee Voice Disclosure in AI-Mediated Organizational ListeningThilo Tamme, Michael Saatkamp, Alma Bonte +3cs.AI2026-09-30
#14GraphCert: Bootstrap Agentic Graph Reasoning with Certified Evidence RubricsWeiqi Jiang, Yuchen Ying, Rui Wang +5cs.AI2026-09-30
#15When Reasoning Goes Astray: Attention Dynamics of Uncontrolled ReasoningYuanhe Zhang, Ziwei Wang, Jie Ren +6cs.AI2026-09-30
#16Whose Voice Survives the Summary? A Voice-Retention Audit of LLM Employee ListeningThilo Tamme, Anton Hantel, Bijan Khosrawi-Radcs.AI2026-09-30
#17More Choices, Fewer Decisions: Ordinal-Scale Bias in JEV-like Direct-Decision ModelsTianxiang Gao, Jinzhe Li, Zhiyuan Li +2cs.AI2026-09-30
#18Diversity Combining for Multi-Path LLM ReasoningGuangsheng Yu, Litianyi Zhang, Qin Wang +5cs.AI2026-09-30
#19OpenJev-RLCD: A Working RLCD ImplementationZhimin Gao, Pichao Wangcs.AI2026-09-30
#20When Context Changes: Understanding Update Failures in LLMsJunyu Guo, Yuchen Fang, Shangding Gu +3cs.AI2026-09-30
#21Talk2Agent: Benchmarking Voice Interfaces for Text AgentsTerumi Chiba, Guangzhi Sun, Zheqi Yuan +1cs.AI2026-09-30
#22Reasoning Externalization for Faithful Large Language Model Narratives of Stock Return PredictionsSujung Kim, Seung Hwan Cho, Sangjin Park +1cs.AI2026-09-30
#23STRATA: Self-Learning Through Role-Aligned Tiered Agents for Real-Time Strategy GamesXinhe Tian, Xiaoyue Zhang, Ziyou Zhang +4cs.AI2026-09-30
#24Consistent Plan-Act for Long-Horizon Agentic TasksHeng-Zhuang Li, Yi-Kai Zhang, Yu Wang +4cs.AI2026-09-30
#25Composing Task-specific Agent Harnesses at Test Time with Reusable PrimitivesPeng Kuang, Haibo Jin, Dehao Wu +4cs.AI2026-09-30
#26Risk-Aware Adaptive Evaluation: Finding High-Impact Failures Under Limited BudgetsPriyanath Maji, Spandan Ghose Chowdhurycs.AI2026-09-30
#27How Much Can Reliability Drift Under a Fixed Confidence Distribution?Wenhao Liang, Lin Yue, Wei Emma Zhang +3cs.AI2026-09-30
#28Prototype-guided Bilateral Alignment Multimodal Federated LearningTianchi Liao Tianchi_Liao, Lele Fu, Sheng Huang +3cs.AI2026-09-30
#29Learning What to Forget: Distributional Unlearning for LLM Representation SpacesPinaki Mohanty, Haoran Tang, Maggie Makar +1cs.AI2026-09-30
#30Routing Probes Can Improve Without New Information: An Exact-Null Audit of Uncertainty Beyond Model OutputsWenhao Liang, Lin Yue, Wei Emma Zhang +3cs.AI2026-09-30
#31Targeted Retrieval, Compact Representations: How CoT Reasoning Improves Long-Context CountingLiang Twist Shan, Tianyu Hu, Hao Yan +1cs.AI2026-09-30
#32Alleviating Hallucination in Reasoning Tasks with Training-Free Uncertainty-Guided SteeringLitian Liu, Qiqi Hou, Yubing Jian +5cs.AI2026-09-30
#33When Order Matters: First-Speaker Bias and Mitigation through Personality in Sequential Multi-Agent DebateDuofeng Xu, Bryan Hooi, Dandan Qiaocs.AI2026-09-30
#34RealWorldShop: Benchmarking and Improving Conversational Shopping Agents in Real-World E-commerceXinwei Yang, Kelong Mao, Yudong Guo +4cs.AI2026-09-30
#35C-STRIDE: An Observation-Driven AI Digital Twin for Predicting Basin-Wide Flood Fields from Sparse Stream-Gauge HistoriesYanjie Tong, Phillip Si, Yuan Qiu +1cs.AI2026-09-30
#36Search Shapes Conclusions: Auditing Evidence Selection Bias in Deep Research AgentsShuyao Xiao, Shengling Wang, Xuan Chen +8cs.AI2026-09-30
#37Multi-LLM Collaborative Alignment via Stackelberg GamesChristina Hahn, Shangbin Feng, Dean Light +3cs.AI2026-09-30
#38Beyond Prediction: Steering VLM Agents with Retrospective World ModelingYongjiang Liu, Jie Zhang, Haoyue Zhang +3cs.AI2026-09-30
#39Reserve-Aware Contrast Certificates for Conservative Bandits with Uncertain BaselinesQinchuan Chengcs.AI2026-09-30
#40MASCRDM: Multi-Agent System for Compliance Risk Detection and Mitigation in Training Process of Large Language ModelsYan Zhang, Chuming Wei, Ruien Li +3cs.AI2026-09-30
#41BELIEFRAG: Making Adaptive RAG State-Aware under Evolving EvidenceHongji Pucs.AI2026-09-30
#42Schema: Discovering Unknown Environments via Agentic Program InductionGuanning Zeng, Jiani Wang, Wenjie Ma +8cs.AI2026-09-30
#43RefCon: Iterative Refinement and Contrastive Memory Extraction for Context-Evolving AgentUbaidillah Ariq Prathama, Bo Liu, Yeo Boon Hong +3cs.AI2026-09-30
#44MADBench: Benchmarking the Security of Multi-Agent DebateYuwan Liu, Jiaming Zhang, Yue Huang +1cs.AI2026-09-30
#45Do Self-Evolving Skills Generalize to Held-Out Tasks?Xihao Piao, Zifeng Wang, Zhen Chencs.AI2026-09-30
#46Rep2Skill: Representation-Guided Skill Self-Evolution for LLM AgentsKaixing Zhang, Changming Li, Yingdong Shi +5cs.AI2026-09-30
#47Beyond the Remembered World: Predictive 4D Belief for Persistent Navigation in Evolving WorldsMingjian Gao, Zhaocheng Li, Haoyang Huang +7cs.AI2026-09-30
#48Reinforcing Multimodal Reasoning via Token-Level Perception-Grounded Advantage EstimationZhihan Zhang, Lizi Liaocs.AI2026-09-30
#49Learning Process Rewards via Reasoning State PropagationKai Gan, Zi-Hao Zhou, Bo Ye +3cs.AI2026-09-30
#50Fyan: A Human--AI Harness with Semantic Auditing for Document-Level FormalizationWei Zhao, Yangshuo Zou, Chengxiang Ding +5cs.AI2026-09-30
#51Effective Does Not Mean Useful: Conditional Functional Substitutability for Redundancy and Scaling in TransformersJiaheng Chen, Jiaxing Li, Yucheng Xiao +4cs.AI2026-09-30
#52ANI: Adaptive Numerical Injection for Unifying Semantic and Arithmetic Representations in Numerical ReasoningJinsung Jeon, Seung-won Hwangcs.AI2026-09-30
#53MiniRep: Robust Reputation-Based Aggregation for Multi-Agent DebateJiaming Zhang, Yuwan Liu, Yue Huang +1cs.AI2026-09-30
#54WorkGenesis: Building the Worlds That Teach Agents to WorkXinyu Zhu, Fenyi Liu, Yuzhu Cai +4cs.AI2026-09-30
#55Understanding as No-Arbitrage: Bounded Dutch Books as a Definition and Training Objective for Language ModelsDaniel Dragonevskiycs.AI2026-09-30
#56The Golden Path Hypothesis: Reusable Schedules in Diffusion CachingDong Wang, Wenwu Tang, Francesco Corti +3cs.AI2026-09-30
#57On the Complexity of Preference-Based BanditsAhmed Ben Yahmed, Marc Abeille, Clément Calauzènescs.AI2026-09-30
#58Autoresearch in Mixed-Integer Linear and Nonlinear ProgrammingYuwei Gu, Yaoxin Wu, Tong Guo +2cs.AI2026-09-30
#59EHR-RobustGym: Benchmarking and Training Agents for Robust Clinical ReasoningYitong Qiao, Yancheng Jin, Lei Liu +4cs.AI2026-09-30
#60SkillFM: Generating Skills for LLM Agents via Latent Flow MatchingZuming Zhang, Jie He, Yizhe Zhang +1cs.AI2026-09-30
#61Experimental Experience Modeling for Autonomous ResearchWenda Wei, Yingchen Zhang, Ruqing Zhang +3cs.AI2026-09-30
#62Can Computation from Earlier Problems Help LLMs Solve New Ones?Jipei He, Wenhui Tan, Xiaoyi Yu +4cs.AI2026-09-30
#63Advancing Entropy-Level Credit Assignment in RLVR via Proximal Entropy Policy OptimizationYun Kim, Nojun Kwakcs.AI2026-09-30
#64Inferring Causal Relations between Two Sequences of Events with Language ModelsNishchal Prasad, Eric Gaussier, Emilie Devijver +3cs.AI2026-09-30
#65Beyond the Shadows of Plato's Cave: Evaluating False Memory in Autonomous Agents via Counterfactual ReasoningQuan M. Tran, Zhuo Huang, Zhen Fang +3cs.AI2026-09-30
#66Who Owns That? Evaluating Ownership Intuitions in Large Language ModelsXizhi Xiao, Yue Wu, Shan Xu +1cs.AI2026-09-30
#67Disentangling Self-Distillation: Measuring and Modeling Acquisition and RetentionLuis Zuin, Alexis Huet, Dario Rossi +1cs.AI2026-09-30
#68Referential Uncertainty in Human--AI CollaborationChristian Poelitz, Finale Doshi-Velez, Siân Lindleycs.AI2026-09-30
#69Growing an Agent/Prover Interface: Evolutionary Tool Design for Cost-Efficient Theorem Proving in Rocq and LeanJules Viennot, Guillaume Baudart, Marc Lelargecs.AI2026-09-30
#70RankEvolve: A Reliable Multi-Agent Auto-Research Harness for Evolving Ranking ModelsZheng Chen, Linfeng Liu, Hong Li +1cs.AI2026-09-30
#71Divide and Collapse: MAPF-Collapse via Exact Decomposition into Independent Sub-InstancesOren Salzmancs.AI2026-09-30
#72A2Z GameSpec-Bench: How Faithfully Can Coding Agents Generate Games from Game Design Specifications?Seonho Lee, Wonryeol Jeong, Alberto Cereser +4cs.AI2026-09-30
#73AVERT-VLN: Abstention-aware Visual Error Recovery and Training for Vision-and-Language NavigationMinrui Liu, Jingke Wang, Yuehao Huang +4cs.AI2026-09-30
#74Why Do Conventional World Models Fail to Learn Cellular Automata?Shaoyang Guo, Ziming Liucs.AI2026-09-30
#75ChronoGraph: Functional 4D Scene Graphs with Vision-Language Models for Interaction Understanding and Grounded PlanningChenyangguang Zhang, Malgorzata Gwiazda, Guanlong Jiao +5cs.AI2026-09-30
#76Values as Style: Disentangling Values from Semantics with One-Way Mixing for Low-Damage LLM SteeringJiale Dai, Hongcan Deng, Liuxian Ma +2cs.AI2026-09-30
#77A helps B while B hurts A: directed transfer in instruction-tuning mixtureNima H. Siboni, Vahid Rostamics.AI2026-09-30
#78ArchitectureIQ: On the Measure of Training IntuitionZirui Ren, Shaoyang Guo, Chencheng Tang +9cs.AI2026-09-30
#79Trust Is Not a Score: Runtime Assurance Contracts for High-Risk AI AgentsSerhii Zabolotniics.AI2026-09-30
#80OverForge: Reasoning Through Strategies and Tactics Helps Cooperative Lifelong AdaptationOana Madalina Fron, Ojas Shirekar, Chirag Ramancs.AI2026-09-30
#81Safety of Latent Communication in Multi-Agent SystemsMuhammad Huzaifa, Sina Mavali, Thorsten Eisenhofercs.AI2026-09-30
#82Learning Steganography Is Easy, Learning Steganographic Reasoning Is HardJulian Schulz, Lukas Fülle, Rieke Fruengelcs.AI2026-09-30
#83FIGS: Evaluating Multi-Turn Sycophancy Without Penalizing EmpathySidharth Pulipaka, Ruta Binkyte, Ivaxi Sheth +1cs.AI2026-09-30
#84Completion-Aware Cross-Fidelity Offline-to-Online Reinforcement Learning for Multi-Line Bus HoldingYifan Zhang, Qifan Zhang, Liang Zhengcs.AI2026-09-30
#85GrammarRL: Effective Grammar-Constrained Decoding via Reinforcement LearningGabriele Tuccio, Antonino Furnari, Aldo Gangemi +1cs.AI2026-09-30
#86OSWorld-Science: A Benchmark of Computer Use Agents for Learning and Using Scientific SoftwareDingyuan Dai, Heli Qi, Lei Liu +28cs.AI2026-09-30
#87ConflictGuide: AutoResearch Improves When Competing Behaviors Are Made VisibleBinqian Xu, Qiran Zou, Xiangbo Shu +1cs.AI2026-09-30
#88Coverage Before Control: Route-Instruction Grounding and Steering for Controllable RetrosynthesisXuemin Chen, Xiaozhuang Song, Xinjian Zhao +2cs.AI2026-09-30
#89Better Deck or Different Judge? Evaluating Agentic Harness Gains in Corporate and Investment BankingLudovic Gibert, Matis Despujols, Andre-Louis Rochetcs.AI2026-09-30
#90AIMS: An Agentic AI Framework for Sim-to-Real Multi-Modal ISACYijie Bian, Kai Zhang, Wei Guo +4cs.AI2026-09-30
#91What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM AgentsShuyang Zhang, Jianshuo Changcs.AI2026-09-30
#92Who Verifies the Graph? Misspecification Attacks on Causal Action Verification for Language AgentsFabio Rovaics.AI2026-09-30
#93PTNO: Training Neural Operators with Noisy Monte Carlo Estimates for Particle Transport ProblemsYubo Cao, Xi Deng, Mengqi Xia +3cs.AI2026-09-30
#94Agent Error Dataset: Scaling 50,000 Error--Diagnosis Pairs for Failure Analysis and Error-Aware Post-TrainingKunlun Zhu, Xuyan Ye, Yibo Li +3cs.AI2026-09-30
#95Unlearnable, or Unmeasured? On the Reliability of Difficulty Labels in RLVRChandak Chakma, Syed Nazmus Sakib, Nafiul Haque +1cs.AI2026-09-30
