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

New Papers · 2026-10-19 637 submissions

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

#TitleAuthorsCatDate
1Ammonia-Hydrogen Phase Equilibria in Planetary Envelopes from First-Principles-Based Machine-Learning Molecular DynamicsAkash Gupta, Austin Guo, Jie Dengastro-ph.EP2026-10-19
2Graph Neural Networks for Astrophysics and CosmologyChristian Kragh Jespersenastro-ph.IM2026-10-19
3The Forward/Inverse Duality of Controlled Emergence:A Computational Design Program from Explanation to EngineeringHao Li, Minghui Ren, Shaowen Lucs.AI2026-10-19
#4Think, Compress, Answer: Reinforcement Learning for Multimodal Grounding via Reasoning CompressionJinbae Seo, Hyeongjun Kwon, Jiyoung Lee +4cs.AI2026-10-19
#5Spherical Fixed-Point Reasoners: Adaptive Loop Halting on the HypersphereArber Zela, Artavazd Maranjyan, Pol Puigdemont +3cs.AI2026-10-19
#6HyperTaxa: Multiscale Genome Representations for Generalized Microbial Taxonomic InferenceAkash Rao, Sushim Gupta, Vishalini Ramnath +2cs.AI2026-10-19
#7LIRQuant: An Efficient Locally Isolated Rotation Quantization Method for Large Language ModelsDesheng Xu, Hanglin Li, Tianchen Song +2cs.AI2026-10-19
#8Neither Over- nor Under-Constrained: Evaluating LLM Personalization under a Constraint Qualification AuditXuran Li, Guanqin Zhang, Imran Razzak +4cs.AI2026-10-19
#9BitFlat: Error-Localized Bitstream Design for Robust Diffusion Image CompressionXinfeng Deng, Li Zhou, Haitao Chen +5cs.AI2026-10-19
#10When Safety Fails Collectively: Robust Alignment Against Harmful Fine-Tuning via Joint Weight PerturbationsZhiyuan Wang, Yuezhi Zhou, Zhu Zhang +1cs.AI2026-10-19
#11ToolOPD: Credit-Aware On-Policy Distillation for Tool-Use AgentsChu Zhao, Lei Tang, Yanming Wang +5cs.AI2026-10-19
#12CVaR-RMD: CVaR Selection Pressure for Robust Metaheuristic DiscoveryRuodai Cui, Li Niucs.AI2026-10-19
#13From Black Box to Controller: Inference-Time Steering of LLM via Feature AmplificationKeqi Chen, Zekai Sun, Yuhua Wen +5cs.AI2026-10-19
#14Whose Credential Is It? How Owner Attribution in Agent MemoryShapes Cross-User Account MisuseHau-Sing So, Daixian Liu, Carl Hou +3cs.AI2026-10-19
#15PFedQFT: Personalized Federated Quantum-Inspired Fine-Tuning for Medical Large Language ModelsQihan Huang, Lingxia Zhang, Guye Zhang +2cs.AI2026-10-19
#16Fine-Grained Units, Flat Decisions: Hierarchical Micro-Expert Pruning for Mixture-of-Experts ModelsZukang Xu, Xinpei Gao, Xing Hu +2cs.AI2026-10-19
#17TimelineAgent: An LLM-based Framework for Query-Centric Event Timeline Extraction Across Multiple DocumentsQingkai Min, Yunxin Bao, Yifeng Lu +4cs.AI2026-10-19
#18ActTime: Action-Conditioned World Modeling for Time SeriesXinxing Zhou, Xiaojie Yuan, Yanlong Wen +1cs.AI2026-10-19
#19TRACE: Tracking Multimodal Clinical Trajectories for Inpatient Risk PredictionMinjun Kim, Jong Hak Mooncs.AI2026-10-19
#20EvalRx: Agentic Diagnosis and Verified Repair of Foundation ModelsJiaqi Liu, Ruinan Jin, Yitong Tang +4cs.AI2026-10-19
#21From Trace to Fix: Residual Task State in Long-Horizon AgentsZile Huang, Ser-nam Limcs.AI2026-10-19
#22Standing on the Shoulders of Giants: Enhancing LLM Agents for Automated Fact-Checking with Human Expert SkillsXinwen Chen, Haorui He, Yupeng Lics.AI2026-10-19
#23OpenSaC: A Python Library for Search as Code in Deep Research AgentsQi Liu, Jiaxin Mao, Fengbin Zhu +2cs.AI2026-10-19
#24Can LLM User-Proxies Stand In for Humans in Reliance Measurement? Replicating Rel-A.I. with Simulated UsersShuai Wang, Rui Hucs.AI2026-10-19
#25SAR: Learning Global Item-Space Matching and Geometry-Aware Placement Ranking for Buffered Online 3D Bin PackingXinpeng Lei, Jin Zhang, Yizhe Yang +2cs.AI2026-10-19
#26When to Stop Asking: Factor Coverage Bias and LLM Determinability Judgments with Underspecified Information in MedicineYusuke Watanabe, Yohei Kobashi, Taisei Tosaki +4cs.AI2026-10-19
#27When Retrieval Partially Conflicts with Skills: Understanding Procedural Hallucination in Language ModelsGuanqun Jiang, Pengfei Cao, Kang Liu +1cs.AI2026-10-19
#28FrontierRefactor: Benchmarking Multi-Scale Performance-Oriented Codebase RefactoringShijian Wang, Fanqing Meng, Jiajun Chen +8cs.AI2026-10-19
#29Not Every Rollout Needs Distillation: Correctness-Filtered On-Policy Self-DistillationHarrison Zhao, Lei Huang, Fei Liu +2cs.AI2026-10-19
#30A Cue's Hidden Price: Auditing Seller Influence on AI ShoppersFelix Buecheler, Gerardo Berbeglia, Mingyu Guocs.AI2026-10-19
#31MASIF: Implicit Failures for Process Observability in Multi-Agent SystemsYanwei Huang, Arpit Narechania, Atanu Sinhacs.AI2026-10-19
#32Are Self-Evolving Agents Continual Learners?Xiaoyin Chen, Yizheng Huang, Yinglun Xu +4cs.AI2026-10-19
#33Minimum-Cost Robust Evidence Certificates for Horn Reasoning under Correlated Source FailuresYukun Yangcs.AI2026-10-19
#34Benefit-Targeted Routing and Bounded Revision for LLM-Based Evidence Screening in Manufacturing Supplier DiscoveryYijiashun Qi, Hanzhe Guo, Yuxuan Lics.AI2026-10-19
#35CODA: Cohort- and Drift-aware Foundation Model for Multimodal Clinical ReasoningChangshuo Liu, Jiaqi Zhu, Wenqiao Zhang +2cs.AI2026-10-19
#36Motor compound fault diagnosis using an attention-based cross-talk architectureWonjun Yi, Wonho Jung, Junho Kim +2cs.AI2026-10-19
#37When Should AI Chime In? Benchmarking Timely Contribution of Proactive Agents in Multi-Party ChatRuotong Wang, Brian S. Yu, Xinyi Zhou +5cs.AI2026-10-19
#38TESS: LLM-guided Translation, Exploration, Simulation, and Search for Embodied Task PlanningPeiran Xu, Yixiang Yang, Jinghan Li +4cs.AI2026-10-19
#39EvoSkill v2: Fully Agentic Skill Evolution from Benchmark Adaptation to a Stateful EvolverDastin Huang, Baran Nama, Salaheddin Alzubics.AI2026-10-19
#40Global probabilistic forecasting of air pollutionAmmar Kheder, Michael Boy, Zhi-song Liucs.AI2026-10-19
#41Claim Laundering: When Agent Decision Models Trust Records Over RealityTina Khezresmaeilzadeh, Seyedarmin Azizi, Erfan Baghaei Potraghloo +2cs.AI2026-10-19
#42OrderGPT: Generation Order as a Learnable Modeling ChoiceChenhe Yang, Yuhuan Lyu, Tianyang Hucs.AI2026-10-19
#43CXBench: A Benchmark for Process-Compliant LLM Agents in Regulated Customer-Experience WorkflowsBoxi Yu, Yuzhong Zhang, Zhenfeng Su +7cs.AI2026-10-19
#44Productive State-Space Exploration for Multi-turn RL in LLM AgentsMohammed Haroon Dupty, Yong Liang Goh, Song Guo +1cs.AI2026-10-19
#45EmbodiedWorld-200K: Toward Embodied World Agents via Embodied-Planning Dataset and Interactive World ModelsX. Feng, J. Tang, Z. Lin +4cs.AI2026-10-19
#46ABACUS: Program-Guided Multistep Reasoning over Frozen Judgment ModelsYuhao Wang, Zelin Zangcs.AI2026-10-19
#47GLOBE: Geometry-Led Online Behavioral Early Exit via Unit-Sphere TrajectoriesXinyue Peng, Zhenlin Liang, Meng Cai +1cs.AI2026-10-19
#48On the Benefits of Uncertainty Estimation for Species Classification: A Case Study on Optimizing Expert re-AnnotationKamenan N'Gadi, Martin Laviale, C{é}dric Pradalier +1cs.AI2026-10-19
#49GraphEvoResearcher: Graph-Aware Training-Free Self-Reflective Reasoning for Cost-Bounded Multi-Hop Question AnsweringSuxing Liucs.AI2026-10-19
#50ClueFlow: Learning Long-Horizon Search through Attributed Research-State TransitionsYicheng Wang, Wentao Tan, Yidan Huang +2cs.AI2026-10-19
#51Map-Distribution Mixture-of-Experts for Multi-Agent PathfindingFumimaro Suzuki, Keisuke Okumuracs.AI2026-10-19
#52Procedural Memory for Language Agents: A Neurosymbolic Perspective on Explicit Goal StructureJonathan Leung, Zhiqi Shen, Deheng Yecs.AI2026-10-19
#53TimesJev: Thinking Fast on Time Series with System 1 SufficiencyChenghao Liu, Wei Fan, Jindong Han +4cs.AI2026-10-19
#54Understanding When Reflective Prompt and Skill Optimization Helps on Locally Served Reasoning Models: A Two-Model Study of GEPA and SkillOptAndrea Giummarra, Carmelo Baglieri, Antonio Di Maria +3cs.AI2026-10-19
#55SPEM: Structure-Aware Procedural Memory for Efficient Skill Use in LLM AgentsRan Zhou, Zehui Kong, Fanyu Lin +3cs.AI2026-10-19
#56AuDQ: Auditable Data Quality through Agentic Rule DiscoveryJacopo Biggiogera, Nicolas Colombo, Krati Saxena +2cs.AI2026-10-19
#57Decision4Rec: A Jev-Inspired Framework of Decision Models on Knowledge and Active Graphs for Multi-Agent Recommender SystemsMarco Polignano, Het Darshan Mehta, Pasquale Lops +2cs.AI2026-10-19
#58FinSafeGuard: A Quality-Driven Synthetic Dataset for Financial AI SafetyJoseph Thomas Thacil, Reetu Raj Harsh, Krati Saxena +2cs.AI2026-10-19
#59CUA-Lite: An Open Platform for Computer Use AgentsZhanhui Zhou, Weichen Zhang, Haoran Liu +6cs.AI2026-10-19
#60From Code to Playable Systems: CEGame-Bench for Long-Horizon Game Creation AgentsZixuan Dong, Yanghai Wang, Hanyan Bian +8cs.AI2026-10-19
#61Reliable Before Profitable: QuantHarness for Governing Financial Strategy Development with LLM AgentsJiasheng Mao, Jiacheng Liu, Hengwei Ye +1cs.AI2026-10-19
#62MoveBench: A Rubric-Based Benchmark for Evaluating Large Language Models in Sports and Health CoachingYitong Li, Jiang Bian, Jingling Wang +2cs.AI2026-10-19
#63On Counting Graphs for Modal Logic with CountingAvijeet Ghosh, François Schwarzentrubercs.AI2026-10-19
#64LLMs Prompted for Legal Context Refuse More: Overrefusal from Small On-Premises LLMs in Criminal Legal ContextAnastasiia Kucherenko, Francois Brouchoud, Dimitri Percia David +1cs.AI2026-10-19
#65Fairness or Fallacy? Mapping the Landscape of AI Bias in Disease DetectionGhulam Mudassir, Hameed Ullah Khan, Ahmad Sami Al-Shamayleh +4cs.AI2026-10-19
#66Towards More Granular Reasoning: Mapping the DSA Transparency Database Taxonomy to Platform Terms and Conditions Using Large Language ModelsAlyson Ranucci, Eline Leijten, David Grauscs.AI2026-10-19
#67CoRS: Fast Neural Flexible Job-Shop Scheduling via Composite Interval State ReuseJiang Sutong, Zhao Peng, Wu Xuan +6cs.AI2026-10-19
#68Machina Pauliana: A neuro-symbolic approach to the actio pauliana in Dutch insolvency lawDaan Boven, Gregor Behnke, David Grauscs.AI2026-10-19
#69Beyond Static Leaderboards: Capability-Focused Evaluation with Structural Diversity for Time Series Foundation ModelsHongyin Zhang, Mingyi Xiang, Rongzhao Chen +7cs.AI2026-10-19
#70LOCU: Lowdin-Orthogonalized Constraint Updates for Multi-Constraint Policy OptimizationJoonyoung Lim, Younghwan Yoocs.AI2026-10-19
#71REFLEX: RNA Ensemble Generation via Flexibility-Calibrated Stochastic BridgeWanli Ma, Tianmeng Hu, Ke Lics.AI2026-10-19
#72The Scheduler Is a Hidden Retriever: How Asynchrony Shapes Evidence Acquisition in Search AgentsRuiyang Ren, Yuhao Wang, Yinan Zhang +1cs.AI2026-10-19
#73Selective Transfer through Sequence Distillation: From Benchmark Knowledge to Backdoor BehaviourJonibek Mansurov, Sholpan Bolatzhanova, Filbert Aurelian Tjiaranta +2cs.AI2026-10-19
#74StrucChunk: Structure-Aware Retrieval for Legal Document RAGSurya Deep Singh, Ashutosh Tripathi, Gaurav Deep Singhcs.AI2026-10-19
#75The Control Layer Behind Rule-Following Agents Trading Across Market ConditionsSaad Naja, Nasser Odtallah, Jake Van-Praag +1cs.AI2026-10-19
#76A Generic On-Board AI Processing Chain for Earth Observation: From Application Development to Embedded Deployment and Mission-Level OrchestrationMichel-Fran{\c c}ois Foulon, Liz Ramos Medina, Thomas Goudemant +5cs.AI2026-10-19
