PaperScope
LIVE · 2026-10-30 05:40 UTC

New Papers · 2026-10-15 513 submissions

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

#TitleAuthorsCatDate
1Missed Detections and False Alarms in a CNN Technosignature Detector on Breakthrough Listen DataOmer Imranastro-ph.IM2026-10-15
2Attention over noisy examples: generalization and memorization in the exponential Hopfield networkFrancesco Alemannocond-mat.dis-nn2026-10-15
3Recursive Reward Improvement via Adversarial Meta-Prompt EvolutionWei Dai, Qianchu Liu, Guanghui Qin +4cs.AI2026-10-15
#4Learning When to Withdraw: Curriculum Coverage and Rule-Specific Failures in Fine-Tuned Language AgentsMohamed Abouzahracs.AI2026-10-15
#5Athanor: An Agent-Native System for Autonomous Post-Training ResearchYufa Zhou, Yichen Wang, Jiakun Fan +5cs.AI2026-10-15
#6OmicsBench: a long-horizon multi-turn benchmark of AI agents on research-study-scale bioinformaticsGideon Shaked, Siddharth Nagisettycs.AI2026-10-15
#7Sci$Π$vot: Benchmarking Principal-Investigator Judgment at Pivotal Moments of Scientific AutoResearch AgentsYouran Sun, Xingyu Ren, Chugang Yi +15cs.AI2026-10-15
#8Probe-and-Resume: When and How to Evaluate Agent ExecutionJiakai Xu, Tiancheng Ge, Tujie Guan +4cs.AI2026-10-15
#9MemComposer: Learning to Assemble Memories for LLM Agents via Reinforcement LearningYixuan Xie, Xueqiang Xu, Xinyi Fan +8cs.AI2026-10-15
#10Planning Commitment of LLM under Partial ObservabilityCassie Huang, Zhanwei Cao, Yeawon Lee +6cs.AI2026-10-15
#11Kolab: Benchmarking Human-Agent Collaboration in Long-Horizon WorkflowsShirley Anugrah Hayati, Patricia Anugrah Setiani, Ruizi Wang +4cs.AI2026-10-15
#12CleanRM: Reward Modeling from Noisy Feedback with a Few Clean Feedback for RLHFLicheng Pan, Haocheng Yang, Yuzhou Chen +7cs.AI2026-10-15
#13All-in-One Memory: Process-Rewarded Reinforcement Learning for Memory AgentsBingbing Wang, Jingjie Lin, Weiming Qiao +2cs.AI2026-10-15
#14GRADS: Graph-Regulated Agentic Data Synthesis with Controllable DifficultyGaocheng Yang, Ruijie Tao, Kai Ye +3cs.AI2026-10-15
#15MemScope: Evolving Agent Memory Architectures through Localized Code RepairMiao Su, Yucan Guo, Zixuan Li +4cs.AI2026-10-15
#16AgentEval: Evidence-Bounded Assessment of Stateful AgentsRuiqi Gaocs.AI2026-10-15
#17Does Latent Chain-of-Thought Actually Reason? A Single, Unifying Taxonomy for Latent ReasoningJingjie Qiu, Sheldon Yu, Xunyi Jiang +6cs.AI2026-10-15
#18Mine, Sample, Render: Test-Time Diversity Alignment Of Generative ModelsKostas Triaridis, Morris E. Sharp, Nebojsa Jojiccs.AI2026-10-15
#19Condition-Contrastive Extrapolation for On-Policy Distillation of Language ModelsWenxuan Luo, Chenxi Li, Haoyue Liu +2cs.AI2026-10-15
#20Who May Release an Agent's Promise? Standing over Commitments in Multi-Party ChatLan Wei, Bingyu Shen, Jiaqi Tang +6cs.AI2026-10-15
#21Entertain, then Cancel: How Thinking Makes Reasoning Models Read Some and Or LiterallyZhizhuo Kou, Jian Yang, Pengfei Hao +4cs.AI2026-10-15
#22Rubric Judgments Lack Uncertainty: Conformal Weighting for LLM EvaluationLicheng Pan, Haocheng Yang, Haoxuan Li +7cs.AI2026-10-15
#23AutoOnboarder: Autonomously Onboarding LLM AgentsTanay Arora, Cong Liucs.AI2026-10-15
#24Auditing Escalation Reliability in Healthcare LLM Agents: A Perturbation-Controlled Benchmark of Workflow-State FailuresZihao Zheng, Junyi Yao, Baichuan Li +1cs.AI2026-10-15
#25Diviner: Agentic RCA with Human-Governed Adaptation for Large-Scale InfrastructurePradipta Ghosh, Gaurav Mitra, Shripad Nadgowda +7cs.AI2026-10-15
#26Mallea: Building, Steering, and Memorizing Worlds with Coding AgentXuanyi Liu, Ruiqi Li, Siwei Macs.AI2026-10-15
#27The Density of Thought: Predicting and Steering Reasoning in Large Language ModelsTanush Kalhan, Anupam Chattopadhyay, Sriram Ranga +1cs.AI2026-10-15
#28Bias Control and Injection for Multi-Agent AggregationSungjae Lee, Soheil Abbasloo, Jabin Koo +1cs.AI2026-10-15
#29Money-Mule Detection as a Relational Learning Problem: A Study on the RBIH NFPC DatasetOwais Ahmad, Anirudh Deodharcs.AI2026-10-15
#30Constrained Multi-Agent Reinforcement Learning in ImaginationRaz Shmueli, Shahaf S. Shperbergcs.AI2026-10-15
#31DocPilot: Interactive Agent Orchestration and Training for Long Visual Document UnderstandingZhuowen Liang, Xiaotian Lin, Yuyu Luo +2cs.AI2026-10-15
#32Quantum Versus Classical Machine Learning for Neuropsychiatric Disorders: A Feature-Matched Multi-Cohort EvaluationUtsav Poudel, Anuj Nepal, Vyas Viswanath +1cs.AI2026-10-15
#33ARGUS: An Agenda-Driven Framework for Reliable User SimulationHang Zheng, Nan Jiang, Zichen Zhu +6cs.AI2026-10-15
#34FedSkillGit: Federated Skill Evolution via Version ControlBoxun Lan, Jiamei Li, Weijian Li +5cs.AI2026-10-15
#35Hierarchical Graph Convolutional Network Approach for Detecting Low-Quality DocumentsJaeyoung Lee, Joonwon Jang, Misuk Kimcs.AI2026-10-15
#36Learning to Reason with Selective Internal FeedbackXun Lu, Shumeng Yang, Xinrui Wang +3cs.AI2026-10-15
#37Self-Guided LLM Reasoning for Error Diagnosis in Vehicle Routing ProblemsNi Zhang, Jianan Zhou, Yue-Jiao Gong +1cs.AI2026-10-15
#38Watts If? A Benchmark for Counterfactual Reasoning About the AI Data Center BuildoutPankaj Chouhan, Rajarshi Das, Aditya Dubey +5cs.AI2026-10-15
#39MemCut: Every Secret Leaves a Trail in the Long-Term Memory of LLM AgentsCheng Zhang, Xuanning Cao, Zhicheng Zheng +1cs.AI2026-10-15
#40Jev-LiteMAS: Separating Decisions from Generation in Multi-Agent WorkflowsKaixiang Wang, Zhaijiacheng Zhou, Jiong Lou +1cs.AI2026-10-15
#41JevAgentHarness: Benchmarking, Deploying and Training Decision Models That Share Control with LLMsKunlun Zhu, Tao Feng, Xu Han +5cs.AI2026-10-15
#42Do Agents Need a New Kind of Paper? SPRA: Structured Paper Representation for AgentsYutong Leng, Haojiong Chen, Fukai Shang +4cs.AI2026-10-15
#43Learning from Interaction Experience via Localized Context DistillationZhezheng Hao, Yongkang Yang, Xilin Xia +9cs.AI2026-10-15
#44Incentivizing Tool-Use Reinforcement Learning for Post-Arrival Emergency Care PredictionPengfei Hu, Chenwei Wu, Qiao Jin +4cs.AI2026-10-15
#45Ontology Refinement with Embeddings and LLMs: A Case Study on CASTONHui Yang, Ziyu Li, Xuan Liu +3cs.AI2026-10-15
#46Tool-Augmented Large Language Models for Reliable Medical Calculation from Patient NotesYang Zhong, Ling Luo, Xuanlyu Zhu +4cs.AI2026-10-15
#47AI-Driven Disaster Response and Displacement MonitoringNoora Al-Emadi, Muhammad Imran, Yin Yang +5cs.AI2026-10-15
#48FlashAttention with Statistics: Low-Overhead Attention Features for Compact Hallucination DetectorsAndrei Volodichev, Maksim Savichev, Nikita Sviridov +3cs.AI2026-10-15
#49MetaExp: Learning to Self-Improve through Experience via Verifiable Cross-Task Environment ScalingRenhao Li, Xinjie Shen, Yang Su +4cs.AI2026-10-15
#50ISW-Agent: Integrating LLM-Driven Dialogue with n8n Workflow for Internal Solitary Wave Remote Sensing Image ProcessingHao Zhang, Hengrui Liu, Lina Sun +1cs.AI2026-10-15
#51Decomposing Brain-LLM Alignment with Interpretable Semantic RepresentationsCamila Kolling, Mariya Tonevacs.AI2026-10-15
#52QREF: Improving DeepSearch Agents by Aligning Search with Reasoning via Query Refinement and Evidence FilteringYujia Chen, Yuhui Wang, Junzhe Wang +15cs.AI2026-10-15
#53SCRIBE: Scalable Contextual Representations of Interpretable Brain-Grounded SemanticsCamila Kolling, Omer Moussa, Emin Çelik +1cs.AI2026-10-15
#54CriticaLLM: Using LLMs as Autonomous Game Master for Tabletop Role-Playing GamesGaëtan Berlaimont, Justin Vanwichelen, Benoît Ronval +1cs.AI2026-10-15
#55Functional Subnetwork Localization for Efficient Continual Learning in Large Language ModelsShuoran Jiang, Wentao Zhu, Yang Xiang +8cs.AI2026-10-15
#56Agent Status Protocol (ASP): A Lightweight Specification for State Reporting in Multi-Agent SystemsDiego Gosmar, Deborah A. Dahl, Emmett Coin +2cs.AI2026-10-15
#57Reinforcement Learning-driven Diffusion Models: Language, Vision, and BeyondZhiyuan Ma, Jiabao Wei, Tianyu Wang +21cs.AI2026-10-15
#58ClaimScope: Label-Blind Witness Verification for Mathematical Claim AuditingMushir Akhtarcs.AI2026-10-15
#59LOADBench: A Large Open Analog Dataset and Benchmark for Machine Learning in IC DesignM. Leibl, F. Azevedo, S. Uhlich +7cs.AI2026-10-15
#60LoopAhead: Speculating Ahead for Faster Decoding in Looped Language ModelsZixuan Liu, Nan Xue, Rui Bao +4cs.AI2026-10-15
#61Evaluating Inquiry Learning in LLM-Based Agents: Hypothesizing, Reasoning, and ExplorationMarta Knežević, Seyed Parsa Neshaei, Jibril Frej +2cs.AI2026-10-15
#62Learning Intrinsic Dynamics in Latent World ModelsJiamin Shi, Yuanhong Zhang, Zhiyang Liu +2cs.AI2026-10-15
#63AgentPerturb: Evaluating LLM Agent Robustness under Controlled Interaction PerturbationsYuanjian Xu, Jinyi Han, Jianing Hao +5cs.AI2026-10-15
#64The Self-Improvement ProblemBrian B. Moser, Stanislav Frolov, Tobias C. Nauen +2cs.AI2026-10-15
#65Data World: Scaling Data Environments from ScratchZhanli Li, Zeyuan Xu, Chaoxu Pang +16cs.AI2026-10-15