#96Learning from Research: Toward Lifelong Agent Harness EvolutionJingbo Yang, Kwei-Herng Lai, Xiaowen Wang +3cs.AI2026-09-30
#97Belief-Aware Multi-Agent Path Finding under Map UncertaintyViraj Parimi, Shao-Hung Chan, Han Zhang +2cs.AI2026-09-30
#98PivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn AgentsYinghui He, Yapei Chang, Khushi Bhardwaj +4cs.AI2026-09-30
#99How Much of a Harness Does a Strong Agent Need for Autonomous ML Engineering?Kirill Brilliantov, Alejandro Hernández-Cano, Emmanuel Abbécs.AI2026-09-30
#100Cogentic: Multi-Agent Orchestration for Automated Proof DiscoveryYang Cai, Vineet Gupta, Yanchen Jiang +4cs.AI2026-09-30
#101WorldAuditBench: Interactive 3D World Auditing with Multimodal AgentsZiyan Jiang, Jingbo Yang, Jiabao Ji +5cs.AI2026-09-30
#102Turbo Harness: Instance-Adaptive Harness OptimizationTunyu Zhang, Hao Wang, Kai Xu +1cs.AI2026-09-30
#103MetaSteer: Context-Conditioned, nonlinear Steering via Attention-Projection AdaptationMehdi Jafari, Hao Xue, Flora Salimcs.CL2026-09-30
#104Training LLM Judges from Language Feedback via Position-Selective Self-DistillationIlgee Hong, Changlong Yu, Zhenghao Xu +5cs.CL2026-09-30
#105Recovering Off-Policy Supervision for Speculative DecodingJungseob Lee, Chanjun Park, Sugyeong Eo +1cs.CL2026-09-30
#106Overlap, Unique and Conflict: Can LLMs Extract What They Can Recognize?Eftekhar Hossain, Santu Karmakercs.CL2026-09-30
#107Uncovering Uncontrolled Repetition through Residual Stream DynamicsYuanhe Zhang, Xinyao Zhou, Haoran Gao +5cs.CL2026-09-30
#108StateTree: Enhancing Long-Term Dialogue Reasoning via Reinforcement LearningNaen Xu, Wanqing Cui, Yibo Hu +5cs.CL2026-09-30
#109Can Terminal Agents Trust Their Own Verification? Diagnosing and Improving Self-VerificationYingfeng Luo, Shaowei Wei, Daixin Wang +7cs.CL2026-09-30
#110You're Hired: Strategic Model Selection for LLM CollaborationZongwan Cao, Ziyuan Yang, Shangbin Feng +5cs.CL2026-09-30
#111BARRAC: Adaptation of an English Aspect-based Sentiment Analysis Approach for Classification Tasks in Arabic DialectsAli Almutairi, Gelareh Mohammadi, Imran Razzak +1cs.CL2026-09-30
#112Forging LLM Authorship Fingerprints with Targeted RewritingHaohan Yuan, Simin Chen, Xi Niu +3cs.CL2026-09-30
#113Scaling Parameter and Context in Attention: Native Sparse Attention from Mixture-of-HeadZizhuo Fu, Runsheng Wang, Meng Lics.CL2026-09-30
#114Where MLLMs Fail and Why: Causal Task Decomposition for Capability Failure DiagnosisXia Hu, Brian Potetz, Chun-Ta Lu +6cs.CL2026-09-30
#115TRACE: Target-Aware Retrieval, Attributed Evidence, and Contract-Constrained Extraction for LitTraceQASachin Gupta, Divya Godaracs.CL2026-09-30
#116GraphForge: Training Working Agents with Graph-Anchored Workspace SynthesisQisheng Su, Hanchen Wang, Guanru Zhu +9cs.CL2026-09-30
#117Making LLMs Say What They Think: Measuring and Improving CoT-Interpretability AlignmentYihuai Hong, Shauli Ravfogel, Chen Zhao +1cs.CL2026-09-30
#118Fairness Beyond a Single Run: Training-Seed Variability in Speech LLM AdaptationSrishti Ginjala, Eric Fosler-Lussier, Srinivasan Parthasarathycs.CL2026-09-30
#119When Clipping Reverses Correction: Failure Dynamics of Pointwise Forward-KL On-Policy Self-DistillationDi Huang, Hao Li, Yixin Chen +1cs.CL2026-09-30
#120Settle: Learning When to Stop ReasoningRyan Brown, Zihao Fu, Chris Russellcs.CL2026-09-30
#121The Invisible Language Tax: Token Premiums of French and Regional Languages in 2026 LLM Tokenizers, and a French-Optimized PrototypeThomas Servalcs.CL2026-09-30
#122Evidence First, Arithmetic Second: A System Report and Failure Analysis for DocSemDivya Godara, Sachin Guptacs.CL2026-09-30
#123A Missing Piece for Trustworthy AI Reviewers: From Benchmarking Rhetorical Robustness to SciCore ReviewChenguang Wang, Ming Li, Chengrui Fan +4cs.CL2026-09-30
#124RSIGame: Autonomous Agentic Game Development with Recursive Self-improvementWenyi Wu, Minghao Fu, Jieyu You +10cs.CL2026-09-30
#125Structure vs. Chain-of-Thought: Evaluating LLM Criteria Extraction for Depression SeverityXinkai Chencs.CL2026-09-30
#126CORE: Conflict-Oriented Reasoning Elimination for Verifiable Language-Model SearchSiyu Song, Rui Xu, Jia Lin +2cs.CL2026-09-30
#127LexReward: A Taxonomy-Driven Reward Framework for Legal Language ModelsYida Cai, Xin Dai, Bingxiang He +5cs.CL2026-09-30
#128Beyond Text: LLM-Based Dimensional Emotion Evaluation in Multimodal DialogueYutong Hu, Jinho Choics.CL2026-09-30
#129False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search AgentsMeijia Chen, Hao Li, Zheng Lu +12cs.CL2026-09-30
#130Bongard: Training Machine IntuitionLi Ding, Haidi Jin, Chen Jics.CL2026-09-30
#131Diagnosing On-Policy Self-Distillation for Reasoning Language ModelsYang Li, Gongle Xue, Yuheng Yuan +4cs.CL2026-09-30
#132DAGent: Evaluate-then-Grow Planning for Deep Research AgentsHanwen Liu, Yuanfu Sun, Qiaoyu Tancs.CL2026-09-30
#133ViLegalExpert: A Large-Scale Benchmark for Vietnamese Legal Retrieval and Question Answering from Real-World ConsultationsDat Tien Nguyen, Nghia Hieu Nguyen, Anh Thi-Hoang Nguyen +3cs.CL2026-09-30
#134Argument Structure Prediction in Online Conversations: A Comparative Study of Modeling Paradigms and Task ArchitecturesSiddharth Bhargava, Sara Tonelli, Patricia Martín-Rodilla +1cs.CL2026-09-30
#135RAIM: Robust Aggregation of Inexpensive Models for Hallucination DetectionElia Onofri, Roberto Di Pietrocs.CL2026-09-30
#1364MT-VLM: How Coarse Is a VLMs Cognitive Map?Markus Freycs.CL2026-09-30
#137Concept Subspaces Compute Beyond the Logit Lens: A Weights-Only Test for Locating Representations Upstream of ReadoutAojie Yuan, Zhiyuan Julian Su, Haiyue Zhang +1cs.CL2026-09-30
#138Offline Guidance, Online Reasoning: Reusing LLM Feedback for Small Language ModelsBohan Zhang, Linan Yue, Weibo Gao +3cs.CL2026-09-30
#139Working Around the Compute Ceiling: Byte-Exact Memory in Galahad Makes LLM Reading a One-Time Cost LLM Reading a One-Time CostSietse Schelpecs.CL2026-09-30
#140Ready2Blend: From Natural-Language Instructions to Composable Alignment PromptsJeesu Jung, Hwan Chang, Juseon Do +5cs.CL2026-09-30
#141Making Grid Beam Search Less GreedySean Papay, Roman Klingercs.CL2026-09-30
#142Exploring Heterogeneous Model Merging Approach for Complex Knowledge TransferJiahe Fan, Si Chen, Yinghao Hou +4cs.CL2026-09-30
#143TTLab at Daleel 2026: STAR-Ar, Sequence Tagging for Argument Recognition in ArabicBhuvanesh Verma, Ali Abusaleh, Alexander Mehlercs.CL2026-09-30
#144QuantCode Model: Specializing Language Models for Executable Algorithmic Trading CodeAlexey Chernysh, Orkhan Ekhtibarov, Dmitry Zmitrovichcs.CL2026-09-30
#145DuplexAct-Bench: Broadening Full-Duplex Speech Evaluation toward Proactive Interaction across Diverse Behavioral RequirementsKeyue Xing, Wentao Ding, Mengmeng Wang +3cs.CL2026-09-30
#146Synthetic Data Characterization via Training DynamicsIrene Lago, Ana Ezquerro, David Vilarescs.CL2026-09-30
#147Right-Wing Rock or Just Rock? A Computational Linguistic Analysis of Frei.WildCarlotta Schneeberger, Kevin Tangcs.CL2026-09-30
#148Spike-driven Vision-Language-Action ModelShuai Wang, Malu Zhang, Mingquan Liu +6cs.CL2026-09-30
#149CATCH: A Controllable Analysis Testbed for Reward Hacking in Coding RLShouli Wang, Yanfeng Jia, Zhihao Ou +6cs.CL2026-09-30
#150Compact Language, Complex Model Shifts: How and Where Ambiguity and Underspecification Affect LLMsMichaela Regneri, Nina Scheller, Sören Lauecs.CL2026-09-30
#151Thinking Outside the Box: Can Language Models Rely on External Guidance Selectively?Minghan Wang, Boyuan Wang, Jinhang Zuo +2cs.CL2026-09-30
#152Is This Evidence Decision-Critical? Learning to Verify Rule-Governed DecisionsHaoyang Zhang, Jianpeng Zhao, Qi Hao +1cs.CL2026-09-30
#153Marginal Response Surface Elicitation for Zero-Label Tabular LearningLiangyu Teng, Yicheng Ding, Jing Liu +5cs.CL2026-09-30
#154Zero-Compute Cross-Lingual Transferability Estimation Using Typological Feature ProxiesDalton Raphael Harmsen, Swier Garst, Thomas van Osch +2cs.CL2026-09-30
#155SEPAL: Separated Expert Pairs with Answer-Level Fusion for Reliable LLM CollaborationWeijie Ren, Yanwen Zhang, Hao Li +3cs.CL2026-09-30
#156The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging TrendsZhentao Tan, Jingyi Shen, Yanbo Li +3cs.CL2026-09-30
#157Better Supervision Is Nearby: Neighborhood On-Policy Self-DistillationXincheng Wei, Yifan Ding, Yoshua Li +6cs.CL2026-09-30
#158Drift Inspector: Exploring and Measuring Scientific Drift with Atomic Contribution ClaimsVsevolod Karimov, Stepan Ostarkov, Anastasia Poroshina +2cs.CL2026-09-30
#159LatentHarness: Learning Latent Actions for Memory and Reasoning via Counterfactual Policy DistillationXiaoqiang Wang, Suyuchen Wang, Bang Liucs.CL2026-09-30
#160MemCodex: Self-Programming Hierarchical Memory for Language AgentsXiaoqiang Wang, Bang Liucs.CL2026-09-30
#161Explore-on-Graph: Hybrid Embedding-LLM Reasoning for Knowledge Graph Question Answering under IncompletenessOla El Khatib, Djellel Difallahcs.CL2026-09-30
#162Stress-Testing LLM Lie Detectors: Role-Play Failures and Spurious CorrelationsMaximilian von Klinski, Sebastian Lapuschkin, Wojciech Samek +1cs.CL2026-09-30
#163Synthetic Pre-pretraining Survives Scale, but Not as a Grammatical PriorAtsuki Yamaguchi, Tatsuro Inaba, Joel Niklaus +3cs.CL2026-09-30
#164When a Kindergartener Solves Calculus: Measuring Capability Leakage in Role-Prompted Reasoning ModelsPakhapoom Sarapat, Saksorn Ruangtanusak, Kunat Pipatanakul +1cs.CL2026-09-30
#165Cognitive Enhancement: Rethinking the Necessity of Role-Playing for Large Language ModelsXingjie Zhuang, Jialong Tang, Chulun Zhou +5cs.CL2026-09-30
#166LLM Persona UnlearningKemou Li, Zhuan Shi, Qizhou Wang +4cs.CL2026-09-30
#167OPSRD: On-Policy Self-Role DistillationWeijie Ren, Yanwen Zhang, Hao Li +3cs.CL2026-09-30
#168The Concrete-Arbitrary Gap: Kinship Reasoning in LLMs Is Not Indifferent to PresentationThomas Pashbycs.CL2026-09-30
#169AdaGEPA: Adaptive Feedback Allocation for Reflective Prompt OptimizationJunyang Chen, Zecheng Wang, Jingbang Chencs.CL2026-09-30
#170LEAP: Learned Block-wise Evidence Retrieval for Long Audio-Video PerceptionJuyi Lin, Zhiqiang Lao, Jiali Cui +9cs.CL2026-09-30
#171UBTree: Parallel Tree Drafting via Unigram and Bigram Models for Speculative DecodingChumeng Liang, Linxuan Wang, Xinyu Peng +6cs.CL2026-09-30
#172Overview of BioASQ 2026: The fourteenth BioASQ Challenge on Large-Scale Biomedical Semantic Indexing and Question AnsweringAnastasios Nentidis, Georgios Katsimpras, Anastasia Krithara +18cs.CL2026-09-30
#173Mid-Harness: Scaling Actions Between Model and Harness for Terminal AgentsMinki Kang, Ryo Hachiuma, Shaokun Zhang +8cs.CL2026-09-30
#174OPTS-TTPO: Enhancing Finite-Sample Policy-Gradient Learning with Tree SearchJunyu Lu, Shichao Weng, Zhiqiang Wang +10cs.CL2026-09-30
#175MGhana-ST: A Low-Resource Speech Translation Dataset for Ghanaian Languages and an Analysis of Multilingual Training Trade-offsFrank Lawrence Nii Adoquaye Acquaye, Eric George Parakal, Jesse Johnson +2cs.CL2026-09-30
#176From Tweets to Trades: Analyzing the Influence of Public Mood over Stock Market Performance in TurkiyeEce Elif Adak, Bertaç Şakir Şahin, Şaziye Betül Özateşcs.CL2026-09-30
#177AutoDataBench: A Data-centric Testbed for Accelerating Auto ResearchRuifeng Yuan, Yizhi Li, Yaxin Du +9cs.CL2026-09-30