#77VibeTraining-Bench: Data-Trainer-Harness Co-Design for Iterative System ImprovementRuotian Peng, Yuanyi Ren, Shuaiqi Liu +7cs.AI2026-10-19
#78CARRS: A Constraint-Aware, Real-Time Routing System for Emergency Vehicles in Urban EnvironmentsVincent Sello, Timothy Adeliyi, Ridewaan Hanslocs.AI2026-10-19
#79GAIDA: Generative AI for Human-in-the-Loop Document AnnotationIslam Mesabah, Ali Elhosary, Priyabanta Sandulu +2cs.AI2026-10-19
#80Autonomous intelligence for mining productivity: a multi-agent AI approach to operational value creationN Guerin, A Dehoux, M Nakhlacs.AI2026-10-19
#81BOSS: Token-Budgeted Online Sampling and Selection for LLM ReasoningYupeng Chang, Yahan Li, Chenlu Guo +3cs.AI2026-10-19
#82Answer Delivery Under a Shared Token Budget: An Audited Study of Stopping and FinalizationYupeng Chang, Linyuan Gao, Zhiyuan Li +2cs.AI2026-10-19
#83Local data augmentation for imbalanced binary classificationHarold Gu{é}neau, Alain Celisse, Pascal Delangecs.AI2026-10-19
#84Physiology-Aware Graph Attention for Early Ventricular Reentry PredictionMa{ë}lis Morier, Jairo Rodr{í}guez Padilla, Patrick Gallinari +1cs.AI2026-10-19
#85Remembering Has a Price: Learning Memory Worth under Resource ConstraintsGuannan Lai, Zi-Yang Bai, Jun-Peng Jiang +1cs.AI2026-10-19
#86VeriCUA: Learning Proactive Verification for Reliable GUI Agent RewardsZhizhou Wang, Yaxi Lu, Zhong Zhang +4cs.AI2026-10-19
#87ScopeMem: Latent Memory That Learns Where to Revise Frozen GUI AgentsZhicheng Zheng, Cheng Zhang, Shengping Yu +1cs.AI2026-10-19
#88RouterWorld: Scaling Conversational AI with Latency-Aware LLM RoutingJinyang Li, Denis Emelin, Simone Tedeschi +6cs.AI2026-10-19
#89Toward Structured Financial Foundation ModelsNatraj Raman, Saumitra Mishra, Vamsi Potluru +1cs.AI2026-10-19
#90Beyond Behavioral Accuracy: Evaluating Individual-Level Fidelity in LLM Investor SimulationJiajie He, Yuanhong Jiang, Xintong Chen +2cs.AI2026-10-19
#91A Semantic Knowledge Graph Construction Pipeline for Vehicle Intention Prediction in nuScenesKhaled Nowara, Mohamed Manzour, Catherine Eliascs.AI2026-10-19
#92Breaking Diffusion: Parallel Reasoning with Draft RefinementJaesang Yu, Seoyeon Byun, Yun Wang +2cs.AI2026-10-19
#93Does Multi-Agent Collaboration Reduce Hallucination in Clinical Tasks?Won Seok Jang, Harry Bhaskar Joshi, Hong Yucs.AI2026-10-19
#94Agentic Orchestration of EDC Data Space Retrieval and Natural Language Driven Data ProcessingMarla Grunewald, Fin Gentzen, Iulisloi Zacarias +1cs.AI2026-10-19
#95Training Natural Schemers: RL Can Amplify Oversight-Conditional BehaviorBart Jaworski, Nathaniel Mitrani, Fred Bruford +1cs.AI2026-10-19
#96BetaMem: Learning to Remember a Changing World for Embodied AgentsMai Liu, He Sun, Siru Zhong +5cs.AI2026-10-19
#97Reward Objectives for Robust (PO)MDPs: A Law-Preserving Equivalence with (Partially Observable) GamesDurgam Latha, Dion Reji, Dorde Zikelic +1cs.AI2026-10-19
#98WhatIf-Bench: Benchmarking Intervention-Aware Time Series ForecastingArjun Ashok, Mihir Parmar, Palash Goyal +6cs.AI2026-10-19
#99Teaching AI Agent to Play Poker Strategically Through Preference OptimizationPhurinat Polasa, Thanapon Thanadunpremdet, Phatthanasak Kraiduang +1cs.AI2026-10-19
#100When the harness decides success: state that cannot be re-observedRaimondas Lenceviciuscs.AI2026-10-19
#101Revision-Based Learning from Interactive Experience and FeedbackJiawen Li, Chenming Ge, Alice Gao +3cs.AI2026-10-19
#102From Outcomes to Components: A Counterfactual Evaluation Framework for LLM-Proposed RepairsHengyu Ye, Songhua Hucs.AI2026-10-19
#103Tandem: Serving Hybrid Linear-Attention GUI Agents on Mobile NPUsZhuomin Chen, Jingchao Ni, Xu Zheng +4cs.AI2026-10-19
#104AllPath: Layered Verification for a Deployed, Self-Revising LLM Trading Agent under Human-Gated and Autonomous RegimesTian Zhang, Meng Lics.AI2026-10-19
#105Honeypots for AI Agent Insider ThreatsJan Wehner, Jam Kraprayooncs.AI2026-10-19
#106StepBench: Diagnosing Real-World Procedural Understanding in AI AgentsHossein A. Rahmani, Bin Wu, Chaeeun Lee +6cs.AI2026-10-19
#107M-Plan: Comprehensive Planning For LLM Agents with Memory ArrangementZiyang Liu, Jiakang Yuan, Jiayuan Fan +1cs.AI2026-10-19
#108Towards Robust Model Organisms for Eliciting Latent KnowledgeLennart Finke, Hardik Bhatnagar, Euodia Dodd +4cs.AI2026-10-19
#109LG-Bench: A Graph-Structured Evaluation Benchmark for Life SciencesLu Sun, Xiangyi Zhang, Xiangyang Zhu +6cs.AI2026-10-19
#110SOMA: Continuous Monitoring and Intervention for System Two Reasoning with System One ModelsRuizhi Qian, Lei Shi, Tianyu Hu +3cs.AI2026-10-19
#111Physical AI: Concepts, Techniques, and ChallengesWeinan Zhang, Chunhua Shen, Tianfan Xue +49cs.AI2026-10-19
#112ReuF2F: Benchmarking Coding Agents on Formalized Undergraduate Research ProblemsZeyu Zheng, Yiyang Liu, Yuyang Zhao +20cs.AI2026-10-19
#113Agent World Model in the Wild: Computer-Use Agent Environment SynthesisZhaoyang Wang, Qianhui Wu, Haorui Wang +9cs.AI2026-10-19
#114ProteinGeoBench: Frontier Structural-Biology Agents Are Fluent at Lookup but Lost in GeometryMatt Turk, Brandon L. Neel, Diana M. Lopez +3cs.AI2026-10-19
#115Same Simulation, Different Evidence: Where Retrieved Tool Output Costs LLM Agents AccuracyKe Zhang, Sahchit Chundur, Jerry Peprah Owusu +2cs.AI2026-10-19
#116AnyGoal: On World Model Generalization Beyond Expert RolloutsHeejeong Nam, Divyat Mahajan, Quentin Le Lidec +2cs.AI2026-10-19
#117Train An Imaginative AgentJiaxin Ge, Junyi Zhang, Tianning Chai +9cs.AI2026-10-19
#118A general-purpose System One decision model for clinical recordsAndrew Zhang, Trinh T. L. Vuong, Sophia J. Wagner +14cs.AI2026-10-19
#119Omni-Woodpecker: Hallucination Correction via Evidence-Prior Rebalancing for Omni LLMsZijian Liu, Chaoyou Fu, Yan Yang +2cs.AI2026-10-19
#120PROVISO: Provenance-Informed Action Selection for Secure LLM AgentsBo Yan, Qi Zhang, Ziwen Kan +2cs.AI2026-10-19
#121PORA: Learning When More Reasoning Pays Off for LLM AgentsBo Yan, Qi Zhang, Zhen Tan +2cs.AI2026-10-19
#122EDMA: Entropy-Driven Multimodal AnsweringEmanuele Mezzi, Gertjan Burghouts, Fabio Massacci +1cs.AI2026-10-19
#123MoSAIK: Motion Search with Artificial Intelligence in K-spaceOscar Dabrowski, Abijith Jagannath, Frédéric Grouiller +1cs.AI2026-10-19
#124Learned Control Variates for Rare Grid-Outage Estimation at Electric Vehicle Charging StationsSulyman Iyanda, Mansur Ariefcs.AI2026-10-19
#125LSA-PAST: Layer-Specific Adaptation and Prototype Transport for Compositional Incremental LearningKyle Stein, Andrew Arash Mahyari, Guillermo Francia +2cs.AI2026-10-19
#126Sparse RL Relaxation for LLM ReasoningJiabin Fan, Matthias Lindemann, Zita Marinho +2cs.AI2026-10-19
#127Magnolia: A Persistent-Memory Agent Framework for Computational ChemistryTao Jiang, Benjamin Navet, Yousouf Taghzouti +3cs.AI2026-10-19
#128EGI-BENCH: An Enterprise General Intelligence Benchmark SuiteZhiwei Liu, Zhujun Lan, Jielin Qiu +12cs.AI2026-10-19
#129TxnQA: Benchmarking Analytical Reasoning and Evidence Grounding over Transaction Event SequencesRabimba Karanjai, Yiming Bian, Yun-Shiuan Chuang +9cs.AI2026-10-19
#130A latent control model for realistic rodent motionAidan Sirbu, Charles Y. Zhang, Yuanjia Yang +3cs.AI2026-10-19
#131TEX: Test-Time Scaling Testing Agents via Execution-based Cross-ValidationAkash Gokul, Srijan Bansal, Yingbo Zhou +1cs.AI2026-10-19
#132Vulnerability Analysis for Safe Multi-Agent ReinforcementTaozheng Zhu, Shixiong Jiang, Fanxin Kongcs.AI2026-10-19
#133Stronger artificial intelligence breakthroughs hasten their own exhaustionBeichen Lu, Honglin Bao, Qi Huang +2cs.AI2026-10-19
#134When Does an Added Planning Capability Create Operational Value? An Observable Evidence StandardYihua Xu, Yan Lyu, Jize Li +4cs.AI2026-10-19
#135Evolving Self-tuning Benchmarks for Long-Horizon Tool UseHyunji Alex Nam, Michael Dennis, Natasha Jaques +1cs.AI2026-10-19
#136Unsupervised Tool Evolution for Coding Agents in Data-Lake AnalyticsYuqing Yang, Yurong Liu, Deqing Fu +5cs.AI2026-10-19
#137Modeling Authentic Research Trajectories: A Graph View of Research IdeationRuochen Li, Zhiyu Chencs.AI2026-10-19
#138An LLM-Based Agent for Legal Compliance Assessment: Architecture, Memory, and Evaluation in a Canadian and Quebec ContextSoukaina Alaoui Ismaili, Jean-Sebastien Dessureaultcs.AI2026-10-19
#139A Small Model Asks Better: Fine-Tuning Query Clarification for Retrieval-Augmented GenerationLihong He, Lucian Popa, Marina Danilevskycs.AI2026-10-19
#140REM: What to Store, When to Recall, What to Forget in Experience Memory for Coding AgentsXinyi Lisa Chen, Pedro Herrero-Vidal, Xiaohan Chen +6cs.AI2026-10-19
#141Correcting Attribution Patching with a Few Exact MeasurementsLuyang Zhang, Minxing Zheng, Jialu Wangcs.AI2026-10-19
#142When PTQ Calibration Helps or Hurts: Dose-Driven Collapse and Validation-Gated Abstention in Quantized Text EmbeddersHyojung Han, Ryangkyung Kang, Youngeun Kim +1cs.AI2026-10-19
#143Unified Sharp Bounds on Probabilities of CausationXin Shu, Ang Lics.AI2026-10-19
#144ProMemAgent: Long-Horizon Proactive Assistance with Context-Aware Prospective Memory from Sensory PerceptionsLilin Xu, Linyang He, Kaiyuan Hou +4cs.AI2026-10-19
#145More Memory, Worse Agents: Error Reproduction and Anti-Persistence in LLM AgentsRuhan Wang, Kishan Panaganti, Dongruo Zhoucs.AI2026-10-19
#1463D-MoE: Complementarity-Guided Hardware-Software Co-Design for MoE Decode on 3D-Stacked NMPYudong Pan, Lian Liu, Shixin Zhao +8cs.AR2026-10-19
#147VHDLBench: Benchmarking and Fine-Tuning Large Language Models for VHDL-Based Chip DesignPatrik Drazic, Benaoumeur Senouci, Boualem Benatallahcs.AR2026-10-19
#148Injection of Space Radiation Errors on Low-power NVM using Generative Deep LearningEleonora Giudici, Antonio Miele, Luca Mottolacs.AR2026-10-19
#149Internalizing Chain-of-thought into Looped TransformersKehang Zhou, Pinyan Lucs.CC2026-10-19
#150Cognitive Map in Large Language ModelsAlbert Qin, Jonathan Cohen, Gautam Reddycs.CL2026-10-19
#151MapSteal: Map-based Autonomous Knowledge Stealing Attack Against Large Language ModelsZhengao Li, Chuxu Zhang, Yushun Dongcs.CL2026-10-19
#152Consistency Training Suppresses Cue Following Without Teaching Cue SelectivityPrakhar Gupta, Terry Jingchen Zhang, Zhijing Jincs.CL2026-10-19
#153Inside the Scorer: Mechanistic Evidence on Rubric Control in LLM-Based Automated Essay Scoring from 25 Base ModelsChungche Huang, Po-Ya Angela Wang, Shu-Kai Hsiehcs.CL2026-10-19
#154No Matter Who You Are: Addressivity and Sycophancy in Large Language ModelsSeungjong Sun, Hyunmin Jun, Minsik Yoon +4cs.CL2026-10-19
#155Does Unlearning Survive Collaboration? Robust Unlearning for Shared-Model LLM TeamsHengsong Liu, Liangyu Teng, Jingnan Cai +5cs.CL2026-10-19
#156A Calibrated Instrument for Detecting Disposition Drift in Language ModelsJerry Kaplancs.CL2026-10-19
#157Truncated Reasoning Under a Budget: Evaluating System-1 Models as Decision-makersZhongyin Wang, Zhaoqian Xue, Junting Mu +4cs.CL2026-10-19
#158CoMem: Learning to Anticipate Failures from Retrieved ExperienceYun Shen, Ming Shen, Tianjun Yaocs.CL2026-10-19
#159Think Before You Transcribe: Context-Steered Reasoning for Hotword-Aware Speech RecognitionQihao Wang, Hang Su, Fan Cui +3cs.CL2026-10-19
#160Modal Sense Disambiguation in Language Models: The Role of Context, Training Domain, and Input FrequencyEzgi Başar, Yevgen Matusevych, Annemarie van Dooren +1cs.CL2026-10-19