#66In-Context Preference-Conditioned Pareto Set Learning from Limited Offline DataYiming Yao, Liang Zhao, Qingfu Zhangcs.AI2026-10-15
#67DeciCAD: Harness-Grounded Learning of Action Policies for CAD AgentsYufeng Peng, Yixin Zhang, Ziyi Liu +5cs.AI2026-10-15
#68From Research Goals to Scientific Closure: Evaluating Agents Through Evidence-Supported Physics ResearchYijia Mao, Song Dai, Tao Chen +14cs.AI2026-10-15
#69RSIFlow: Adaptive Self-Improvement Workflows with an Evolving Meta-AgentHuan Zhang, Mingju Chen, Dongxu Zhou +4cs.AI2026-10-15
#70Co2In: a Bi-level Memory Incremental Learning Framework with Knowledge Encoding, Consolidation, and IntegrationWenju Sun, Qingyong Li, Boyang Li +4cs.AI2026-10-15
#71CIM-Embed: Learning Instruction-Conditioned Multimodal Embeddings for ClusteringYinghua Xu, Pengyang Xie, Yanxiang Zhou +4cs.AI2026-10-15
#72RoleQ: Role-Aligned Scales for Converting Language Models to TernaryJohannes Knittel, Alec Helbling, Hanspeter Pfistercs.AI2026-10-15
#73CoWorld Reasoner: Agentic Multimodal Reasoning with the Evolving Video World Model-Driven HarnessDongjie Cheng, Ruifeng Yuan, Ran Wei +3cs.AI2026-10-15
#74OntoAct: Hypothesis-Based Neuro-Symbolic Agents through Ontological AbstractionDonghyeok Lee, Bong Gyun Kang, Junyong Ahn +1cs.AI2026-10-15
#75CARA: Causally Guided Retrieval Agent for Question AnsweringWeicheng Liu, Xiangcheng Wu, Depeng Xu +2cs.AI2026-10-15
#76GraphACM: Graph-based Action Consistency Measurement for Uncertainty Quantification in LLM AgentsYaxin Ma, Wenbo Zhang, Satya Krishna Pothapragada +1cs.AI2026-10-15
#77Progress Reward Model for Reinforcement Learning via Large Language ModelsXiuhui Zhang, Ning Gao, Xingyu Jiang +4cs.AI2026-10-15
#78FAOPs: Normal Forms and an Algebra for AI Agent WorkflowsAli Mohammadi Shanghooshabadcs.AI2026-10-15
#79Prism-1: Position- and Rival-Independent Scoring for System One ModelsYao Long Teng, Jianguo Huang, Yanchen Deng +2cs.AI2026-10-15
#80When Reasoning Is Not Enough: Proactive Inquiry for Cross-Modal Safety in Multimodal Large Language ModelsWei Cai, Jian Zhao, Yuchen Yuan +1cs.AI2026-10-15
#81Learning from Unverified Peers via Shared Residual DistillationFeiyang Chen, Runze Ma, Zichen Wang +4cs.AI2026-10-15
#82PROBE: Learning to Audit Policy Compliance in Tool-Using LLM AgentsKshitij Mishra, Abhijith Sharma, Nils Lukas +1cs.AI2026-10-15
#83DropKV: Decoupling Residual-Output Perturbation for Near-Optimal KV-Cache EvictionAozhong Zhang, Selcuk Gurses, Yanxia Deng +8cs.AI2026-10-15
#84CART: Compatible Routing for Multimodal Continual Instruction TuningLing-Xiang Zhang, Tao Hu, Da-Wei Zhoucs.AI2026-10-15
#85Believed but Not Said: Measuring Hidden Belief Collapse in Multi-Agent LLM DiscussionsLiangjie Huang, Henry Peng Zou, Wei-Chieh Huang +3cs.AI2026-10-15
#86Are You Sure Your LLM Is Sure? Repairing and Auditing ConfidenceArijit Dey, Bhartendu Kumar, Ramya Hebbalaguppe +1cs.AI2026-10-15
#87RAG-RST: Retrieved Exemplars as In-Context Discourse Schema for RST ParsingMohammadreza Sediqin, Shlomo Engelson Argamoncs.AI2026-10-15
#88Realtime-Bench: Can Frontier Models Solve Real-time Interactive Problems?Jingyu Tang, Xu Yang, Zhehao Zhang +7cs.AI2026-10-15
#89Multi-sourced AI Tutor for Non-Native English Speaker StudentsYiyin Shen, Xinyi Ai, Weibing Wang +2cs.AI2026-10-15
#90Terminal-RSI: Recursive Self-Improving Terminal Agents via Recursive Self-Rewrite and Policy-RefineJunyao Yang, Zongxia Li, Yucheng Shi +6cs.AI2026-10-15
#91AutoSFT: An Agentic System for Automated Data Research in Supervised Fine-TuningBingxiang He, Pengqi Sun, Shihao Peng +18cs.AI2026-10-15
#92HTN-Orchestrate: A Hierarchical Task Network Framework for Multi-Agent OrchestrationYanchen Deng, Jianguo Huang, Yao Long Teng +6cs.AI2026-10-15
#93GNN-Guided Local Refinement for Efficient Layout Decomposition with DSA-MPYu Feng, Liyi Zhou, Haoyu Wang +5cs.AI2026-10-15
#94Shortcut Sensitivity in Agent-Safety EvaluationsHasan Demirkiran, Jens Ernstbergercs.AI2026-10-15
#95Disagreement-Guided Weak-to-Strong RoutingSima Noorani, Shayan Kiyani, George Pappas +1cs.AI2026-10-15
#96X-RIC: An Agentic RAN-Intelligent Controller Benchmark for Enhancing Reinforcement LearningAdhwaa Al-Chaab, Ayman Younis, Dario Pompilics.AI2026-10-15
#97LEASH: Uncertainty-Aware Weak-to-Strong Escalation and Oversight for Computer-Use AgentsQingni Wang, Changdae Oh, Yuzhe Yang +4cs.AI2026-10-15
#98Improving Environment-Agnostic Coding Agents: The Role of ScaffoldingSergey Rodionovcs.AI2026-10-15
#99EliteReplay: Preserving Diverse Solutions in RL Post-Training via Quality-Diversity SearchHanane Nour Moussa, Doeun Lee, Sachin Kumarcs.AI2026-10-15
#100Private Retrieval Augmented Generation via Random ProjectionDixi Yao, Tahseen Rabbani, Tian Lics.AI2026-10-15
#101A team of Gemini 4 Argon agents beats MinecraftMaxence Faldor, Satinder Singh, Roberta Raileanucs.AI2026-10-15
#102Designing Transformers for Continuous Diffusion Language ModelsWeijian Luo, Yujian Chen, Hao Jiang +2cs.AI2026-10-15
#103KnowGPO: Knowledge-Grouped Policy Optimization for Search AgentsSiqi Chen, Zhengxi Lu, Yuchen Yan +10cs.AI2026-10-15
#104Evaluation Awareness Beyond English: Do LLMs Act Differently When Tested in Indic Languages?Trizal Garg, Sibayan Mitra, Arya Karanjkar +6cs.AI2026-10-15
#105MLExpert: Towards a Generalist Agentic Model for Autonomous Machine Learning EngineeringShangheng Du, Jinxin Shi, Shuaiyu Zhang +7cs.AI2026-10-15
#106FDE-Gym: The Last Mile of AI DeliveryDongxu Yang, Hongda Yan, Renxin Wang +23cs.AI2026-10-15
#107Independent Data-Integrity Verification for LLM-Driven Functional Coverage Closure in Hardware DesignVenkata Krishna Kumar Vedantamcs.AR2026-10-15
#108Compiling Multi-Threshold Operators for Quantized Non-Monotonic and Fine-Granular Activations in Custom-Tailored DNN AcceleratorsChristoph Berganski, Felix Jentzsch, Marco Platznercs.AR2026-10-15
#109ReviewPilot: A Multi-Agent System for Screening and Data Extraction in Systematic ReviewsZhaoqian Xue, Shaoze Zhou, Xuexin Li +10cs.CL2026-10-15
#110PremiseCheck: Efficient Fact-Checking of Human and AI Peer ReviewsDingjie Song, Zhiling Yan, Ziqian Zhang +2cs.CL2026-10-15
#111SHIP: Structured and Hierarchical Insight with PrivacyKai Chen, Guisi Ni, Albert Cheu +4cs.CL2026-10-15
#112Multimodal AI Detection for Math-Heavy Scientific TextYixuan Huang, Danish Pruthi, Bhuwan Dhingracs.CL2026-10-15
#113A Jury, Not an Electorate: Label-Free Reliability Estimation for Ensembles of Language ModelsAlessandro Rozza, Davide Mambelli, Steven Motta +1cs.CL2026-10-15
#114ToolBottleneckBench: Measuring Tool-Agent Performance under Controlled Pressures and Fixed Harness BudgetsZichuan Xu, Yuyang Dong, Makoto Onizuka +1cs.CL2026-10-15
#115Compression Does Not End at Selection: Post-Selection Positional Geometry for Sparse KV CachesWanyang Hong, Zhaoning Zhangcs.CL2026-10-15
#116When Judges Agree and Are Wrong: Consistency-Accuracy Dissociation as a Blind Spot for Label-Free EvaluationXiang Zhang, Lovedeep Gondara, Jekaterina Novikovacs.CL2026-10-15
#117CoSTA: Compressed Speech Token Adaptation for Efficient Spoken Dialogue ModelsYingzhuo Deng, Chong Li, Bingxin Liu +6cs.CL2026-10-15
#118From Observation to Intervention: Distilling Self-Generated In-Context Demonstrations via Executable Causal InterventionMinming Ye, Min Liu, Haoang Chi +2cs.CL2026-10-15
#119Stop Training Against Soft Users: Mentalized Adversarial Self-Play for Proactive DialogueZanwu Liu, Dan Zhang, Xiaodi Wang +6cs.CL2026-10-15
#120Automatic Sentence Completion Using Bengali Audio Speech with a Transformer-Based Early Speech Recognition SystemMd Asif Akram, Arif Faisal, Sakir Hossain Faruque +1cs.CL2026-10-15
#121From Long Context to Selective Memory:A Survey of Memory-Centric Compression for Large Language ModelsChaogui Goucs.CL2026-10-15
#122Beyond Retrieval Failure: Understanding Why LLMs Miss Evidence in Multi-Hop RAGJiaqi Wei, Wenxuan Huang, Chengdong Xu +2cs.CL2026-10-15
#123KBS: A Korean Benchmark Suite for Foundation Model EvaluationYeonkyoung So, Jongmin Kim, Sungmok Jung +13cs.CL2026-10-15
#124What Should We Remove? Evaluating the Reliability and Costs of RLVR Data DecontaminationEsther Xincs.CL2026-10-15
#125System1-Arena: Which Decisions Can Be Left to System 1?Tianyu Chen, Xinyang Liu, Ruyi An +2cs.CL2026-10-15
#126FGSS-BO: Feedback-Guided Hypothesis Management for LLM-Based Bayesian OptimizationHao Chen, Ziyang Ling, Ronald X. Xu +1cs.CL2026-10-15
#127LLM-Based Weak Annotation for Cybersecurity Tweet Classification: A Teacher-Student FrameworkFerry Afit Kurniawan, Kazushi Okamoto, Koki Karube +2cs.CL2026-10-15
#128TRACER: Trajectory-Aware Tool Retrieval for LLM AgentsTanish Kher, Sarvesh DK, Abedelkadir Asi +2cs.CL2026-10-15
#129Making every stage of medical device document assessment with large language models deterministicRyosuke Suzukics.CL2026-10-15
#130VALCON: Benchmarking and Enhancing Value Consistency in Large Language Models via Dual-Role VariationJunru Wu, Jingting Zheng, Yuqi Ren +1cs.CL2026-10-15
