PaperScope
LIVE · 2026-10-08 05:40 UTC

New Papers · 2026-10-07 516 submissions

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

#TitleAuthorsCatDate
1Constrained Diffusion for Data-Scarce Orbital Monte Carlo in Constellation TaskingOmar Ramadan, Sam Siavoshian, Amir Kashif Saeed +3astro-ph.IM2026-10-07
2Origins of Universal Machine Learning Force-Field Errors in Multicomponent MaterialsHongwei Du, Dingyang Lv, Baole Wei +10cond-mat.mtrl-sci2026-10-07
3Progress and Prospect of AI in ARPES WorkflowSandy Adhitia Ekahana, Aalok Tiwari, Pratik Saud +4cond-mat.other2026-10-07
#4The Winner's Curse in LLM Self-Improvement Loops: Selection Noise, Lock-in, and Acceptance RulesLitao Hu, Yutong Tangcs.AI2026-10-07
#5We Query, Therefore We Compute: On Oracle Computation beyond the Machine, with an Application to AgentsKefan Liu, Fengning Ou, Yelin Luo +1cs.AI2026-10-07
#6RT-Safe: Benchmarking Agent Safety in Real-Time Embodied EnvironmentTianruo Rose Xu, Jiawei Ren, Yichi Yang +2cs.AI2026-10-07
#7The AI Evaluation EcosystemYash Dave, Sang T. Truong, Serena Wang +1cs.AI2026-10-07
#8SearchWorld: Spatial Value-Grounded Imagination for UAV Object Search via World ModelsYatai Ji, Zhengqiu Zhu, Yong Zhao +5cs.AI2026-10-07
#9Relevance Is Not Sufficiency: What Actually Closes the Evidence Gap in Long-Term Memory QAYufeng Li, Shuxin Li, Zhenhua Xu +7cs.AI2026-10-07
#10TopoGraphRAG-Bench: Evaluating Multimodal GraphRAG on Layout-Grounded Evidence ReasoningRuochi Li, Jianzhe Lin, Haoxuan Zhang +4cs.AI2026-10-07
#11DUDA-Bench: Benchmarking LLM Agents on Multimodal Data-Driven Urban DiagnosisYizhi Song, Hang Ni, Weijia Zhang +1cs.AI2026-10-07
#12From Plausible Hierarchies to Useful Taxonomies: Evaluating Agentic Harnesses on Customer FeedbackPrabhath Chellingi, Raviraja G, Viraj Bagalcs.AI2026-10-07
#13Let the Library Speak: Self-Advertised Method Selection for Formal ProvingXiaopeng Yuan, Suijin Wang, Yanli Wang +5cs.AI2026-10-07
#14Efficient Reasoning with Flow Language ModelsHanru Bai, Faissal Izermine, Oscar Davis +1cs.AI2026-10-07
#15RSI-Forge: From Research Papers to Environments for Recursive Self-ImprovementRenxiong Wang, Darvin Yi, Abril Herrlein +16cs.AI2026-10-07
#16LLM-Enabled UAV Dispatch: A System-Level Survey and TaxonomyXiao Han, Aoyang Quan, Xiangyu Zhao +2cs.AI2026-10-07
#17MIMESIS: Learning User Simulators as Training Environments for Interactive AgentsHoang Phan, Dat Huynh, Andrey Zhmoginov +7cs.AI2026-10-07
#18The Attribution Blind Spot: Layerwise Trajectory Diagnostics for Source Reliance in Retrieval-Augmented Language ModelsZhe Yu, Wenpeng Xing, Yunzhao Wei +4cs.AI2026-10-07
#19Cognitive Schemas, Laws and TasksAntal Jakovác, András Telcscs.AI2026-10-07
#20Ream: Unfolding Mutual Awareness in Human-Agent WorkspacesPeiling Jiang, Sangho Suh, Varsha Kishore +6cs.AI2026-10-07
#21Reliability of LLM Judges for Evaluating Entity AlignmentVaibhava Lakshmi Ravideshik, Mayank Kejriwalcs.AI2026-10-07
#22DrugTargetWorld: A Synthetic Biobank for Training and Benchmarking AI ScientistsSamuel Margolis, Paul Schmiedmayer, Alan Huang +12cs.AI2026-10-07
#23World Potential Model: Pretrained World Knowledge as Progress PotentialsJun Zhao, Jixin Tang, Yang Shu +6cs.AI2026-10-07
#24Dual- versus Single-Suggestion AI Support for Radiographic Interpretation in Residents: Randomized Multireader StudyLin Wu, Zhe Xu, Hongyi Wang +10cs.AI2026-10-07
#25Learning Situation-Conditioned Thinking Policies for Long-Term LLM AgentsHong Sucs.AI2026-10-07
#26SafeEvo: Deciphering the Safety Alignment Mechanism and Evolution in Language ModelsMiao Yu, Hao Huang, Lu Yuan +3cs.AI2026-10-07
#27How Do Agentic LLMs Decide to Call Tools? A Tool-Call Vector Shaped by SuppressionXijie Gong, Tingxu Han, Jiahao Zhang +5cs.AI2026-10-07
#28Automatically Building and Updating a Knowledge Graph of MLIP ModelsAlexis Beer, Liudmyla Klochko, Mathieu d'Aquincs.AI2026-10-07
#29MeshSIPP: Efficient Lattice Planning in Dynamic EnvironmentMarat Agranovskiy, Konstantin Yakovlevcs.AI2026-10-07