#178JuryFlow: Disagreement-Guided Human-in-the-Loop Multi-Agent EvaluationMufeng Yang, Junwei Yu, Yepeng Dingcs.CL2026-09-30
#179OverdoseMoE: A Multi-Expert Framework for Opioid Overdose Risk PredictionMingchen Li, Rohan Pandey, Junhui Qian +5cs.CL2026-09-30
#180Persistent Context Graphs for Efficient Memory Compaction in LLM AgentsJingbo Yang, Kwei-Herng Lai, Xiaowen Wang +6cs.CL2026-09-30
#181On the (In)effectiveness of AMR Augmentation for Large Language ModelsHoa Quynh Nhung Nguyen, Jacopo Staiano, Michael Sullivancs.CL2026-09-30
#182Debias It Yourself: Teaching LLMs Cognitive Bias Mitigation InterventionsChahat Raj, Sina Mansouri, Aylin Caliskan +2cs.CL2026-09-30
#183Index-Translate: A Multilingual Translation Model Family -- Text, Speech, Controlled Dubbing, and Long-Document TranslationTianjiao Li, Mengran Yu, Chenyu Shi +8cs.CL2026-09-30
#184Provably Tractable NFA-Constrained Language Generation via HMMsJialiang Sun, Kuldeep Meelcs.CL2026-09-30
#185SCB: SpeechConversationBench for Evaluating Multi-Turn Reasoning in Speech-to-Speech ModelsKanpat Vesessook, Saksorn Ruangtanusakcs.CL2026-09-30
#186Comparison of techniques for fine-tuning open-weight models for entity extraction from radiology reportsAawez Mansuri, Kush Mehta, Mohammadreza Chavoshi +10cs.CL2026-09-30
#187Linguistic Loopholes in LLM Unlearning: From a 174-Language Benchmark to Coverage-Aware UnlearningTyler Skow, Shravan Chaudhari, Rama Chellappa +1cs.CL2026-09-30
#188How Much Is an AI Token Worth? Scaling Laws for Wild AI-Generated Web TextJenna Russell, Ben Glickenhaus, Katherine Thai +4cs.CL2026-09-30
#189EvoDuet: Bilevel Co-Evolution of Web Searching and Task Solving for Scientific DiscoveryYoung-Jun Lee, Jinheon Baek, Soyeong Jeong +5cs.CL2026-09-30
#190Anchor-ECC: Local Integrity Checking for Watermarked LLM Outputs via Error-Correcting CodesZewei Deng, Muhammad Siddeek, Liyan Xie +4cs.CR2026-09-30
#191SceneJail: Exploiting Video Scenario Context to Jailbreak Multimodal LLMsWenyu Chen, Li Wang, Chuanchao Zang +5cs.CR2026-09-30
#192PrivCert: Certifying Statement Support under Differential PrivacyTsubasa Takahashi, Takumi Hiraokacs.CR2026-09-30
#193APTInvestBench: Evaluating Autonomous APT Investigation under Varying TelemetryYu Wang, Shuhao Li, Tao Yin +4cs.CR2026-09-30
#194Approval Laundering: Systematizing Approval--Execution Binding Failures in AI Coding-Agent HarnessesYang Wangcs.CR2026-09-30
#195Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent SystemsDeema Alnuhait, Gengyu Wang, Muhammad Khalifa +1cs.CR2026-09-30
#196Can Agents Trust Their Skills? Uncovering Unsafe Chains of Trust in Skill-Based LLM AgentsYan Wang, Zhihao Zhang, Ke Chen +5cs.CR2026-09-30
#197RAGScope: A Leakage-Controlled, Cost-Aware Evidence-Gating Protocol for RAG Hallucination TriageZeming Liu, Qibai Chen, Jingtao Zhang +1cs.CR2026-09-30
#198Faithful Dual-constrained Erasure for Robust LLM Safety AlignmentJiaqing Li, Shide Zhou, Zhibo Zhang +3cs.CR2026-09-30
#199Hiding in Plain Sight: Decoupling Pretext from Actuation for Skill Poisoning in LLM AgentsWenxin Wu, Lingyong Yan, Lei Sha +2cs.CR2026-09-30
#200ActionGuard: Tool Call Authorization under Poisoned SkillsJihun Han, Yejin Jang, Byung Il Kwak +1cs.CR2026-09-30
#201Speculative Safety Honeypot: Toward Proactive Defense Against Multi-turn Agent AttacksZezhong Wang, Xueyang Tang, Rui Lian +2cs.CR2026-09-30
#202Cybersecurity in Edge Computing: A Trust-Aware Federated Hybrid Intrusion Detection FrameworkZawad Yalmie Sazid, Robert Abbascs.CR2026-09-30
#203Pretext: Defeating Malicious Skill Detection Frameworks for AI AgentsTobias Kaisar, Aritra Dharcs.CR2026-09-30
#204PassGPT+: Leveraging Linguistic Priors for Password ModelingRajneesh Anand, Neeraj Lakshmanan, Masoud Yarics.CR2026-09-30
#205CodeMimicry: Exploiting Safety Generalization Lag in Large Language Models via Structured Code CompletionZhen Liang, Hai Huang, Wentao Chencs.CR2026-09-30
#206ReGain: Restoring Subject Fidelity in Personalization on Synthetic ImagesShubhang Bhatnagar, Ishan Bhatnagar, Viraj Shah +1cs.CV2026-09-30
#207Unveiling the Value of Motion for Cinematic Camera TrajectoriesZiqi Zhou, Yujian Yuan, Laura Sevilla-Laracs.CV2026-09-30
#208EPIC: Epipolar-Consistent 360° Immersive Stereo Video GenerationDebabrata Mandal, Dongdong Fu, Jonathon Miller +3cs.CV2026-09-30
#209No Corners Cut: State-Grounded Transitions for Mid-Stream Prompt Switches in Video GenerationZejing Rao, Ketong Ren, Xiaoqiang Liu +3cs.CV2026-09-30
#210SCALE: Synthetic Calibration via Agreement Labeling in Embedding SpaceWenjun Liu, Saeed Hassanpourcs.CV2026-09-30
#211Hard-Region Supervision: #1 on the Waymo Open Dataset 2D Video Panoptic Segmentation LeaderboardJinghan Yangcs.CV2026-09-30
#212SpatialCORE: Confidence-Aware Grounded Spatial Reasoning in Large Vision--Language ModelsRafi Ibn Sultan, Xiangyu Zhou, Md. Sajid Alam Chowdhury +4cs.CV2026-09-30
#213Soft Spatial ReasoningRafi Ibn Sultan, Md. Sajid Alam Chowdhury, Saleh Zare Zade +4cs.CV2026-09-30
#214Matisse: Evidence-Space Reasoning for Active 3D ReconstructionXihang Yu, Kaichen Zhou, Lorenzo Shaikewitz +4cs.CV2026-09-30
#215Consensus-Aware Multi-Source Fusion for Reference-Guided Camouflaged Object DetectionJunyang Xia, Luocheng Zhang, Wenwen Pan +4cs.CV2026-09-30
#216Here the World in Stereo: Learning Dynamic Spatial Correspondence for Immersive Joint Video-Audio GenerationHanmo Chen, Chengcheng Liu, Tianxiao Chen +7cs.CV2026-09-30
#217Agentic Relative Camera Pose Estimation via Learned Ranking and VerificationZhining Gu, Shangjie Du, Weimin Qiu +3cs.CV2026-09-30
#218Event-Driven Refresh and Recurrence Memory to Reduce Stale Grounding in Referring Video Object SegmentationAbu Hanif Muhammad Syarubany, Jaehyun Jang, Siwoo Lim +2cs.CV2026-09-30
#219Distill the Visual Evidence, Not Just the Answer: Cross-World On-Policy Distillation for Vision-Language ModelsYuanhao Sun, Huawei Ji, Jiaxin Ding +2cs.CV2026-09-30
#220CRAFT: Causal Responsibility and Failure Tracing in Medical Vision Language ModelsChunzheng Zhu, Jiaqi Zeng, Hongbo Zhao +3cs.CV2026-09-30
#221DCM-SAM: Defect-Conditioned Mixture of LoRA Experts for NPU-Deployed AM Defect SegmentationMd Mushfiqur Rahaman, Md Mahedi Hasan, Imtiaz Ahmed +1cs.CV2026-09-30
#222Future Video Generation Better Aligns with the Human Visual Cortex than Observed VideoChang-Bae Bang, Hyungjin Chung, Byung-Hoon Kimcs.CV2026-09-30
#223DecoMoE: Decoupling Visual Propagation and Expert Computation for Efficient Multimodal MoE InferenceXudong Tan, Peng Ye, Ming Xie +4cs.CV2026-09-30
#224FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video GenerationBo Yin, Xiaobin Hu, Jiaqi Zhao +1cs.CV2026-09-30
#225Decoupling Spherical Reasoning from Dense Prediction for 360 Depth EstimationZhijie Shen, Chunyu Lin, Shuai Zheng +4cs.CV2026-09-30
#226AdaOcc: Adaptive 3D Occupancy Prediction for Embodied TasksJinglong Wang, Yunjie Wang, Zhiyang Zhang +4cs.CV2026-09-30
#227MEMO: Multi-Level Entity-Aware Memory for Streaming Video UnderstandingYinying Li, Yuqian Fu, Yulin Dai +3cs.CV2026-09-30
#228FLOW: Feature-Level Optimal Warping for Generalized Remote Physiological MeasurementBo Zhao, Junzhe Cao, Dan Guo +5cs.CV2026-09-30
#229From Image Interpretation to Clinical Reasoning: Upstream Physician-Context-Aware Multimodal Learning with Causal Reinforcement LearningJialu Pi, Yanan Ma, Weijie Chen +8cs.CV2026-09-30
#230On the Relaxation of Conditional Independence Assumption for Image SegmentationZixun Wang, Ben Daics.CV2026-09-30
#231Beyond Spatial-Domain Supervision: A Relation Constrained Space for Multi-Modal Image FusionZeyu Wang, Mingyu Ge, Haiyu Song +1cs.CV2026-09-30
#232PARK: Accurate Block Retrieval for Sparse Attention in Video Diffusion TransformersYun Dai, Jiarui Wen, Huiping Zhuang +2cs.CV2026-09-30
#233Mitigating Object Hallucination in Large Vision-Language Models via False Discovery Controlled Visual Data SplittingChang Liu, Yu Tian, Rui Xiecs.CV2026-09-30
#234MeshOctave generates meshes via cascading resolution transitionsJunkai Lin, Tianhao Zhao, Hang Long +10cs.CV2026-09-30
#235When Integral Meets Decomposition: A Signal-Level Self-Supervised Feature Decompose Paradigm for Multi-Modal Image FusionZeyu Wang, Jiayu Wang, Haiyu Song +1cs.CV2026-09-30
#236Frame Differential On-Policy Self-Distillation for Video ReasoningHaiying He, Xin Zheng, Shaoli Hu +4cs.CV2026-09-30
#237Persistent Watermarking of Text-to-Image ModelsDixi Yao, Kaiwen Chen, Tahseen Rabbani +1cs.CV2026-09-30
#238TED:Text-Axis Evidence Decomposition for Prompted Anomaly LocalizationJinYoung Kim, Geonho Kim, GiJeong Park +2cs.CV2026-09-30
#239BadAction: Backdoor Attacks on Interactive Video Generation via Action-Guided TriggersZhihang Wu, Zhongqi Wang, Jie Zhang +3cs.CV2026-09-30
#240TSMD: Temporal-Stream Modality Dropout for Robust Video Highlight DetectionBo-Yuan Cheng, Kuan-Yu Chen, Po-Han Huang +2cs.CV2026-09-30
#241Agentic Tool-Augmented Reasoning for Explainable Image Forgery DetectionZhiya Tan, Jing Huang, Changtao Miao +5cs.CV2026-09-30
#242MRI Super-Resolution with RCDM/WaveMix and Task-Aware SegmentationKavitha Viswanathan, Harsh Choudhary, Amit Sethics.CV2026-09-30
#243UGOD: Uncertainty-Guided Opacity and Dropout for Sparse-View 3D Gaussian SplattingZhihao Guo, Peng Wang, Zidong Chen +7cs.CV2026-09-30
#244DeCoPrune: Efficient KV-Cache Pruning for Autoregressive Video Diffusion via Denoising ConsistencyZeqi Xiao, Qingle Liu, Kaiwen Zhang +3cs.CV2026-09-30
#245CamAgent: An LLM-Agent Framework for Multi-Species Camera-Trap WorkflowsYutong Deng, Qi Song, Xi Guo +3cs.CV2026-09-30
#246Beyond Local Linearity: Scale-Resolved Geometry of Learned Image EncodersJakub Szymkowiak, Wojtek Pałubicki, Kamil Adamczewskics.CV2026-09-30
#247GRC-Pose: Generation-Reconstruction Correspondence for Prior-Free 6D Object Pose TrackingShiyang Liu, Weiquan Lin, Luping Xiao +4cs.CV2026-09-30
#248Is Better Teacher Supervision Enough? Unlocking Student-side Learning in Multimodal On-Policy DistillationSiyuan Liu, Kanghui Tian, Yue Duan +4cs.CV2026-09-30
#249How to Reduce Localization Ambiguity? Geometry-Semantic Constrained BEV Representation Learning for Satellite-Ground LocalizationJunming Feng, Panwang Xia, Qiong Wu +8cs.CV2026-09-30
#250GeoGAT: Bidirectional Temporal Sampling Meets Hierarchical Graph Attention for Global Video Geo-localizationJunchao Cui, Xuanzi Ma, Wenqi Shi +4cs.CV2026-09-30
#251Perceptual Color Difference Modeling Using Machine Learning and Human Similarity JudgmentsElnara Kadyrgali, Muragul Muratbekova, Adilet Yerkin +6cs.CV2026-09-30
#252Uncertainty-Aware Consistency Distillation for Few-Step Video GenerationLingyu Liu, Yaxiong Wang, Li Zhu +1cs.CV2026-09-30
#253Feature-Aware Token Attack for Compression-Triggered Stealthy Failures in Large Vision-Language ModelsShilinlu Yan, Bowen Chen, Yuechen Zhang +3cs.CV2026-09-30
#254Asking the World: Generalist Physical Reasoning through Agentic World Modeling and ProbingShenxiang Zeng, Chen Yang, Peiyao Chen +3cs.CV2026-09-30
#255When Can Text Replace Vision? Structural Bottlenecks in Diagram ReasoningYunbei Zhang, Janet Wang, Jihun Hamm +1cs.CV2026-09-30
#256MindWorldBench: Evaluating Mental-State-to-Behavior Reasoning in Image-to-Video GenerationRuiqi Li, Xuanyi Liu, Sijia Li +9cs.CV2026-09-30
#257OP-CAD: On-Policy Clean-Audio Distillation for Robust Audio-Visual ReasoningXingming Shui, Dapeng Chen, Bowei Liu +5cs.CV2026-09-30