#131Hybrid Generative-Tagging Decoding for Efficient Product Attribute-Value ExtractionKeshav Kolluru, Manas Gupta, Maroof Ahmad +1cs.CL2026-10-15
#132QuasiLeak-Bench: Evaluating LLM-Based Privacy Detectors on Policy-Conditioned Quasi-Evidence Group RecoveryYufan Zhu, Yangfan Jiang, Yang Fei +3cs.CL2026-10-15
#133OpCredit: Operation-Aware Policy Learning for Agentic Knowledge Graph Question AnsweringYucheng Li, Mingyuan Li, Xiaxia Wang +1cs.CL2026-10-15
#134Emotion Is Not External Knowledge: Internal Attention Signals for Affective State ReasoningWenqiu Tang, Zhen Wan, Yihui Wang +2cs.CL2026-10-15
#135RenoLayout: Unified Floorplan Renovation and Furniture Layout for Constraint-Aware Residential DesignJingguo Liu, Yuanqing Liu, Chong Zhang +1cs.CL2026-10-15
#136ESG-Kor: A Korean Dataset for ESG-related Information Extraction and Practical Use CasesJaeyoung Lee, Geonyeong Son, Misuk Kimcs.CL2026-10-15
#137DPA-MoE: A Runtime Precision Control Framework for MoE InferenceJaeyun Kim, Hoonki Lee, Susie Shin +3cs.CL2026-10-15
#138Calibration Language Shapes Block-Influence Pruning in Multilingual Language ModelsVedant Pandhare, Piyush Dhokacs.CL2026-10-15
#139Beyond Invariance: Factor-wise Selective Treatment of Shifts for Multimodal LearningGuimin Hu, Qiwei Pengcs.CL2026-10-15
#140Identifying Effective Strategies in Prompt Evolution for Stress and Emotion PredictionSeungHyun Yi, Seungjun Yi, Sriram Sattiraju +12cs.CL2026-10-15
#141HyCo: Hybrid Drafting for Cost-Efficient Mobile-Cloud Speculative DecodingHanbin Bae, Heejin Choi, Joohyung Lee +3cs.CL2026-10-15
#142SITAR: A Situational Distortion Metric for Automatic Speech Recognition EvaluationMingzhe Lu, Jinhao Liu, Yunpeng Li +3cs.CL2026-10-15
#143Translation Circuit Discovery and Targeted Optimization for Low-Resource Multilingual TranslationAtai Waris Khan, Abdullah Mazhar, Raghu Kumar +1cs.CL2026-10-15
#144Trajectory-Level Speculation with Semantic Verification for Tool-Using AgentsZilin Wang, Yinhong Liu, Chao Chen +2cs.CL2026-10-15
#145Can LLMs Tell Stories Out of Order? A Corpus and Benchmark for Nonlinear Narrative GenerationSyed Rifat Raiyan, Md. Tariquzzaman, Md Farhan Ishmam +1cs.CL2026-10-15
#146OPRD: On-Policy Reminder Distillation for Long-Horizon Coding AgentsYuechen Luo, Zhiyi Lai, Miao Ziqi +9cs.CL2026-10-15
#147Writability and the Pathway: A Controlled Study of Knowledge Injection into Addressed MemoryWei Gao, Cheng Tian, Duan Yang +1cs.CL2026-10-15
#148DialFork: Going Beyond Factuality to Evaluate Procedural Hallucination in Conversational AgentsSergio Burdisso, Esaú Villatoro-Tello, Dairazalia Sánchez-Cortés +4cs.CL2026-10-15
#149Rethinking the Role of Tool Graph Memory in Multi-Turn Tool UseUiji Hwang, Richeng Xuan, Taeuk Kimcs.CL2026-10-15
#150ContextLift: Breaking the Spurious Correlation Behind Conditional Emergent MisalignmentFlorian Mai, David Kaczércs.CL2026-10-15
#151Enhancing Multimodal RLVR with Pairwise Token Contrast and Adaptive Trajectory ConfidenceYiran Zhang, Hanbo Huang, Jielan Li +3cs.CL2026-10-15
#152No Single Tokenizer Feature Reliably Predicts Downstream Language Model PerformanceAntonio Lopardo, Luis Frentzen Salim, Shikhar Srivastava +3cs.CL2026-10-15
#153Data Strategies for Large Language Models: A Unified Perspective on the Training LifecycleYuanjian Xu, Jianing Hao, Tianze Sun +7cs.CL2026-10-15
#154Abstracts or full text? Evaluating input scope and computational efficiency in biomedical lay summarizationEgecan Çelik Evgin, İlknur Karadeniz, Olcay Taner Yıldızcs.CL2026-10-15
#155Retrieved but Not Read: Understanding Why Search-Augmented LLMs Fail to Use Available EvidenceOwen Walters, Lihu Chen, Francesca Tonics.CL2026-10-15
#156SceneWeave: Audience-Guided Scene Exploration for Dramatic AdaptationAolin Li, Xiao Xu, Haihua Xiecs.CL2026-10-15
#157Reliable Knowledge Acquisition for Continual Learning AgentsYixu Huang, Jiaqi W. Macs.CL2026-10-15
#158Bias Mitigation in Audio-Enabled LLMs through Adversarial Training and Distillation MethodsAdnan Al Ali, Jindřich Libovický, Anne Lauschercs.CL2026-10-15
#159In the Guise of Correction: How Framing and Cultural Adaptation Erode LLM Safety on Real-World Criminal CasesMohsinul Kabir, Md. Tariquzzaman, Karam S. R. Elradie +4cs.CL2026-10-15
#160Behavioral Forgetting Is Not Privacy in Machine UnlearningTyler Lizzo, Larry Heckcs.CL2026-10-15
#161Content associations with answer selection and engagement in supply chain community question answeringHisatoshi Naganawacs.CL2026-10-15
#162Dynamic ordering in sequence generation in Transformers: experiments on low-resource Tagging scenariosGiacomo Bais, Tejaswini Deoskarcs.CL2026-10-15
#163TEM: Temporal State Tracking Memory for Large Language Model AgentsPengfeng Song, Yunkai Zhuang, Liye Shics.CL2026-10-15
#164Learning Speech Attribute Representations via Multi-Teacher DistillationMaryem Bouziane, Salima Mdhaffar, Yannick Estèvecs.CL2026-10-15
#165Priming Base Models for Agentic Post-Training: An Open Midtraining RecipeSoumye Singhal, Joseph Jennings, Ka Shun Shum +11cs.CL2026-10-15
#166Name-Bias in Large Language ModelsKalyan Bhetwal, Ceren Mert, Ian Whitehousecs.CL2026-10-15
#167Beyond Context Length: Characterising the Difficulty of Long-Context ReasoningShiwen Qin, Cameron Barker, Henry Gouk +4cs.CL2026-10-15
#168The Right Byte First: How UTF-16 Helps Multilingual Boundary PredictionHyunsik Kimcs.CL2026-10-15
#169Multi-SFT: Permissively-Licensed Multilingual Instruction-FollowingDaniela Baiamonte, Kamyar Zeinalipour, Elena Fano +2cs.CL2026-10-15
#170Patch where the text is new: a compression view of where byte-level models should spend computeNicolás Vera Zúñigacs.CL2026-10-15
#171Unfragmenting Nawatl NMT: Single-Variant Specialization for MasewalkopaLuis A. Mercado-Campos, Alexis Palmercs.CL2026-10-15
#172Explaining the Roles of Experts in Mixture-of-Experts LLMs for PersonalizationSekh Mainul Islam, Pepa Atanasova, Isabelle Augensteincs.CL2026-10-15
#173Intern-Decision: Efficient Multimodal Decision Making with Autoregressive Masked Language ModelingTong Zhu, Zhe Xu, Zefeng He +7cs.CL2026-10-15
#174PremiseSQL: Evaluating Premise Critique and Abstention in Text-to-SQL SystemsShuo Lin, Jinzhe Li, Chenlu Guo +3cs.CL2026-10-15
#175EMO: A Closed-Loop Test-Time Computation Framework via Alternating Context Optimization and Logits SteeringWei Xia, Yehui Tang, Zhi-Hong Dengcs.CL2026-10-15
#176CLUE: Uncovering Social Context for Pragmatic UnderstandingChengfei Wu, Zhaoqing Wu, Dan Goldwassercs.CL2026-10-15
#177Lexical Reference Frames: Interpreting LM Residual Streams in Native SemanticsJian Gu, Hongyu Zhang, Chunyang Chen +1cs.CL2026-10-15
#178Mosaic: Multi-Session Agentic Reinforcement LearningYilong Xu, Minrui Xu, Xinyu Zhou +3cs.CL2026-10-15
#179Change the Number, Change the Answer: Assessing Rating Scale Sensitivity in LLM-Based Text ScoringWonjeong Jo, Gyuwan Kim, Ming Shan Heecs.CL2026-10-15
#180Hy-Memory-30B-A3B: Attributed Reinforcement Learning for Long-Term Memory WritingTianxiang Fei, Jiazheng Kang, Mao Zheng +2cs.CL2026-10-15
#181Beyond Downstream QA: Rethinking How We Evaluate Agent MemorySebastian-Antonio Toma, Jean de Kernier, Mike Ply +1cs.CL2026-10-15
#182Not X, but When: Diagnosing a Mandarin LLM Writing Tic through Contextual AppropriatenessYihang Peng, Yi Jing, Dewen Liu +2cs.CL2026-10-15
#183Multi-Target Few-Shot Prompting with Diffusion Language ModelsAnton Xue, Alan Li, Rahul Sahacs.CL2026-10-15
#184AI Consilium: a Benchmark of LLM Clinical Multidisciplinary Second OpinionsAlexey A. Bokov, Ivan I. Panin, Nikolay B. Nechaev +10cs.CL2026-10-15
#185Knowledge That Is Linear Before Fine-Tuning Generalizes After ItFaridoun Mehri, Hinrich Schützecs.CL2026-10-15
#186Grid-Bench: Can LLMs Predict How Discrete Worlds Change?Zixiang Xu, Zirui Song, Wanrong Zheng +16cs.CL2026-10-15
#187MindEval2: Clinically Grounded Patients and Rubrics for Evaluating Language Models in Mental Health SupportJohn Mendonça, Daniel Tschernutter, José Pombal +6cs.CL2026-10-15
#188Training Reasoning Models to Generate Diverse Scientific IdeasManya Wadhwa, Pranav Narayanan Venkit, Hiroaki Hayashi +3cs.CL2026-10-15
#189OmniVerifier-C1: Decomposed Graded Verifier for Rule-Governed Generative World ModelingBowei Liu, Xinchen Zhang, Xuhuan Li +10cs.CL2026-10-15
#190Approve What, Exactly? Effect Binding and Trusted Rendering for Agent Step-Up AuthorizationSai Varun Kodathala, Prashanth Pollishetty, Jaylen Cargillcs.CR2026-10-15
#191Stronger Judges Do Not See More: Deployment-Integrity Blindness in LLM EvaluationJianchang Su, Dawei Xiang, Yifan Zhang +1cs.CR2026-10-15
#192CARE-SD: Explainable Reasoning Architecture for Local SLM Self-Disclosure Analysis in Textual DataAisvarya Adeseye, Adeyemi Adeseye, Mohammad Tahir +1cs.CR2026-10-15
#193FedSumUp: User-Auditable Privacy-Aware Representation Sharing for Resource-Constrained Federated IntelligenceJingwei Zhao, Tiantong Sun, Yuanyuan Song +6cs.CR2026-10-15