#161Diffusion Language Models Change Speed Across Tasks and LanguagesMohsen Fayyaz, Ali Modarressi, Daniel Israel +2cs.CL2026-10-19
#162Where RL Breaks: Localizing and Repairing Failures via Targeted Continued PretrainingXinyi Wang, Danqi Chencs.CL2026-10-19
#163Measurement Validity and Representation Dynamics of Confidence Signals in Large Language ModelsDebojeet Ghosh, Shreyansh Kumar, Ayushman Gargcs.CL2026-10-19
#164Arabic Financial NLPMo El-Hajcs.CL2026-10-19
#165Learning to Reason Efficiently with Interventional Step CreditGuanda Li, Xuefeng Bai, Yulong Chen +3cs.CL2026-10-19
#166CALM: Consistency-Aware Logit Masking in Decoding Space for Mitigating Overthinking of Large Reasoning ModelsShengjing Liu, Feiyang Li, Yuxuan Yang +2cs.CL2026-10-19
#167FisherEdit: Fisher Information Guided Knowledge Editing for Large Language ModelsYizhou Yang, Jiahong Fu, Zhiwu Wang +6cs.CL2026-10-19
#168LEAPS: Long-context Evaluation of Adaptive Pattern Learning and State TrackingHoward Yen, Nitya Mani, Alex Renda +1cs.CL2026-10-19
#169MITRA-lexicon: Lexica of attested translations from Sanskrit into English, Tibetan and ChineseSebastian Nehrdich, Kengo Harimoto, Sven Sellmer +1cs.CL2026-10-19
#170Speech LLMs That Breathe: Modeling Non-Verbal Vocalizations in DialogueHeyang Liu, Lixin Zhang, Jiayi Huang +6cs.CL2026-10-19
#171TRACE: Training-aware Robustness and Challenge Evaluation for Text-Vision Embedding ModelsPume Tuchinda, Tinnakit Udsa, Peerat Limkonchotiwatcs.CL2026-10-19
#172AdaExploreBench: Benchmarking LLM Agents for Proactive Exploration and Test-time Adaptation in Evolving EnvironmentsRui Wang, Zishen Lai, Jiayu Liu +15cs.CL2026-10-19
#173How to get the best and fairest performance out of your ASR system using activation steeringFelix Herron, Alex Colagrande, Solange Rossato +3cs.CL2026-10-19
#174TempoMoE: Identifying and Steering Fast-Slow Thinking Experts for Efficient Multimodal ReasoningXiyue Zhang, Keru Zhou, Ziyi Wang +2cs.CL2026-10-19
#175Scaling Synthetic Pre-training Data and Evaluation for Indic LLMsAbhinav Khattar, Aishwarya Chhabra, Ameya Velingker +24cs.CL2026-10-19
#176Accelerated Drift of Scientific Prose in the LLM Era: Evidence from an Interrupted Time-Series AnalysisHanna Hubarava, Benjamin V. Ineichencs.CL2026-10-19
#177Balance-Aware Pivot Selection for Parallel Diffusion LLM DecodingYejin Lee, Hyundong Jin, Yo-Sub Hancs.CL2026-10-19
#178Honeyed Words, Hidden Daggers: Benchmarking and Training LLMs to See Through Mock PolitenessCaixin Kang, Sitong Gong, Tianyu Yan +3cs.CL2026-10-19
#179Evaluating Tibetan Speech Recognition Across Dialects and Adaptation Regimes: A Multi-Granularity AnalysisJacob Moore, Sheng Lics.CL2026-10-19
#180DeepSEA: A Multilingual Evaluation Benchmark for Southeast AsiaJiuzhou Han, Abhishek Bijay Mishra, Trevor Cohn +1cs.CL2026-10-19
#181VISAGENT: An Agent-Based End-to-End Voice Interaction SystemXiang Wang, Zhaoxiang Liu, Xiang Chen +3cs.CL2026-10-19
#182Conditional information Retrieval for Longitudinal Survey HarmonisationWing Yan Li, Zeqiang Wang, Michelle Lin +2cs.CL2026-10-19
#183Reading Time Modeling with Pixel-Based Language ModelsJunlin Li, Sara Alhajeri, Tatsuki Kuribayashics.CL2026-10-19
#184VEILED-SH: Vulnerability Expression through Indirect Language Evaluation Dataset (Self-Harm)Leanne Tan, Keith Chua, Shaun Khoo +7cs.CL2026-10-19
#185Rethinking BPE: Merge Selection as Model SelectionVijini Liyanage, François Yvoncs.CL2026-10-19
#186Heartbeat Thinking: Speculative Reasoning and Tool Execution While Listening in Realtime Voice AgentsZhenyu Zhang, Kewei Fu, Yongqi Tong +4cs.CL2026-10-19
#187Shaping the Document, Not the Model: Optimized Suffixes for Context FollowingGia-Bao Dinh Ho, Sekh Mainul Islam, Masahiro Kaneko +2cs.CL2026-10-19
#188Decomposed Relation Extraction from Aviation Accident Narratives: Evaluating Transformer-Based Safety Knowledge Discovery under Relational SparsityAziida Nanyonga, Mustafa Tahsin Yilmaz, Saad Ezzini +2cs.CL2026-10-19
#189Answering While You Type: Optimizing Time-to-Answer with Streaming GenerationNikita Dragunov, Matvey Mikhalchuk, Anton Razzhigaevcs.CL2026-10-19
#190Large-Scale Biomedical RAG: Corpus Scaling, Document Representation, and Efficiency Trade-offsAdrián Sánchez-Freire, Gonzalo Pérez-Gómez, Aitziber Atutxa +1cs.CL2026-10-19
#191Bridged Self-Distillation for On-Policy LearningRunsheng Chen, Yihong Liu, Raoyuan Zhao +3cs.CL2026-10-19
#192How Benchmark Graph Construction Shapes Multi-Hop KG Navigation: A Controlled Audit of PathQuestion and PathQuestion-LargeEduin E. Hernandez, Sergio A. Diaz, Luis F. Garcia +2cs.CL2026-10-19
#193Expert L2 English Speech Evaluation on a Gaming PC: Accuracy, Fluency, and Prosody with XLS-R, XEUS, and PhoneticXeusRichard Rosecs.CL2026-10-19
#194Co-Evolving Policy and Reward for Code Generation: A Mechanistic Study of Single-Adapter DriftAmarsaikhan Batjargal, Noriko Tomurocs.CL2026-10-19
#195Self-Consistency of Entity Sets and Citations in a Deep Research System under Repeated PromptingLauri Pykälä, Kimmo K. Kaskics.CL2026-10-19
#196Governing the Rule Space. Ruliology, Computational Irreducibility and Anticipatory Governance of Quantum TechnologiesAntonio Felice Uricchio, Francesco Scagliolacs.CL2026-10-19
#197SNO-PI: Label-Scarce SNOMED CT Entity Linking with Pre-trained Encoders and Curated Terminology KnowledgePiyawoot Songsiritatcs.CL2026-10-19
#198HarnessRL: Co-Evolving Policies with a Just-in-Time Training Harness for Open-Ended RLXiaoqiang Wang, Ting-En Lin, Yuchuan Wu +7cs.CL2026-10-19
#199The Geometry of Agent Memory: Forecasting Retrieval-Bound Memory Failures, and Characterizing Its LimitsIliya Zhechev, Radoslav Ralev, Chris Coleman +4cs.CL2026-10-19
#200WenSight-Decision-1 for Direct Decisions under E-commerce RulesMingwen Liu, Jun Sun, Sichen Wangcs.CL2026-10-19
#201TeleASR-Amharic: A Benchmark for Robust Amharic ASR in Realistic Telecommunication ConditionsDagnachew Mekonnen Marilign, Enrique Molero, Abrham Haile +2cs.CL2026-10-19
#202Training Negatives Still Matter After Calibrating Answerability ReadoutsJinchen Zhang, Zheyuan Liu, Yihan Zhu +1cs.CL2026-10-19
#203AfriGuard: Safety and Robust Refusal For African LanguagesIsrael Abebe Azime, Jesujoba O. Alabi, Iffat Maab +19cs.CL2026-10-19
#204Mitigating Reward Hacking in Preference Reward Models with Evolving PenaltiesAfonso Baldo, António Farinhas, Marcos Treviso +2cs.CL2026-10-19
#205ReAnchor: Reusing Rejected Verifier States for Diffusion DraftingSanghyun Lee, Wonjin Nam, Seungho Jang +4cs.CL2026-10-19
#206BERT Is Already a Denoiser: Cheaply Unlocking Iterative Generation in Masked Language ModelsJulio C. Amador Diaz Lopezcs.CL2026-10-19
#207Conducting Reliable Keyword Estimation with Unreliable ASR in Police Audio DataRobert Cole Molloy, Rhiannon N. Miller, Stephen Morgan +1cs.CL2026-10-19
#208The Development of Sycophancy in Language Models: Tracing Vulnerabilities from Pretraining to Post-TrainingHaonan Huang, Chengkun Caics.CL2026-10-19
#209Hierarchical Token Merging with Recursive Autoencoders for Unsupervised Grammar InductionMurat Guney Kemal, Robert Lieckcs.CL2026-10-19
#210HoloCosm: Beyond Single-Metric Benchmark Compression Across Multiple MetricsYupei Lin, Zhongzhan Huang, Junxin Li +5cs.CL2026-10-19
#211Fluent but Fallible: Benchmarking Hallucination and Factual Reliability in Large Language ModelsOsama Shabih, Dayam Nadeem, Shahab Saquib Sohail +1cs.CL2026-10-19
#212EpiLens: Lightweight RAG for Epidemiological Knowledge AcquisitionVincenzo Perri, Ciro Cattuto, Daniela Paolottics.CL2026-10-19
#213TokenGate: Adapting LLMs for Fast and Memory-Efficient Prefill with Learned Token PruningLiana Patel, Rishabh Ranjan, Ion Stoica +2cs.CL2026-10-19
#214Monsoon: Scalable Spontaneous Speech Collection for Low-Resource ASR in 50 LanguagesShobhit Banga, Manas Dhir, Aaditya Pareek +8cs.CL2026-10-19
#215RESIN: Multi-Chain Reasoning with Entity-Structured IndexingXuanyu Meng, Jash Rajesh Parekh, Jiawei Hancs.CL2026-10-19
#216Cross-Lingual Reusability of LLM Pipelines: Financial Extraction, Multilingual Reasoning, and Semantic ScreeningJoong Ho, Choi, Sherine George +5cs.CL2026-10-19
#217Safety Mid-Training: Internalizing LLM Safety as a Foundational CapabilityZhengyue Zhao, Liwei Jiang, Yejin Choi +1cs.CL2026-10-19
#218ASTOR: Benchmarking and Improving Autoformulation for Soft-Constraint Optimization with a Formal GrammarAmer Goel, Yeganeh Alimohammadi, Andrew Dawcs.CL2026-10-19
#219AfriBED: a Speech Recognition Bias Evaluation Dataset for Low Resource African LanguagesClaytone Sikasote, Hussein Suleman, Jan Buyscs.CL2026-10-19
#220SpecMRL: Redesign Matryoshka Representation Learning within Parametric SpectrumZhongxin Chen, Songhao Wu, Heng Cui +3cs.CL2026-10-19
#221MemT-1.0: Towards Memory-Native EvolutionZhiyu Li, Zeyu Zhang, Linyun Liu +71cs.CL2026-10-19
#222RefCraft: Benchmarking Visual-Reference-Conditioned Agentic Generation through Web DevelopmentYuchi Wang, Rongyao Fang, Weihao Yu +7cs.CL2026-10-19
#223KEEP-Bench: Evaluating Evidence Preservation in Context CompressionZiqing Man, Di Wu, Jia-Chen Gu +3cs.CL2026-10-19
#224Competing Learning in Hybrid ArchitecturesXingyu Shen, Yingfa Chen, Ziqing Qiao +3cs.CL2026-10-19
#225Discrete Neural Interlingua for Ontology-Agnostic EHR ModelingTong Ding, Caiwei Tian, Dongmin Bang +6cs.CL2026-10-19
#226LatComm: Reusable Context Compression for Latent Communication between Large Language ModelsHuawei Lin, Jinting Liu, Tan Yu +1cs.CL2026-10-19
#227OpenVLHarness: Real World Visual Agentic Tool-Use with Multimodal MemoryYu Zhou, Cheng-Fu Yang, Rui Sun +8cs.CL2026-10-19
#228Joint Constraint Aggregation for Qualifier-Sensitive Retrieval-Augmented QAJennifer Hsia, Zachary C. Lipton, Aarti Singhcs.CL2026-10-19
#229ICLHerd: Herding-Based Data Selection for LLMs with In-Context Learning as a ProxyYuqiao Wen, Lili Moucs.CL2026-10-19
#230GRID: Modeling Health Influencer Discourse as Argument Networks for Credibility AssessmentNishanth Sridhar Nakshatri, Eylon Caplan, Dan Goldwassercs.CL2026-10-19
#231SITO: Sifting a Commercial Text-Safety API for Missed Harm and False Flags in English, Ukrainian and SurzhykAndrii Tuzhykovcs.CL2026-10-19
#232On the Fragility of Tasks under Composition: Implicit Budgeting in Language ModelsChenpan Li, Thies Brockmoeller, Stefanie Jegelka +2cs.CL2026-10-19
#233Preference-Aware Pareto Steering for Multi-Task Speech LLMsLiuyuan Jiang, Vishal Sunder, Samuel Thomas +4cs.CL2026-10-19
#234The Culture Within: Towards Mechanistic Understanding of Cultural Reasoning in LLMsSamee Arif, Furkan Danisman, Angana Borah +6cs.CL2026-10-19
#235LoWAgent: A Low-Resource Multilingual Benchmark for Web AgentsOcean Monjur, Daud Ahmad Nisar, Shahriar Kabir Nahin +4cs.CL2026-10-19
#236Which Agent's Skill Should Change? Group-Relative Credit Assignment for Evolving Multi-Agent TeamsYanan Ma, Yang Wang, David Le +6cs.CL2026-10-19
#237MMedAgent-Plus: Scaling Multimodal Medical Agents across Modalities, Tasks and WorkflowsRuoxin Wang, Yuanting Pan, Binxu Li +13cs.CL2026-10-19
#238CEFR-oriented Russian Text Simplification Using Reinforcement LearningKristina Mustakova, Alexey Sorokincs.CL2026-10-19
#239Predicting Linear Relational Decodability Without the RelationJonas Rohweder, Adrian Mülthaler, Farid Mehri +2cs.CL2026-10-19