#258TripleFlow: Training-Free Video Object Removal by Bridging Residual Editing and Native GenerationSonghe Wang, Lifu Wei, Shuolin Xu +2cs.CV2026-09-30
#259MEND: Label-Free Detection, Localisation, and Correction of Latent Hallucination in World ModelsAli J Alrasheed, Aryan Yazdan Parast, Basim Azam +2cs.CV2026-09-30
#260Aligning Thoughts with Answers: Probability Rewards to Tame Thinking DriftPengzhan Sun, Shiu-hong Kao, Shijie Li +4cs.CV2026-09-30
#261Fiber-Resolved Microstructure Quantification from Multi-Shell Diffusion MRI using Detection TransformersSebastian Endt, Marcus Wirth, Johannes Reinhold Schlund +1cs.CV2026-09-30
#262Uruqi: Learning Spatial Cognition from Visual ExperienceShichao Li, Meiqi Wang, Fei Su +1cs.CV2026-09-30
#263DC-SAE: Deep Compression Semantic Autoencoder for Faster Diffusion ConvergenceXu Huang, Ye Huang, Zijun Liao +6cs.CV2026-09-30
#264Emergent Multi-View Geometry Through Self-DistillationDavid Nordström, Thibaut Loiseau, Vincent Lepetit +3cs.CV2026-09-30
#265Universal Cross-Prompt Adversarial Attacks on Promptable Concept SegmentationZiqi Zhou, Yifan Hu, Yufei Song +5cs.CV2026-09-30
#266PLRS-IC: A Dual-Calibration Framework for Chest X-Ray Vision-Language AlignmentQixing Zhao, Jinpeng Lics.CV2026-09-30
#267MegaAvatar: Controllable Talking Avatar GenerationJunyao Gao, Sibo Liu, Weidong Zhang +2cs.CV2026-09-30
#268BMASH: Ball-Motion-Aware Soccer Header SpottingAhmed Endris Hasen, Muhammad Shahzad Khan, Nikolaos Passalis +1cs.CV2026-09-30
#269Rethinking Generative Image Compression at Extremely Low BitratesTianyu Zhang, Zhaoyang Jia, Houqiang Li +1cs.CV2026-09-30
#270TexTailor: Texture-Preserving Video Virtual Try-On via Adaptive Garment ConditioningZijing Qin, Jun Zhou, Ruicheng Zhang +5cs.CV2026-09-30
#271Rethinking Multi-Image Re-Representation in Multi-Image UnderstandingGengyuan Zhang, Xiao Han, Xinyu Xie +2cs.CV2026-09-30
#272COBICount: Separating Object and Background Responses for Remote Sensing Object Counting Without Training on Target DataJunjing Zheng, Zhiyi Zhou, Ningrui Yang +1cs.CV2026-09-30
#273EgoTools: Towards Tool-Centric Reasoning in Real-World Egocentric VideosShulin Tian, Junsu Kim, Shuai Liu +17cs.CV2026-09-30
#274InfoAgent: Traceable Generation and Repair of Evidence-Grounded InfographicsYifan Li, Tong Li, Qi Zeng +6cs.CV2026-09-30
#275PCB-MC: Missing Component Analysis in Printed Circuit BoardsBetsy Villa Brochero, Ian Gibson, Estefania Talaveracs.CV2026-09-30
#276Towards Trustworthy AI for Glioma Diagnosis: A Task-Aware Evaluation of Uncertainty QuantificationGonzalo Esteban Mosquera Rojas, Sebastian R. van der Voort, Carolin M. Pirkl +3cs.CV2026-09-30
#277CAST: Causal Advantage-Structured Training with Spatially Grounded Compositional Rewards for Diffusion ModelsShu Yu, Chaochao Lucs.CV2026-09-30
#278ResARC: Residual-Aware AutoRegressive Coding for Ultra-Low Bitrate Image CompressionQin Yan, Ruixiao Dong, Yutao Xie +5cs.CV2026-09-30
#279DensePed-Lite: Quality-Aware Adaptive Detection for Dense Pedestrians under OcclusionZiAn Wang, MingZhe Liu, Chaoyi Guo +2cs.CV2026-09-30
#280From Wrecks to Wisdom: Recovering Crash Mechanics from Real-World Multi-View PhotosOndřej Valach, Václav Diviš, Ivan Grubercs.CV2026-09-30
#281OmniReasoning: Pushing the Limits of Audio-Visual Joint ReasoningJunming Lin, Yuxuan Wang, Zhenxin Lei +11cs.CV2026-09-30
#282Front-to-Back: Benchmarking Vision-Language Models for Asymmetric Cross-View Vehicle Re-IdentificationMoseli Mots'oehli, Thulani Babelics.CV2026-09-30
#283PartiCam: Camera Controlled Video Generation with Reward GuidanceAmine Ouasfi, Runjia Li, Junlin Han +3cs.CV2026-09-30
#284Lens Flare Removal and ReconstructionTarun Yenamandra, Jonathon Luiten, Daniel Cremers +1cs.CV2026-09-30
#285Comparative study of adapting pre-trained models for driving behavior video captioningSayak Mallick, Philipp Geiger, Augustin Kelavacs.CV2026-09-30
#286Learning Normal Diffusion Dynamics for Backdoor Defense in Text-to-Image ModelsJunjian Li, Xiaolong Liu, Peng Sun +4cs.CV2026-09-30
#287EffGS: Efficient and High-Fidelity Gaussian SplattingChangbai Li, Shuo Yang, Yichen Yang +2cs.CV2026-09-30
#288RESUME: Recurrent State Updates from Motion and Residual Signals for Efficient Video Language ModelingCan Zhang, Xiaotian Han, Junyuan Shang +5cs.CV2026-09-30
#289From Given to Gathered Evidence: Agentic Learning for Longitudinal Medical ReasoningMinye Shao, Chaohui Yu, Yixuan Wu +3cs.CV2026-09-30
#290Invariant Shape Analysis of Surfaces with Spherical TopologyT. Shaska, M. -R. Siadatcs.CV2026-09-30
#291Steering Fields: Adaptive Vector Fields for Safe Image Generation and BeyondSimone Facchiano, Jan Eric Lenssen, Bernt Schiele +3cs.CV2026-09-30
#292A Generalizable and Explainable Framework for Synthetic Video Detection Using First-Digit Gradient StatisticsSidharth Shanu, Gautam Kumar, Tej Singhcs.CV2026-09-30
#293KilometerVision: A New Frontier for Large-Scale Spatial Intelligence in VLMsAravindh Mahendran, Michael King, Matthew Koichi Grimes +12cs.CV2026-09-30
#294SPOON: Towards Coherent Compositional 3D Scene Generation from Uncalibrated Multi-view ImagesGuibiao Liao, Mochu Xiang, Heng Li +6cs.CV2026-09-30
#295Structural Limits of the Information-Theoretic Uncertainty DecompositionJakob Lønborg Christensen, Christian F. Baumgartner, Morten Rieger Hannemose +2cs.CV2026-09-30
#296GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash SpeedQize Yu, Lianrui Fan, Bowen Ping +19cs.CV2026-09-30
#297GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual PrimitivesQize Yu, Lianrui Fan, Boyu Chen +23cs.CV2026-09-30
#298FOMO: Forget the Concept, Don't Miss Out on the Scene in Selective Video UnlearningŁukasz Rudnik, Agnieszka Polowczyk, Alicja Polowczyk +1cs.CV2026-09-30
#299Semantic Watermarking for Malicious Image Manipulation DetectionYoonseo Kim, Seungwoo Baek, Junyoung Parkcs.CV2026-09-30
#300ExpandDiff: Dynamic Range Expanding Diffusion for Single-Image HDR ReconstructionMehmet Emre andıran, Zhuoqian Yang, Liying Lu +2cs.CV2026-09-30
#301D-Scope: Decomposing and Steering Diffusion Transformers with Sparse AutoencodersXinyue Xu, Jiahao Zhang, Lijie Hu +2cs.CV2026-09-30
#302Introduction to Computer VisionStan Birchfieldcs.CV2026-09-30
#303SAGE: Salient Factor Discovery and Generation with Visual Foundation RepresentationsShuang Liang, Lejun Liao, Shiyuan Zhang +5cs.CV2026-09-30
#304FANVIDv2: Evaluating Video Super-Resolution by Face and Licence-Plate Recognition Under Compound DegradationKavitha Viswanathan, Vrinda Goel, Shlesh Gholap +5cs.CV2026-09-30
#305Diffusable Latents from Structure-Agnostic DistillationAdrien Ramanana Rahary, Nicolas Dufour, Patrick Pérez +1cs.CV2026-09-30
#306BAM! Bayesian Anything Model: a foundation model for generative computational imagingAlessio Spagnoletti, Charlesquin Kemajou Mbakam, Jonathan Spence +2cs.CV2026-09-30
#307Typographic Attack Against VLM-based AI-generated Image DetectionEunmin Lee, Jungwoo Kim, Jong-Seok Leecs.CV2026-09-30
#308MC-PanDA++: Simpler, Stronger, and More Robust Domain-Adaptive Panoptic SegmentationIvan Martinović, Josip Šarić, Yuki M. Asano +1cs.CV2026-09-30
#309Unapologetically Distributed: A Call for Decentralized Document AnalysisAdrià Molina, Oriol Ramos Terrades, Josep Lladóscs.CV2026-09-30
#310ShieldCLIP: Selective Safety Alignment for Harmful Content Mitigation in Multimodal Foundation ModelsTobia Poppi, Silvia Cappelletti, Samuele Poppi +4cs.CV2026-09-30
#311When Masking Helps or Hurts Robustness in Compressed CLIP: A Pre-Deployment DiagnosticMuhammad Zawish, Steven Davycs.CV2026-09-30
#312BTC3D: Blended Tile Conditioning for Detail-Enhancing Image-to-3D GenerationJunyu Li, Qiuyu Chen, Pengcheng Wang +5cs.CV2026-09-30
#313Let the Carrier Carry the Attack: Preserving the Subject in Adversarial Image GenerationLinfeng Jiang, Steven McDonagh, Yuhang Chen +3cs.CV2026-09-30
#314FAST: Flow Any Scene TransformerYongjian Zhang, Longguang Wang, Zhuo Song +3cs.CV2026-09-30
#315Determining Vertical Displacement of Agricultural Areas Using UAV-Photogrammetry and a Heteroscedastic Deep Learning ModelWojciech Gruszczyński, Edyta Puniach, Paweł Ćwiąkała +1cs.CV2026-09-30
#316Seeing as Humans Do: Learning from Motion to Segment Anything Without SupervisionWeijian Jian, Xiaoyue Zhang, Bin Xiao +5cs.CV2026-09-30
#317Inline Memory Meets Reusable Skills: Memory-centric Framework for Vision-Language-Action ModelZaijing Li, Rui Shao, Bing Hu +3cs.CV2026-09-30
#318P-SRM: Selective Recovery of Rejected Predictions in Visual TrackingYoubin He, Siwei Wangcs.CV2026-09-30
#319Spherical Interpolation for Backward-Compatible Multimodal RepresentationsSimone Ricci, Niccolò Biondi, Federico Pernicics.CV2026-09-30
#320DyRAD: Radar Novel View Synthesis for Dynamic Driving ScenesMerav Keidar, Tomer Borreda, Rajalakshmi Nandakumar +1cs.CV2026-09-30
#321Hyperspectral Image Models: Technical ReportTanishq Rachamalla, Aryan Das, Srishti Kaushik +1cs.CV2026-09-30
#322Grounding with Confidence: Controllable Generative Video Temporal GroundingJinhao Chen, Benlei Cui, Ruijian Jia +7cs.CV2026-09-30
#323Spatial-Temporal Multi-scale Network for Screen Content Video Quality EnhancementZiyin Huang, Sik-Ho Tsang, Xinyuan Qin +3cs.CV2026-09-30
#324Learning Where to Look: Anatomical Grounding and Guided Attention for Cardiac MRI Vision-Language ModelsBangwei Guo, Xiao Chen, Boris Mailhe +8cs.CV2026-09-30
#325NavHarness: Adaptive Goals for Agentic Vision-Language NavigationHaoxiang Shi, Zaijing Li, Muhe Ding +3cs.CV2026-09-30
#326MCD: Causal Distillation of Multimodal In-Context Learning in Large Vision-Language ModelsYanshu Li, Jiaqian Li, Canran Xiao +3cs.CV2026-09-30
#327CoVisco: Codec-Native Vision Encoder with Native Token Compression for Unified Image-Video UnderstandingYulong Liu, Xiaotian Han, Junyuan Shang +6cs.CV2026-09-30
#328Super-Resolving Unseen Hyperspectral Sensors at Any Scale via Spatial OperatorsJi-Xuan He, Guohang Zhuang, Bo Junge +6cs.CV2026-09-30
#329Learning to Reason with Compressed Context: Ground-Truth-Free Adaptation of OmniLLMs via Self-DistillationJianghao Wang, Ke Meng, Jian Li +7cs.CV2026-09-30
#330Reconstructing the Dynamic World: A Representation-Centric View of 4D Scene ReconstructionZiren Gong, Guo Chen, Yongjia Li +13cs.CV2026-09-30
#331Can We Anticipate Violence? Multimodal Learning from Pre-Incident Behavioral CuesSindhuja Penchala, Mohammed Yusuf Mujawar, Noorbakhsh Amiri Golilarz +2cs.CV2026-09-30
#332WARP: A Unified Benchmark for Invisible Image Watermarking -- Robustness and Protection Against AttacksKhaled Abud, Aleksey Yakushev, Aleksandr Akimenkov +9cs.CV2026-09-30
#333Enhancing Autoregressive Video Generation via Representation Adversarial DistillationFangyu Lin, Xingtong Ge, Lunjie Zhu +8cs.CV2026-09-30
#334CoEvoWhen: Policy-Tool Coevolution for Ultra-Long Video Temporal GroundingYiduo Jia, Muzhi Zhu, Jinchuan Shi +4cs.CV2026-09-30
#335Less Data, Better Timing: Student-Curriculum Coupling for VLM On-Policy Distillation in Temporal Video GroundingJiacheng Qiu, Yunsoo Kim, Ruichen Xu +3cs.CV2026-09-30
#336LongEmo: Towards Emotion Understanding and Reasoning in Long VideosShuo Zhang, Yifan Zhou, Han Wang +15cs.CV2026-09-30
#337GateSPINE: Gated Cross-View Fusion for Lumbar Spine MRI Report GenerationHoang Nguyen Van, Cuong Vuong Tuan, Trang Mai Xuan +3cs.CV2026-09-30