#194Clean Data Can Still Carry Backdoors: Support-Persistent Backdoors for Model ReuseJunhoo Lee, Baekseung Kim, Seungyeon Kim +1cs.CR2026-10-15
#195Matoi: Selective Revalidation of Consequence Evidence for Agent AuthorizationZexun Wangcs.CR2026-10-15
#196BiShield-TEE: On the (In-)Security of Unilateral Weight Obfuscation in On-Device TEE-Shielded LLM PartitionZhiyuan Wang, Yuezhi Zhou, Ziqi Zhang +3cs.CR2026-10-15
#197Encoded but Exposed: Language Embeddings can Reveal More Than They Should in Recommender SystemsLinda Beková, Rodrigo Alvescs.CR2026-10-15
#198Language Is a Security Surface for Agent GuardsHasan Demirkiran, Jens Ernstbergercs.CR2026-10-15
#199RoPE-Flow: Monocular Vision-based Robot Pose Estimation via 2D Graph-Conditioned 3D Flow MatchingLiangjing Shao, Wanhao Liu, Zhiwei Fang +6cs.CV2026-10-15
#200RoboCloth: A Large-Scale Real Cloth Material Dataset for Neural Reflectance ReconstructionZhen Li, Haoran Qin, Francesco Di Sario +2cs.CV2026-10-15
#201Can World and Action Modeling Benefit Each Other under Unified Causal Training?Yue Su, Bokai Lin, Xinkai Wang +9cs.CV2026-10-15
#202Sparse Attention for Video Generation Acceleration via Growing Sparsity and Reduced SearchYun Dai, Yuyun Chen, Jiarui Wen +3cs.CV2026-10-15
#203Trajectory Prediction Method for person under WSN with Hierarchical Envelope Adversarial Domain AdaptationWenqian Jiang, Qifeng Sun, Xiaosong Gao +4cs.CV2026-10-15
#204VisualTrust: Video Reasoning under On-Screen Claim FramingHuachao Zhu, Junjielong Xu, Sicheng Li +5cs.CV2026-10-15
#205ControlFlow3D: Distilling Multi-View Knowledge into Latent Flow Matching for Point Cloud UpsamplingYuang Liu, Zhi Zuo, Zhengkai Zhao +4cs.CV2026-10-15
#206UltraDiff: Transferring High-Fidelity Priors to Compressed Latent Spaces for High-Resolution Image GenerationJingjing Ren, Haitian Zheng, Haoyu Chen +5cs.CV2026-10-15
#207SpaceCache: Intermediate Feature Reuse for Efficient Semantic Segmentation on Point Cloud StreamsDongheon Yang, Beomseok Kang, Jae-Joon Kimcs.CV2026-10-15
#208DLOSAC: Joint Spatial-Geometric Image Estimation via Delaunay-Guided Local Optimization RANSACYu Liu, Meiqi Zhou, Zipei Fan +2cs.CV2026-10-15
#209A large-scale climate-aware satellite image dataset for domain adaptive land-cover semantic segmentationSonglin Liu, Linwei Chen, Li Zhang +2cs.CV2026-10-15
#210FocusOPD: Structure-Guided On-Policy Distillation for Diffusion ModelsXinrui Lin, Shumin Wang, Suqi Song +2cs.CV2026-10-15
#211Do VLAs Really Follow Instructions? Diagnosing How-Level Instruction Following in Vision-Language-Action ModelsSangwu Park, Wonjoong Kim, Yeonjun In +1cs.CV2026-10-15
#212TRACER: A Multimodal Harness for Patient Care in HospitalsZane Durante, Paul Tang, Keshigeyan Chandrasegaran +11cs.CV2026-10-15
#213ReState: Noise-Level-Aware State Correction for Training-Free Object Removal in Few-Step Diffusion ModelsDonghwan Lee, Sanghyun Jo, Sihyun Kim +2cs.CV2026-10-15
#214GeoPano: Towards Geometrically Accurate 3D Reconstruction from a Single PanoramaJing OU, Zidong Cao, Liaoyuan Fan +7cs.CV2026-10-15
#215Dusting the Phantom: Gaussian Allocation for Fading Dynamic ContentMinhyeok Roh, Minseo Lee, Jun Young Jeong +4cs.CV2026-10-15
#216VLA-$Δ$: Learning Physical State Transition for Vision-Language-Action ModelsQi Lu, Jiarun Li, Ce Zhang +5cs.CV2026-10-15
#217Loud and Clear: Making Visual Evidence Count in Multimodal Document RAGEunchan Jo, Seounghyun Jang, Sangwoo Mocs.CV2026-10-15
#218ZoomCap: Evidence-Routed Visual Zooming for Recoverable Visual Information TransferHao Shi, Jiafeng Wang, Yuzhuo Fu +5cs.CV2026-10-15
#219CoViG: Coarsened Vision GNN for Image ClassificationMartial Guidez, Stefan Duffner, Christophe Garciacs.CV2026-10-15
#220AdaLoop: Thinking with the Vision EncoderXinran Nicole Han, Yiyang Lu, Katelyn Gan +1cs.CV2026-10-15
#221CertEx: Exact Visual Retrieval at Scale by Certified ExclusionDongfang Zhaocs.CV2026-10-15
#222Semantic Latent Alignment for Flow Matching with Invertible Bi-Lipschitz AdaptersFelix Nützel, Mischa Dombrowski, Luca Hagen +1cs.CV2026-10-15
#223When Should a Low-Light Pipeline Generate? Auditable Risk Control for Selective Generative EnhancementQiyi Xie, Wei Chen Ng, Suyang Xi +5cs.CV2026-10-15
#224L2GSSL: Label-Efficient Local-to-Global Self-Supervised Learning for Volumetric Healthcare DataPo-Cheng Cheng, Hung-Hsuan Chencs.CV2026-10-15
#225CoDeFont: One-Shot Font Generation via Multi-Scale Factor-Specific Representation LearningRejoy Chakraborty, Prasun Roy, Saumik Bhattacharya +1cs.CV2026-10-15
#226SATOR: Backpropagation-Free 3D Test-Time Adaptation via Sample-Adaptive Token RoutingInseok Kong, Geunyoung Jung, Jiyoung Jungcs.CV2026-10-15
#227Perception or Reasoning? Diagnosing and Tackling Reinforcement Learning Bottlenecks in VLMsZeyuan Yang, Zhuohao Chen, Jiaben Chen +3cs.CV2026-10-15
#228CLAD: Keypoint Matching Using Global Line CorrespondencesMasaki Satohcs.CV2026-10-15
#229Where, How, and When: Query-Guided Grounding for Video UnderstandingYogesh Kumarcs.CV2026-10-15
#230ManiFusion: Unlocking the High-Throughput Generation via Superposition in Manifold SpaceMinkyu Kim, Baekseung Kim, Junhoo Lee +2cs.CV2026-10-15
#231RLDF: A Region-Level Deepfake Dataset and Benchmark for Partial-Face Manipulation DetectionShukesh Reddy, Abhijit Dascs.CV2026-10-15
#232PET Quantification-Preserving Registration for Longitudinal Whole-Body PSMA PET/CTFryderyk Kögl, Anna Reithmeir, Daniel M. Lang +3cs.CV2026-10-15
#233Can Visual Generation Expand What Unified Multimodal Models Know?Wenkai Li, Wenyi Hong, Zhuoyi Yang +1cs.CV2026-10-15
#234Cross-Prompt Inference Mitigates Rare-Class Suppression in Imbalanced VLM FinetuningEmanuel Ben Baruch, Sivan Biham, Alon Shoshan +2cs.CV2026-10-15
#235GRASE: Geometry-native Real-to-sim Agentic Scene Modeling from VideoZhaorui Lin, Haohan Liu, Zhen Chen +1cs.CV2026-10-15
#236FilterFusion: Prior-Guided Adaptive Filter Fusion for Efficient Video DenoisingWenlong Yang, Weihang Yuan, Canran Jin +3cs.CV2026-10-15
#237Rethinking Classifier-Free Guidance for TI2I Flow MatchingAndreas Floros, Elena Koritska, Teofilo de Campos +4cs.CV2026-10-15
#238Decoupled Safety Control: A Safety-Control Algorithm for Training-Free Safety GuidanceHuilin Zhou, Ruoxi Cheng, Yuhang Wang +4cs.CV2026-10-15
#239MYOPIA: Understanding the Limits of Tree-Based Reasoning in Vision-Language ModelsIslam Mesabah, Sary Elmansoury, Gerrit Großmann +2cs.CV2026-10-15
#240Hear, Localize, and Reason: Spatially Aware Scene Understanding for Audio-Visual LLMsKim Sung-Bin, Lee Jung-Mok, Jinwoo Jung +4cs.CV2026-10-15
#241A Decision-Aware Evaluation Protocol for Uncertainty in Medical Image SegmentationSaket Maganti, Shreyank N Gowdacs.CV2026-10-15
#242Anchor3DGS: Feed-Forward 3D Gaussian Splatting with Compact Anchor-Based RepresentationSheng Ye, Jiangke Lin, Fudong Wang +3cs.CV2026-10-15
#243Spurious Attention Heads in Vision Transformers: Mechanistic Identification of Annotation-Driven Bias in Medical Chest X-Ray AnalysisJoshua Muhumuza, Cornelius Kalenzics.CV2026-10-15
#244DIAL: Dynamic and Informed Adjustment of the Native Stochastic Law for Reliable Weather EnsemblesYucheng Wang, Haonan Guo, Tianhao Zhao +4cs.CV2026-10-15
#245SCMerge: Spatial-Consistency-Aware Token Pair Merging for Efficient Semantic SegmentationJunfeng Ren, Yi Gong, Yuan Zengcs.CV2026-10-15
#246Digital Typhoon Dataset V3: Benchmarking for Multi-spectral Extension and Analyzing Systematic Bias in Intensity RegressionAsanobu Kitamoto, Victor Le Louarn, Noelia Falczuk +2cs.CV2026-10-15
#247FusionAudit: Pathway-Conditioned Robustness Auditing for Native Multimodal ModelsJiaming Zhang, Zherui Li, Siqi Guo +3cs.CV2026-10-15
#248Edit4D: Editable 4D Scene Generation with Textual ControlChanwoo Kim, Tackgeun You, Hwasup Limcs.CV2026-10-15
#249Bridging the Markerless Tracking Validation Gap: Intraoperative X-ray Workflow IntegrationConnor Daly, Salvatore Russo, Jinendra Ekanayake +2cs.CV2026-10-15
#250Mixture of Multi-Sequence Feature Difference for Contrast-Enhanced MRI SynthesisJonghun Kim, Junmo Kwon, Hyunjin Parkcs.CV2026-10-15
#251International Multi-Centre Validation of Unsupervised Domain Adaptation for Precise Discrimination between Normal and Abnormal Retinal DevelopmentZhanhan Tu, Nikhil Reddy, Helen J. Kuht +27cs.CV2026-10-15
#252The Dormant Spiking Neuron: A State-Driven Mechanism for Efficient Spiking Neural NetworksRuichen Ma, Yicai Chen, Pujun Zhou +5cs.CV2026-10-15
#253Beyond Source Prompts: Towards Visually Grounded AI-Generated Video Quality AssessmentKehao Zhou, Yixuan Li, Yuxuan Jiang +1cs.CV2026-10-15
#254Beyond Generation: Using Multimodal LLMs as Detectors of LLM-Generated Deepfake Facial ImagesOlivia Salamon, Virginia N. L. Franqueira, Shujun Lics.CV2026-10-15
#255FuseAdapt: Parameter-Efficient Multimodal Fusion for Semantic Segmentation with Missing ModalitiesXin Zhang, Robby T. Tancs.CV2026-10-15
#256DINO-FIL: Multi-Layer Transformer Fusion for Generative Inpainting Forgery LocalizationSimon Freitter, David Fischinger, Silvia Poletti +2cs.CV2026-10-15