#30Shared and structured inputs undermine collective random choice by reasoning AI agentsTakahiro Ezaki, Naoto Imura, Katsuhiro Nishinarics.AI2026-10-07
#31Cost-Efficient Theorem Proving via Agent Orchestration in Program VerificationShuangjie Yao, Nikolaus Holzer, Mark Paul Santolucito +3cs.AI2026-10-07
#32System Switch: When Should a Fast Decision Model Stop and Think?Gian Luca Bailocs.AI2026-10-07
#33A Tale of Two Error Categories: Exploring Concealed Trade-Offs in the Errors of Automated Judges in Evaluation of Uncertainty QuantifiersEvgenia Ilia, Wilker Azizcs.AI2026-10-07
#34From Expert-Guided Proof Search to Automated Open-Problem SolvingAdrián Zámečník, Matěj Kripner, Martin Koutecký +5cs.AI2026-10-07
#35SkillForge: Co-Evolving Skills and Agents via Dynamic Skill LifecyclesYuyao Ge, Yiwei Wang, Yuchen He +5cs.AI2026-10-07
#36Self-Evolve With a Reference:Anchored Training of Tool-Integrated AgentsWenjie Liao, Liangjie Zhao, Zehong Caocs.AI2026-10-07
#37LiveMACE: Process-Aware Evaluation of LLM Agent Capabilities in Evolving MarketsJun Zhao, Leiming Fu, Yanbo Wen +9cs.AI2026-10-07
#38Think Before You Paint: Recursive Latent Reasoning for Diffusion ModelsPaweł Skierś, Małgorzata Grzanka, Wojciech Masarczyk +2cs.AI2026-10-07
#39Outperformance Inverse Optimization: Learning Objective Functions that Outperform Agent DecisionsAkira Kitaokacs.AI2026-10-07
#40NL2Hull: A Natural Language-Driven Constrained Ship Design Decision FrameworkWenhua Huo, Fenglei Han, Wangyuan Zhao +2cs.AI2026-10-07
#41Where Can a Decision Model Diagnose HVAC Faults? Reasoning Demand, Physical Representation, and Robustness Under ShiftWooyoung Jungcs.AI2026-10-07
#42AgentTime: Can Agents Estimate and Control Their Own Runtime?Michael Ofengenden, Maksym Andriushchenkocs.AI2026-10-07
#43Successive Training Stages and Large Language Model Persuasion: Effects of Misalignment, Supervised Fine-Tuning, and Preference OptimizationAntony Dalmiere, Pascal Marchand, Guillaume Auriol +1cs.AI2026-10-07
#44From Expected Harmfulness to Likelihood: A Probabilistic Reformulation of Jailbreaking LLM AgentsJuanyang Xu, Zheng Wang, Xingyu Zhao +2cs.AI2026-10-07
#45What the Sleeve Feels: Explainable Machine Learning for Textile Pressure-Based Postural ScreeningLimon Bin Hossain, Md Sadib Rahman Anantacs.AI2026-10-07
#46Learning to Accumulate Knowledge with Mutual InformationYuyang Zhao, Lizi Liao, Leyang Shen +4cs.AI2026-10-07
#47Loud Failures, Quiet Failures: Fault Detection and Recovery in Tool-Using Language Model AgentsObada Kraishancs.AI2026-10-07
#48HGP:An on-device personalized agent memory via hybrid graph storageRan Zhou, Xueming Han, Jiaheng Liu +4cs.AI2026-10-07
#49SkillSandbox: Skill Verification via Dynamic Scenario SynthesisSerin Kim, Kwangwook Seo, Dokyung Song +2cs.AI2026-10-07
#50RewardWeaver: Long-Horizon Interactive Learning for Language Agents via Self-Evolving Reward AdaptationHengbo Xiao, Boyao Zhang, Purui Liu +4cs.AI2026-10-07
#51UniSkill: Learning Actor-Aligned Skill Proposals for an Evolving PolicyYifei Lu, Cheng Liu, Dianzhi Yu +4cs.AI2026-10-07
#52Agentic AI-Assisted Modeling for Production Scheduling: Assessment in Constraint ProgrammingÁngel Sánchez-Fernández, Javier Pernas-Álvarez, Diego Crespo-Pereiracs.AI2026-10-07
#53GAGR-Lab: Evaluating Joint Spatial-Geometric and Analytic Function ReasoningJingyao Zhang, Yun Li, Lu Hancs.AI2026-10-07
#54OOM-RL II: Reality Is an Oracle, Not a Debugger Provenance-Constrained Diagnosis in Continually Evolving Agent-Engineered SystemsKun Liu, Liqun Chencs.AI2026-10-07
#55Stale, Misattributed, or Late: Where Personal Memory Fails Before GenerationHaonan Deng, Park Sinchaisrics.AI2026-10-07
#56AI Safety Considerations for Agents With Limited Time to ActLeo Zeitler, Jack Richings, Victoria Nocklescs.AI2026-10-07
#57The Handover Problem: Governing Autonomy Transitions in Human-AI CollaborationVicente Pelechano, Antoni Mestre, Manoli Albert +1cs.AI2026-10-07