#338VR-JEPA: Learning Contrastive-State Latent Guidance for Generation-based Video ReasoningZehua Ma, Kun Xiang, Yunshuang Nie +9cs.CV2026-09-30
#339MemLife: Curating and Reasoning over Long-Term Egocentric Video MemoriesGuangzhi Xiong, Xinyuan Zhang, Xiao Yang +14cs.CV2026-09-30
#340Recognition of Urbanized Areas in UAV-Derived Very-High-Resolution Visible-Light ImageryEdyta Puniach, Wojciech Gruszczyński, Paweł Ćwiąkała +2cs.CV2026-09-30
#341Learning Skills from Historical Action Trajectories: Action Experience Dictionary for World Action ModelsQi Lyu, Jiahua Dong, Hao Shen +9cs.CV2026-09-30
#342LOCI: Spatial Linear Memory for Streaming World ModelsJi Xia, Tingting Liao, Xuezhi Liang +2cs.CV2026-09-30
#343EviRover: Reinforcing Agentic Perception Beyond a GlanceKaixuan Fan, Kaituo Feng, Tianshuo Peng +4cs.CV2026-09-30
#344StreamRig: Exploiting Intra-Rig Geometry for Streaming Multi-Camera OdometryYufei Wei, Shuhao Ye, Qi Wang +4cs.CV2026-09-30
#345ComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use AgentsYong Du, Tongbo Chen, Zhengxi Lu +5cs.CV2026-09-30
#346Looped Diffusion TransformerYong Xien Chng, Tianyi Chen, Wenwen Tong +7cs.CV2026-09-30
#347GLARE: Generating Listening Heads with Appropriate ReactionsZikai Liao, Yumin Suh, Yi Ouyang +3cs.CV2026-09-30
#348Atomizer-IO: Beyond Pixels, Patches and GridsHugo Riffaud de Turckheim, Sylvain Lobry, Nicolas Houdré +3cs.CV2026-09-30
#349MatLoom: Layered Text-to-Material Generation in a Compact Program SpaceAnson Y. Lam, Shuqing Li, Michael R. Lyucs.CV2026-09-30
#350I Have a Stream: Making Self-Supervised Learning Work on Continuous VideoIvan Martinović, Lukas Knobel, Yuki M. Asanocs.CV2026-09-30
#351Image Classifiers are Efficient Self-Supervised Video Representation LearnersOwais Iqbal, Sudipta Sarkar, Shyam Marjit +3cs.CV2026-09-30
#352AssemblyWorld: Rethinking 3D Assembly with General-Purpose AgentsJiahao Zhang, Yeying Fan, Moitreya Chatterjee +5cs.CV2026-09-30
#353ViTeX-Bench: Benchmarking High-Fidelity Video Scene Text EditingXinghao Chen, Xiangbo Gao, Jiongze Yu +2cs.CV2026-09-30
#354Physis-Lang: Self-Evolving Language as a Physical Representation for Video World ModelLiming Lu, Xianzheng Ma, Wenkun He +14cs.CV2026-09-30
#355Multimodal Flow: Unified Flow Modeling of Language and Vision in Embedding SpacesHongyuan Tao, Xinggang Wang, Lianghui Zhu +7cs.CV2026-09-30
#356A Reusable Semantic Web Framework for Evidence-Grounded Fundamental Rights Impact Assessments under the EU AI ActFaith Olopade, Delaram Golpayegani, David Lewiscs.CY2026-09-30
#357A 3GPP-Compliant Benchmark Dataset for RIS-Aided Beyond 5G NetworksPujitha Mamillapalli, Pankaj Singh Rathour, Abhinav Kumarcs.DB2026-09-30
#358Cascadia: A Control-Plane-Free Alternative to Hyperconverged AI InfrastructureMatias Parij, Pawan Paudel, Tate Berenbaum +1cs.DC2026-09-30
#359Taming Speculative Search for Test-Time Scaling in LLM ServingJinwoo Jeong, Woohyung Choi, Myeongjae Jeon +1cs.DC2026-09-30
#360HAPMoE: Heterogeneity-Aware Automatic Parallelism Planning for Mixture-of-Experts Models TrainingMengyuan Fan, Peizhuang Cong, Zixiao Huang +7cs.DC2026-09-30
#361About the Influence of Workflow Topology on Task Intensity Prediction through Graph LearningMax Otto, Haci Ismail Aslan, Joel Witzke +2cs.DC2026-09-30
#362Efficient Expert-Parallel Communication on PCIe-Connected Consumer GPUsJaehwan Lee, Sangmin Lee, Chaewon Kim +2cs.DC2026-09-30
#363Reinforcement Learning-Guided Graph Transformations for SpTRSV OptimizationBuse Yılmazcs.DC2026-09-30
#364Optimal VC Dimension of Contrastive Learning with MarginDionysis Arvanitakis, Vaggos Chatziafratis, Yiyuan Luo +1cs.DS2026-09-30
#365Component-Weighted Centroid Search for Exact Incremental BPEHarshit Verma, Rex Yingcs.DS2026-09-30
#366Robust and Learned Online Matching in Growing TreesMarek Gałązka, Hanna Wdowickacs.DS2026-09-30
#367Where the Evidence Lives: Auditing AI Companions' Self-DescriptionsSeiya Ikeda, Shin-nosuke Ishikawacs.HC2026-09-30
#368Characterizing Questioning Patterns and Student Engagement Through Contextual Analysis of Real-Time Classroom InteractionsRohit Sharma, Pavani Ayinampudi, Aditya B. M. V. +5cs.HC2026-09-30
#369NarrativeSteward: Coordinating Delegation, Guidance, and Verification in Agent-Assisted Interactive Narrative AuthoringWenjin Wang, Jiazhen Lei, Yuxin Sha +6cs.HC2026-09-30
#370Understanding Parents' Complex Views of AI for Children's Pretend PlaySungho Oh, Mohammad Namvarpour, Maxi Heitmayer +2cs.HC2026-09-30
#371Richard: Voice-First Mobile Interaction for Persistent TasksXinyang Chencs.HC2026-09-30
#372SkillSeek: Revisiting Agent Skill Retrieval at Marketplace ScaleGuanqun Yang, Wenlong Zhang, Tian Shi +1cs.IR2026-09-30
#373RouteRec: Behavior-Guided Sparse Routing for Sequential RecommendationJunyeong Song, Jaemin Yoocs.IR2026-09-30
#374Decision-Oriented Recommendation Reranking: An Empirical Study of JevHanjia Lyu, Yinglong Xiacs.IR2026-09-30
#375Coding Agents for Coding TheoryAbraham Yeungcs.IT2026-09-30
#376CAS II: Symmetric Partitions as Kolmogorov ModelsRomie Banerjeecs.IT2026-09-30
#377Molecular Property Prediction under Structural Shift with Tabular Foundation ModelsJinmo Lee, Dooho Lee, Minho Jeong +1cs.LG2026-09-30
#378Lasting Effects of Abstract Pretraining Beyond PerplexityZachary Shinnick, Hemanth Saratchandran, Damien Teney +1cs.LG2026-09-30
#379dattri-LLM: A Unified and Efficient Library for Training Data Attribution at LLM ScaleShixuan Liu, Tongli Zhou, Junwei Deng +2cs.LG2026-09-30
#380Learning Under Forgetting: Statistical Support-Selective Retention in Stochastic Training DynamicsFujie Gao, Zuyue Zhang, Gang Suncs.LG2026-09-30
#381Distilling Diffusion Score Discrepancy for Efficient Training Data AttributionShixuan Liu, Joan Serrà, Kin Wai Cheuk +6cs.LG2026-09-30
#382ChartDensity-Bench: Benchmarking MLLMs for Numerical Data Reconstruction under Visual DensityXinhe Wu, Yadong Jincs.LG2026-09-30
#383Does a Shared Temperature Imply a Shared Angular Scale in Probabilistic Contrastive Learning?Ningkang Peng, Qianfeng Yu, Jingyang Mao +4cs.LG2026-09-30
#384How Accurate Is Accurate Enough?Ningkang Peng, Qianfeng Yu, Jingyang Mao +2cs.LG2026-09-30
#385Same Loss, Different GradientsNingkang Peng, Xiaoqian Peng, Yifan He +4cs.LG2026-09-30
#386LEARN-TS: LLM-Enhanced Alignment and Reconstruction with Normality Guidance for Multivariate Time-Series Anomaly DetectionJahyeob Koo, Kio Yun, Byoungmo Koo +1cs.LG2026-09-30
#387Evaluating Persistent Calibration under Evolving Model KnowledgeVictor Wang, Thomas Hofweber, Mohit Bansal +1cs.LG2026-09-30
#388Explicit Trajectory Diversity for RL-Based Post-Training of LLM AgentsHuaiyu Fu, Heng Cao, Hao Wang +2cs.LG2026-09-30
#389Blackboard Intelligence Can Surpass Autoregressive on Globally Constrained ProblemsWoosang Jeon, Jaeyeon Kim, Sham Kakade +6cs.LG2026-09-30
#390Learning Chaos Without Seeing Chaos: Extrapolation of Global Dynamics in Autoregressive TransformersYilun Liu, Yi Zhang, Ganyu Wu +5cs.LG2026-09-30
#391SparLeak: Privacy Leakage from Sparse Attention in LLM Inference on Shared GPUsFahao Chen, Linkang Du, Jinhao Zhou +2cs.LG2026-09-30
#392ReSCENE: Server-Side Replay for Structural Mitigation of Catastrophic Forgetting in Federated Continual LearningSungmin Kang, Zhengzhong Tu, Sunwoo Leecs.LG2026-09-30
#393scTrilemma: Balancing Identity, Invariance, and Fidelity in Single-Cell Representation LearningYunhak Oh, Yoonho Lee, Junseok Lee +9cs.LG2026-09-30
#394Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level RubricsMaoqi Liu, Junwei He, Bowen Zhang +5cs.LG2026-09-30
#395Visualizing Distribution Coverage in Generative Diffusion ModelsYifei Wang, Xiaoyu Wu, Tsu-Jui Fu +4cs.LG2026-09-30
#396Mitigating the Length-Scaling Tax with Online DistillationXu Wan, Wenyue Xu, Shengjie Zhao +1cs.LG2026-09-30
#397Optimal Design for Active Preference Learning with Biased LLM JudgesZhongman Du, Huiming Zhang, Haodong Zhu +1cs.LG2026-09-30
#398GeoNest: Learning to Select Failure-Aware Neighborhoods for the Irregular Knapsack Problem in a Circular ContainerZhongman Du, Huiming Zhang, Linlin Yang +2cs.LG2026-09-30
#399On Parameters of Nonlinear Scalar Dynamics from Video: Invariants, Calibration, and IdentifiabilityWenjie Wang, Yuanyuan Wang, Zixiang Jiang +2cs.LG2026-09-30
#400Does Learning Protein Folding Generalize to Broader Reasoning?Yong Liu, Zhanpeng Shi, Yizhou Dang +4cs.LG2026-09-30
#401Right Answers, Costly Models: The Efficiency Gap in LLM-based Optimization ModelingZhong Li, Xin Huang, Jinhui Wan +6cs.LG2026-09-30
#402VERA: Verifiable Feasibility Representations with Counterfactual Credit for Constrained Multi-Agent ControlBo Yin, Dongbo Li, Hongkai Chen +2cs.LG2026-09-30
#403Learning Continuous Neural Representation of Stochastic Hybrid SystemsSangli Teng, Hang Liu, Koushil Sreenathcs.LG2026-09-30
#404Unmerge: Efficient Machine Unlearning via Task ArithmeticHaoran Tang, Andrew Tan, Rajiv Khannacs.LG2026-09-30
#405K2P: Label-Free Knowledge to Prompt DistillationYingchuan Zhang, Haoran Lu, Wenxuan Zhong +1cs.LG2026-09-30
#406Certified Approximation for Interpretable Representer LandmarksJayanta Mukherjee, Shourya Verma, Mengbo Wang +2cs.LG2026-09-30
#407Amortized Data Borrowing with Exchangeability-Aware Neural Posterior EstimationChin-Hung Huang, JooChul Lee, Huan Hecs.LG2026-09-30
#408DAMPER: Return-Prioritized Gradient Control for Smooth PoliciesSeokmin Ko, Taewon Goo, Kihyuk Hongcs.LG2026-09-30
#409Unlearning Deceptive Behaviors in LLMs with Contrastive Forget SetsHaoran Tang, Rajiv Khannacs.LG2026-09-30
#410Generalized Residual Closure: General Learning Dynamics for Stability-Plasticity CompatibilityDongxu Li, Yinuo Zhang, Hongyu Zhang +1cs.LG2026-09-30
#411Flow Matching under Noisy Latent Structure: Beyond Exact Low-Dimensional SupportLifeng Hao, Shaolin Jics.LG2026-09-30
#412Learning Where to Steer: Noise-Space Geometry for Efficient Offline Multi-Objective Optimization with Generative ModelsYuan Lu, Esha Singh, Yi-An Ma +1cs.LG2026-09-30
#413World-as-Graph: Relational World Modeling Through Latent Space GraphsYaqi Yang, Shuo Huang, Yujin Huang +3cs.LG2026-09-30
#414Adaptive Self-Consistency: From Black-Box Sampling to Distribution-Valued FeedbackJingkai Huang, Yunfan Zhang, Will Ma +2cs.LG2026-09-30
#415EFormer: Temporally Aligned Local Correction for Continuous sEMG-Based Hand Pose TrackingJiaCheng Ge, SiYu Zhangcs.LG2026-09-30
#416Signal-Routed Temperature Scaling: Low-Capacity Risk-Conditioned Calibration for Small Validation BudgetsWenhao Liang, Liangwei Nathan Zheng, Lin Yue +4cs.LG2026-09-30
#417Robust Risk-Sensitive Reinforcement Learning from Corrupted Human FeedbackXinyi Ni, Lifeng Laics.LG2026-09-30
#418Loop-Free Inverse Reinforcement Learning via Sequential Value Recovery with Q-Score MatchingYang chen, Yitan Zhang, Michael Witbrock +1cs.LG2026-09-30
#419Scale-Split Neural Operator for Memory- and Data-Efficient 3D Turbulence PredictionShaoxiang Qin, Yucheng Zhao, Zongyi Li +2cs.LG2026-09-30
#420SCORE-LM: State-Space Radar Representations with Language Models for Fault DiagnosisMainak Mallick, Seung-Kyum Choics.LG2026-09-30
#421Smaller Models, Better Rejects: Preference Distillation ScalingRui Cai, Wenhui Zhu, Xiwen Chen +15cs.LG2026-09-30
#422Anchoring Adversarial Trajectories to Data Manifolds: A Bilevel Transfer Optimization FrameworkYaohua Liu, Yifan Guo, Jiaxin Gaocs.LG2026-09-30