#257Learning to Think and Explore in 3D WorldYijiang Li, Bingyang Wang, Nuno Vasconceloscs.CV2026-10-15
#258NICE Toolbox: Nonverbal Interpersonal Communication Exploration ToolboxAleksandr Evgrashin, Carolin Schmitt, Timo Lübbing +8cs.CV2026-10-15
#259MedPAO-VL: Interpretable and Protocol-Compliant Agent for Structured Radiology Report GenerationShrish Shrinath Vaidya, Gowthamaan Palani, Minmini Selvam +2cs.CV2026-10-15
#260Single-stage joint diffusion of sky images and clear-sky index for ultra-short-term irradiance forecasting: what the frame-to-irradiance stage discardsKanawut Suwandee, Suwichaya Suwanwimolkulcs.CV2026-10-15
#261Teaching DINOv3 About Partial 3D Geometry: A Self-Supervised Geometry-Aware ApproachViktoria Ehm, Dongliang Cao, Riccardo Marin +4cs.CV2026-10-15
#262From Adults to Children: Benchmarking Foundation Models for Chest X-Ray Classification under Domain ShiftSara Inácio, Hugo Proença, João C. Nevescs.CV2026-10-15
#263Temporal Periodic Image Registration with Implicit Neural RepresentationsMathias Lowes, Kristine Aavild Sørensen, Maxime Sermesant +1cs.CV2026-10-15
#264Seeing Both the Forest and the Trees: Reusing Holistic 3D Priors for Part-Decomposed GenerationYiqun Zhao, Binbin Huang, Haobin Duan +2cs.CV2026-10-15
#265Anvil: Scaling Embodied Spatial Intelligence through Knowledge RecirculationWeilin Ruan, Bohan Zhou, Jinghao Li +12cs.CV2026-10-15
#266SurgStreamer: proactive, request-driven monitoring of surgical video streams with structured state and a reusable reasoning layerBowen Xiang, Jon S. Heiselman, Michael I. Migacs.CV2026-10-15
#267Seeing is Believing: Benchmarking and Mitigating the Interference of Language Priors on Visual Perception in MLLMsLi Ma, Yan Zhuang, Jiawen Deng +1cs.CV2026-10-15
#268BridgeAfford: Bridging Query-Target Gap for Generalizable 3D Affordance GroundingYijie Su, Yakun Zhu, Yi Bin +5cs.CV2026-10-15
#269Flow-CLIP: Image-Conditioned Residual Scoring for CompositionalImage-Text MatchingMinghong Wei, Enguang Zhu, Pu Cao +2cs.CV2026-10-15
#270VesperMUSE: Multi-Modal Fusion Vision Transformer for Image Semantic Segmentation Under Diverse Light ConditionsRaul Balmezcs.CV2026-10-15
#271Data-Efficient ConvNeXt Pretraining for High-Resolution Sentinel-1 GRD SAR Representation LearningYuki Natsume, Sang-Ho Yun, Chai Kiat Yeocs.CV2026-10-15
#272Visual Sanad: Auditing Vision-Language Models for False Acceptance of Qur'anic CitationsNiaz Mohaiman Abtahi, Reyana Shahid, Evan Maksudcs.CV2026-10-15
#273When Models Misread Ink: Auditing VLMs for Arabic Calligraphy RecognitionNiaz Mohaiman Abtahi, Evan Maksud, Reyana Shahidcs.CV2026-10-15
#274FeaTok: Feature-Loss Tokenization for Image GenerationZhang Xiaofeng, Samuel Lavoie, Nicolas Beltran-Velez +6cs.CV2026-10-15
#275Memory as Weights: Internalizing Long-Term History for Streaming VideosZhuoming Liu, Jinhong Lin, Lin Zhang +2cs.CV2026-10-15
#276Retrofitting Recurrent Vision-Language Models from Pretrained BackbonesMadhav Iyengar, Andreas Geiger, Hilde Kühnecs.CV2026-10-15
#277Pathology foundation models for training-free case retrieval in salivary gland tumorsMaximilian J. Roesel, Niklas Kiermeyer, Philipp Keyl +1cs.CV2026-10-15
#278Beyond the Dominant Label: Recovering Coexisting Lesion Evidence with Multiple Instance LearningLubin Gan, Jing Zhang, Xinming Zhang +3cs.CV2026-10-15
#279SCCL-DT: Semantic-Conflict-Aware Contrastive Learning with Dual-Rule Teacher Distillation for Zero-Shot Chest X-Ray DiagnosisTing Liu, Haoran Lai, HaobinChen +2cs.CV2026-10-15
#280FALCON: FPGA-Accelerated Latency-Certifiable Occupancy Networks for Camera-Based Autonomous DrivingHaohua Que, Mingkai Liu, Handong Yaocs.CV2026-10-15
#281Motion- and Gravity-Aware Feedforward 3D ReconstructionShiyao Qian, Yuan Ren, Dongfeng Baics.CV2026-10-15
#282LAMP: Layerwise Adaptive Mixing of Predictors for Training-Free Few-Shot Vision-Language AdaptationZhipeng Ye, Feng Jiang, Qiufeng Wang +1cs.CV2026-10-15
#283EVA-Cap: Optimizing Audiovisual Video Captioning via Event-Centric AlignmentJiapeng Shi, Qiuxia Hou, Jiaqi Leng +5cs.CV2026-10-15
#284OpenGCUA: Toward a Fully Open Stack for Generalist Computer UseHanzhang Zhou, Long Li, Quyu Kong +12cs.CV2026-10-15
#285TRACE: Topology-Aware Reconnection via Prediction-Adaptive Connectivity Enforcement for Thin-Structure SegmentationJunho Moon, Ikbeom Jangcs.CV2026-10-15
#286FutureLift: Lifting Trajectory Proposals into Bidirectional Future Graphs for Motion ForecastingDaniel Grimm, J. Marius Zöllnercs.CV2026-10-15
#287Skill-Decoupled On-Policy Expert Distillation for Unified Vision-Language ModelsYuqi Xiong, Chunyi Peng, Zhipeng Xu +5cs.CV2026-10-15
#288How Much Physics Can Vision Learn from Audio? Probing and Distilling Damping StructureZainab Afolabi, Vadim Selyutin, Zhao Gao +2cs.CV2026-10-15
#289WaveLLM: Wavelet-Domain LLM Entropy Modeling for Lossless Image CompressionYue Yu, Bowei Kang, Changsheng Gao +2cs.CV2026-10-15
#290MMSearch-OPD: Easy Made Hard, Hard Made Learnable for Long-Horizon Multimodal Search AgentsHuanyao Zhang, Jiepeng Zhou, Jiaye Lin +9cs.CV2026-10-15
#291FPG-Seg: Annotation-free Retinal Vessel Topology SegmentationJames Willoughby, Irina Voiculescucs.CV2026-10-15
#292SCOPE: Semantic Bounded Credit Optimization for Prompt Engineering in Text-to-image GenerationYufei Jiao, Jinfa Huang, Zeyue Xue +5cs.CV2026-10-15
#293Beyond Pairwise Repulsion: Collective Diversity via Determinant Maximization in Diffusion SamplingKwanyoung Lee, SeungJu Cha, Yebin Ahn +2cs.CV2026-10-15
#294Unsupervised Clustering of Public Transport Vehicles Using Deep Morphological Features and Color HistogramsJuan Irving Vasquezcs.CV2026-10-15
#295MJev-Spatial: System One Spatial Intelligence via Native Attention MatchingLuozheng Qin, Yuhan Zhu, Changhai Zhou +9cs.CV2026-10-15
#296Routing Policy Optimization for Online Diffusion Reinforcement LearningQiuhong Shen, Yiding Yang, Yuxin Zhang +8cs.CV2026-10-15
#297Grounded Human-Attributed Description and Activity Recognition in VideosJay N. Paranjape, Jurijs Nazarovs, Rohan Sarkar +5cs.CV2026-10-15
#298ARC-SORT: Adaptive, Robust, Compensated Multi-Object Tracking with Interacting Multiple ModelsGirish Kumar Adarics.CV2026-10-15
#299Velox: Spatial Memory Makes World Models EfficientQiuhong Shen, Shizun Wang, Xinchao Wangcs.CV2026-10-15
#300Not Just a Subject: Capturing Adaptive Scene-Specific Variance for Visual StorytellingSeungJu Cha, Ye-Chan Kim, Kwanyoung Lee +1cs.CV2026-10-15
#301AVC-Reward: Event-Centric Audio-Video Consistency EvaluationYuruo Wu, Kaihang Pan, Kai Shen +6cs.CV2026-10-15
#302Dense4D: Pixel-Level 4D Human CorrespondenceRıza Alp Gülercs.CV2026-10-15
#303ACEdit: Stable Multi-Turn Image Editing via Asymmetric ConditioningSara Dorfman, Nir Goren, Gal Barak +2cs.CV2026-10-15
#3043DCodeVerse: Exploring 3D Worlds as CodeYipeng Gao, Ziyao Zeng, Jinfa Huang +16cs.CV2026-10-15
#305GeoState: Learning View-Decoupled Geometry States for 3D World ModelingHongchang Liu, Jian Liu, Yujuan Ding +5cs.CV2026-10-15
#306Speculative Forcing for Efficient Autoregressive Video GenerationHyunwook Choi, Seungryong Kim, Dongyoon Han +1cs.CV2026-10-15
#307SUPRA-TEX: 3D Generation with Super-Aligned TextureChen Yang, Jiemin Fang, Fanpeng Meng +5cs.CV2026-10-15
#308DK-VLM: Geometry as Position for Spatial Reasoning in Vision-Language ModelsHan Su, Meng Tian, Tianyu Huang +7cs.CV2026-10-15
#309Grounding Generative Verification in 3D ContentShuanglin Li, Jiaying Lin, Shuquan Yecs.CV2026-10-15
#310Perceive, Predict, and Plan: a Unified World Action Model for Egocentric Dexterous ManipulationZirui Wu, Chen Guo, Tianjian Jiang +11cs.CV2026-10-15
#311SoftCache: Adaptive Step Size Caching for Diffusion TransformersShimon Malnick, Nadav Orenstein, Ohad Fried +1cs.CV2026-10-15
#312Which Tokens to Merge? Diffusion Dynamics for Efficient Image GenerationSeungJu Cha, Ye-Chan Kim, HyunGee Kim +2cs.CV2026-10-15
#313Gen4P: Video Generators are 4D PerceiversYitong Xia, Zeren Jiang, Chuanxia Zhengcs.CV2026-10-15
#314MARS: A Momentum-Aware Adaptive Rating System for Personalized AssessmentVikrant Sahu, Khethavath Sunil Naik, Gagan Raj Guptacs.CY2026-10-15
#315Coordination-Free Workload Regularization for Variable-Cost Distributed TrainingTao Huang, Chen Zhu, Antonio Alonso +4cs.DC2026-10-15
#316When the KV Cache Is Slower Than the GPU: Scaling Remote KV Tiers for Context-Parallel PrefillMuhammad Ibrahimcs.DC2026-10-15
#317ETH: Data-Balanced Heterogeneous Pipeline Parallelism for Training Large ModelsMianjie Yu, Zhongmin Zhao, Zizhao Mo +9cs.DC2026-10-15
#318Architecting for Hardware Diversity: Meta's End-to-End Co-Design for High-Performance AI Training on AMD GPUsHaoyu Zhang, Arshad Rahman, Adnan Aziz +55cs.DC2026-10-15
#319ResStreamGS: Residual-Sensitive Dual-Stream Gaussian Splatting for Mobile Volumetric Video StreamingHaoran Liu, Di Wu, Wang Luo +3cs.GR2026-10-15
#320From Sketch to Scene: Relightable Garment Reconstruction from Marked SketchesAhmet Neçirvan Doğan, Eren Acar Başaran, Metin Sezgin +1cs.GR2026-10-15