#240Diagnostic Analysis for Large Language Model ReasoningXinyu Liu, Dongqi Fu, Jun Wucs.CL2026-10-19
#241Target-Aware Curation of Hallucination Stress Tests for Large Language ModelsJiho Lee, Bingquan Zhang, Lin Ting Liang +2cs.CL2026-10-19
#242Auditing Safety Preference Supervision with Recorded DerivationsChenhan Lyu, Amir Rahmanics.CL2026-10-19
#243African Languages AI Safety Readiness ReportIsrael Abebe Azime, Jesujoba O. Alabi, Tajuddeen Gwadabe +1cs.CL2026-10-19
#244When Does Hate Transfer? A Large-Scale Study of Cross-Lingual Hate Speech DetectionZahra Bokaei, Walid Magdy, Bonnie Webbercs.CL2026-10-19
#245RealControlBench: A Benchmark for Interpretability-Informed Fine-Grained Control of LLMs and AgentsXinying Cai, Bin Hu, Mingyu Jin +16cs.CL2026-10-19
#246Evaluating Context Compaction on the Questions That Come LaterJunwei Yao, Yongxi Zhou, Zike Yang +4cs.CL2026-10-19
#247Global Security Blind Spots: Translation as a Safety Bypass in Low-Resource LanguagesJalil Alva, David Harper, Abigail E. Thornton +8cs.CL2026-10-19
#248On the LLM Verification for Argument Graph GenerationJakub Bąba, Jarosław A. Chudziakcs.CL2026-10-19
#249Explore More, Validate Less: Efficient Reflective Prompt OptimizationXiaofan Zhou, Lu Chengcs.CL2026-10-19
#250SHAM-Bench: A Span-level Hallucination Benchmark Across Multiple TasksSicong Huang, Ian Lanecs.CL2026-10-19
#251DStill: Trajectory Consistency Distillation for Accelerated One-Step Drafting in Block Diffusion Speculative DecodingShreyas Kulkarni, Uttam Gurram, Madhav Kanda +5cs.CL2026-10-19
#252Looking Into The Past: The Impact of Context on Detecting Deceptive StatementsAlex Clay, Ernesto Jimenez-Ruiz, Pranava Madhyasthacs.CL2026-10-19
#253Budgeted Attack Scheduling for LLM Red-Teaming: The Roles of Static Priors, Semantic Guidance, and Online FeedbackZhicheng Fang, Han Sun, Jiachen Lei +5cs.CR2026-10-19
#254Secure Agentic Coding through Counterexample-Grounded FeedbackTue Le, Anh Nguyen Hoang, Gabriel Sasseville +3cs.CR2026-10-19
#255Auditor-Assisted Summary-Channel Verification for Hosted LLM Identity SubstitutionZiyi Zhang, Ziyao Wang, Guoheng Sun +2cs.CR2026-10-19
#256NIOCIS: Typed-Decision Next-Hop Routing with Node-Conditioned Option Spaces for Tool-Use AgentsJin Han, Mingfeng Xin, Feng Liang +1cs.CR2026-10-19
#257SPLASH: Contrastive Audit Pressure for Detecting and Localizing Security Hallucinations in Generated CodeMirza Masfiqur Rahman, MD Ajwad Akil, Imtiaz Karim +3cs.CR2026-10-19
#258LeakBench: Auditing Reward Hacking through Prediction-Time Leakage in Clinical Modeling AgentsXiaoyuan Bao, Jingsi Jiang, Jiao Shan +4cs.CR2026-10-19
#259Fake News, Real Crashes: Information Injection Attacks on LLM Financial Trading AgentsMengxiao Wang, Nitesh Saxenacs.CR2026-10-19
#260Reliable Estimation of Differential Privacy under Selection BiasValentin Dorseuil, Meenatchi Sundaram Muthu Selva Annamalai, Jamal Atif +2cs.CR2026-10-19
#261BR-MoE: Budgeted Semantic Release for Privacy-Preserving Traffic AnalyticsAbdolazim Rezaeics.CR2026-10-19
#262Beyond Attack Success Rate: Cost-Aware Metric for Evaluating Iterative LLM JailbreaksRohan Menon, Chih-Hong Chengcs.CR2026-10-19
#263Game of Phones: Harnessing Game Theory and LLMs in 'Bot Wars' to Counteract Phone ScamsNardine Basta, Robin Carpentier, Benjamin Zi Hao Zhao +1cs.CR2026-10-19
#264Mind Your Boundaries: Boundary-Aware Model Obfuscation against Cross-node AttackYuyang Zhang, Yihui Jin, Kangjie Chen +2cs.CR2026-10-19
#265Model Exposure on One Device Endangers Others: Rethinking Edge Neural Network Security across DevicesYuyang Zhang, Kangjie Chen, Yihui Jin +1cs.CR2026-10-19
#266Profile-DP: Differential Privacy for User-Controlled Profile Release in Personalized LLM InferenceMingchen Li, Zifan Peng, Kewei Sha +5cs.CR2026-10-19
#267AutoRedClaw: Automated Red-Teaming for Claw-Style AgentsHao Li, Tongyan Hu, Weidi Luo +8cs.CR2026-10-19
#268When Models Know but Can't Linearly Say: Relational Encoding Limits Linear Vulnerability Classification in Code LLMsRui Melo, Andre Catarino, Claudia Mamede +2cs.CR2026-10-19
#269Guided Diffusion for Trustworthy Synthetic Text GenerationQi Pang, Hanshen Xiao, Andre Manoel +4cs.CR2026-10-19
#270Exposing Vulnerability Monoculture Through Systemic Adversarial RobustnessLeo Elmecker-Plakolm, Lukasz Szpruch, Avishek Joey Bose +1cs.CR2026-10-19
#271CheXFuse: Guided Differential Joint Attention Fusion for Robust Multimodal Chest X-Ray Classification in Data-Scarce Medical SettingsMuntaqim Ahmed Raju, Priyanka Siddappa, Md Shifat Haider Al Amin +2cs.CV2026-10-19
#272Recurrent Vision Transformers for Event-Based Spacecraft Pose Estimation Under Slow Relative MotionsSofia McLeod, Mohsi Jawaid, Carl Seubert +1cs.CV2026-10-19
#273Where Do the Gaussians Go? Foreground Attraction for Camera-Based Weakly Supervised 3D OccupancyJeagon Song, Jhonghyun Ancs.CV2026-10-19
#274Confidence-Guided Pseudo-Label Refinement for Unsupervised Cross-Domain Person Re-IdentificationSundas Iqbal, Danish Ali, Qing Tian +3cs.CV2026-10-19
#275Clean Forcing: Drift-Resistant Autoregressive Video Diffusion with a Frozen BaseWenqing Wang, Joonghyuk Shin, Jonathan Tremblay +2cs.CV2026-10-19
#276TNVD-SC: Diagnosing Scan Context Failures in Forests with Terrain-Normalized Vertical DistributionsJineon Kim, Jhonghyun Ancs.CV2026-10-19
#277ACorD: Adaptive Correspondence Discovery for Medical Image RegistrationArghavan Rezvani, Kun Han, Xiaohui Xiecs.CV2026-10-19
#278Visual Memory and Textual Alignment for Cross-Modal Few-Shot SegmentationTianqi Wei, Zhi Chen, Xin Yu +2cs.CV2026-10-19
#279Negation without Confusion: Decomposing Bias and Recomposing Style in Text Embeddings for Negation-aware Image GenerationSooyeon Park, Hemraj Singh, Kyunghyun Min +2cs.CV2026-10-19
#280FluidGen: Physics-Aware Fluid Video Generation via Motion-Guided Post-TrainingYang Zheng, Zizhang Li, Boyang Deng +6cs.CV2026-10-19
#281PoSTCache: From Forecasting to Postdictive Smoothing for Revisable Diffusion CachingLiwei Lan, Hui Chen, Jungong Han +1cs.CV2026-10-19
#282Frechet Forcing: Training Long-Horizon Streaming World Models from Short ClipsYian Zhao, Yu Yan, Hongcan Guo +3cs.CV2026-10-19
#283RxGS: Relightable Gaussian Stylization via BRDF DecompositionWanrong Hong, Liu Jiang, Mukesh Prasad +1cs.CV2026-10-19
#284Multi-View Structural Representations for Physically-Consistent TeX GenerationDaoheng Li, Jianjun Qian*, Mengkai Yan +1cs.CV2026-10-19
#285LEVI: Benchmarking Visual Identity Fidelity with Verifiable Low-Entropy ConstructsXiao Ma, Zhonghao Zhan, Hamed Haddadi +1cs.CV2026-10-19
#286Think Densely, Act Sparsely: Latent Expert Cognitive Chains for Vision-Language-Action Autonomous DrivingJie Wang, Guang Li, Zhijian Huang +5cs.CV2026-10-19
#287Functional Cross-layer Experts Routing for One-step Diffusion DistillationZile Huang, Ser-nam Limcs.CV2026-10-19
#288VHA: VQA-based Hallucination Assessment for Generative Image Super-ResolutionDonghun Ryou, Inju Ha, Jaeyoo Park +1cs.CV2026-10-19
#289See the Future, Classify the Present: Stochastic Latent World Modeling for Hyperspectral ImagesMuhammad Ahmad, Gemine Vivone, Ronny Hänsch +3cs.CV2026-10-19
#290UniJev: Separating Accuracy from Calibration in Trimodal System One Decision ModelsJianing Wang, Youwen Jian, Derong Wang +5cs.CV2026-10-19
#291Do We Need Learned Targets? Classical Gradients as Supervision for 2D Gaussian InitializationKyungjune Baekcs.CV2026-10-19
#292Hihaze: One-Step Diffusion for High-Resolution Real-World Image DehazingZheng Chen, Yuchen Huang, Xiaoyang Liu +3cs.CV2026-10-19
#293Auditing Semantic and Relational Reliability in Open-Vocabulary Human-Object Interaction EvaluationS M Asif Hossain, Ruksat Khan Shayoni, Md Kishor Morolcs.CV2026-10-19
#294REST: Reliability-Guided Spatial Transcriptomics Supervision for Gene Expression Prediction from Histopathological HE-Stained ImagesLanfeng Zhong, Xiangyu Sun, Guixuan Xu +4cs.CV2026-10-19
#295ActionRoPE: action as coordinates for spatially consistent control in planar-camera game world modelsZhiyang Deng, Yuzhe Wu, Zijun Lin +1cs.CV2026-10-19
#296Rethinking Sparse-View 3D Gaussian Splatting: A Few-Shot Learning Perspective on Overfitting PreventionLejia Ye, Bin Wu, Jingjing Gao +2cs.CV2026-10-19
#297Multi-scale Fusion of Fast Vision Mamba and Foundation Model Features for Patch-Level Gleason Grading in Computational PathologyZihe Zhang, Weimiao Yu, Piumi Don Simongecs.CV2026-10-19
#298LEAP: Accelerating ODE-based Diffusion Sampling with Optimal Linear LeapsHaowei Zheng, Zhenyu Zhou, Jiawei Chen +2cs.CV2026-10-19
#299SAPO: Self-Supervised Attention Policy Optimization for Improving Temporal Video Grounding in Vision-Language ModelsZixuan Chen, Depeng Wang, Wei Chen +5cs.CV2026-10-19
#300MIRA: A Multimodal Illustrated Deep Research Agent for Controllable ReportsHongrui Wu, Kaiwen Tuo, Congcong Wang +7cs.CV2026-10-19
#301CondenseVLA: Learnable History Condensation for Efficient Multi-Frame VLAFeiyang Hong, Yujie Wei, Bo Zhao +3cs.CV2026-10-19
#302OmniGround: Strengthening Omni-Modal Temporal Grounding via Attention-Consistency TrainingZixuan Chen, Depeng Wang, Hao Lin +5cs.CV2026-10-19
#303HORIA: 4D Human and Object Reconstruction from a Monocular Video with Interaction-Aware Re-RenderingHyeongjin Nam, Taeryung Lee, Daniel Sungho Jung +1cs.CV2026-10-19
#304Token-Set Choice Confounds POPE: A Systematic Audit of Yes/No Extraction in VLM Hallucination EvaluationKesav Kumar Jayakumar, Karthigeyan Thilakcs.CV2026-10-19
#305Curvature as a Baseline: Monocular Pose Measurement of Cylindrical Objects with Dual Colour Stripe MarkersJaesung Hong, Dong Won Leecs.CV2026-10-19
#306FrameGRPO: Incentivizing Video Reasoning via Multi-Frame Rollouts and Temporal CreditJiaxuan Sun, Biao Wang, Shuai Lics.CV2026-10-19
#307TamedFlow: Trajectory-Aware Distillation\\for Teacher-Assisted Diffusion SamplingShuaiqi Cheng, Jiahao Zhang, Boyuan Gu +6cs.CV2026-10-19
#308After the Federation: Benchmarking Knowledge Portability to Heterogeneous NewcomersXinyuan Zhaocs.CV2026-10-19
#309AVTime: Reinforcing Dense Audio-Visual Captions with Bidirectional AlignmentMingyang Wu, Kaituo Feng, Bohao Li +3cs.CV2026-10-19
#310Procedural Exposure Bias in Skill-Augmented Language Model AgentsQing Yang, Yuqi Xiong, Pengcheng Huang +5cs.CV2026-10-19
#311Learning the Dose Manifold: A Latent Diffusion Framework for Volumetric Dose Prediction in Automated Radiotherapy Treatment PlanningJ. Boyer-Chammard, R. Vauclin, M. C. Biston +7cs.CV2026-10-19
#312PhysSkin++: Real-Time and Generalizable Physics-Based Animation via Self-Supervised Neural SkinningYuanhang Lei, Baofei Liu, Xingxuan Li +9cs.CV2026-10-19
#313Risk Decomposition for Hallucination-Aware Video SamplingChenyan Zheng, Fan Wu, Ruibo Li +4cs.CV2026-10-19
#314Not All Similarity Is Leakage: Distribution-Aware Identity Leakage Assessment in Synthetic Face DatasetsPaweł Borsukiewicz, Daniele Lunghi, Wendkûuni C. Ouédraogo +3cs.CV2026-10-19
#315DCR-TSF: Dual-Level Compositional Reasoning with Triadic Spherical Fusion for Training-Free Zero-Shot Composed Image RetrievalGwang-Ho Na, Ho-Joong Kim, Seong-Whan Leecs.CV2026-10-19
#316Toolkit for Facial DeidentificationEsteban Leiva-Montenegro, Matthieu Pillot, Manfred Gonzalez-Hernandez +3cs.CV2026-10-19