#58Open-MMUnlearning: Unifying Methods and Evaluation for MLLM UnlearningJunkai Chen, Yuhao He, Qianshan Wei +19cs.AI2026-10-07
#59Reasoning-Token Spikes Under Prompted Untruthful Responding in Large Language ModelsMaverick Morales, Tomáš Dominik, Vermut Gao +4cs.AI2026-10-07
#60SOTA: Stock Options Trading Agents Guided by Option-Implied Return DistributionsYizhen Xie, Mengyang Liucs.AI2026-10-07
#61RunningTab: Direct Workspace Interaction with Environment-Side TabsJinheon Baek, Soyeong Jeong, Yumin Choi +2cs.AI2026-10-07
#62Before They Can Solve: Predicting Post-Training Coding-Agent Performance from Base ModelsTan Yu, Alexander Bukharin, Khushi Bhardwaj +19cs.AI2026-10-07
#63EmbodiedRSI: Active Continual Robot Learning Through Hypothesis-Guided Co-EvolutionPython Song, Zhixuan Liang, Kelsey Fu +3cs.AI2026-10-07
#64Validity Without Ground Truth: What Stated-Preference Economics Offers the Evaluation of Language ModelsDaniel Robert Kling Alexander, Catherine Louise Klingcs.AI2026-10-07
#65RECAST: Learning to Compute the Right Context through Adaptive Evidence RoutingYilun Hao, Krishna Sayana, Isabella Ye +4cs.AI2026-10-07
#66SciExam for ENSO: Can AI Agents Build Climate Models?Yinling Zhang, Langchen Liu, Dongbin Xiu +4cs.AI2026-10-07
#67RoboJEPA: Scaling Robotic Latent World ModelsArtem Zholus, Nicolas Beltran-Velez, Jianhao Yuan +9cs.AI2026-10-07
#68When Algorithmic Exploration Becomes Cheap: A Case Study of Agentic Research in EDAKeren Zhu, Yu Deng, Xiaoyu Hao +6cs.AR2026-10-07
#69Evolve on the Host, Predict on the Edge: Deploying Online Neuroevolutionary Architecture Search for Cross-sectional Stock Return PredictionJonathan Chang, Zimeng Lyucs.CE2026-10-07
#70Dialect-Robust Speech Language Models with Synthetic Pseudo-Dialect AugmentationShunsuke Mitsumori, Tomoya Mizumoto, Yusuke Fujitacs.CL2026-10-07
#71OnlineQAT: On-Policy Distillation for Ultra-Low-Bit Large Language ModelsWenjun Wang, Heng Li, Yanggan Gu +1cs.CL2026-10-07
#72Expert Coupling in MoE Pretraining: Reducing All-to-All Overhead with Correlated Placement and Token ShufflingRadha Gulhane, Quentin Anthony, Beren Millidgecs.CL2026-10-07
#73The Persona Hierarchy Model: Understanding Contextual Generalization in Fine-Tuning LLMsJiachen Zhao, Zhengxuan Wu, David Bau +1cs.CL2026-10-07
#74ARCS: Towards Precise Text-to-SQL via Structured DisambiguationYihao Hu, Yanlin Feng, Naoki Otani +1cs.CL2026-10-07
#75Arctic Questions, Missing Answers: A Dataset and Benchmark for LLM Abstention in Arctic ScienceBenjamin Wilcox, Dawei Gao, Pradeeban Kathiravelu +3cs.CL2026-10-07
#76Right Number, Wrong State? Measuring Cross-Jurisdiction Substitution in LLM Recall of State PolicyJiayu Fengcs.CL2026-10-07
#77BanglaRhet: Benchmarking Classical and Transformer Models for Rhetorical and Persuasion Detection in Bangla Political SpeechRohit Kumar Sen, Anik Chowdhurycs.CL2026-10-07
#78Goldsmith: Gold-Loss-Guided Definition Optimization with an Agentic Annotation HarnessYihan Li, Hanyi Zhang, Xiaoxi Jiang +1cs.CL2026-10-07
#79A Comparative Study of Evaluation Metrics for Long-Document Financial Narrative Summarization with TransformersNadhem Zmandar, Mo El-Haj, Paul Raysoncs.CL2026-10-07
#80RELATE: An Evaluation Framework for measuring Relational Orientation of Large Language ModelsShivam Shukla, Jihye Kim, Shubham Gaur +2cs.CL2026-10-07
#81How Do LLMs Change Predictions Under Negation?Jongwook Yoon, Jongwon Lim, Sungjib Lim +2cs.CL2026-10-07
#82Which Language Should a Skeleton Speak? Language Choices in Multilingual ReasoningHyeonSeok Lim, SeungWoo Song, Inho Won +3cs.CL2026-10-07
#83On-Policy Distillation Teaches New Skills but Not New KnowledgeYixuan Tang, Yi Yangcs.CL2026-10-07
#84Rubric Spans are Label Representations: Joint LLM Encoding for Short Answer ScoringZhifan Sun, Sebastian Gombert, Fabian Zehner +3cs.CL2026-10-07
#85Alice: A Large-Scale German Benchmark for Rubric-Based Multi-Dimensional Automatic Short Answer ScoringZhifan Sun, Sebastian Gombert, Jannik Lossjew +6cs.CL2026-10-07