#321Learning Rewards in Strategic GamesAntoine Bergerault, Cyrille Kone, Giorgia Ramponics.GT2026-10-15
#322Decentralized LLM Workflows via Sequential AuctionsIan Gemp, Shubhendu Trivedi, Adam Fisch +7cs.GT2026-10-15
#323OnBodyAI - Why the Next AI Needs a BodyMichael Beiglcs.HC2026-10-15
#324What do AI chatbots do after users decline therapeutic redirection for suicide thoughts?Subigya Nepal, Ruth Heo, Emma M Parrish +1cs.HC2026-10-15
#325Following Delegation Traces to Study Human Oversight in Interaction with Multimodal AIAgnese Chiatti, Matteo Matteucci, Viola Schiaffonatics.HC2026-10-15
#326Learning When to Think: Utility-Guided Adaptive Reasoning for Efficient Text RetrievalYingtao Luo, Kangyi Zhao, Shiyi Du +1cs.IR2026-10-15
#327RecSoup: Efficient Model Merging Approach for Controllable Multi-Objective RecommendationZidong Jia, Guofu Xie, Xiao Zhangcs.IR2026-10-15
#328VoteGEO-Bench: Measuring the Impact of Generative Engine Optimization on Electoral VisibilityShiqi Zhang, Xiaokui Xiaocs.IR2026-10-15
#329Uncertainty-Aware Federated Learning for Joint Communication and Computation in XR SystemsRobert-Jeron Reifert, Hayssam Dahrouj, Alaa Alameer Ahmad +2cs.IT2026-10-15
#330INCONVENIENT: A Benchmark to Assess LLM Generalization Capabilities from Convenience SamplesSara Rezaeimanesh, Chad Klochko, Kundan Thind +1cs.LG2026-10-15
#331SALTO: Solver-Anchored Lifted Transfer Operators for Nonlinear Event InferenceQi Wang, Rylie Fostercs.LG2026-10-15
#332Bellman-Consistent Trajectory RL for LLM Arithmetic ReasoningLianfa Lics.LG2026-10-15
#333StochLOB: Heavy-Tailed Score Matching for Robust Limit Order Book Trend PredictionArshia Abolghasemi, Seyed Reza Tavakoli, Parsa Naderi +7cs.LG2026-10-15
#334SIEVE: Overcoming Topological Obstruction in Equivariant Self-Supervised LearningJongann Lee, Sun Woo Park, Yun Young Choics.LG2026-10-15
#335Spectral-Spatial InterpretationHaotian Ma, Ruqi Yang, Philip Townsendcs.LG2026-10-15
#336DST-Net: Decomposed Spatio-Temporal Network for Time Series ForecastingYaohua Zha, Hai Wu, Shu-Tao Xiacs.LG2026-10-15
#337Noise-Space Reward Alignment for Few-Step Generative ModelsWoocheol Shin, Taeyoung Yun, Jiwon Sung +7cs.LG2026-10-15
#338Predicting Live Birth After Fresh Embryo Transfer in IVF/ICSI: Differential ICM/Trophectoderm Morphology Encoding and a Hybrid Attention--Logistic Regression EnsembleAbdul Raheem Shahzad, Jinxin Chen, Ming Zhang +1cs.LG2026-10-15
#339Language Models Share a Readout Bottleneck in Working MemoryDongyu Gongcs.LG2026-10-15
#340Judging the Judges: Confidence and Disagreement in Rubrics as RewardsMichael Tian-Yue Liu, Anne Harrington, Trevor Darrell +1cs.LG2026-10-15
#341Sensor Diagnosis for Fuel and Emissions Monitoring in Heavy-Duty Diesel VehiclesTejas Dahiya, Saurabh Kumar Guptacs.LG2026-10-15
#342Resisting Harmful Instructions through Training-Free Weight EditingAli Ebrahimpour-Boroojeny, Xiaocong Yang, Samuel Schapiro +4cs.LG2026-10-15
#343Poisoning the corpora of protein design systems during pre-training and retrievalCharalampos Koilakos, Kimon-Antonios Provatas, Michail Patsakis +3cs.LG2026-10-15
#344Hard Way, The Only Way: Provable Merits of Training on Hardest ExamplesElvis Dohmatobcs.LG2026-10-15
#345Learning and Forecasting Multiscale Spatiotemporal Epidemic Dynamics with Lagrangian-Eulerian Graph Neural ODEsJinyi Duan, Qian Li, Biao Tangcs.LG2026-10-15
#346Not All Change Is Damage: Update-Matched Unlearning for Large Language ModelsJie Li, Youming Tao, Bowei He +1cs.LG2026-10-15
#347Compatibility Matters: A Framework for Token-Level Teacher Selection in On-Policy DistillationStanley Wei, Jiin Woo, Kaan Ozkara +1cs.LG2026-10-15
#348Representation Redistribution in Sparse AutoencodersZiye Mei, Haotian Macs.LG2026-10-15
#349Isolating a Language Model's Judgment with a Label-Free SubspaceChaemin Jang, Donggyu Lee, Jeesoo Kim +2cs.LG2026-10-15
#350Fractional Power-of-Two Quantization for Efficient and Effective Multiplier-Free LLM InferenceSunghyun Wee, Geunjae Choi, Hyeonjin Kim +2cs.LG2026-10-15
#351Behavioral Compositionality of Sparse Autoencoder RepresentationsHaotian Ma, Ziye Mei, Frederic Salacs.LG2026-10-15
#352Rethinking Learning from Label Proportions via Moment MatchingTianhao Ma, Wei Wang, Yivan Zhang +4cs.LG2026-10-15
#353Regret Lower Bound for Online Learning of Quantum States with Logarithmic Loss, with Applications to Quantum State Tomography and Confidence Sequences for Matrix MeansYen-Huan Li, Wei-Fu Tsengcs.LG2026-10-15
#354TimeCap: A Scalable Open-Source Pipeline for Captioning Wearable Health Time-Series DataMax Rosenblattl, Milana Gurbanova, Karl Aurel Deck +16cs.LG2026-10-15
#355Can Capability Enhancement be Localized?Anh Tuan Nguyen, Anna Bair, Zico Koltercs.LG2026-10-15
#356Personalized Projected Ascent for Federated Stackelberg OptimizationM Yashwanth, Sharannya Ghosh, Saikiran Bulusu +1cs.LG2026-10-15
#357PocketTSLM: Deploying an On-Device Soft-Prompt Time-Series Language Model for Privacy-Preserving Smartphone ReasoningMax Rosenblattl, Nikhil Krishnaswamy, Leon Nissen +9cs.LG2026-10-15
#358Spectrum Is Not Enough: A Random-Matrix Account of Data-Free Preconditioning for Differentially Private LearningShilin Zhang, Kangning Wangcs.LG2026-10-15
#359Ranking and Partitioning of Attention Heads for Sparse and Continual Reinforcement Learning Fine-tuningRuizhe Shi, Zaiwen Yang, Qiubo Wang +2cs.LG2026-10-15
#360Does On-Policy Distillation Need to Complete Every Rollout?Zhengxin Zhang, Maosen Tang, Ning Wang +6cs.LG2026-10-15
#361Online Quantile Omniprediction for Proper LossesHyunsuk Kim, Isaac Gibbs, Michael W. Mahoney +1cs.LG2026-10-15
#362Honesty is the Best Policy ... or is it? Demand Management for Probabilistic Service OptionsDaniela Sailer, Robert Klein, Claudius Steinhardtcs.LG2026-10-15
#363Same Target, Different Origins: Aligning Latent Rollout for Consistent PDE EmulationXinying Li, Jing Xu, Wenjun Wang +4cs.LG2026-10-15
#364Memorilla: Latent Semantic Memory for LLMsAdibvafa Fallahpour, Parsa Idehpour, Vignesh Kothapalli +4cs.LG2026-10-15
#365Does Compression Imply Generalization? A Minimum Description Length PerspectiveLincen Yang, Jiayang Shi, Nan Pu +4cs.LG2026-10-15
#366RDL-Bench: A Benchmark for Task-Aware Question Answering over Relational DatabasesYao Cheng, Siqiang Luocs.LG2026-10-15
#367Fault Detection and Bit-Error Rate Diagnostics in Optical Wireless Links Using Edge-AISarthak Bhattarai, Sheshadri Shikhar Bandyopadhyay, Suprabh Dhakal +1cs.LG2026-10-15
#368Multi-Reward Hacking: From Aggregation-Induced Drift to Trust-Anchored DefenseYushu Li, Jiin Woo, Xiaoxiao Li +1cs.LG2026-10-15
#369Learning to Forecast on Multiple Spatiotemporal HierarchiesValentina Moretti, Cesare Alippi, Andrea Cinics.LG2026-10-15
#370What Does History Add? Calendar Controls and Information-Timing Audits for University Trajectory ForecastingZepei Caocs.LG2026-10-15
#371Each Reward to Its Relevant Tokens: Reward-Specific Token-Level Credit Assignment for Multi-Reward RLSkylar Zhai, Haonan Wang, Zhining Liu +4cs.LG2026-10-15
#372V-SHARE: Provable Convergence Guarantees for Advantage-based AlgorithmsKintan Saha, Hamed Masoudi, Xinyi Sheng +3cs.LG2026-10-15
#373Kolmogorov-Arnold Networks: Curse of Dimensionality and Structural BiasYunhao Ni, Yuxin Guo, Jie Luo +2cs.LG2026-10-15
#374Phase Kernel Lifts Capacity of Dense Associative MemoryYifei Zhao, Ying Tangcs.LG2026-10-15
#375Activation-Adjacent Layer Normalization: Effects on Approximation PowerYunhao Ni, Yuxin Guo, Jie Luo +2cs.LG2026-10-15
#376Federated Art Chase: Privacy Leakage and Data Poisoning in Federated Fine-TuningVasileios Perifanis, Nikolaos Pavlidiscs.LG2026-10-15
#377Finite-Time Guarantees for Constrained Reinforcement Learning under Partial ObservabilityValentina Zaccaria, Philip Jordan, Tingting Ni +2cs.LG2026-10-15
#378Uncertainty Quantification in Pairwise Difference Learning for ClassificationMohamed Karim Belaid, Maximilian Rabus, Eyke Hüllermeiercs.LG2026-10-15
#379When Does Muon Actually Win? A Paired Data-, Time-, and Tuning-Budget BenchmarkMushir Akhtar, Hazem N. Nounou, Majdi Mansouri +1cs.LG2026-10-15
#380A Quantum Machine Learning Approach to Content-Based Media RecommendationMina Abbaszadeh, Ouissal Moumou, Anna Pearson +4cs.LG2026-10-15
#381Sharp and Stable Label-Free Calibration Certificates from Logical CoherenceTakahiro Katocs.LG2026-10-15
#382From Perception to Prediction and Intervention: Benchmarking Proactive Video Assistants in Real-Life ScenariosBoyu Cui, Junhao Luo, Zhihao Wang +5cs.LG2026-10-15
#383Learning to Search for Executable Patternmaking from Certified ProgramsZhuotao Xu, Chi Zeng, Liying Yang +2cs.LG2026-10-15
#384Transfer Learning in Bandits from Unknown Adaptive Policies: Problem-Dependent Lower and Upper BoundsAdrien Prevost, Timothee Mathieu, Waris Radji +1cs.LG2026-10-15
#385Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy DistillationBingxi Hou, Guochao Jiang, Guofeng Quan +4cs.LG2026-10-15
#386Market Incentives for AI Safety InvestmentNikita Tsoycs.LG2026-10-15