#317DeOverlay: A Benchmark and Source-Anchored Flow for Video Overlay RemovalDeshui Miao, Yuhang Ma, Shaoyong Jia +4cs.CV2026-10-19
#318Context-Aware Topological Distillation Graph Network for Asymmetric EEG-Eye Movement Emotion RecognitionPeijun Shi, Xiujin Zhu, Zhenguo Lao +4cs.CV2026-10-19
#319RGB--Event Object Detection Across Operating Frequencies via Reliability-Supervised Routing and Asymmetric-Resolution FusionPeijun Shi, Jiannan Zhao, Xiujin Zhu +3cs.CV2026-10-19
#320GeoNaviDiff: Transferring Disentangled Semantic Controls to Diffusion Features via Local Riemannian NavigationTao Sun, Huanting Guo, Baao Xie +4cs.CV2026-10-19
#321How Robust Are Prognostic Radiomic Features? Comparing Selection Techniques on Pooled Glioblastoma CohortsYannick Sodonougbo, Marlene Schnieders, Alexia Rizoudis +3cs.CV2026-10-19
#322PnP-Transformer: A Neural Pose Solver for 6D Object Pose EstimationEmirkan Burak Yilmaz, Yakup Genccs.CV2026-10-19
#323TriTD: Tri-Partite Trajectory-Distribution Distillation for Real-Time Autoregressive Video GenerationJia Li, Xurui Peng, Haowei Zhu +7cs.CV2026-10-19
#324Learning Goal-Conditioned Subgoals through Frozen Hierarchical World ModelsXiang Kaibo, Liu Qingfengcs.CV2026-10-19
#325HP-PnP-Flow: Hybrid Time Scheduling and Projection for Plug-and-Play Image Restoration via Flow MatchingYong Li, Xiaojie Wang, Xiaoyan Zhangcs.CV2026-10-19
#326Wan-Alpha++: Animating a Single RGBA Asset into Controllable Transparent Video EffectsHaotian Dong, Xin Wang, Wenjing Wang +7cs.CV2026-10-19
#327GeoEdit: Adversarial De-Evidencing for Silent Geoprivacy Protection via Image EditingYu Yan, Shengjia Cheng, Fei Ma +2cs.CV2026-10-19
#328Focused Omni-Modal GUI AgentsFuyao Zhang, Wenwen He, Jiaming Zhang +6cs.CV2026-10-19
#329ExMR: Extremity Motion Refinement for Monocular Human Motion CaptureTom Wehrbein, Bodo Rosenhahncs.CV2026-10-19
#330RoAR-VAE: Improving Latent Diffusability through Robust PredictionYang Yue, Fangyun Wei, Yitong Wang +4cs.CV2026-10-19
#331SAR2Net: Learning Spatially Anchored Representations for Retrieval-Guided Cross-Stain AlignmentTianle Shen, Fang Yan, Xiaofan Zhangcs.CV2026-10-19
#332RECAP: Reciprocal Sparse Attention and Hierarchical Caching for Efficient Video DiffusionTiange Xu, Kai Liu, Linghe Kong +1cs.CV2026-10-19
#333XGLASS: X-Ray, Gaze and Language Assisted Slice Sequencing for CT VolumesMichael Glöckler, Timo Ropinskics.CV2026-10-19
#334Dynamics-Aware Sparse Attention for Efficient Autoregressive Video DiffusionYuanyu He, Zhuokun Chen, Yefei He +5cs.CV2026-10-19
#335TIM: Temporal Decoupling with Iterative Mutual-Refinement Model for Longitudinal Radiology Report GenerationYiheng Dong, Yi Lin, Shilong Huang +2cs.CV2026-10-19
#336From Cause to Effect: Generating Intermediate Event Chains in VideosRidouane Ghermi, Vicky Kalogeiton, Ivan Laptevcs.CV2026-10-19
#337CARNet: End-to-End Coupled Association-Recognition Network for Fine-Grained Multi-Drone Collaborative DetectionZhao Zhang, Ruigang Fu, Yu Zhang +3cs.CV2026-10-19
#338MCDA: Multi-View Graph Contrastive Learning with Dynamic Topology Augmentation for Functional MRI AnalysisHao Zhang, Xiaoyun Liu, Shuo Huang +4cs.CV2026-10-19
#339TriScore: Post-Hoc Out-of-Distribution Detection with Energy, Boundary Probes, and Transform ConsistencyEge Gursoy, Nicolas Mansardcs.CV2026-10-19
#340HGASurv: Hierarchical Granularity-Aware Integration for Multimodal Survival PredictionPeike Yu, Wuchao Liu, Jihong Guan +1cs.CV2026-10-19
#341Long-wave Infrared Polarimetric Remote Sensing Image Fusion for Vehicle DetectionWenjuan Zhang, Xiangrui Peng, Zhen Li +4cs.CV2026-10-19
#342From Legacy to Contemporary: Scalable Color Modernization for Long VideosDongyun Kim, Jiwoo Choi, Jaeseong Lee +1cs.CV2026-10-19
#343One Fact, Many Places: Redundant Evidence in Long Visual Documents Breaks Single-Gold Evaluation of Retrieval, Citation and AttributionXiaokang Yuan, Binhui Yao, Luwei Yang +2cs.CV2026-10-19
#344LaMER: Language-Conditioned Multi-Expert Routing for Weakly Supervised Referring Expression ComprehensionYu Yu Chang, Tzu-Hsuan Weng, Youssef Mohamed Amin +4cs.CV2026-10-19
#345Policy-Adaptive Credit Assignment for Spatial Reasoning with Verifiable RewardsHailiang Yang, Shengchao Chencs.CV2026-10-19
#346Long-form Video-to-Text Summarization using Recursive Language ModelsAlessia Intini, Lorenzo Vaiani, Enrico Chen +1cs.CV2026-10-19
#347When Guidance Becomes a Guard: Early Interception of Unsafe Inputs in Text-to-Image GenerationYanchun Li, Yujin Wu, Gangkai Shen +5cs.CV2026-10-19
#348YUTELA: A Scalable Edge Cloud AIoT System for Multi-Site Video Anomaly Detection with Scene Specific AdaptationShanle Yao, Babak Rahimi Ardabili, Amir Kimiyaie +1cs.CV2026-10-19
#3493D Diffusion Models for Medical ImagingFrank-Peter Schilling, Daniel Barco, Philipp Denzel +1cs.CV2026-10-19
#350PDNet: Exploring Pruning and Distillation for Real-Time Worker Activity Recognition in Industrial AssemblyMalek Baba, Thinesh Thiyakesan Ponbagavathi, Alina Roitbergcs.CV2026-10-19
#351Interpretable Face Contrast Modeling for Smartphone Portrait RenderingYujin Cho, Benoît Pochon, Jean-Michel Morel +1cs.CV2026-10-19
#352Holi-World: Building Holistic World Intelligence from Human-Ego ExperienceHao Li, Xiyuan Zheng, Yuanyuan Gao +7cs.CV2026-10-19
#353MRI Reconstruction Risk Estimation from Inference DynamicsTamir Shor, Alex Bronsteincs.CV2026-10-19
#354PrismWAM: Decoupling State Representations in World Action ModelsTianyu Xin, Wanqi Zhong, Bowen Hu +8cs.CV2026-10-19
#355DenseHap: Dense Hand Haptic Estimation from Monocular ImagesJunhan Xue, Rolandos Alexandros Potamiascs.CV2026-10-19
#356Drive2Gauss: FeedForward 4D Gaussian Reconstruction from Multimodal Generative Driving VideosTong Zhao, Zhiyuan Han, Lin Chen +10cs.CV2026-10-19
#357Scaling Vision Foundation Models for Toxicologic PathologyJessica Loo, Theodoros Pissas, Byunghak Kang +7cs.CV2026-10-19
#358EgoXperience: Learning World-Grounded Egocentric Representations from Human ExperienceXinhao Ji, Hui En Pang, Hao Li +12cs.CV2026-10-19
#359Dual-Scale Condition-Shift Editing for Robust Real-World Image DemoiréingShiyang Zhou, Haijin Zeng, Congpei Qiu +6cs.CV2026-10-19
#360SpatialScout: Can VLM Agents Actively Explore and Map 3D Scenes?Zhaoxi Zhang, Hao Liang, Linxuan Wu +7cs.CV2026-10-19
#361CaptionFuse: Training-Free Composed Product Retrieval Via VLM Intent Captioning and Weighted Embedding FusionZhao Gao, Mina Metias, Mohamed Noordeen Alaudeen +1cs.CV2026-10-19
#362From Short Clips to Real-Time Streams: Identity-Aware Supervision and Context-Efficient Generation for Video Face SwappingZekai Luo, Yuwei Liang, Ruiqi Ma +8cs.CV2026-10-19
#363BrushOff: Stroke-Based Re-rendering as a Watermark Removal Attack on PaintingHao Chen, Junnan Xucs.CV2026-10-19
#364Foundation Model Driven Optical FlowPraroop Chanda, Suryansh Kumarcs.CV2026-10-19
#365PVBench: Quantifying Physical Plausibility in Video Generation with Object-Level Physical MeasurementsKaiwei Chen, Moran Li, Zhenye Gan +5cs.CV2026-10-19
#366A Flexible ROI Analysis Tool for Spatially Consistent Vegetation Index Extraction from Turfgrass ImageryKibon Ku, Thai Thanh Tuan, Jinhyun Ahncs.CV2026-10-19
#367PlanarCityLoc: Breaking Silhouette Ambiguity in LoD Aerial Localization via 3D PlanesOussema Dhaouadi, Shao Jie Hu-Chen, Jakob Gollreiter +10cs.CV2026-10-19
#368CheckDistill: Adaptive Checklist Distillation for Efficient Distributional Reward Modeling in Image EditingYaqi Cai, Zuan Gao, Mengting Chen +2cs.CV2026-10-19
#369Beyond Omni: A Unified MLLM for Embodied Sensory UnderstandingShiyun Xiong, Dongming Wu, Peiwen Sun +5cs.CV2026-10-19
#370Robustness of Internal Signals for Hallucination Detection in Vision-Language ModelsAllison Chen, William Yang, Salma Abdel Magid +3cs.CV2026-10-19
#371V-JEPA Hand: Simple, Accurate and Fast 3D Hand and Camera Trajectory Recovery from Egocentric VideosRuicheng Li, Qixiu Li, Yu Deng +3cs.CV2026-10-19
#372Mise-en-Video: Fine-Grained 3D Control for Multi-Shot Video GenerationYingshuang Zou, Xiaoyu Shi, Yawen Luo +8cs.CV2026-10-19
#373What Language Adds, and at What Cost: Four Controlled Probes of Pathology Vision-Language ModelsWenhao Zhang, Zhongliang Zhou, Yi Ping +2cs.CV2026-10-19
#374State World Models: Execute the Rules, Generate the PixelsChan Yan Ki, Yanran Zhang, Wenzhao Zheng +5cs.CV2026-10-19
#375PICA-WAM: Visual Perturbation Invariance via Cross-Appearance Self-Alignment in World Action ModelsYude Zou, Yifei Yao, Guanbo Jiao +3cs.CV2026-10-19
#376Real-Time Radar Semantic and Panoptic Scene UnderstandingSantosh Parit, Julia Hindel, Rohit Mohan +4cs.CV2026-10-19
#377Open-Form Geometric Style TransferAdar Elad, Gal Metzer, Omer Dahari +2cs.CV2026-10-19
#378SpecKCast: Spectral Kalman Forecasting for Diffusion AccelerationJavad Rajabi, Hakki Can Karaimer, David B. Lindell +2cs.CV2026-10-19
#379GenOlympiad: Benchmarking Frontier Image Models at Their Capability BoundariesXi Hu, Martin Bell, Liang Zhengcs.CV2026-10-19
#380Manga2Animate: An Agentic Framework for Faithful Manga Animation with Script and Storyboard PlanningSheng-Wei Zhang, Hsi-An Chen, Yan-Ting Liou +3cs.CV2026-10-19
#381InfiniDream: Open-Ended Photorealistic 3D Worlds Through Procedural GenerationYi-Chuan Huang, Hao-Jen Chien, Zheng-Hui Huang +3cs.CV2026-10-19
#382VitronEdit: Universal Visual Editing across Images, Videos, and 3D ScenesJing Wang, Yanlin Li, Mong-Li Lee +3cs.CV2026-10-19
#383Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human ExperienceTianqi Liu, Hanfei Zhao, Qifeng Liang +12cs.CV2026-10-19
#384VideoMaMa++: Temporally Consistent Video Matting via Preserve-and-Refine TokenSangbeom Lim, Seoung Wug Oh, Heeji Yoon +2cs.CV2026-10-19
#385Reinforcement Learning with Visually Attributable On-Policy Self-DistillationShiao Xie, Siyu Chen, Jianwei Lv +2cs.CV2026-10-19
#386Can It Actually Work? Synthesizing Functional CAD MechanismsWenqian Zhang, Yangyi Huang, Zigeng Xu +2cs.CV2026-10-19
#387BUMP: Body-driven Unified Multi-object Physics for HOI SynthesisWonjung Woo, Hyeonwoo Kim, Hanbyul Joocs.CV2026-10-19
#388SciFigBench: A Benchmark for Scientific Method Figure UnderstandingLijia Wu, Zheng Li, Yuxuan Liu +3cs.CV2026-10-19
#389LVMem: Image-Augmented Memory for Long-Horizon Question AnsweringVictoria Khoruzhaya, Maksim Kalmykov, Tuong Do Minh +3cs.CV2026-10-19
#390Counting Contributions, Not Views: Occlusion-Aware Densification for 3D Gaussian SplattingMarcel Rogge, René Schuster, Didier Strickercs.CV2026-10-19
#391MatchCityLoc: Aerial Localization in LoD City Models via Surface Normal MatchingOussema Dhaouadi, Zuria Bauer, Johannes Michael Meier +3cs.CV2026-10-19
#392PRIMFLOW: Learning Trajectory Primitives for Few-Step DistillationHongyi Fang, Benjia Zhoucs.CV2026-10-19
#393CARLAR Influence: A Structured Hallucination Risk in Multimodal Cheque Extraction and an Exploratory Compressed-Image CountermeasureJoong Ho, Choi, Aditya Paul +1cs.CV2026-10-19
#394Language Guidance for Supervised Vision Training: An Empirical Study of GeneralizationShruthi Gowda, Nikita Jain, Elahe Arani +1cs.CV2026-10-19
#395Generalizing Multimodal Foundational Models in Context-Driven Class Incremental LearningAvi Gupta, Nilotpal Sinha, Vishnu Raj +4cs.CV2026-10-19
#396What Not to Erase: Saliency-Constrained Augmentation for Low-Resource Handwritten Character RecognitionParaskevi Platanou, John Pavlopouloscs.CV2026-10-19