#86SAPD: Step-Aligned Privileged DistillationTianle Wang, Jiayu Liu, Ruizhi Zhao +1cs.CL2026-10-07
#87InsClaimBench: Benchmarking Insurance Claim Adjudication Across the Decision ChainLinqi Zhang, Chong Qi, Yan Cheng +4cs.CL2026-10-07
#88From Pareto to Preference: Personalized Test-Time Scaling via Amortized Agentic Policy DiscoveryXinglin Wang, Zishen Liu, Tong Zheng +9cs.CL2026-10-07
#89SpikingVLA: Asynchronous Spiking Vision-Language-Action ModelsJingya Wang, Dehao Zhang, Shuai Wang +3cs.CL2026-10-07
#90Bridge Routing Heads: Where Multilingual Multi-hop Reasoning Lives in LLMsSeunghan Kim, Minyeong Choe, Hyunil Kim +1cs.CL2026-10-07
#91Shaer: Controlled Arabic Poetry Generation with Meter Subform and Semantic ConditioningAhmad Abbas, Tamara Fakih, Nour Fakih +1cs.CL2026-10-07
#92Decoupling Logic from Persona: Structural Immunity of Edge LLM Agents to Context PollutionMasaaki Nakatsu, Reno Wangcs.CL2026-10-07
#93Judging in Latent Space: Efficient Generative Reward Modeling via Semantics-Preserving CompressionMingqing Yuan, Xiaobo Liang, Junwei Yang +5cs.CL2026-10-07
#94MIRROR: From Imitation to Internalization in LLM PersonalizationHuayi Lai, Jicheng Yang, Min Yi +1cs.CL2026-10-07
#95A Deafening Silence: Catastrophic Forgetting Lives in the Output Embeddings of Tokens the Data Never SpeaksJonghyun Han, Younghoon Song, Jongyoul Parkcs.CL2026-10-07
#96Training Advisors for LLM Agents from Task OutcomesSergei Polezhaev, Barys Liskavets, Ori Press +1cs.CL2026-10-07
#97Itgan at NADI 2026 shared task: Parameter-Efficient Whisper Adaptation for Robust, Mixed-Dialect and Code-Switched Arabic ASRIbrahim Almajaics.CL2026-10-07
#98EASE: Entropy-Adaptive Distribution Shaping for Evading AI-generated Text DetectorsJicheng Zhou, Kahim Wong, Jialong Wang +1cs.CL2026-10-07
#99The Long Road to the Same Answer: Cognitive Bias Under Escalating Reasoning Budgets in Large Language ModelsObada Kraishancs.CL2026-10-07
#100Cache the Encoder Within:Compact, Reusable Memory across LLM QueriesHanzuo Liu, Chunyu Liu, Chaofan Lin +2cs.CL2026-10-07
#101ExperienceIndex: Artifact-Grounded MemoryPeter Baile Chen, Geoffrey X. Yu, Xinming Liu +5cs.CL2026-10-07
#102I would rather quit NLP than read another paper like this: The rise of antithesis in NLP papersOlga Zamaraeva, Adrián Gude, Roi Santos-Ríos +1cs.CL2026-10-07
#103Mechanics of Long-Context Hybrid Models Part 1.1: From Hybrid Attention to Hybrid PositionXiaoran Liu, Ziwei He, Xipeng Qiucs.CL2026-10-07
#104LLM4Impact: Integrating Heterogeneous Information for Scientific Impact PredictionYong Cao, Markus Flicke, Haoyu He +2cs.CL2026-10-07
#105InterView-C: A Synchronized Multimodal Corpus of VR Avatar-Mediated Survey InterviewsPatrick Schrottenbacher, Leon Hammerla, Lydia Kleine +2cs.CL2026-10-07
#106HySPE: Positional Encoding via Symplectic Dual ShearsZhongping Jics.CL2026-10-07
#107Beyond Outcome Rewards: Constructing and Assigning Retrieval Credit for Search AgentsWenyu Huang, Xinyu Hou, Pavlos Vougiouklis +2cs.CL2026-10-07
#108LLM Persuasion Is in the Eye of the EvaluationKamile Dementaviciute, Julija Vaitonyte, Tijl De Biecs.CL2026-10-07
#109Nobody Truly Agrees on Sentiment: Humans, Bespoke Tools, and LLMs Struggle with Social Media TextsHimarsha R. Jayanetti, Sivakanesan Dhanushkanda, Shuai Hao +2cs.CL2026-10-07
#110Learning to Act with Task Progress: Distilling Small Agents from Compact Teacher SupervisionWenxi Gancs.CL2026-10-07
#111Document-Level Text Simplification in Estonian Using Large Language ModelsMeeri-Ly Muru, Eduard Barbucs.CL2026-10-07
#112CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-EvolutionJixuan Chen, Jiaxin Zhang, Qinyuan Ye +11cs.CL2026-10-07
#113PHRBench: A Behavioral Evaluation of Post-Hallucination Reasoning in LLMsLinghao Meng, Feng He, Xuan Yang +5cs.CL2026-10-07
#114Your Prompt Should Do More: Effects of Retrieval Instructions in Embedding ModelsAmanda Myntti, Jenna Kanerva, Veronika Laippala +1cs.CL2026-10-07
#115EngramEdit: Decoupled Knowledge Updates in LLMs through Conditional MemoryHongru Cai, Ran Wei, Wenjie Wang +4cs.CL2026-10-07