#387Local Temporal Contrasts on Human Motion Data Induce a Latent GeometryLourenço A. Rodrigues, Felix Putzecs.LG2026-10-15
#388ReFlow: Replay-Driven Decoupling for Efficient RL Post-TrainingYukun Tian, Junwei Su, Haofeng Xu +6cs.LG2026-10-15
#389Efficient Pairwise Difference Learning: A Comparative Study of Encoding Strategies and Training Pair SelectionBernard Georges, Mohamed Karim Belaid, Manuel Rodriguescs.LG2026-10-15
#390Approaching Backpropagation Accuracy with Weight Perturbation on MNISTPatrick Inouecs.LG2026-10-15
#391Diffusion Language Models as Open Quantum SystemsAkinori Tanaka, Yukinao Akamatsu, Takuki Tomita +1cs.LG2026-10-15
#392Classical methods for modern applications: synthetic tabular data generation using lightweight discrete response continuous latent variable modelBartosz Barzdajn, Mateusz Krzysztońcs.LG2026-10-15
#393Router Drift Control: Mitigating Off-Policy Degradation in Mixture-of-Experts Reinforcement LearningLiangyao Jin, Zhixin Wang, Liming Liu +8cs.LG2026-10-15
#394ShiftQAT: Quantization-Aware Training for the Numerical Contract of a Fixed-Function Edge CNN AcceleratorOguzhan Buyuksolak, Osman Erman Okman, Mehmet Gorkem Ulkarcs.LG2026-10-15
#395Human Interventions as Labels: Localizing, Steering, and (Sometimes) Editing the Computations Behind LLM Agent FailuresCesare Zavattari, Alessandro Tommasi, Giuseppe Prencipecs.LG2026-10-15
#396FIRM: Fisher-Informed Retention Merging for Federated LLM UnlearningReeyansh Shah, Maram Hasan, Subhasis Chaudhuri +1cs.LG2026-10-15
#397Sparse Federated Echo State Networks for Time-Series Classification via Smooth-L1 RegularizationGengcheng Lyu, Manuel Röder, Frank-Michael Schleifcs.LG2026-10-15
#398Pairwise AUC Optimization Needs Corrective Power: A Unified ViewJia Chen, Zhiyong Yang, Shilong Bao +2cs.LG2026-10-15
#399Harmful Partial Interventions and Benign Leakage in Concept-based ModelsGregory Verghese, Christopher J. Soelistyo, Mateo Espinosa Zarlenga +2cs.LG2026-10-15
#400Q($γ_H$): Entropy-Guided Horizon Mixing in Multi-Discount Q-LearningArwa Albelaihi, Abdulrahman Altahhancs.LG2026-10-15
#401N-Gram Memories at Two Bits: Quantizing Lookup Tables in Large Language ModelsDonghoon Han, Minseop Jung, Dong Woo Kwak +2cs.LG2026-10-15
#402Measuring the local shape of learning-rate transfer curvesSatoki Ishikawa, Rio Yokota, Ryo Karakidacs.LG2026-10-15
#403A Closed Form Depth-Width Law for Neural Collapse in Deep Linear NetworksPankhil Gawade, Kirsten Fischer, Guy Wolf +1cs.LG2026-10-15
#404Local Epochs as Optimal Stopping: Theory and Evidence in Federated LearningKe Xiao, Qiyuan Wang, Christos Anagnostopouloscs.LG2026-10-15
#405Physics-Aware Distillation of a Grid Foundation Model for Real-Time Edge InferenceVlad Alexandru Sănduleac, Shahariya Rasheed Rayamarakkarveettil Puthanpurayil, Noman Khan +1cs.LG2026-10-15
#406Lethe: Link Inference Attacks For Evaluation of Edge Unlearning MethodsAndrea D'Angelo, Francesco Gullo, Davide Mottin +2cs.LG2026-10-15
#407Provably Efficient Risk-Sensitive Offline Reinforcement Learning via Optimized Certainty EquivalentsHanzhen Wang, Boxiang Lyu, Zhongxiang Dai +3cs.LG2026-10-15
#408Learning Lean Feedback for Efficient Proof-Candidate Evaluation on GPUsLazar Milikic, Etienne Bamas, Emmanuel Abbe +1cs.LG2026-10-15
#409Graph Dirichlet Energy for Fitting-Free Bivariate Causal InferencePovilas Daniušiscs.LG2026-10-15
#410Self-Calibrated Subspace Robust PCA for Parameter-Free Removal of Mixed Noise and Line Stripes in Hyperspectral ImagesWenzhe Wangcs.LG2026-10-15
#411In-Context Learning Before Specialisation: Theory of Learning in a Solvable Topic ModelFrancesco Cagnetta, Casper L. Christensencs.LG2026-10-15
#412The Tilted Sampling Problem: Optimism, Posterior Sampling, and Logarithmic RegretMohammad Pedramfar, Siamak Ravanbakhshcs.LG2026-10-15
#413The Lagrangian Structure of Cost-Penalized Active Feature AcquisitionJoseph Binghamcs.LG2026-10-15
#414ChronoSheaf: Joint Spatio-Temporal Spectral Filtering on Cellular SheavesAbeer Mostafa, Zahra Ahmadics.LG2026-10-15
#415Why Shallow Neural Networks Learn Sinusoidal Components First: An Orthogonal Polynomial Dynamics FrameworkYanyang Xiaocs.LG2026-10-15
#416Time to Fake It: Continual Machine Learning Intensifies Unfairness in Deepfake DetectionKajaree Das, Oliver Böse, Subarnaduti Paul +2cs.LG2026-10-15
#417Learn Only Where You Can't Compute: Structured Corrections to Gaussian Process PosteriorsTobias Weber, Carla Sagebiel, Philipp Hennigcs.LG2026-10-15
#418P2TPO: Structure-Aligned Page-to-Token Credit Assignment for Full-Page Document ParsingYong Zu, Ninghua Yang, Zezhong Tan +3cs.LG2026-10-15
#419Interfaces and Modules: A Scalable Representation for Weight-Space Learning across ArchitecturesMichał Kozyra, Michael Bronsteincs.LG2026-10-15
#420GraphBEAT: Graph-based Bucketized Event Aggregation Over Time for Early Risk Stratification of Gastrointestinal CancersLeo Y. Li-Han, Chris Varghese, Elizabeth B. Habermann +4cs.LG2026-10-15
#421Close Enough is Nowhere Near: Fidelity-Consumability Decoupling in KV CachesAdam Deng, Shicheng Liu, Yada Zhucs.LG2026-10-15
#422Not All Unlabeled Data Are Equal: Unlabeled Data Selection for Semi-Supervised QSAR Modeling with Large Chemical RepositoriesOliver Majer, Saso Dzeroski, Jurica Levaticcs.LG2026-10-15
#423Augment the Cache, Replace the Activation: A 2x2 Study of Internal-State SharingAdam Deng, Shicheng Liu, Yada Zhucs.LG2026-10-15
#424Selection Is Not Learning: Choosing Model FuturesHaoyi Yang, Kshitij Mishra, Nils Lukas +1cs.LG2026-10-15
#425Momentum, Commentary Tone, and Earnings Surprise in LLM Financial ForecastsAlina Khaybullinacs.LG2026-10-15
#426Effectiveness of Hidden-State Probes for Localizing Reasoning FailuresShubham Subhnil, Yannis Belkhiter, Erik Miehling +2cs.LG2026-10-15
#427Decoding Naturalistic Speech from fMRI with Temporal Modeling and Multimodal AlignmentCorentin Caris, Louis Jalouzot, Nona Rajabi +9cs.LG2026-10-15
#428ABNAT: Attention-Based Noise-Aware Training for Robust Transformers on Analog Compute-in-Memory SystemsWenshuai Yao, Wenyong Zhou, Hanyong Shao +5cs.LG2026-10-15
#429Can AI Forecast the Extremes? Evaluating Probabilistic Weather Models on Tropical CyclonesNathan Chalumeau, Xavier Renard, Remi Meynadier +3cs.LG2026-10-15
#430TIPS: A Tiny Inference-time Policy for Scaling in Diffusion Language ModelsYa-Shi Zhang, Jian Tang, Pierre-André Noël +1cs.LG2026-10-15
#431Scene Reconstruction Using Ubiquitous Wireless Signals via Diffusion Posterior Inference Over physics-Grounded RepresentationsVahid Yazdnian, Yasaman Ghasempourcs.LG2026-10-15
#432Beyond Fixed Acquisition Functions: Temporal Difference Active Learning for Perturbation DiscoveryXudong Zhang, Jianzhe Li, Yitong Tang +1cs.LG2026-10-15
#433Causal Integrated Gradients: Scalable Feature Attribution Along Causal PathsJoran Michiels, Anis Ismail, Maarten De Vos +1cs.LG2026-10-15
#434Specification Gaming and a Constrained Reinforcement Learning Mitigation in a Cleaning GridworldHilda Adwubi Oseics.LG2026-10-15
#435The importance of tensor handling and implementation of physics-informed DeepONetsNahum Banks, Gustavo A. M. de Almeida, Sergio Maldonadocs.LG2026-10-15
#436LCT: Losslessly Compressed Tensors with GPU friendly execution for TrainingMax Zhu, Bohang Sun, Pietro Lio +1cs.LG2026-10-15
#437Generalization Guarantees of Randomized Block Coordinate Descent for Nonconvex LearningRuixi Hu, Liang Wucs.LG2026-10-15
#438OS-Helix: Unifying GUI Interaction and Code Execution in Native Computer-Using AgentsBowen Yang, Kaiming Jin, Zichen Ding +8cs.LG2026-10-15
#439Training-Free On-Policy DistillationBangji Yang, Jiajun Fan, Zhaoyu Zhu +2cs.LG2026-10-15
#440Query-Efficient Rejection Sampling for Parallel Masked DiffusionShiyuan Zhang, Xuheng Li, Qiwei Di +1cs.LG2026-10-15
#441Explore Once, Evaluate Many: Multiple Policy Evaluation for Stochastic Linear BanditsSpyros Dragazis, Yilei Chen, Aldo Pacchianocs.LG2026-10-15
#442BitSparse: Compact Activation Storage for ReLU Feed-Forward NetworksMax Zhu, Bohang Sun, Pietro Lio +1cs.LG2026-10-15
#443Topology-Inspired Fine-Tuning for Wind-Field Super-ResolutionArjun Dadhwal, Brian Summacs.LG2026-10-15
#444Baselines and Score Centering in Policy Gradient EstimationShuo Han, Ziqing Hucs.LG2026-10-15
#445Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future QueriesAnikait Singh, Teresa Zhang, Yoonho Lee +3cs.LG2026-10-15
#446Learning Rational Strategies for Temporal Objectives in Multi-Agent SystemsOmar Adalat, Edwin Hamel-De le Court, Francesco Belardinellics.LG2026-10-15
#447CAT-alyzing Honesty: Continuous Adversarial Training for Transferable LLM HonestyYuan-Chen Chang, Niklas Herbster, Gauthier Gidel +1cs.LG2026-10-15
#448Towards Continual Learning: Mitigating Forgetting With Subspace TuningArnav Chavan, Kusha Sareen, Rishabh Tiwari +6cs.LG2026-10-15
#449Learning to Steer LLM Agents and Multi-Agent SystemsLeyang Shen, Yaxin Gong, Yang Zhang +7cs.LG2026-10-15