#397Steering Vision-Language Models for Visual-Contextual Privacy in Location DisclosureWenyue Chen, Yuhan Cheng, Ruixin Yang +5cs.CV2026-10-19
#398Look Before You Reason: Implicit Visual Thinking for Efficient Multimodal ReasoningZerui Chen, Changrui Chen, Fei Ni +1cs.CV2026-10-19
#399On the Limits of Scale: Inverse Scaling in Vision-Language ModelsRohit Saxena, Alessandro Suglia, Marek Rei +1cs.CV2026-10-19
#400PerQ: Inverse Generative Modeling for Neural Image Compression via Quantization Error CompensationTianhao Peng, Ho Man Kwan, Fan Zhang +2cs.CV2026-10-19
#401Causal Humility: Governing the Authority of Fairness Claims Under Causal UncertaintyKhadija Zanna, Rodrigo Ferreira, Frederick L. Oswald +1cs.CY2026-10-19
#402Reasoning-Aware Multicalibrated Reliability Predictors for Language ModelsEkaterina Fedorova, Alessandro Morosini, Chara Podimatacs.CY2026-10-19
#403MultiCard: Multiple Attribute Cardinality Estimation via Deep LearningMobina Koochaknia, Maryam Ramezani, Mohammad Hasan Shafaatcs.DB2026-10-19
#404SafeWall: A Risk-Aware Job Walltime Recommendation for HPC SchedulingKanglin Xu, Michael Papka, Zhiling Lancs.DC2026-10-19
#405Fundamental Impossibility Results in AI Safety: Trading Off between DesiderataIda Mattsson, Ratip Emin Berker, Emanuel Tewolde +11cs.GT2026-10-19
#406Small Average Error, Wide Individual Error: General-Purpose LLMs Estimating Energy Intake from Meal Photos in a Feeding TrialXiaomeng Lics.HC2026-10-19
#407ValiAssist: Scaling LLM-generated Programming Feedback Validation by DemonstrationXiaohang Tang, Rehema Abulikemu, Peng Gao +1cs.HC2026-10-19
#408Knowledge Manifold Optimization for Scientific DiscoveryShigeru Obayashi, Yoshiaki Kawagoe, Kazuhiko Komatsu +1cs.IR2026-10-19
#409Cross-Pollination Retrieval: Finding Transferable Ideas Across Fields in Scientific LiteratureSeokwon Jung, Yerang Kim, Yejin Kim +5cs.IR2026-10-19
#410MAPS: A Multi-Agent Personalized Script-Driven Video Advertising System Enhanced by Reinforcement LearningZhongyu Wang, Chen Zuo, Qingxuan Sun +4cs.IR2026-10-19
#411Multimodal Decoupling for Diversified Recommendation through Semantic and Structural ShapingChangran He, Jiaming Wei, Jianghong Ma +3cs.IR2026-10-19
#412Don't Rewrite the SID Map: Topology Preservation for Generative Retrieval in Dynamic E-Commerce SearchJianbo Zhu, Xing Fang, Xiaopeng Chu +5cs.IR2026-10-19
#413FLMNet: Self-Ensemble Distillation from Masks to Seeds for Single-Tower CTR PredictionYifan Wang, Yifei Ducs.IR2026-10-19
#414Neighborhood-Aware Unlearning for Generative RecommendationPierre Lubitzsch, Yubao Tang, Maarten de Rijke +1cs.IR2026-10-19
#415FLINT: Fixed-budget Late InteractionHimank Handa, Negar Arabzadeh, Matei Zahariacs.IR2026-10-19
#416Fundamental Limits of Information-Theoretic Secure Aggregation with User Dropouts in Federated LearningJinbao Zhu, Kai Wan, Giuseppe Cairecs.IT2026-10-19
#417Text Dominance in Paralinguistic Conflict: Tracing Suppression Through Audio LLM CircuitsAnkur Banerjee, Vishnu Guntakala, Danity Pike +3cs.LG2026-10-19
#418Adversarial Post-Training of Foundation Models for High-Frequency TradingAlexandre Bismuth, Kang Li, Aramis Marti-Shahandeh +3cs.LG2026-10-19
#419PRISM: Prior Relational Information for Self-supervised Modeling to Enhance Solubility OOD GeneralizationXinyi Chen, Jiahuan Pang, Titus Chima +2cs.LG2026-10-19
#420Safety Offset Learning: When Benign Fine-Tuning Misaligns LLMsJesson Wang, Zhanhao Hu, Minghao Lin +3cs.LG2026-10-19
#421Curriculum Learning Teaches LLMs Long-Horizon Implicit Reasoning, Up To A LimitJimson Huang, Maxwell Nickell, Ruowang Zhang +1cs.LG2026-10-19
#422Weighted State Souping for Efficient Long-Context RetrievalWilliam L. Tong, Aryo Lotfi, Emmanuel Abbe +3cs.LG2026-10-19
#423Zephyrus-R1: Agentic Reinforcement Learning for Weather ReportingFengfei Yu, Marshall Fisher, Isadora White +13cs.LG2026-10-19
#424Conditional Average Treatment Effect Distillation for Hypothetical State-Intervention Targeting Under Budget ConstraintsVasundhara Acharya, Bülent Yenercs.LG2026-10-19
#425Latent Projection for Latent PlanningYoo Sung Jang, Michael Ryoocs.LG2026-10-19
#426OPDArena: Understanding Learning and Forgetting in On-Policy DistillationYuanze Xu, Tianzhu Ye, Hui Sun +3cs.LG2026-10-19
#427A "feature ODE" describing the learning behavior of shallow MLPs on simple functionsJoseph Turnbull, Berkan Ottlik, Jamie Simoncs.LG2026-10-19
#428Can Metadata Fix the Gauge? Calibration Turns Sparse Multi-Source Learning from Sparse PCA into Sparse Mean RecoveryYirong Xiang, Yibo Zhoucs.LG2026-10-19
#429LOOP: Recovery-Aligned Iterative Layer Pruning via On-Policy DistillationLiang Xu, Shufan Shen, Zhongni Hou +4cs.LG2026-10-19
#430MT-CC: Multi-Group Temperature Scaling for Asymmetric Calibration Behavior in Class-Incremental LearningSungjun Yun, Yonghee Choi, Dong-Jun Hancs.LG2026-10-19
#431Progress-Guided Preference Generation for Aligning Generative Control PoliciesTung M. Luu, Tri Ton, Duc M. Nguyen +8cs.LG2026-10-19
#432Stochastic Tracking of Drifting Affine Fixed PointsSajad Khodadadiancs.LG2026-10-19
#433Predictive Bandit Curriculum Reinforcement Learning via Gradient-Based Sample Group DiscoveryLiang Xu, Shufan Shen, Zhongni Hou +5cs.LG2026-10-19
#434Evidence Sufficiency and Model Comparisons in MexRegQA: An Item-Level Audit of Mexican-Spanish Regulatory QAFred Hu, Yeqi Wang, Xing Zhoucs.LG2026-10-19
#435Learning to Couple: Context-Adaptive Joint Denoising for Diffusion Language ModelsZilei Shao, Ian Li, Heng Zhao +4cs.LG2026-10-19
#436Anatomy of Off-Policy Policy Gradient: Importance Sampling, KL Regularization, and BaselinesHaoqun Cao, Yurun Yuan, Tengyang Xiecs.LG2026-10-19
#437Neural Video Coding under Limited Delay: Theoretical Optimality and System DesignLikun Cai, Jun Chen, Ashish Khistics.LG2026-10-19
#438How Much Does One Wrong Answer Cost? Error Propagation in Constraint Pruning with Noisy LLM OraclesZhengtao Gui, Weining Shencs.LG2026-10-19
#439Bayesian Model Discovery with Language Models: Closing the Loop between Hypotheses and ExperimentsJooKyung Yuh, Byungmin Park, Eunseo Choi +6cs.LG2026-10-19
#440Cognitively Decoupled Meta-Induction for Out-of-Distribution GeneralizationYuqian Wang, Yuanzheng Wang, Chaojun Xiao +7cs.LG2026-10-19
#441NADS: Navigator-Guided Data Selection for Mitigating Catastrophic Forgetting in Fine-TuningJianhao Zhang, Ou Wu, Yi Ducs.LG2026-10-19
#442Which Answers Agree? Evaluating Self-Consistency from Incomplete LogsZhengtao Gui, Zexi Chen, Weining Shencs.LG2026-10-19
#443Remember Less, Adapt Longer: Bounded-State In-Context Reinforcement Learning with Recurrent Summary MemoryJiawen Wang, Cheng Xue, Peng Zhang +1cs.LG2026-10-19
#444Computation, Not Memory: Chain-of-Thought and State Tracking in LLM AgentsPedram Mouseli, Massieh Moayedics.LG2026-10-19
#445Detection Augmented Learning In Non-Stationary Bandit EnvironmentsArgyrios Gerogiannis, Yu-Han Huang, Subhonmesh Bose +1cs.LG2026-10-19
#446Sector-Ring Linear Reservoirs: Sector-Wise Decay-Timescale Allocation With State Reuse Across Candidate SettingsYudai Ebato, Sou Nobukawa, Yusuke Sakemi +3cs.LG2026-10-19
#447Communication-Efficient Federated Domain Generalization in Edge Networks via Dynamic Prototype RegulationYuankun Xia, Hui Wang, Ling Yuan +3cs.LG2026-10-19
#448Is it RL or Data? A Controlled Comparison of GRPO and Rejection-Sampling Fine-TuningLakshya Chaudhrycs.LG2026-10-19
#449SWIFT: Self-guided Weak-to-strong dIFfusion models via Target extrapolationYanjin He, Cuifeng Shen, Wanzhou Lei +5cs.LG2026-10-19
#450ACE-Trader: Adversarial Co-Evolution for Generator-Critic Trading SystemsChang Zhou, Jiarun Zhou, Xingtong Yu +3cs.LG2026-10-19
#451Rubrics Beyond Evaluation: Exploiting Rubric Structure in Reinforcement LearningYuxun Huang, Yunyao Zhang, ZeLiang Chen +3cs.LG2026-10-19
#452Statistical Learning Theory for Direct Preference OptimizationJoel Wills, Yuanfan Li, Yiming Ying +1cs.LG2026-10-19
#453Adaptive Decoding Methods for Token-Efficient Reinforcement LearningZhaonan Li, Zelei Cheng, Amritansh Mishra +5cs.LG2026-10-19
#454Residual-Guided Adaptive Tucker Rank Allocation for Parameter-Efficient MCI Conversion PredictionGuanghua He, Hancan Zhu, Gaohang Yu +1cs.LG2026-10-19
#455DeltaTrace: Efficient Signed Attribution for Reasoning Language ModelsChen Liang, Daoping Wu, Donghua Yang +4cs.LG2026-10-19
#456Asynchronous On-Policy Self-DistillationXidong Wu, Qi Qi, Yuqiong Ji +1cs.LG2026-10-19
#457Learn the Interface, Not the Implementation: Output Representation Dominates Training Regime in LLM-Based RTL GenerationSiddharth Patel, Vikram Singh, Siddharth Savyasachi Malu +1cs.LG2026-10-19
#458Out-of-Distribution Detection in Continual LearningNimeshika Udayangani, Flora D. Salim, Christopher Leckie +1cs.LG2026-10-19
#459An Analysis of Semantic and Spatio-Temporal Co-evolution for Edge Classification on Dynamic Text-Attributed GraphsTyler Bonnet, Marek Reics.LG2026-10-19
#460Maestro: Agentic Formal Proof Development by CoordinationHaoyu Li, Zeren Shui, Yuhao Zhang +4cs.LG2026-10-19
#461UtilityBench: Measuring Language Model Utility When Errors Have Different CostsQifeng Lei, Zhiyong Yang, Zitai Wang +4cs.LG2026-10-19
#462Keep the Lineages Alive: Diversity-Preserving SMC for Diffusion LLM DecodingMinoo Ahmadi, Seyedarmin Azizi, Mehdi Kamal +1cs.LG2026-10-19
#463The KV-Surgeon: Compensation-Aware Offline KV-Cache CompactionMoritz Wagner, Christophe Roux, Max Zimmer +1cs.LG2026-10-19
#464CoASFL: Coupled Consistency Optimization for Asynchronous Split Federated LearningJunhao Cheng, Yunming Liao, Hongli Xu +2cs.LG2026-10-19
#465Correctness-Dependent Asymmetric Target Distributions for Self-Distillation Policy OptimizationSuwan Yoon, Seongryong Jung, Changhee Leecs.LG2026-10-19
#466Graph-to-Table Interfaces Control Relational GeneralisationAlessandro Cagiano, Lorenzo Molfetta, Gianluca Moro +2cs.LG2026-10-19
#467PnP-CF: A Consensus Flow-Matching Solver for General Inverse ProblemsDibyanshu Kumar, Magda Gregorovacs.LG2026-10-19
#468Scenario Generalization and Sector Transfer in Real Surface Irrigation Surrogate Modelling with Tabular ModelsAlessandro Cagiano, M. Aybars Seyhan, Fabiola Gangi +2cs.LG2026-10-19
#469ProtGlycanDock: Towards Accurate Protein-Glycan Docking with Tailored Dataset, Benchmark and ModelMinghao Xu, Jiaze Song, Jinyu Wang +1cs.LG2026-10-19
#470Truncate or Not? A Scaling Study of Looped Transformers with Truncated BackpropagationXuyuan Xiong, Siyu Chen, Zihan Shao +5cs.LG2026-10-19
#471FinHopper: A Progressive Multi-Hop Benchmark for Complex Financial Agents with Step-wise EvaluationYuxuan Wu, Miaopei Lin, Qiufang Ying +9cs.LG2026-10-19
#472CorteXforge: Scenario-Based RF Dataset Generation on Real TestbedsAndréa Joly, Leonardo S Cardoso, Jean-Marie Gorcecs.LG2026-10-19
#473ORBIT: Autoregressive Time Series Generation via Next Frequency-Band PredictionChunyi Hou, Xiangfei Qiu, Hanyin Cheng +5cs.LG2026-10-19
#474HierDTA: Hierarchical Structure-Aware Representation Learning for Drug--Target Affinity PredictionHuangchao Xu, Baohua Zhang, Qian Liu +2cs.LG2026-10-19
#475Provable Adversarial Detection: Prime Quantization meets Gromov--WassersteinManohar Kaul, Sadbhavana Babar, Aditya Ramesh +4cs.LG2026-10-19
#476Learning from a Bandit LearnerMichela Petriconi, Nicolas Menet, Claire Vernadecs.LG2026-10-19