#116Adversarial Images Hijack Web Agents from Visual Grounding to Browser ExecutionWanjing Han, Levi Taiji Li, Mu Zhang +2cs.CR2026-10-07
#117Package Hallucination Attacks on Coding Agents through Prompt Injection in Rule FilesYupu Wang, Zhengyuan Jiang, Reachal Wang +1cs.CR2026-10-07
#118Ask the Expert: LLM-Guided Reinforcement Learning for Autonomous Cyber DefenseFernando Martinez, Abhishek Satyam, Tao Li +3cs.CR2026-10-07
#119Secure-CUA: Controlling Untrusted Influence in Computer-Use AgentsSarthak Choudhary, Mihai Christodorescu, Ashish Hooda +3cs.CR2026-10-07
#120Constitution-Guided WatermarkingToluwani Aremu, Samuele Poppi, Nils Lukascs.CR2026-10-07
#121MARS: Malware Analysis with Rule-Based Scoring of LLM ClaimsHyeongjun Choics.CR2026-10-07
#122Correct Answers, Unsupported Findings: Evidence Binding in Forensic Reconstruction of LLM Agent LogsTaehyeon Yun, Dongho Kim, Geonwoo Kim +3cs.CR2026-10-07
#123Understanding and Mitigating Token-Pruning-Induced Vulnerabilities in VLMsShuailong Wang, Xinyu Lyu, Shengming Yuan +3cs.CR2026-10-07
#124Defensive Sufficiency in a Stackelberg Model of AI SecuritySubhabrata Majumdar, Rajlakshmi Chavancs.CR2026-10-07
#125Constrained-Action AI Remediation for SIEM/XDR via a NeMo-Guardrails ProxyGeorgios Koutidis, Nikolaos Kekatos, Tom Nianios +1cs.CR2026-10-07
#126Sensitive-Topic Leakage Through LLM Routing Metadata: Measurement and MitigationTeng-Ruei Chencs.CR2026-10-07
#127SLDR: Defending Against Malicious Fine-tuning via Selective Layers Recovery and Dynamic RoutingHui Zhang, Yachao Yuan, Jiayun Wang +3cs.CR2026-10-07
#128Pooling Representation Autoencoders for Efficient DiffusionRamón Calvo-González, Youssef Saied, François Fleuretcs.CV2026-10-07
#129Adaptive Visual Token Reduction for Accelerated Image UnderstandingSeyoung Jeong, Jong Pil Yun, Sang Jun Leecs.CV2026-10-07
#130PhyDiCT: Plug-and-Play CT Reconstruction from Sparse X-Rays via Differentiable Rendering and Strong PriorsWeicheng Dai, Shantanu Ghosh, Kayhan Batmanghelichcs.CV2026-10-07
#131Hardware-aware Calibrated Clustered Attention for Efficient Visual Geometric TransformersWeitian Wang, Shubham Rai, Cecilia De La Parra +1cs.CV2026-10-07
#132EM-SNN: Efficiently Modulated Spiking Neural Network for Remote Sensing Image DehazingJie Shao, Jiaqi Ma, Wenwen Min +4cs.CV2026-10-07
#133Why VLMs Miss Small Objects, and When Zooming In Is SafeJunzhe Shi, Yuan Gan, Shida Jiangcs.CV2026-10-07
#134SAREO-FM: Decoupled Semantic Supervision for SAR-EO Foundation ModelsJeonghyeok Do, Munchurl Kimcs.CV2026-10-07
#135VIS-Ground: Video Interactive Storytelling with Contextual GroundingBingxuan Li, Yiwen Song, Xueqing Wu +10cs.CV2026-10-07
#136Visual Jev Rewards: Reference-Bound Verification for Multi-Subject Image GenerationBaoteng Li, Wenzhuo Wu, Kongming Liang +1cs.CV2026-10-07
#137GRC-Net: Global Representation Consistency Network for Unsupervised Multimodal Anomaly DetectionSeyoung Jeong, Jong Pil Yun, Sang Jun Leecs.CV2026-10-07
#138CRT-HMAR: Causal Requirement Tracing-Guided Hierarchical Multi-Agent Regulation for Open-Task-Aware Infrared-Visible Image FusionZengyi Yang, Shuai Yuan, Zhong-Cheng Wu +3cs.CV2026-10-07
#139TileSkipper: Region-Adaptive Tile Pruning for 3D Gaussian SplattingJingxing Li, Yongjae Lee, Deliang Fan +3cs.CV2026-10-07
#140Do Image Editors Follow Depth-Dependent Blur and Aperture Response? A Rendered-Ground-Truth Pilot AuditZhihan Chen, Yuhuan Zhao, Yijie Zhu +4cs.CV2026-10-07
#141Closing the Loop on Contrail Avoidance with Satellite VerificationSpandan Ghose Chowdhurycs.CV2026-10-07
#142Unified Multi-plane Autoregressive Diffusion for 3D Multi-contrast MRI SynthesisYejee Shin, Geonhui Son, Jinglu Wang +3cs.CV2026-10-07
#143PPCAR-Net: Projection-Refined Parametric 3D Coronary Artery Reconstruction from Sparse X-ray Angiographic ViewsYu Ren, Hwee Kuan Lee, Tat-Jen Cham +2cs.CV2026-10-07