#423Not all solutions are created equal: An analytical dissociation of functional and representational similarity in deep linear neural networksLukas Braun, Erin Grant, Andrew M. Saxecs.LG2026-09-30
#424Synchronous Multi-view Neural DiffusionYongquan Shi, Weijun Huang, Yueyang Pi +3cs.LG2026-09-30
#425A Rank Graduation metric for Algorithmic fairnessDalia Atif, Paolo Giudicics.LG2026-09-30
#426Switching Linear AttentionHyun Dong Lee, Xavier Gonzalez, Nicolas Zucchet +3cs.LG2026-09-30
#427Cycle-Aware Autoencoder with Cross-SignalConsistency for Railway Door Anomaly DetectionAmmar Bouketta, Smail Niar, Hamza Ouarnoughi +1cs.LG2026-09-30
#428Hard-Gate Candidacy in a Deployed Validator SuiteXin Xucs.LG2026-09-30
#429Structure-aware Reinforcement Learning for Protein Directed EvolutionZikun Nie, Suyuan Zhao, Yizhen Luo +2cs.LG2026-09-30
#430The Missing Coefficients: Bayesian Pairwise Merging for Model PersonalizationYaling Shen, Tongtong Wu, Siyuan Yan +1cs.LG2026-09-30
#431Argus: A Real-EKS Study of When Predicting Spot Interruptions Beats Simple CheckpointingAngshuman Chakravertty, MD Rayyancs.LG2026-09-30
#432SparseEngine: Sparse-First Inference EngineJitai Hao, Quansheng Gu, Qiang Huang +1cs.LG2026-09-30
#433HO-FL: Hybrid-Order Federated Learning for Heterogeneous Edge DevicesQiyuan Chen, Xian Wu, Yanan Ma +1cs.LG2026-09-30
#434Parameter symmetries determine representational geometry in overparameterized nonlinear networksMarvin Theiss, Lukas Braun, Andrew M. Saxe +1cs.LG2026-09-30
#435Shared Phase and Retention Control for Efficient Adaptive Spectral RecurrenceWentao Wang, Hengyu Zhong, Yunhan Jiang +2cs.LG2026-09-30
#436Learning Infinite-Horizon Average-Reward CMDPs via State AugmentationKihyun Yu, Seoungbin Bae, Dabeen Leecs.LG2026-09-30
#437A Generalisation Signal Need Not Be a Model-Selection SignalAditya Nagarsekar, M P Ashish Bhat, Aadi Nesarkar +5cs.LG2026-09-30
#438T-Router: Learning Thalamic Routing for Reasoning with Parameter-Efficient Reinforcement LearningLiuxian Ma, Jiale Dai, Jiaqi Li +1cs.LG2026-09-30
#439The Row Normalization Puzzle in MuonJiayu Zhang, Tianyi Lincs.LG2026-09-30
#440Prequential E-Values for Selected-GP Near-Optimality CertificatesAmi Tavory, Noa Cohencs.LG2026-09-30
#441CDMD: A Cross-Dataset Mixed-Type Diffusion Model for Tabular DataMohamed Amine Ketata, Maximilian Schambach, Stephan Günnemanncs.LG2026-09-30
#442Characterizing High Bandwidth Flash for LLM ServingZack Yu, Chloe Wong, Coleman Hooper +7cs.LG2026-09-30
#443ID Balancing: Stable Training of Extremely Sparse MoE via PID-Based Load ControlPeng Jin, Zihan Qiu, Zekun Wang +8cs.LG2026-09-30
#444Sharp Stationary Gaussian Approximation for Constant-Stepsize SGDJunghoon Seocs.LG2026-09-30
#445QuanVI: Score-based Variational Inference via Quantum Maximally Mixed StatesYuchen Cong, Zerui Tao, Chao Li +2cs.LG2026-09-30
#446Whitening Improves Robustness to Spurious Correlations in Linear ProbesFloris Holstege, Bram Wouters, Noud van Giersbergen +1cs.LG2026-09-30
#447Low-Discrepancy Dither for Quantized Recurrent State CachesSnigdha Chandan Khilarcs.LG2026-09-30
#448Attention Function as an Intrinsic Inductive Bias: How Models' Behavior Diverges in Novel ContextsDong Gyun Kang, Megha Thukral, Kwangsoo Kimcs.LG2026-09-30
#449Dynamics to decision: A mathematical theory of Lyapunov spectra and decision boundaries in deep classifiersShirin Panahi, Amirhossein Nazerian, Ali Pezeshkics.LG2026-09-30
#450Importance-Aware Feature Sparsification for Wireless Split LearningBumjun Kim, Yoon Huh, Wan Choics.LG2026-09-30
#451In a Streaming World, Should You Stand Still? A Comprehensive Benchmark of Anomaly Detection in StreamsMagali Parrino, Antoine Ajenjo, Emmanuel Remy +3cs.LG2026-09-30
#452QATFactory: A Versatile, Deployment-Aligned Framework for Quantization-aware Training and Distillation of LLMsWeili Xu, Jisen Li, Yuqing Jian +8cs.LG2026-09-30
#453What Streaming Anomaly Detection Finds (and Misses) in Industrial Time SeriesMagali Parrino, Antoine Ajenjo, Emmanuel Remy +2cs.LG2026-09-30
#454A differentiability framework for zigzag persistent homology via linear interpolationEnrico Maria Ferrari, Clemens Bannwart, Matteo Biagettics.LG2026-09-30
#455Right Answer, Wrong Mechanism: Detecting Pernicious Divergence in Causal InterventionsBeiming Liu, Minjie Chencs.LG2026-09-30
#456Trust the Critic MoreKaiyue Wen, Luke Bailey, Arvind Mahankali +1cs.LG2026-09-30
#457Client and Training Data Selection for Computationally Efficient Synchronized Federated LearningMuzaffer Citir, Hiroki Nishikawa, Sangyoung Parkcs.LG2026-09-30
#458From Benchmarks to Production: Transferring Time Series Anomaly Detection Methods for Electricity Production MonitoringNicolas Vautier, Paul Caron, Nardi Xhepi +4cs.LG2026-09-30
#459Jacobian Rank Collapse in Decision-Focused LearningAojie Yuan, Haiyue Zhang, Zijian Sucs.LG2026-09-30
#460A Time-Aware Bag-of-Receptive-Fields for Interpretable Irregular Time Series ClassificationFrancesco Spinnatocs.LG2026-09-30
#461RW-Flow: One-Step Generation on Compact Manifolds via Wasserstein Gradient FlowsUalibyek Nurgulan, Seungwoo Yoo, Prin Phunyaphibarn +1cs.LG2026-09-30
#462ReTaCo: Residual-Target Control for On-Policy DistillationZixiang Ni, Zhuo Hu, Renjie Cao +8cs.LG2026-09-30
#463A Tilted Bowl Is Not a Slippery Slope: Compressing Looped ModelsSteven Kolawole, Pearse Jim, Opegbemi M. Busoye +2cs.LG2026-09-30
#464Physics-Informed Method of Group Data Handling: Adaptive Construction of Functional Representations with an Application to the Navier-Stokes EquationsMykhailo Minincs.LG2026-09-30
#465Semantic-Aware Joint Source-Channel Optimization for Encoder-Agnostic Digital Video CommunicationXiangben Zhu, Caili Guo, Yang Yang +2cs.LG2026-09-30
#466ReSAIL: Mitigating Collapse in Iterative Agent Self-DistillationShengjie Jin, Hengbo Xu, Zelong Sun +2cs.LG2026-09-30
#467GRPO Training Dynamics for Small Language ModelsRajat Ghosh, Vaishnavi Bhargava, Henry Wong +2cs.LG2026-09-30
#468PatchKV: Weight-Space Compensation of KV CacheChanryeol Lee, Chanhyuk Lee, Yeonwoo Choi +2cs.LG2026-09-30
#469How Many Samples Are Enough for Learning Across Domains?Hong Zhengcs.LG2026-09-30
#470Learning Beyond Full Imitation: Task-Preserving Knowledge DistillationQianfeng Yuan, Wenbing Taocs.LG2026-09-30
#471WinoTS: Wavelet-based Self-Distillation for Time Series ModelsNoam Major, Kathy Razmadze, Yoli Shavitcs.LG2026-09-30
#472ElectrolyteFM: Unifying Electrolyte Property Prediction through Cross-Property Knowledge LearningJiaxin Yu, Shuo Wang, Peng Wang +2cs.LG2026-09-30
#473Robustifying Asynchronous SGD via Soft ThrottlingKaoru Otsuka, Maxime Meyer, Yuki Takezawa +2cs.LG2026-09-30
#474LampAttention: Look-Ahead Mixed-Precision FlashAttention for Dedicated AcceleratorsStanislav Budzinskiy, Marian Gloser, Tolunay Yilmaz +5cs.LG2026-09-30
#475Wavelet Flow Matching for Time SeriesLucas Poinsignon, Jorge da Silva Gonçalves, Samuel Ruipérez-Campillo +1cs.LG2026-09-30
#476From Search to Signal: Online Post-Training in Automatic Heuristic DesignYilun Yuan, Tianyu Zhou, Zhenzhou Tangcs.LG2026-09-30
#477When, Not How Much: Evaluating Time-Series Foundation Models on Sparse EventsDaniel Schoess, Florian von Wangenheimcs.LG2026-09-30
#478Beyond Simulation: Retain-and-Repair Neural Operators for Real-World AdaptationWoojin Cho, Junghwan Parkcs.LG2026-09-30
#479Decoupled and Distilled: Task-Adaptive LoRA-Teachers with Ensemble Knowledge Transfer for Few-Shot Class-Incremental LearningHongwei Zhao, Rui Liu, Yansong Liu +2cs.LG2026-09-30
#480No Task Vector Is an Island: A Comprehensive Study on the Composability of Task Vectors from On-Policy DistillationJingang Zhou, Feiyu Han, Han Zhu +6cs.LG2026-09-30
#481Awakening of the Buddha: Subspace Learning During Population-Loss PlateausAkash Kumarcs.LG2026-09-30
#482From Imitation to Reward Discovery: On-Policy Warmup for Agentic RLYitong Qiao, Tiantian He, Lei Liu +4cs.LG2026-09-30
#483Network-based Spatial Context Retrieval for Open-weight LLMs: A Faithfulness Benchmark for Grounded Geographic ReasoningJoan Perezcs.LG2026-09-30
#484Raw-Routed Mixture of Adapters: A Causal Intervention for Routing Collapse in Time Series Foundation ModelsHung Phan, Thuy T. Nguyen, Minh Ngoc Dinh +1cs.LG2026-09-30
#485Mutual Equilibrium: Multimodal Representation Learning through Reciprocal FeedbackHo-min Park, Byungkon Kangcs.LG2026-09-30
#486Understanding Head Geometry and Dynamics in Federated Regression through a Natural Solution Selection Rule: An Unconstrained Feature Model AnalysisChuang Ma, Tomoyuki Obuchics.LG2026-09-30
#487T-ARC: Topology-Aware Randomized Clustering via Distributionally Robust Stochastic Block ModelsSerena Grazia De Benedictis, Andersen Ang, Nicoletta Del Buono +2cs.LG2026-09-30
#488Also Small Models Can Reasonably Self-Evaluate Their ConfidenceIdil Kapikiran, Thomas Decker, Thomas Runklercs.LG2026-09-30
#489Correcting CondOT: Exact Finite-Step Sampling in Gaussian Flow MatchingRon Levy, Michael Eladcs.LG2026-09-30
#490Towards Robust Time Series Learning via Capacity-Centric ModulationSiru Zhong, Senzhang Wang, James T. Kwok +1cs.LG2026-09-30
#491When the Right Answer Is Missing: An Arithmetic-Dependent Rejection Bottleneck in JevJike Zhong, Ming Li, Yuxiang Laics.LG2026-09-30
#492The Geometry of Randomized Smoothing on Feasible SetsSyed Izhan Khilji, Alireza Furutanpey, Schahram Dustdarcs.LG2026-09-30
#493Can Domain Generalization be Guaranteed in Small-Sample Learning?Hong Zhengcs.LG2026-09-30
#494CIDER-FM: Foundation Models for Causal Inference from Diverse Experimental RegimesYuche Gao, Arik Reuter, Siyuan Guo +3cs.LG2026-09-30
#495Learning Reliable GUI Agents under Imperfect PriorsBo Han, Qianyi Wang, Shuai Liu +9cs.LG2026-09-30
#496Hyperbolic Prototype Routing for Rehearsal-Free Class-Incremental LearningHongWei Zhao, Rui Liu, Yong Chencs.LG2026-09-30
#497Self-Repulsive Sampling for Diffusion Language ModelsMichael Helcig, Martin Jaggics.LG2026-09-30
#498Candidate Retention for Abductive LearningHao-Yuan He, Yu Liu, Ming Lics.LG2026-09-30
#499Robust Transfer Learning for Paper ECG RecognitionYinghao Xie, Zhenbang Dai, Haojun Wang +6cs.LG2026-09-30
#500Convergence of Practical Muon with Finite Newton-Schulz Iterations and Nesterov MomentumHanyng Peng, Hui Wang, Yue Yucs.LG2026-09-30
#501Hybrid Methods for Robust Tabular Data ImputationJinwei Li, Michelle Bruch, Daniel Tenbrinckcs.LG2026-09-30
#502Parameterization method of reservoir properties for ensemble-based data assimilation using intermediate latent space of StyleGANMarcio A. Sampaio, Paulo H. Ranazzi, Martin J. Bluntcs.LG2026-09-30
#503MIND: Marginal-Invariant Neural Dependency Diffusion for Mixed-Type Tabular GenerationPengfei Li, Mohammad Khalilcs.LG2026-09-30
#504Certification-Based Differentially Private LearningMihnea Ghitu, Matthew Wickercs.LG2026-09-30
#505PEG-Tab: Sampling-Time Record Repair and Release Control for Tabular SynthesisPengfei Li, QinYi Liu, Mohammad Khalilcs.LG2026-09-30
#506Towards Better Exploration in Sequential Test-Time ScalingJoseph Rance, Fabio Pizzati, Juil Sock +4cs.LG2026-09-30
#507Free Everywhere, Exact on Trees: PPO's Dropped Correction Buys Sample Efficiency Under Aggressive ReuseNima H. Sibonics.LG2026-09-30