#477Declarative Explanations for Graph Neural Networks: A DemonstrationCibo Yu, Haitong Tang, Yinghui Wu +4cs.LG2026-10-19
#478From Retrieval to Recognition:Knowledge-Enhanced Post-training of Time Series Foundation Models for ClassificationZhen Liu, Yucheng Wang, Yingpeng Du +5cs.LG2026-10-19
#479Variance-Aware Non-Stationary Bandits:All-Budget Regret Bounds and Adaptation CostsXiaojin Zhangcs.LG2026-10-19
#480Optimal Multi-Kernel Combination for Online Multi-Label ClassificationTingting Zhai, Wei Liu, Renjian Yucs.LG2026-10-19
#481Nash-MOPD: Optimizing Task Trade-offs in Multi-Teacher On-Policy DistillationSiyuan Gan, Bo Yang, Linjian Meng +4cs.LG2026-10-19
#482Dynamical Batching: How Class-Cycling Training Shapes the Internal Structure of Neural NetworksNicolás Ratier-Werbin, Samuel Lozano, Miguel Ruiz-Garcíacs.LG2026-10-19
#483TaQFormer: A Treatment-as-Query Transformer with Data-Fusion for Multidimensional Treatment Modeling in Coupon AllocationJiahong Li, Zeqin Yang, Yu Xiang +8cs.LG2026-10-19
#484OceanTensorCube and ST-MMT: A Multimodal Data and Transformer System for Seven-Day Forecasting of Pyropia BleachingGwangjin Kim, Cheolyoung Jang, Yosep Jocs.LG2026-10-19
#485SEAM: Spectral Embedding Alignment and Merging for Low-Resource TTSWalaa Othman, Baher Mohammad, Stamatios Lefkimmiatis +1cs.LG2026-10-19
#486Exploration via Activation-Space Steering for Reinforcement Learning with Verifiable RewardsYunan Zeng, Jinhao Jing, Xi Cheng +1cs.LG2026-10-19
#487Trust Your Targets: Is Target Propagation Block-Diagonal Gauss-Newton?Giuseppe Castiglione, Christopher Buckley, Ivor Simpsoncs.LG2026-10-19
#488Learning SOCP Solver Dynamics with Graph Neural NetworksAdam Ghalem, Lou Salaün, Davide Rinaldi +1cs.LG2026-10-19
#489Toward Online Robust Zero-Sum Markov Games with Function ApproximationChenhao Zhou, Jiyu Weics.LG2026-10-19
#490CAST: Cast-Admissible Generative Design and Shape Optimization with Paired Depth ImagesJihoon Kim, Yongmin Kwon, Namwoo Kangcs.LG2026-10-19
#491Typed Decision Models under Prevalence Shift: Decision Training, Calibration, and Implicit PriorsAbdul Rahman Iqbal, Muhammad Fawad Nasim, Amir Saleemcs.LG2026-10-19
#492CIS-Transolver: A Cross-Layer Incremental-State Neural Operator for Fine-Scale Automotive Aerodynamic Flow PredictionJianglong Liu, Zhicheng Zhu, Jia Hao +1cs.LG2026-10-19
#493Logit Averaging During Training Sets a New State of the Art for Non-Invasive Speech BCIMiran Özdogan, Gereon Elvers, Michael Bronstein +1cs.LG2026-10-19
#494An Empirical Study of Parameter-Efficient Fine-Tuning for Mixture-of-Experts LLMsMinglei Li, Peng Ye, Haonan He +3cs.LG2026-10-19
#495CTLite: Lightweight Irregular Multivariate Time Series Forecasting with Reusable Continuous-Time SummariesShusen Ma, Xudong Zuo, Yangchun Xie +1cs.LG2026-10-19
#496A Simple and General Approach to top-$k$ SelectionMotti Goldberger, Nils Rudics.LG2026-10-19
#497Rethinking LLM Fine-Tuning via Weight Space Reparameterization: Preserving Safety during Downstream AdaptationMinseong Kim, Jongbok Won, Jeesup Park +2cs.LG2026-10-19
#498On Learning Expand-and-Sparsify RepresentationsAlireza Asghari, Parikshit Ram, Kaushik Sinhacs.LG2026-10-19
#499A Simple and Unified Method for Gradient-Variation RegretHang Yu, Peng Zhaocs.LG2026-10-19
#500Wet-Biased Data Pipelines Mislead the Training and Evaluation of Generative Precipitation NowcastingChristoph Metzl, Stefan Kapsreiter, Kianusch Vahid Yousefnia +4cs.LG2026-10-19
#501Strength Controls Change How Interventions Compare Across Sparse Autoencoder CodesJinchen Zhang, Zheyuan Liu, Yihan Zhu +1cs.LG2026-10-19
#502A Fisher-Geometric View of Multi-Teacher On-Policy DistillationLiu Kaiyuan, Zhuang Ziyuan, Ma Haoxuan +4cs.LG2026-10-19
#503EGiME: Entropy-Guided Model Evaluation in Few-Shot LearningDequan Jin, Tao Li, Lifeng Xing +2cs.LG2026-10-19
#504Concerns in Benchmarking Jailbreaks: An Empirical Study of Attack Success RatesLeon Tu Nguyen, Rohan Menon, Rafael Tappe Maestro +2cs.LG2026-10-19
#505Bombadil: A Foundation Model for Plant ElectrophysiologyJames Kirk, Piotr Bednarski, Filip Twardy +2cs.LG2026-10-19
#506ITU-DESC: a missingness-aware machine-learning dementia risk score in the UK Biobank cohortAbdullah Kavaklı, Faik Boray Tekcs.LG2026-10-19
#507Degree Bounds for Separating Polynomial and Neural Invariants for Point CloudsSnir Hordan, Harm Derksen, Mircea Petrache +1cs.LG2026-10-19
#508Hilbert-Scale Stability of Posterior Diffusion Priors for Ill-Posed Signal RecoveryBahman Moraffah, Raha Moraffahcs.LG2026-10-19
#509Global Time-Aware Conditioning (GTC): A Mechanism for Time-Aware Pediatric Sleep Representation LearningSaurav Raj Pandey, Harlin Leecs.LG2026-10-19
#510SleepPairNet: Learning Multimodal Pediatric Sleep Representations with Random-Pair Cross-AttentionSaurav Raj Pandey, Harlin Leecs.LG2026-10-19
#511VaDar: Implicit Goal Conditioning via Value DisaggregationShashwat Saxena, Mehul Goel, Sreyas Venkataraman +2cs.LG2026-10-19
#512The Effectiveness and Durability of Pretraining Data Filtering in Protein Language ModelsAaron Maiwald, Roderick McNeill, Jaeyoung Lee +9cs.LG2026-10-19
#513Nested Shared-Operator Recursion on ARC-AGI-1: An Empirical Study of HRM, TRM and URMSara Neri, Eugenio Gaeta, Andrea Ceschini +2cs.LG2026-10-19
#514PACT: Plan-Augmented Coordination via Trace-Graphs for Dynamic Multi-Agent Combinatorial OptimizationXiao Zhou, Alex Schutz, Victor-Alexandru Darvariu +1cs.LG2026-10-19
#515Which Model for Which Role? Cost-Efficient Pareto Recommendation for LLM Agentic WorkflowsQian Xie, Wenyue Hua, Yueli He +7cs.LG2026-10-19
#516Intra-Rubric Reward Divergence: Mitigating Rubric Hacking through Latent Dimension Recovery and BalancingJianqiang Xia, Han Xu, Dianxi Shics.LG2026-10-19
#517Parallel Language Models via Variational DecodingFelix Draxler, Robin C. Geyer, Daniel Geyfman +13cs.LG2026-10-19
#518GeoSplit: Selective Edge--Server Map Acquisition for Cross-User Travel-Mode RecognitionZepu Wang, Luyao Niu, Ruolin Li +2cs.LG2026-10-19
#519Doubly Robust Learning of Heterogeneous Survival Treatment Effects under Time-Varying TreatmentsTomàs Garriga, Munib Mesinovic, Luke De Bretton-Gordon +3cs.LG2026-10-19
#520Deep Pontryagin Learning for Continuous-Time Stochastic Control with JumpsJean-Loup Dupret, Patrick Cheriditocs.LG2026-10-19
#521Copying Under Repetition: From Prefix Matching to Position HashingAnxin Guo, Tianlong Huang, Chenxiao Yang +1cs.LG2026-10-19
#522Cross-Fitting for Neural Posterior EstimationJeffrey Regiercs.LG2026-10-19
#523CAVA: Complementary-Label-Aware Data ValuationTan-Ha Mai, Hsuan-Tien Lin, Vu Nguyencs.LG2026-10-19
#524recAMPLIFY: Large-Scale Pretraining of Recursive Protein Language ModelsSaurav Jha, Qianli Liao, Robert Vernon +2cs.LG2026-10-19
#525Trajectory Replay: Continuous-Time Mixture Transport for Lifelong Generative ModelsAlessandro Palma, Charles Jones, Tristan Cinquin +2cs.LG2026-10-19
#526Simulation Priors for Rapid Adaptation in Model-Based RL for Autonomous RacingAdrian Remonda, Jiajun Xi, Nicklas Hansen +5cs.LG2026-10-19
#527HarnessPro: Recursive Harness Self-Improvement with Pareto Optimization for Performance-Cost Trade-offsZhuoshi Pan, ZhiYuan Feng, Yukuo Cen +6cs.LG2026-10-19
#528Topological Sheaves of Irreducibility: A Theoretical Framework for Multi-Agent Task ObstructionsSteven Motta, Davide Mambelli, Alessandro Rozzacs.LG2026-10-19
#529Training with ML-labeled Data via Stochastic First- and Zeroth-Order OptimizationMaria-Eleni Sfyraki, Jun-Kun Wangcs.LG2026-10-19
#530On Data Scaling in Tabular ML: More Data, Better Generalization?Ivan Rubachev, Nikita Lazarev, Artem Babenkocs.LG2026-10-19
#531Two hidden layer suffice: the caterpillar netJakob Paul Zimmermanncs.LG2026-10-19
#532Learning to Refer: Inference-Time Collaboration in Decentralized Federated LearningYuheng Ma, Chendi Wang, Qiong Zhangcs.LG2026-10-19
#533Scaling Parameter-Efficient Fine-Tuning for Brain EncodingZhuofan Josh Ying, Guanglong Sun, Nolan Ho +6cs.LG2026-10-19
#534Next Best Action: Causal Constrained Offline RL for Business Action TargetingSurya Ramachandiran, Yiming Li, Juan Mancilla-Caceres +2cs.LG2026-10-19
#535Kronecker Delta Rule for Long Context Linear AttentionAnamaria-Roberta Hartl, Levente Zólyomi, Michael List +3cs.LG2026-10-19
#536WeAct: Dynamic Weight Switching as Agent ActionsRui Shi, Xunjian Yin, Jiacheng Sang +2cs.LG2026-10-19
#537Text-to-Image Generative Modeling Without Language PretrainingKeshigeyan Chandrasegaran, Yue Zhao, Armin W. Thomas +5cs.LG2026-10-19
#538LEAF: LUT-aware Efficient Attention on FPGAsArianna Cox, Chang Sun, Lauri Laatu +7cs.LG2026-10-19
#539ClockMark: Adaptive and Host-Dependent Watermarking for Large Language ModelsYupeng Qiu, Han Fang, Ee-Chien Changcs.LG2026-10-19
#540RGH-GNN : Risk-Gated Heterogeneous Graph Neural Network for Financial Fraud DetectionMythreyee Hari, Subin Sahayam, Vegesna S M Srinivasavarmacs.LG2026-10-19
#541Reconstruction-Optimized Expert Pruning for Mixture-of-Experts Language ModelsJelena Markovic-Voronov, Petros Prastakos, Kayhan Behdin +7cs.LG2026-10-19
#542Glass-Box Deep Reinforcement Learning for High-Speed Flow ControlAmeya D. Jagtapcs.LG2026-10-19
#543Ontic state recovery through predictionPing Zhang, Quang-Huy Nguyen, Yingtie Lei +1cs.LG2026-10-19
#544Representing short-term movement to reveal animal identity and learning progressPing Zhang, Quang-Huy Nguyen, Yingtie Lei +5cs.LG2026-10-19
#545A Hybrid TFT-NBEATS Framework for Robust Multi-Horizon Photovoltaic Power ForecastingShafi Bin Sultan, Sabik Bin Sultan, Mohammad Tajrian Arafat Alvi +2cs.LG2026-10-19
#546Understanding the Benefits of Scaffolds through Computational SeparationsJingchu Gai, Adam Block, Andrej Risteskics.LG2026-10-19
#547Meta-iLaD: Identifiable Latent Dynamics via Meta-Learning of Dynamics EnvironmentsYubo Ye, Sweekar Piya, Xiajun Jiang +1cs.LG2026-10-19
#548You Are the Trigger: Speaker-Activated BackdoorsNataša Krčo, Euodia Dodd, Peter Romov +1cs.LG2026-10-19
#549A Theoretical Analysis of Environment-Aware Out-of-Distribution Detection for Vision-Language ModelsSalimeh Sekeh, Mary Wisellcs.LG2026-10-19
#550Deep catastrophic-risk-aware reinforcement learningCarlos Pérez Octavio Mendoza, Frédéric Godincs.LG2026-10-19
#551Solving the Ho--Nguyen Conjecture for Gaussian Mixtures: Applications to Mixtures of ExpertsYuyang Zhang, Qihuang Zhangcs.LG2026-10-19
#552VPFlow: Value-Predictive Planning with Imperfect World Models for Offline Goal ReachingYunzhe Hu, Dong Xucs.LG2026-10-19
#553VampPrior UnleashedAndrew A. Stirn, Abhejit Rajagopal, David A. Knowles +1cs.LG2026-10-19
#554Automated Brick Schema Knowledge Graph Completion Across BuildingsDaniel Ma, Jalil Huseynov, Xinyi Pan +4cs.LG2026-10-19
#555LiBRA: Logit Fingerprints for Byzantine-Robust Client Selection in Federated LearningSaheed A. Tijani, Frank Jiang, Ming Liucs.LG2026-10-19
#556Predictive Closure: A Set-Level Characterization of JEPA's Feature SelectionMosh Levy, Aly Lidayan, Yoav Goldbergcs.LG2026-10-19
#557Trail-Weighted Influence Scores for Approximate Outcome Prediction in Bayesian NetworksSahil Kumar Rajput, Randhir Kumarcs.LG2026-10-19
#558Shaped SAEs: Expanding the Toolkit for Mechanistic InterpretabilityOveys Delafrooz Noroozi, Bhagyashree Puranik, Upamanyu Madhowcs.LG2026-10-19