#144Quantifying Volumetric Risk: Class-Aware Asymmetric Weighted Conformal Prediction for 3D Medical Image SegmentationShadi Alijani, Fereshteh Aghaee Meibodi, Homayoun Najjarancs.CV2026-10-07
#145One Frame, Full Heartbeat: ECG-Free Cardiac Cine MRI Synthesis via Phase-Conditioned Flow MatchingShiyi Wang, Ruochen Sun, Peirong Liu +2cs.CV2026-10-07
#146TiTok: Audio-Visual LLM for Multi-Segment Temporal GroundingEunji Shin, Dahyun Choi, Seungyeon Jo +2cs.CV2026-10-07
#147trACT: temporal revelation Airborne Camera TrapOliver Bimber, Rakesh John Amala Arokia Nathan, Mohamed Youssef +3cs.CV2026-10-07
#148Spatial Latent Reasoning for Embodied Reference UnderstandingLing Li, Jianhui Zhong, Wei Liu +3cs.CV2026-10-07
#149Event-Aligned Visual Action Reasoning for World Action ModelsXiaomeng Yang, Yushu Wu, Yi Gao +4cs.CV2026-10-07
#150SkillCycle: Co-Evolving Agent Policies and Skill BanksLing Li, Qiuyu Shen, Zheng Jiang +3cs.CV2026-10-07
#151Controllable Crowd Generation through World-Model PlanningJunGyu Lee, Jisu Shin, Seunghyun Shin +1cs.CV2026-10-07
#152InscriptionOCR: A Dataset and Method for Understanding InscriptionsJaidev Sanjay Khalane, Akbar Ali, V. N. Prabhakar +1cs.CV2026-10-07
#153Mixture of Layers: Dynamic Layer Routing for Visual ReasoningJeonghwan Kim, Sofia Stoica, Jiwan Chung +5cs.CV2026-10-07
#154TIRA: Tumor Immune Representation Adaptation for Zero-Shot Cross-Cancer MSI and TMB PredictionDasari Naga Rajucs.CV2026-10-07
#155LighTROcc: Lightweight 4D Occupancy Forecasting via Instance-Centric 3D GaussiansHwanhee Jung, SeungHyeon Kim, Inkyu Koo +3cs.CV2026-10-07
#156From Global Alignment to Local Grounding: Zero-Shot Chinese Character Recognition with Radical VerificationYu-Heng Shih, Bing-Chen Wu, Tsz-To Wong +6cs.CV2026-10-07
#157Iris-3B: Going Beyond the Latent with Pixel-Space Diffusion Training, Conversion and Fine-TuningHanqiu Li Cai, Chema Garabitocs.CV2026-10-07
#158RLHND: Video Foundation Models as Physically Grounded Hand Trackers for Robot LearningSeungjun Moon, Subin Jeon, Sangwoo Kim +2cs.CV2026-10-07
#159An Invariant Tangent-Angle Descriptor and a Band U-Net for 2D Fragment Adjacency PredictionGuillaume Brouillette, Alain Goupil, Pierre-Olivier Parisé +1cs.CV2026-10-07
#160InstanceBench: Diagnosing Referential Reasoning and Target Identity in Referring Expression SegmentationYuchen Li, Shaoyang Zhou, Yiran Wang +5cs.CV2026-10-07
#161Gaussian Material Fields for Volumetric Multi-Energy CT DecompositionJian Lin, Jiancheng Fang, Hongming Shan +3cs.CV2026-10-07
#162SpatialUQ: Post-Hoc Uncertainty Quantification from Spatial Consistency in Black-Box Vision ModelsMd Kawsher Mahbub, Milon Biswas, Mirza Niaz Morshed +1cs.CV2026-10-07
#163RT-DETR-World: Transferring Rich LLM Semantics to Real-Time Open-Vocabulary DetectionYupeng Zhang, Ziyi Zhao, Juntao Cheng +4cs.CV2026-10-07
#164TERRA: Learning Transportable Latent Actions through Temporal Effect Representation and Relational AlignmentTianxingjian Ding, Mubarak Shah, Yu Tiancs.CV2026-10-07
#165LiG-DETR: Local-in-Global Reassembly in Latent Space for Aerial Object DetectionYupeng Zhang, Fangzhuo Gao, Juntao Cheng +3cs.CV2026-10-07
#166OmniCam: Omni-Camera Trajectory Generation via Geometry-Grounded Pose Token LearningZhenyang Liu, Chenjie Cao, Yisu Zhang +5cs.CV2026-10-07
#167STRIKE: Learning Visual State Transitions for Physical World ModelingWenbin Teng, Tianshuo Xu, Depu Meng +5cs.CV2026-10-07
#168It Is Not Seeing the Hazard: A Frozen Vision-Language Safety Score Measures Its Caption BankSamuel Tetteh, Cody Flemingcs.CV2026-10-07
#169ActiveLang: Active Open-Vocabulary 3D Mapping with Semantic-Uncertainty-Guided ExplorationLiyan Chen, Hairong Yin, Huangying Zhan +3cs.CV2026-10-07
#170KASALv2: Fully Automatic 3D Rotational Symmetry Classification and Axis LocalizationMengxin Zhang, Yulin Wang, Chen Luo +2cs.CV2026-10-07
#171WAPR: A Foundation Model for Wide-Angle Refinement in Unseen Object Pose EstimationYulin Wang, Mengting Hu, Hongli Li +2cs.CV2026-10-07
#172Visual Evidence Under Cross-Examination: Evaluating and Controlling Decision-Level Evidence Use in Vision-Language ModelsHuiyao Zhang, Jin Bai, Zilong Su +6cs.CV2026-10-07