#508RiboUnmix: Learning Shared Translational Dynamics from Biased and Noisy Ribo-seq MeasurementsGabriele Martino, Denis Skibinski, Ivo L. Hofacker +1cs.LG2026-09-30
#509Beyond Uniform Compression: Budgeted Transmission Allocation for Extreme Federated LearningPengfei Li, Mohammad Khalilcs.LG2026-09-30
#510From Modes to Memories: Characterizing the Scale-Space Dynamics of Diffusion ModelsCristina López Amado, Marco Fumero, Francesco Locatellocs.LG2026-09-30
#511Graph Residual Conjugate Diffusion: SNR-Equalized Heat Flow for Graph SignalsJinwei Li, Daniel Tenbrinckcs.LG2026-09-30
#512NodeGround: A Node Classification Benchmark in the Graph Foundation Model EraJinmo Lee, Dooho Lee, Minho Jeong +1cs.LG2026-09-30
#513GFD-OPD: Guidance-Folded On-Policy Distillation of Diffusion Models Across ScalesZhenxing Zhang, Jiayan Teng, Wenxu Wu +6cs.LG2026-09-30
#514A library for differentiable signal processing and machine learning on the sphereThorsten Kurth, Max Rietmann, Mauro Bisson +6cs.LG2026-09-30
#515CNCGEN: A Dataset and Framework for Machining Process Planning and Toolpath Generation from B-rep ModelsXiaolei Zhou, Boyi Lin, Yuchao Feng +1cs.LG2026-09-30
#516Stable Transformers for Graph GenerationLuca Miglior, Alessio Gravina, Davide Bacciucs.LG2026-09-30
#517The Nixtlaverse: An Open-Source Ecosystem for ForecastingOlivier Sprangers, Max Mergenthaler Canseco, Marco Peixeiro +8cs.LG2026-09-30
#518Validity-Preserving Hierarchical RL for Joint Routing and Switch Placement in EDADorian Gailhard, Ugo Lecerf, Enzo Tartaglione +2cs.LG2026-09-30
#519Revisiting On-policy Adversarial Black-Box Distillation: Calibrating Groupwise Reward Geometry for Effective Advantage ConstructionXiao Cui, Mo Zhu, Yulei Qin +3cs.LG2026-09-30
#520How Does Local Landscape Geometry Evolve in Language Model Pre-Training?Zhanpeng Zhou, Yuhan Sun, Bingrui Li +4cs.LG2026-09-30
#521Riemannian Flow Models with Reinforcement Learning for Molecular Crystal Structure PredictionThomas Egg, Harry Winston Sullivan, Maya M. Martirossyan +8cs.LG2026-09-30
#522GraphMAS: A Systematic Benchmark of Multi-Agent Coordination for Graph LearningJiayi Yang, Yifang Chen, Yuanfu Sun +2cs.LG2026-09-30
#523CORD: Learning Reusable Degradation Representations Across Heterogeneous Physical SystemsHaibo Li, Zhiguo Zengcs.LG2026-09-30
#524Pseudo-Label-Triggered Retraining from Forecast Errors for Online Time Series ForecastingYeryeong Kwak, Yoo-Min Jung, Jonghun Parkcs.LG2026-09-30
#525TopTimeNet: Topologically-assisted time-series classification modelSharareh Sayyad, Sophia Bazzics.LG2026-09-30
#526Probabilistic Adversarial TrainingAndi Zhang, Xingyu Zhao, Siddartha Khastgircs.LG2026-09-30
#527Finite-Horizon Fisher Memory in Two-Sided Power-Bounded Recurrent SystemsJeonghoon Leecs.LG2026-09-30
#528RATIO: Reasoning Analysis and Token-level Inference Optimization for Quantized Reasoning ModelsChengzhu Bao, Xianglong Yan, Tianao Zhang +3cs.LG2026-09-30
#529A Comprehensive Benchmark of Source-Free Universal Domain Adaptation on Time Series RepresentationsRomain Mussard, Fannia Pacheco, Maxime Berar +2cs.LG2026-09-30
#530Backward-State Policy Is Part of the Learning AlgorithmShuxiao Xie, Shuyang Xie, Dezhi Ran +2cs.LG2026-09-30
#531Beyond Accuracy: Prefix-Invariant Realizations of Low-Precision Fast Matrix MultiplicationShuxiao Xie, Shuyang Xie, Yuan Cao +3cs.LG2026-09-30
#532Should I stay or should I show? Learning to selectively disclose informationCarlotta Giacchetta, Alessando Bogani, Cesare Barbera +4cs.LG2026-09-30
#533RainAtlas: A Multi-Continental Dataset for Precipitation DownscalingPierre-Louis Lemaire, Luca Schmidt, Wietze Suijker +2cs.LG2026-09-30
#534Fast Regularized Policy Mirror Descent with One-Step TD UpdatesQipei Chen, Wenye Li, Yule Sun +1cs.LG2026-09-30
#535Dynamic LoRA-Experts and Prototype-Ensemble Matching for Class-Incremental LearningHongwei Zhao, Rui Liu, Yansong Liucs.LG2026-09-30
#536Predicting Multi-View Rashomon Representation: Can We Learn Where Models Disagree?Mingyue Ma, Zongbo Han, Changqing Zhang +1cs.LG2026-09-30
#537Dimension-Free Rank Lifting from Random Hyperplane ArrangementsLuca Becchetti, Matteo Russo, Ruben Skorupinskics.LG2026-09-30
#538Fork-dLLM: Avoiding the Flexibility Trap in Diffusion Language ModelsStipe Frković, Metod Jazbec, Christian A. Naessethcs.LG2026-09-30
#539Preemptive LLM Unlearning against Forbidden Capability Acquisition via Gradient SealingKemou Li, Qizhou Wang, Yue Wang +6cs.LG2026-09-30
#540Algorithmic Recourse Under CompetitionShahin Jabbarics.LG2026-09-30
#541Markovian Dynamics Enforcer: Feasibility Preserving Correction on Learned Dynamics ManifoldsKevin Yu, Tao Guo, Constantinos Antoniou +1cs.LG2026-09-30
#542Shared Weights, Selected Computations: How Looped Transformers Route What Each Loop DoesJiaju Wu, Yi Hu, Muhan Zhangcs.LG2026-09-30
#543Do Better Goal Representations Improve Goal-Conditioned Reinforcement Learning?Syed Nazmus Sakib, Abdul Monaf Chowdhury, Nafiul Haque +2cs.LG2026-09-30
#544Patient-Centered Treatment Planning for Chronic Multimorbidity: A Hierarchical Reinforcement Learning Framework for Preference ModelingNafiseh Payani, Soham Das, G. Anthony Wilson +1cs.LG2026-09-30
#545TRACE: Trajectory Selection for Parallel Scaling of Search AgentsQisheng Zhou, Zhen Xiong, Qiaoyu Tancs.LG2026-09-30
#546RoPE at the End of Its Rope? Theory, Diagnosis, and Mitigation of Long-Context FailuresYuyang Wu, Yufeng Du, Hao Pengcs.LG2026-09-30
#547Reliability-Aware Checkpoint Selection for Domain GeneralizationJinshi Liu, Jiahao Li, Pan Liu +5cs.LG2026-09-30
#548What Limits Recursive Reasoning Models: Optimization, Architecture and Test-Time ScalingYuliana Shakhvalieva, Dmitrii Kharchev, Viacheslav Bezrukov +4cs.LG2026-09-30
#549Learning to Explain While Planning: Rule-Aligned Diffusion Planning for Autonomous DrivingJiaxi Yecs.LG2026-09-30
#550DashVMC: Real-Time Discrete World Model Control in Geometry DashFlorent Tariolle, Florian Ygercs.LG2026-09-30
#551Fenchel Tilting: Weighted Correction for Efficient Finetuning of Generative ModelsMaksim Bobrin, Maksim Zhdanov, Dmitry Dylovcs.LG2026-09-30
#552Efficient Active Auditing of Multi-Group Fairness with Bias ProbesAyoub Ajarra, Debabrota Basucs.LG2026-09-30
#553Gromov-Wasserstein Distillation for Inductive Multi-View EmbeddingRafael Pereira Eufrazio, Eduardo Fernandes Montesuma, Charles Casimiro Cavalcantecs.LG2026-09-30
#554LARC: Low-Rank Adaptive Residual Connections for Learning in Frozen ModelsJunyi Zou, Avrova Donzcs.LG2026-09-30
#555Inference AuctionsKeegan Harris, Siddharth Prasad, Asher Trockman +2cs.LG2026-09-30
#556Accelerated Algorithm for Sparse Regularized Partial Optimal TransportKhoa Nguyen, Dung T. Nguyen, Thong Huynh +4cs.LG2026-09-30
#557Replay on Demand: An Emergent Curriculum for Balancing Adaptation and Forgetting in Continued PretrainingLukas Thede, Shengzhuang Chen, Stefan Winzeck +3cs.LG2026-09-30
#558Beyond Model Ranking: Regime Diagnosis for Distributional-Statistical Misspecification in Industrial Time-Series ForecastingPengyu Nie, Chenglang Xu, Yaoshi Chen +4cs.LG2026-09-30
#559Scalable Cox Regression via Grouped Risk Sets and Sharper LogSumExp RatesElizaveta Iashchinskaia, Egor Gladincs.LG2026-09-30
#560Learning Functional Subspaces for Neural Network CompressionMassimo Bini, Anders Christensen, Stephan Alaniz +5cs.LG2026-09-30
#561Prototype-Rule Neurosymbolic Regularization for Rank-Constrained Tensor Neural Networks under Label ScarcityEftychios Protopapadakis, Konstantinos Makantasis, Konstantinos M. Giannoutakiscs.LG2026-09-30
#562Game-Guided Skill Discovery through Self-Play for Playable Agent ControlSeungeun Rho, Jeonghwan Kim, Xue Bin Peng +1cs.LG2026-09-30
#563From DNA Design to DNA Slimming: Auditable Agentic Discovery of a Deletion-Only DesignerJoel Shorcs.LG2026-09-30
#564Policy Iteration Is Not Strongly Polynomial for Deterministic Markov Decision Processes: The Price of Algorithmic AnarchyHan Zhong, Yinyu Yecs.LG2026-09-30
#565From Spectra to Joint Schedules in LLM Pre-training: 3+3(+2) Scaling-Law RegimesYichen Wang, Fanghui Liu, Yudong Chencs.LG2026-09-30
#566Role-Adaptive Policy Optimization for Offline Reinforcement LearningSeonvin Cho, Soohyun Choi, Songnam Hongcs.LG2026-09-30
#567MANET-GNN: Learned Decentralized Optimization of Power Allocation in Multi-Channel MANETsTomer Alter, Nir Shlezinger, Michael Segalcs.LG2026-09-30
#568Cheap to Draw, Expensive to Trust: Certifying Test-Time Scaling CurvesSohail, Sarkar, Shakuntala Baichoocs.LG2026-09-30
#569Near-Linear Accuracy Bounds for Moreau--Yosida Unadjusted Langevin SamplingYuchen Xin, Zhihua Zhangcs.LG2026-09-30
#570PhantomEnvironments: Training LLM Agents in Fictional WorldsAnmol Kabra, Swathi Saravana Selvam, Albert Gong +5cs.LG2026-09-30
#571Distribution Matching Distillation for Continuous Diffusion Language ModelsPaul Le Van Kiem, Dario Shariatian, Umut Simsekli +1cs.LG2026-09-30
#572OpenTSLM TeeMoE: A Unified Time-Series Language Model for Forecasting, Contextual Prediction, and ReasoningTony Chen, Timo Stoffregen, Maxwell Xu +8cs.LG2026-09-30
#573cua-speedrun: Standardized Benchmarking of the Speed of Computer-Use AgentsPranjal Aggarwal, Lawrence Keunho Jang, Sean Welleck +3cs.LG2026-09-30
#574PMosFM: Preconditioned Manifold Matching for One-Step Physics-Constrained GenerationZhangyong Liang, Haibin Lingcs.LG2026-09-30
#575Disentangling Computation in Multi-Task Neural Networks with the Green's OperatorJames Hazeldencs.LG2026-09-30
#576Compression Footprints as Security Signals for Model-Poisoning Defense in Federated LearningSachi Shome, William Eierscs.LG2026-09-30
#577Scaling Laws for Looped Mixture of ExpertsYanbei Chen, Anirudh Goyal, Raghuraman Krishnamoorthics.LG2026-09-30
#578Is Weight Tying Still Beneficial for Decoder-Only LLMs in Private Settings Under DP-SGD?Razan El Mais, Ali Chehab, Ibrahim Issa +1cs.LG2026-09-30
#579Removing Timing Shortcuts Improves Non-Invasive Brain-to-TextDulhan Jayalath, Oiwi Parker Jonescs.LG2026-09-30
#580Semifactual Credit-Augmented Policy OptimizationJunshu Pan, Zhizhang Fu, Shulin Huang +5cs.LG2026-09-30
#581Ranking-Aware Prompt Optimization for Multimodal Clinical DiagnosisTian Xia, Minghao Liu, Yiqing Liang +2cs.LG2026-09-30
#582Security Properties of Neural Networks as Decision ProblemsAdrian Wurmcs.LO2026-09-30
#583PrecipJEPA: JEPA-Regularized Future-State Prediction with Motion-Source Rendering for Precipitation NowcastingYufeng Zhu, Dan Niu, Qiliang Wu +4cs.MM2026-09-30
#584Online Evolution Strategy for Flow-Matching VLA Policies via Self-Supervised Trajectory Distribution OptimizationGongxin Yao, Yongsheng Zhao, Jiayin Deng +4cs.RO2026-09-30
#585Efficient Multi-Modal Planning with Reward-Guided Preference Optimization for Autonomous DrivingChenglin Chen, Lujia Wang, Xinhu Zheng +2cs.RO2026-09-30
#586DrivingBench: Can Vision-Language Models Drive a Toyota Corolla?Aditya Ramabadran, Simon Mahns, Tobias Gesslercs.RO2026-09-30
#587SimEX: Simulation-Integrated Robotics AutoResearchJiaheng Hu, Roberto Martin-Martin, Peter Stone +3cs.RO2026-09-30
#588Sparse-WAM: Accelerating World Action Models via Action-Guided Sparse ImaginationXinling Xie, Haodong Wang, Jiazhi Mi +8cs.RO2026-09-30
#589Make Code as Policy Great Again: Frontier Agents Write, Call, and Evolve Robot ToolsShijia Ge, Alex Zhou, Jianshu Zeng +12cs.RO2026-09-30