#450Twice Upon a Time: Complementary Representations for Time-Series ReasoningHedi Zisling, Liran Nochumsohn, Ilan Naiman +2cs.LG2026-10-15
#451Robust Reinforcement Learning for Dynamic Treatment Regimes under Model and Measurement UncertaintyChengze Xie, Xuan Wang, Ying Ding +2cs.LG2026-10-15
#452Lean Graph Search for Formal Theorem ProvingYihan Xu, Jia-Chen Gu, Junyi Zhang +7cs.LG2026-10-15
#453Rethinking Routing Exploration in Modern Mixture-of-ExpertsBingcong Li, Hao Ma, Michael Muehlebach +2cs.LG2026-10-15
#454PathFM: Fast Generative Forecasting of Multivariate TrajectoriesJiachen Yao, Xiyuan Zhang, Annan Yu +5cs.LG2026-10-15
#455SCARCE: Emergent Institutions in Long-Horizon Multi-Agent Coding SystemsAbhinav Kumar, Rediet Abebe, Eugene Bagdasarian +1cs.MA2026-10-15
#456SSR: Structural Signal Retriever for Scalable Agent Discovery in LLM-Orchestrated Multi-Agent SystemsGiancarlo Maldonado Cárdenas, Carlos A. Astudillo, Nelson L. S. da Fonsecacs.MA2026-10-15
#457A Responsibility-Centered Coordination Mechanism for Decentralized Multi-Agent SystemsThi-Nhung Nguyen, Viet-Thanh Pham, Linhao Luo +2cs.MA2026-10-15
#458The Delegation Dilemma: Economies of Scale, Accountability, and Polycentric GovernanceArin Mukhopadhyay, Aris Filos-Ratsikas, Panayiotis Danassiscs.MA2026-10-15
#459Agentic-Priors: Using Large Language Models to Address the Cold Start Problem in Preference ElicitationBruno Arcanjo, Zhaoxing Li, Sebastian Steincs.MA2026-10-15
#460Learning Self-Orchestration in Decentralized Agent SwarmsGuowei Xu, Zhenting Qi, Amani Kiruga +2cs.MA2026-10-15
#461PriorityFEC: Deadline-Aware Streaming FEC for KV-Cache Handoff in Edge Multi-Agent SystemsHan Shen, Qifu Tyler Sun, Fanyang Meng +2cs.NI2026-10-15
#462Decoding What iOS Location Services Send to Apple: An LLM Is an Unreliable Analyst but a Useful ToolmakerDouglas Leithcs.NI2026-10-15
#463LICOA: Learning Instruction-Conditioned Optical Actions for Mobile Spatial Augmented RealityYuchen Deng, Shunkai Zhou, Ruixuan Zhu +2cs.RO2026-10-15
#464LTM: Latent Transition Based In-Context Memory for Vision-Language-Action ModelsQixin Sun, WenLong Gao, Xiansheng Chen +3cs.RO2026-10-15
#465Policy-Aligned Predictive Verification for Adaptive VLA Action-Chunk ExecutionMinkyu Kim, Junhoo Lee, Seungyeon Kim +4cs.RO2026-10-15
#466X-Fly: Learning to Reach and Stop in Full-Chunk Aerial Vision-Language NavigationRuibin Ju, Ruifeng Cai, Min Xu +1cs.RO2026-10-15
#467CarryOn: A Dual-Loop Harness for Personalized and Reliable Robot AssistanceZixuan Wang, Yuqi Liu, Yuxin Chen +7cs.RO2026-10-15
#468AVALON: Zero-Shot Indoor Navigation with Human-Seeded Topological MemoryJing Xia, Changyan Li, Yuduo Wang +5cs.RO2026-10-15
#469Training-Free Target-Aware Refinement of 3D Gaussian Language MapSibaek Lee, Kyeongsu Kang, Seongbo Ha +9cs.RO2026-10-15
#470Cross-Embodiment Causal Transfer from Human Videos to Robot ManipulationXingyu Zhang, Yingchao Li, Peizheng Guo +3cs.RO2026-10-15
#471GRID-Planner: Graph-Structured Relational Reward Shaping for Diffusion PlanningZhao Yang, Zezhong Qian, Yinan Shi +2cs.RO2026-10-15
#472DemoStream: Batched Task-and-Motion-Plan Optimization for Automated Learning from DemonstrationCaelan Garrett, Neel Jawale, Fabio Ramoscs.RO2026-10-15
#473REKI: Registering Knowledge in VLAsJuliette Marrie, Paul Pacaud, Adrien Ramanana Rahary +2cs.RO2026-10-15
#474Whole-Body DexterityConor Mc Gartoll, An Dang, Pranay Thangeda +5cs.RO2026-10-15
#475Asking Smarter Questions: Targeted Active Preference Learning for Underspecified RewardsHelena Merker, Nick Walker, Andreea Bobucs.RO2026-10-15
#476Dexterity from Supervised PlayBotao He, Yiming Dou, Yiannis Aloimonos +3cs.RO2026-10-15
#477CoDA: Co-Evolution of Data Engines and Action PoliciesTianjiao Yu, Zhilin Ou, Yifan Shen +5cs.RO2026-10-15
#478T2-z: Test-Time Optimization of Environment Latents for Robotic World ModelsChenyuan Zhou, Yining Hong, Huang Huang +9cs.RO2026-10-15
#479LIBERO-PeRM: Benchmarking Personalized Robotic ManipulationZhixu Li, Keqian Tang, Litian Gong +7cs.RO2026-10-15
#480DuET: Note-Frame Dual Encoding for Piano Performance-to-Score TranscriptionWei Zeng, Ye Wangcs.SD2026-10-15
#481Qwen-Audio-Jev: A Unified Interface for Audio DecisionsYing Fang, Zhifu Gao, Qing Gu +5cs.SD2026-10-15
#482CF-AVSS: A Coarse-to-Fine Audio-Visual Speech Separation Framework with Target-Speaker Refinement and Post-Fusion for Real-World AVSE ChallengeLongjie Luo, Zhongshu Hou, Yuepeng Li +3cs.SD2026-10-15
#483Backward Compatibility in Zero-Bit Neural Audio WatermarkingAdmir Krnić, Kosta Pavlović, Petar Nedić +3cs.SD2026-10-15
#484Poison Valleys: Diagnosing Path-Dependent Failure in LLM Code RepairVeljko Skarichcs.SE2026-10-15
#485CodeHealth Predicts the Token Cost of Agentic Code Review: A Pre-Registered Study of 465 Agent-Authored Pull RequestsLo Gullstrand Heander, Markus Borg, Emma Söderberg +1cs.SE2026-10-15
#486Stateful Testing for Deep Learning CompilersJiatao Ge, Ruixiang Qian, Yibo Hu +5cs.SE2026-10-15
#487WEAVE: Weaving Real-World Code Evolution into Dependency-Structured Tasks for Benchmarking and Training Code AgentsWeihao Li, Zihang Xu, Zhongqiu Wang +7cs.SE2026-10-15
#488Full-Duplex Interaction with Speech, Expressions and GesturesSiyin Wang, Wenyi Yu, Terumi Chiba +5eess.AS2026-10-15
#489Hierarchical Interpretable Multitask Audio Representation Learning: An Analysis of Event-Scene Relationships through the Information BottleneckClaudia Montero-Ramírez, Alba Martínez-Serrano, Carmen Peláez-Morenoeess.AS2026-10-15
#490Monotone Piecewise-Linear Harmonization of Multitemporal Multispectral Surface Reflectance With Unsupervised Deep Multiview Pseudoinvariant Features LearningLino Garda Denaro, Chia-Hsiang Lineess.IV2026-10-15
#491Denoising Textures is a Different Ballgame Altogether!Saptarshi Mandal, Oindrila Haldar, Chirayata Bhattacharya +4eess.IV2026-10-15
#492Deep Learning of Topological Equivalence ClassesLinden Disney-Hogg, Max Zuevmath.AG2026-10-15
#493Adaptive Randomized Neural Networks for PDEs: Structure-Aware Feature Redistribution and Residual-Driven Block EnrichmentYou Yang, Fei Wangmath.NA2026-10-15
#494When is a better LLM worth paying for? Stochastic Optimization with Switching Mixed-Fidelity OraclesSwati Gupta, Tianjiao Limath.OC2026-10-15
#495Two Sample Sizes in Test-Time LLM Ensembling: Buffered ERM and Minimax TheoryZhi Zhang, Arash A. Aminimath.ST2026-10-15
#496Documenting Trofinetide Treatment Phenotypes in Rett Syndrome with a Dual-LLM Consensus PipelineDaniel Palacios, Guantong Qi, Mikael Guzman Karlsson +6q-bio.QM2026-10-15
#497When Does "Post-Call" Begin? An Availability Contract for Earnings-Call NLP BenchmarksXiaoyu Ma, Kelvin J. L. Koa, Yuncong Liu +1q-fin.CP2026-10-15
#498When do quantum views help? Complementary classical-quantum representations in multi-view fusionAzadeh Alavi, Fatemeh Kouchmeshki, Hossein Akhoundi +3quant-ph2026-10-15
#499Reducing the Cost of Qudit State Preparation by Learning a Sparse Structure for SNAP GatesMarco Pennazio, Leonardo Ignazio Pagliochini, Riccardo Pellini +2quant-ph2026-10-15
#500Same Spectrum, Harder First-Order Training: Phase-Locking in Single- versus Multi-Qubit Re-Uploading CircuitsMichael Poppel, David Bucher, Maximilian Zorn +5quant-ph2026-10-15
#501Discovering state-of-the-art quantum circuits with large language modelsAndi Gu, Alek H. Kemeny, Susanne F. Yelin +1quant-ph2026-10-15
#502Pathwise Shrinkage and Probabilistic Calibration of the Multiplicative Half-Cauchy ProcessSiddhesh Kulkarnistat.ME2026-10-15
#503Efficient Agnostic Learning of Univariate Densities Under Local Differential PrivacyMohammad Afzali, Hassan Ashtiani, Sivan Sabatostat.ML2026-10-15
#504Score Mismatch and Set-Constrained Sampling in Zero-Shot Conditional Discrete DiffusionRenxiang Huang, Yuchen Liang, Yingbin Liang +2stat.ML2026-10-15
#505Dimension-Free PAC-Bayes Generalization for Deep Neural Networks via Dirichlet ProcessesSumit Vashishthastat.ML2026-10-15
#506When Is Muon Optimal? Radial Fragility and Minimax GeometryAo Xustat.ML2026-10-15
#507Conditional Mean Flows: Few-Step Densities for Simulation-Based InferenceJonas Arruda, Jan Hasenauer, Stefan T. Radevstat.ML2026-10-15
#508Robust Covariance Estimation for Entry-wise Contaminated and Partially Observed Data via Expectation Maximization AlgorithmMatys Savidan, Mohammed Nabil El Korsostat.ML2026-10-15
#509SelectPFN: Amortized Bayesian Variable Selection for Sparse Nonlinear Regression with Prior-Data Fitted NetworksBin Luostat.ML2026-10-15
#510Designing Experiments for External Decision MakersSahel Iqbal, Tom Rainforthstat.ML2026-10-15
#511Rethinking Successive Rejects AlgorithmsMohamed Khair, Junpei Komiyamastat.ML2026-10-15
#512Learning Changes the World and Then What Was Learned has Changed: Training and Deploying Neural Networks in the Control LoopVittorio Lippistat.ML2026-10-15
#513SurvICL: a Foundation Model for in-context Survival AnalysisJulie Alberge, Linus Bleistein, Judith Abécassis +3stat.ML2026-10-15

latest · trends · arXiv announcement batches follow US Eastern weekdays