#173Gradient-Based Trajectory Optimisation over Continuous Poses for Sparse-View Cone-Beam CTLinda-Sophie Schneider, Simon Wittl, Gabriel Herl +1cs.CV2026-10-07
#174STORK: Spatio-Temporal Observation of uterine contRactions via neural networKsMelissa Schween, Tristan Gottwald, Jordina Aviles Verdera +3cs.CV2026-10-07
#175Identity-Duplication Auditing in National-Scale Neuroimaging RepositoriesJiheng Li, Michael E. Kim, Trent M. Schwartz +19cs.CV2026-10-07
#176Quasi-Binarized Autoencoders: An Architecture-Independent Information Bottleneck for Medical Image Anomaly DetectionShouhei Hanaoka, Takahiro Nakao, Atsushi Takamatsu +2cs.CV2026-10-07
#177A Multi-Source Ultrasound Benchmark Revealing the Limits of Contemporary Self-Supervised Anomaly Detection MethodsMarco Riedenauer, Daniel Kienzle, Pratik Mayekar +1cs.CV2026-10-07
#178What Makes Synthetic Hard Negatives Work in Vision-Language Pretraining?Nikos Giakoumoglou, Paschalis Giakoumoglou, Andreas Floros +2cs.CV2026-10-07
#179Latent Watermarks under Generative Editing: A Benchmark and Analysis of Detection SurvivalSung Ju Lee, Nam Ik Chocs.CV2026-10-07
#180Enhancing Multi-Region Stylization with Interior-Guided Boundary RepairHong-Son Nguyen, Thi-Ngoc-Hanh Lecs.CV2026-10-07
#181DynStream: Online Streaming 4D Gaussian Reconstruction of Dynamic Worlds from Unposed VideoDingwei Xian, Xiaoyu Zhou, Yajiao Xiong +2cs.CV2026-10-07
#182MeshCarve: Artisan Mesh Generation with Flow Matching in Compact Latent SpacesXiyu Wang, Ruocheng Wu, Yufei Wang +3cs.CV2026-10-07
#183Beyond Group Splits: Specimen-Level Cross-Validation and Visual Attribution for Remaining-Shelf-Life Regression in Climacteric FruitRovhona Mudau, Jean Frederic Isingizwe Nturambirwe, Clement Nthambazale Nyirendacs.CV2026-10-07
#184SoccerNet-FoulRet: Retrieving Semantically Similar Soccer Foul VideosJacobus Arthur, Ahmad Sait, Batool Hani +6cs.CV2026-10-07
#185Flow-of-Thought: A Framework for Visual ReasoningMariia Baidachna, Nicolas Pugeaultcs.CV2026-10-07
#186Diffusion-Generated Image Watermarking: A Two-Axis Taxonomy and Three Protocol-Bounded Case StudiesSung Ju Lee, Nam Ik Chocs.CV2026-10-07
#187PARC-Loc: Text-to-Point-Cloud Localization with Partial Assignment and Relational ConsistencyShengkai Ma, Zhenyu Hou, Weihua Caocs.CV2026-10-07
#188Relational Abstractions for Spatial Reasoning with Diffusion ModelsAna Ezquerro, Ozan Özdenizcics.CV2026-10-07
#189CIRSeg: Coarse-to-Fine Intensity-Robust Liver Segmentation with Source-Free Continual Test-Time AdaptationRuoshi Xu, Mingqi Gao, Shengda Luo +1cs.CV2026-10-07
#190UltraWorld: Learning Interactive Ultrasound World Models from Untracked Clinical Videos with Acoustic Sampling MapKeke Yang, Erqi Wang, Sainan Guan +1cs.CV2026-10-07
#191Counterfactual Route Optimization for Gaussian Head Avatar ModelingShikun Zhang, Yong Li, Yiqun Wang +2cs.CV2026-10-07
#192Beyond Masks and Trajectories: Flow-Guided Latent Action Injection for Stable Surgical Video GenerationTsz-Yui Qin, Siyu Zhou, Chi-Keung Tang +2cs.CV2026-10-07
#193DisParQ: Self-Supervised Part Concepts for Interpretable Vision Foundation ModelsAdam Pardyl, Siddhartha Gairola, Sukrut Rao +4cs.CV2026-10-07
#194Concentration, Not Uncertainty: Why Targeted Synthetic Data Doesn't Help Camouflaged Object DetectionAkshat Dobhal, Sanjay Singhcs.CV2026-10-07
#195Efficient 3D Gaussian Head Avatars for Edge DevicesUmar Farooq, Jean-Yves Guillemaut, Adrian Hilton +1cs.CV2026-10-07
#196UltraText Bench: A Comprehensive Bilingual Benchmark for Evaluating Visual Text Rendering in Image GenerationDeyuan Liu, Yihao Hu, Jingxuan Zhang +13cs.CV2026-10-07
#197MOTIF: Person-of-Interest Deepfake Detection Beyond 3DMM CoefficientsGiovanni Affatato, Sara Mandelli, Paolo Bestagini +1cs.CV2026-10-07
#198ORCA: Hunting Compositional Failures in Text-to-Image DiffusionArshia Hemmat, Amirhossein Vahidi, Amitis Shidani +4cs.CV2026-10-07