#590DiFF: Doppler-informed Flow Matching for Human Motion FlowKai Wang, Mingle Zhaocs.RO2026-09-30
#591Blackout vs. Freeze: Analyzing Physical Failure Modes of VLAs under Camera FaultsHeejae Suh, Jongwook Han, Zahra Gholami +1cs.RO2026-09-30
#592Linear Recurrent Memory Suffices to Distil a World-Model Policy for Robot Air HockeyF. Olivia Fan, Oliver Obstcs.RO2026-09-30
#593Exploiting Vulnerabilities: Universal Adversarial Attacks on Vision-Language-Action Models in RoboticsSonghua Yang, Ziyu Liu, Yuanwei Liu +5cs.RO2026-09-30
#594The Planning Limits of Latent World ModelsAli Alrasheed, Basim Azam, Naveed Akhtarcs.RO2026-09-30
#595Scale and Selection: What Makes Automatic Harness Evolution Work for Visual-Interface Robot AgentsZhijie Wei, Ferris Tan, Jinghui Wangcs.RO2026-09-30
#596HiWE: Hierarchical World Knowledge Model with Visual Keypoint Enhancement for Zero-Shot 3D Path PlanningGuoqing Ma, Mingqi Yuan, Chen Gao +2cs.RO2026-09-30
#597MotionWeave: Learning Motion-Centered Future Dynamics for Vision-Language-Action PoliciesJingqiu Wang, Yan Wangcs.RO2026-09-30
#598Beyond the Current Scene: Event-Referential Grasping with Active View SelectionHyunjoon Lee, Haebeom Jung, Eunsung Cha +4cs.RO2026-09-30
#599UniWAM Technical Report: Unified Mobile Manipulation via Mixed-Stream World-Action Modeling and Manipulation Anchor Pose SupervisionWei Xue, Keliang Liu, Mingzhang Cui +14cs.RO2026-09-30
#600General Performance Guarantee for Human Torque Estimation-Based Task-Agnostic Assistive Exoskeleton ControlDuy Hoang, Bastien Berret, Olivier Bruneau +1cs.RO2026-09-30
#601ECHO-G: Embodied Co-speech Humanoid mOtion GenerationYizhao Li, Pusen Gao, Ming Wang +3cs.RO2026-09-30
#602Text-to-3D Policy: Fine-Grained Language-Behavior Alignment for Unseen Specification GeneralizationXinhao Yang, Wenhao Wu, Ning Lv +5cs.RO2026-09-30
#603RoboCoach: World Models as Active Coaches for Compositional Robot SkillsJiajun Liu, Yifan Chen, Yichao Liu +7cs.RO2026-09-30
#604DiffWAM: A Fast and Efficient Navigation World Action ModelMo Zhu, Yuze Wu, Xijie Huang +3cs.RO2026-09-30
#605Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action ModelsMingyue Cui, Zheyuan Liu, Yihan Zhu +2cs.RO2026-09-30
#606TACTIC: Temporal and Context-Aware LLM Tactical Planning for Roadside LiDAR AttacksYiming Gao, Shaocheng Luocs.RO2026-09-30
#607When Instructions Retrieve Trajectories: Diagnosing and Mitigating Generalization Failures in VLA ModelsHung-Jen Chen, Yu-Hsun Hou, Yan-Hong Chen +4cs.RO2026-09-30
#608Multi-Link Safety Filtering for VLA Policies Around Moving HazardsYatharth Agarwal, Vijay Raghunathancs.RO2026-09-30
#609BatSLAM 2.0: Sequence-Verified Sonar Place Recognition in a Robust Pose GraphJan Steckelcs.RO2026-09-30
#610Tactile Curiosity Drives Robot InteractionKlemens Iten, Alexander Proshkin, Bhavya Sukhija +4cs.RO2026-09-30
#611PrefPI: Preference-Guided Steering into Out-of-Distribution BehaviorsSeungeun Rho, Wontaek Kim, Danfei Xu +1cs.RO2026-09-30
#612STARS: From Spatiotemporal Dynamics to Social Representations in Human-Robot InteractionNathan Tsoi, Michael J. Munje, Tejas Oberoi +5cs.RO2026-09-30
#613DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot AgentsHaoyuan Deng, Jiebin Liu, Tengxiao Zhang +3cs.RO2026-09-30
#614Ego4WAM: What Matters When Scaling Egocentric Human Data for Robot Learning?Zhihao Sun, Liu Liu, Xinjiang Wang +6cs.RO2026-09-30
#615RAST: Resolution-Aware Privileged Structure Transfer for Low-Resolution Audio Activity RecognitionJi Hwan Park, Gautham Krishna Gudur, Yufei Shen +2cs.SD2026-09-30
#616Audio Token Attention Is Predictable Before the Language Model RunsKyoungjun Park, Yunzhe Li, Lili Qiucs.SD2026-09-30
#617FFASR: Benchmarking Far-Field Automatic Speech Recognition using High-Fidelity Simulated RIRsShivam Saini, Eric Bezzam, Georg Götz +5cs.SD2026-09-30
#618SCIC: Scope- and Codebook-Aware Instruction Conditioning for Speaker-Adapted Expressive TTSLongyu Lu, Zongwei Du, Mengtao Xing +4cs.SD2026-09-30
#619Training-Free Affinity Fusion of Neural and Embedding-Based Speaker DiarizationYehoshua Dissen, Joseph Keshet, Eduard Golshteincs.SD2026-09-30
#620UniAE-MoE: A Unified Audio Encoder via Mixture of ExpertsShengbo Cai, Zhisheng Zhang, Zichao Nie +3cs.SD2026-09-30
#621Who Said What, and Will It Be Remembered? Evaluating Persistent Speaker Attribution Across MeetingsShantanu Vispute, Aditya Mishra, Siddhartha Saxenacs.SD2026-09-30
#622From Speech to Editable Concepts: Probing Emotion Recognition with Concept Bottleneck ModelsHezhao Zhang, Thomas Haincs.SD2026-09-30
#623Ghost in the Encoder: Decodable Artist Identity Representations in Lyrics-to-Song GenerationArhan Vohra, Choenden Kyirong, Laura Ibáñez-Martínez +1cs.SD2026-09-30
#624SE-ADD: Self-Evolving Audio Deepfake Detection with Mistake-Driven SupervisionRong Wan, Wei Xie, Jiaxi Li +4cs.SD2026-09-30
#625SEAR: Spoofing Evidence-Grounded Audio Reasoning Benchmark for Audio Language ModelsRong Wan, Suliu Qin, Jiaxi Li +5cs.SD2026-09-30
#626MeanVoiceFlow2: Joint Optimization of Mean Flow and Content Encoder for Fast One-Step Zero-Shot Voice ConversionTakuhiro Kaneko, Hirokazu Kameoka, Kou Tanaka +1cs.SD2026-09-30
#627Adaptive-GEPA: Make Your Harness Fit Heterogeneous RequestsTianyu Chen, Yasi Zhang, Ruiyi Wang +3cs.SE2026-09-30
#628From Verification Failures to Reusable Guidance for Coding AgentsYuqing Zhai, Xiaohong Chen, Lingming Zhang +2cs.SE2026-09-30
#629Trustworthy Runtime Error Healing in Real-World Repositories: A Benchmark and GuardrailGou Tan, Pengfei Chen, Zhensu Sun +9cs.SE2026-09-30
#630EngramBench: A Capability-Grounded Benchmark for Skill-Evolution HarnessesZhixuan Tan, Pengjie Gu, Zhao Li +4cs.SE2026-09-30
#631Self-Spec Verifiable Code GenerationJiaru Qian, Yihong Dong, Yongmin Li +3cs.SE2026-09-30
#632DoGBench: Can Agents Meet Expert Standards for User-Facing Documentation?Frances Liu, Manny Silva, Paige Calvert +2cs.SE2026-09-30
#633Learning When and How to Intervene: A Hindsight-Distilled Sentinel for Coding AgentsJiangrui Zhao, Chenglong Li, Meng Zhang +1cs.SE2026-09-30
#634Community-Driven API and AI Writer Design for Openly Scaling Community NotesBrad Miller, Jay Baxter, Jiansong Chao +3cs.SI2026-09-30
#635VOSSA: Voiceprint Optimization for Streaming Speech ArchitecturesMu-Ruei Tseng, Waris Quamer, Ghady Nasrallah +1eess.AS2026-09-30
#636Tissue Detection Determines False Positives in Diffusion-Based Histopathology Artifact DetectionKonstantinos Moutselos, Ilias Maglogianniseess.IV2026-09-30
#637Grounding Time-Series Foundation Models in Digital Twin Topology for Predictive MaintenanceSizhe Ma, Katherine A. Flanigan, Mario Bergéseess.SP2026-09-30
#638MADGRAV: a multilevel anomaly-detection pipeline for gravitational-wave searches applied to LIGO dataGianluca Inguglia, Huw Haigh, Ulyana Dupletsa +1gr-qc2026-09-30
#639PINNing the pion: conformal deep learning for $F_π(s)$ and the $(g-2)_μ$ hadronic contributionMayank Goel, Subhadip Mitra, Monalisa Patrahep-ph2026-09-30
#640Cluster Attention Neural Operators for Solving Parametric Partial Differential EquationsMing Zhong, Antonio Colanera, Gianluigi Rozza +1math-ph2026-09-30
#641Generalized Geometry Block Proximal Linearized Method for Multiblock Nonconvex and Nonsmooth OptimizationWeifeng Yangmath.OC2026-09-30
#642WEIRDO: WEak resIdual Regularized DOob's h-transform diffusion alignmentDenis Suchkovmath.ST2026-09-30
#643Less is more: error-distance scaling relation for data-efficient kilometer-scale downscaling of extreme heatAhmed Marey, Henry Lu, Abhishek Gaur +6physics.ao-ph2026-09-30
#644A strategic roadmap for an atomistic machine-learning ecosystemJörg Behler, Michele Ceriotti, Cecilia Clementi +46physics.chem-ph2026-09-30
#645An Uncertainty-Guided Digital Twin Framework for Online Adaptive Proton Therapy in Head and Neck Cancer: A Feasibility StudyYizhou Wu, Ryan J. Sanford, Huiqiao Xie +12physics.med-ph2026-09-30
#646CellMSA: Context Modeling for Single-Cell Representation LearningSuyuan Zhao, Minghao Liu, Yizhen Luo +1q-bio.GN2026-09-30
#647Association profile conditioning in a set-temporal transformer for cross-session intracortical motor decodingXinyuan Zhang, Handong Mo, Pengfei Wen +5q-bio.NC2026-09-30
#648Belief-Based Maximum Occupancy Principle and Active InferenceManolis Mylonas, Rubén Moreno Boteq-bio.NC2026-09-30
#649Average-and Last-Iterate Lower Bounds for Optimistic Matrix Mirror-Prox in Quantum Zero-Sum GamesYiheng Su, Emmanouil-Vasileios Vlatakis-Gkaragkounis, Pucheng Xiongquant-ph2026-09-30
#650A Width-Matched Comparison of Hybrid Quantum-Classical Self-Supervised Learning for Fingerprint RecognitionMaria S. Edwards, Kidwell Dlamini, Pin-An Lin +2quant-ph2026-09-30
#651Learn-Then-Differentiate Gradient EstimationNifei Lin, Qingkai Zhang, L. Jeff Hongstat.CO2026-09-30
#652Always-On ExperimentationRicardo J. Sandoval, David Arbour, Avi Feller +1stat.ME2026-09-30
#653Sharp Statistical Rates for Asynchronous TD Learning with Markovian DataYang Pengstat.ML2026-09-30
#654Warm-starting PDE solvers with any-dimensional machine learningWilson G. Gregory, George A. Kevrekidis, Ben Blum-Smith +1stat.ML2026-09-30
#655Minimax rates for learning spectral Barron functions by deep ReLU neural networksSongqiu Ma, Yunfei Yangstat.ML2026-09-30
#656Steepest Guidance: A Practical and Principled Approach to Inference-Time Alignment of Flow and Diffusion-based ModelsShokichi Takakura, Akifumi Wachi, Rei Higuchi +2stat.ML2026-09-30
#657Asymptotic Properties of Support Vector Machines in High-Dimension, Low-Sample-Size Settings under a Spiked ModelYugo Nakayamastat.ML2026-09-30
#658Minimax Additive Regression under Unknown Dependent DesignsBaptiste Ferrere, Fabrice Gamboa, Jean-Michel Loubesstat.ML2026-09-30
#659Discrete Score Matching Enables Causal Discovery from Count DataEuijong Song, Hyewon Park, Gunwoong Parkstat.ML2026-09-30
#660A Dynamical Theory of LoRA in Continual LearningThéo Marchetta, Filippo Alessandroni, Alessandro Breccia +2stat.ML2026-09-30
#661Towards Optimal Inventory Control under Censored Demand: A Biased Sample-Average Approximation ApproachYuxuan Han, Xiaoyu Fan, Jiawei Zhang +1stat.ML2026-09-30
#662Principal Component Regression Dominates all Monotone Spectral Filters for Linear RegressionJuno Kim, Hengyu Fu, Peter Bartlett +2stat.ML2026-09-30
#663Distributionally robust linear regression through the lens of adversarial trainingElis Stefansson, David Vävinggren, Antônio H. Ribeirostat.ML2026-09-30
#664CAMOS: Coupled Oscillatory State-Space Model for Multimodal Clinical Time-SeriesMaxx Richard Rahman, Mostafa Hammouda, Wolfgang Maassstat.ML2026-09-30
#665Mitigating Representation Gaps in Amortized Bayesian Inference with Auxiliary SupervisionHans Olischläger, Svenja Jedhoff, Šimon Kucharský +3stat.ML2026-09-30
#666Estimation of the Label-Noise Transition Matrix with Performance Guarantees via Selective ClassificationXabier de Juan, Santiago Mazuelas, Yilun Zhu +1stat.ML2026-09-30
#667BayesNDE: Bayesian Generative Modeling for Neural Density EstimationChenglin Li, Qiao Liustat.ML2026-09-30
#668Amortized Bayesian Inference on Multilevel Models of Arbitrary StructureDaniel Habermann, Andreas Bulling, Stefan T. Radev +1stat.ML2026-09-30
#669Proximal Balancing for Causal Effect Estimation under Unmeasured ConfoundingYonghan Jungstat.ML2026-09-30

latest · trends · arXiv announcement batches follow US Eastern weekdays