#559Sample-efficient learning with Dense Associative MemoriesAndrew Lucas, Dmitry Krotovcs.LG2026-10-19
#560Fixed-Size Active Statistical InferenceErik Skalnes, Michael Oberstcs.LG2026-10-19
#561Beyond Leaderboards: A Method for Application-Specific Capability Profiling of Large Language ModelsOleg Grynets, Vasyl Lyashkevych, Andrii Salyk +11cs.LO2026-10-19
#562Theorem prover ArendFedor Part, Valery Isaev, Sergey Sinchukcs.LO2026-10-19
#563Behavioral Probes for Information Flow in LLM SwarmsJunhui Chen, Yu Zhang, Lantian Li +1cs.MA2026-10-19
#564Robust Lightweight IoT Device Fingerprinting Under Network Traffic AnomaliesRoya Taheri, Shamik Senguptacs.NI2026-10-19
#565InteractAgent: Agentic Human Motion Interaction with Memory-Augmented ReflectionTao Zhang, Senhe Zhang, Zeyu Zhang +2cs.RO2026-10-19
#566SpaRV: Sparse Radiance Voxels for Scalable Geometrically Consistent LiDAR-Visual Mapping and RenderingJianheng Liu, Yunfei Wan, Fangming Cheng +7cs.RO2026-10-19
#567OV-PEAR: Observation-Verified Pose-Scale Estimation and Reconstruction for Unknown Industrial Manipulation ObjectsGuoqin Tang, Qingxuan Jia, Yichen Tan +4cs.RO2026-10-19
#568Vision-Language-Delta-Action: Learning Compact Deltas as Actionable Transition Interfaces for Robotic ManipulationLingsen Zhang, Wei Li, Jie He +5cs.RO2026-10-19
#569Policy Search in Code Space for Multi-Agent PathfindingMatthias Eder, Pantelis Emmanouil, Vivek Farias +7cs.RO2026-10-19
#570PaceVLA: Adaptive Temporal Action Quantization in Vision-Language-Action ModelsHojin Jeon, Jimin Lee, Taekwan Kim +6cs.RO2026-10-19
#571Reconstruction and Discrete-Event Simulation Assessment of an AnalyticalMohsen Reda Mahmoud Moursi, Ahmed Stohycs.RO2026-10-19
#572Robotic Photography System based on Vision-Language-Action ModelSong-Li Wu, Chubin Zhang, Wenbo Ding +1cs.RO2026-10-19
#573ForagerSim: Evaluating Embodied Map-Based Reasoning in Large-Scale Dynamic WorldsTomáš Musil, Martin Kotík, Michal Vavrečka +3cs.RO2026-10-19
#574ALIGN: Aligning Condition Estimation and Expression in Advantage-Conditioned Behavior CloningZechen Wang, Zhenqi Qiu, Houlong Xiong +8cs.RO2026-10-19
#575SPAR: Structural Pruning and Action Recovery for Vision-Language-Action ModelsShenli Zheng, Zhou Fang, Yuan Du +2cs.RO2026-10-19
#576Learn the Task, Not the Schedule: Reducing Spurious Cross-Arm Coupling in Bimanual Imitation LearningShuyuan Hu, Deng-Ke Wu, Yifan Jin +4cs.RO2026-10-19
#577A Probabilistic, Rotation-Preserving Kernel Operator Surrogate for Continuum-Robot Design SpacesBranden Frieden, Alan Kuntz, Varun Shankarcs.RO2026-10-19
#578Where is Physical RSI capability from? An Observational Scaling Law of LLM-as-policyZekai Li, Jiayi Yu, Jinlu Zhang +8cs.RO2026-10-19
#579CoopUQ: Robust Multi-Robot Social Navigation via Uncertainty-Aware Cooperative ForecastingZehao Wang, Jianpeng Yao, Yuping Wang +9cs.RO2026-10-19
#580Towards Interaction State Recognition in Sensorized Gecko-Inspired Adhesive Interfaces for Orbital ServicingEduart Abdullahu, Francesco Grella, Carol Martinezcs.RO2026-10-19
#581Visual Task Modeling and Automated Planning for Humanoid Robots in Education of Individuals with Autism Spectrum DisorderLada Kudláčkovács.RO2026-10-19
#582Which Depth Estimator for Jetson AGX Orin? A 2026 Benchmark of Monocular and Stereo MethodsLeaf Jiangcs.RO2026-10-19
#583On Maximum Clique and Maximum Consensus Formulations in Point Cloud RegistrationAbolfazl Babanazari, Kaveh Fathiancs.RO2026-10-19
#584What Would Removing This Corruption Change? Failure Attribution for Vision-Language-Action ModelsCarson Sobolewski, Anjali Parashar, Fei Chen +2cs.RO2026-10-19
#585Refuses When Asked, Complies When Acting: A Runtime Safety Check for Robot Control LoopsArnav Grovercs.RO2026-10-19
#586Training Controllable World Models via Action Influence MaximizationSamuel M. Bateman, Tenny Yin, Chongyi Zheng +5cs.RO2026-10-19
#587Manifold-Constrained Residual Adaptation with Frame-Adaptive Layer Aggregation for Speaker VerificationZezhong Jin, Xiaoyu Wang, Zhe Li +4cs.SD2026-10-19
#588Multilingual Voicemail and Answering Machine Detection via Pretrained Audio Embeddings and Gradient Boosting MachinesKemal Altwlkany, Muamer Pariccs.SD2026-10-19
#589AudioScorer: Learning Question-Aware Token Relevance for Large Audio Language ModelsMarwan Farag, Bin Yangcs.SD2026-10-19
#590Label Authority in Speech Emotion Recognition: Intended and Perceived Ground Truth in EmozionalmenteMarco Giordano, Stefano Giacomelli, Claudia Rinaldi +1cs.SD2026-10-19
#591Beyond Two Tracks: Speaker-Anchored Full-Duplex Dialogue RecoveryYuxuan Chen, Yang Xiao, Jack Sun +3cs.SD2026-10-19
#592Steering intonational tunes in text-to-speech synthesisJuan Pablo Vigneaux, Jennifer Colecs.SD2026-10-19
#593Selecting and Composing Agent Design Patterns: Industrial Case Evidence and Controlled Reference-System ExperimentsJia Huang, Bingsheng Ru, Bo Liang +3cs.SE2026-10-19
#594SWE-Residual: Evaluating Starting-State Robustness of Coding AgentsJinze Li, Weijie Liu, Jinfeng Xu +6cs.SE2026-10-19
#595When Coding Agents Outpace Review: Evaluating PRD-Driven Development in Mature Enterprise RepositoriesTianqi Liu, Yandong Guan, Songze Li +3cs.SE2026-10-19
#596VerifierBench: Benchmarking the Generation of Executable Verifiers for LLM AgentsJianing Yin, Ziyi Chen, Hao Wang +4cs.SE2026-10-19
#597Certifying Repeatable Entry-Replay Witnesses for COBOL-to-Java MigrationAndras L. Ferenczi, Mariya Bessonov, Allwyn Ponnudurai +3cs.SE2026-10-19
#598Optimizing Marketing Budgets for Social Influence: A Generalized Fractional Incentives FrameworkAbhishek K. Umrawal, Akhil Bhimaraju, Eliot W. Robson +1cs.SI2026-10-19
#599Where Does Rhetorical Distortion Live? A Multi-Platform, Multi-Language Measurement of Influencer ContentXucheng Yu, Jiangping Chen, Haohan Wangcs.SI2026-10-19
#600When Better Opportunities Backfire: Service Worker Responses to Parallel AI Deployment in Customer AcquisitionXinyu Fu, Shulong Luo, Narayan Ramasubbu +3econ.GN2026-10-19
#601Uncertainty-Gated SHAP-Dirichlet Refinement for MRI-Based Depression ClassificationPhuc Truong Loc Nguyen, Nguyen Truong Toan To, Truong Thanh Hung Nguyen +2eess.IV2026-10-19
#602Progressive multi-scale tumor-state memory for incomplete multimodal brain tumor segmentationMilad Rostamian, Mohammadreza Mohammadi, Mohsen Soryanieess.IV2026-10-19
#603Channel-Level Mask Guidance for Slimmable Image CompressionChen Chen, Chenggang Wu, Yongbiao Chen +3eess.IV2026-10-19
#604Sampling of Signals on Multigraphs: From Removable and Uniqueness sets to Spectral ProxiesAlejandro Parada-Mayorgaeess.SP2026-10-19
#605Physics-Driven Framework for QoS-Constrained Satellite System with Non-Linear PA DistortionHamza Ahmed Qureshi, Abuzar Babikir Mohammad Adam, Vu Nguyen Ha +2eess.SP2026-10-19
#606PhyPro-FM: A Physics and Prompt-Guided Graph Foundation Model for Contingency AnalysisXu Yang, Zhanyuan Sheng, Chenhui Lin +4eess.SY2026-10-19
#607This is SParTA: A modular, efficient and scalable transformer architecture for jet-taggingRajneil Baruah, Subhadeep Mondal, Sunando Kumar Patra +1hep-ph2026-10-19
#608Residual-Based Adaptive Refinement in Hybrid Variational-Collocation PINNs for Singular Elliptic PDEs with Mixed Dirichlet-Neumann Boundary ConditionsSomnath Giri, Muslim Malik, Rishikesh Yadavmath.NA2026-10-19
#609Polar Switch: Fast Muon Orthogonalization with Polynomial CircuitsZhehang Du, Weijie Sumath.NA2026-10-19
#610Low Residuals, Wrong Value: Learning the Viscosity Solution of Hamilton-Jacobi-Isaacs Equations with PINNsRaul Jimenez, Pablo Tejerina-Pérez, Leonid Sarieddine +6math.NA2026-10-19
#611Gradient descent reaches arbitrary accuracy in a fixed number of large steps on multiclass logistic regressionAndreea-Alexandra Musat, Nicolas Boumalmath.OC2026-10-19
#612Newton-Based Methods for Bilevel Optimization Beyond Lower-Level Strong ConvexityYouran Dong, Junfeng Yang, Wei Yao +1math.OC2026-10-19
#613Physics-Inspired Optimizers beyond the Edge of Stability: Period-Two Orbits and Delayed InstabilityAlexander Itinnlin.CD2026-10-19
#614AirMPA: A Meteorology-to-Pollution Adapter for Global Air Quality ForecastingYiheng Wang, Kai Zheng, Yuetan Lin +5physics.ao-ph2026-10-19
#615Machine-learned spectral PDE solvers for fluids and plasmasMellow Baixuan Chen, Alan A. Kaptanogluphysics.comp-ph2026-10-19
#616Reinforcement Learning Controllers for Fusion Scenario DevelopmentEvgeny Adishchev, Maxim Nurgaliev, Dmitry Sorokin +5physics.plasm-ph2026-10-19
#617Cross-disorder Learning of Imaging-derived Joint Mophometric Markers in Alzheimer's and Parkinson's DiseasesYuji Zhao, Boris Gutmanq-bio.QM2026-10-19
#618EMBER: Predicting TCR--pMHC Binding Without a Docked ComplexLin Ha, Chen Zhou, Haozheng Luo +3q-bio.QM2026-10-19
#619Arbitrage-Free Implied Volatility Surface Reconstruction via Additive MartingalesHaochen Luo, Sifan Lin, Xiaolong Luo +3q-fin.CP2026-10-19
#620Regime-Aware Interpretable Ranking for Sector RotationKelvin J. L. Koa, Ziling Liu, Xinyang Li +7q-fin.PM2026-10-19
#621LOB-Impact Benchmark: Emergent Market Impact in Generative Limit Order Book ModelsGeorge Nigmatulin, Valentin Mohl, Sascha Frey +6q-fin.TR2026-10-19
#622Physics-anchored residual quantum neural networks for cloud-cover parameterizationZhuo Wang, Ce Yu, Bin Yangquant-ph2026-10-19
#623Supervised Learning with Quantum Hamiltonian EmbeddingsRiccardo Molteni, Minjun Jeon, Paolo Braccia +8quant-ph2026-10-19
#624A Pitfall in the Evaluation of Gene Perturbation ModelsGeorge Panagopoulos, Saman Omidi, Tsz Pan Tong +1stat.AP2026-10-19
#625Corrected Block Sparse Spectral Optimization: Exact Models, Finite Identification, and Local DynamicsOmid Shams Solaristat.ML2026-10-19
#626Fair Regression under Approximate Demographic ParityWeiwei Wang, Xianyang Zhang, Raymond K. W. Wongstat.ML2026-10-19
#627Dynamic Dual-Feedback Conformal Inference for Time Series ForecastingSonglin Du, Ling Luo, Uwe Aickelinstat.ML2026-10-19
#628Federated Community Detection in Bipartite NetworksWanjie Wangstat.ML2026-10-19
#629Towards instance-dependent regret optimality in Episodic MDPs with Posterior SamplingVictor Boone, Cyrille Kone, Waris Radji +2stat.ML2026-10-19
#630Robust Latent Variable Graphical Models: Exact Recovery and Fundamental LimitsChuansen Peng, Xiaojing Shenstat.ML2026-10-19
#631Selecting the Best Few with Human Evaluators: Adaptively Combining Ratings and Pairwise ComparisonsMotti Goldberger, Nils Rudistat.ML2026-10-19
#632R2-GP: Variance-Calibrated Priors for Additive Gaussian ProcessesJavier Enrique Aguilar, Soham Mukherjee, David Kohnsstat.ML2026-10-19
#633Gaussian Approximation of Besov Functions for Logistic Classification on ManifoldsGuanhang Lei, Lei Shi, Xiaoming Yuanstat.ML2026-10-19
#634Cooperative Multi-Agent Reinforcement Learning for Market Making on Prediction-Market Order BooksSkander Lejmistat.ML2026-10-19
#635Teacher Supervision, Fixed Representations and Calibration: Exact Risk Calculations for Candidate-Scoring Decision ModelsAgus Sudjianto, Denis Burakovstat.ML2026-10-19
#636Diffusion Score Estimation with Shallow Neural Networks: Regularity, Approximation, and Finite-Sample RatesFan Liu, Yahong Yang, Wei Zhustat.ML2026-10-19
#637Communication Complexity of Universal FeaturesLunjia Hu, Anish Jayant, Peter Li +2stat.ML2026-10-19

latest · trends · arXiv announcement batches follow US Eastern weekdays