#199Hard, Yet Reducible: Controlled Forward Transfer for Synthetic Degradation CurationChunming He, Kailai Zhou, Jiaming Zuo +6cs.CV2026-10-07
#200DeltaSplat: Iterative Gaussian Refinement for Pose-Free Feed-Forward 3D Gaussian SplattingChanung Park, Seunghyeon Song, Joo Chan Lee +2cs.CV2026-10-07
#201DeepTopoClustering: Unsupervised Derivation of Surface Process Taxonomy from 4D Point Clouds for Topographic MonitoringJiapan Wang, Daan Hulskemper, Mathilde Letard +2cs.CV2026-10-07
#202Global Average Precision for Representation LearningBill Psomas, Mohammad Mahdi, Michalis Thomas +3cs.CV2026-10-07
#203Bringing BNNs to Fast Event ProcessingPaul Longour, Julien Moreau, Franck Davoinecs.CV2026-10-07
#204SANet: Selective Attention Network for Infrared Small Target DetectionYingmei Zhang, Wangtao Bao, Qin Xiao +5cs.CV2026-10-07
#205FedSSMCoOp: SSM Encoders for light-weight Federated Prompt Learning for Few-shot ClassificationAnkita Das, Ambarish Parthasarathy, Sumohana S. Channappayya +1cs.CV2026-10-07
#206Do Generative Priors Align with Human Naturalness Perception?Taiki Fukiagecs.CV2026-10-07
#207Purifying Backdoored Large Vision-Language Models by Removing Hijacked DirectionsBojun Yang, Haochen Zhou, Zhifang Zhang +3cs.CV2026-10-07
#208MSU Team at the Explainable Deepfake Detection Challenge 2026: Grounded Artifact Evidence for Deepfake DetectionArtem Filippov, Aleksandr Gushchin, Kirill Koltsov +2cs.CV2026-10-07
#209Perceptually Aligned Evaluation of Style TransferYang Deng, Eleftherios Ioannou, David Mould +3cs.CV2026-10-07
#210Playing with Kruskal: algorithms for flat and hierarchical watershed cutsJean Cousty, Laurent Najman, Benjamin Perret +1cs.CV2026-10-07
#211Scalable Patch-Level Self-Supervised LearningMaximilian Seitzer, Gabriele Trivigno, Antonín Vobecký +5cs.CV2026-10-07
#212AdSpark: A Large-Scale Dataset and Benchmark for Product-Centric Advertisement Video GenerationZhifei Yang, Zhao Jiang, Keyang Lu +6cs.CV2026-10-07
#213From Pixel to Coding: Evaluating the Figure Reproduction Capabilities of MLLMsZijian Chen, Zhengyu Chen, Bohan Liang +7cs.CV2026-10-07
#214Temporal Residual Bottleneck for Robust Asynchronous Collaborative PerceptionMelih Yazgan, Ahmed Abouelazm, J. Marius Zöllnercs.CV2026-10-07
#215A Probabilistic Perspective on Wasserstein-Based Evidential Uncertainty for Out-of-Distribution SegmentationArnold Brosch, Abdelrahman Eldesokey, Michael Felsberg +1cs.CV2026-10-07
#216HarnessIR: Harnessing Multimodal Foundation Models for Universal Real-World Image RestorationXiangtao Kong, Shuaizheng Liu, Rongyuan Wu +5cs.CV2026-10-07
#217HeiCo-FOCUS: A Clinically Grounded Dataset for Long-Context Video UnderstandingLeon Mayer, Lucas Luttner, Patrick Godau +42cs.CV2026-10-07
#218BagDINO: Multi-View Baggage Re-Identification with DINOv3Vita Santa Barletta, Danilo Caivano, Rebecca Margiotta +2cs.CV2026-10-07
#219Beyond Anonymous Captions: Grounding Character Identity in Video Captioning and Question AnsweringAnas Filali Razzouki, Killian Steunou, Khalil Guetari +3cs.CV2026-10-07
#220Argos: Adapt Rich Geometric Priors for Generalizable Online Scene-Change-DetectionRuihan Xu, Jiae Yoon, Kaichen Zhou +2cs.CV2026-10-07
#221VideoEvolve: Co-Evolving Memory and Retrieval for Long Video UnderstandingYongchao Xu, Bowen Ye, Jiefeng Gan +5cs.CV2026-10-07
#222HuLiGen: Human LiDAR Generation from Parametric Body ModelsSalma Galaaoui, Nermin Samet, David Picardcs.CV2026-10-07
#223VolCo: Volumetric Contact for High-Fidelity Human Grasp GenerationZhuo Chen, Yihua Cheng, Aleš Leonardis +1cs.CV2026-10-07
#224Masked Feature Encoding for Large-Scale Whole Slide Image RepresentationHaoyu He, Basile Tessier-Cloutier, Yang Wang +1cs.CV2026-10-07
#225Geometry-Supervised Visual Representation Learning for Multi-Phenotype Lesion Interpretation in Medical VLMsHao Wang, Qiwei Zeng, Shuchang Ye +5cs.CV2026-10-07
#226LoomSC: Scalable Deep Subspace Clustering with Projector Factorization and Exact Spectral ReductionNairouz Mrabah, Youssef Melki, Mohamed Bouguessa +3cs.CV2026-10-07
#227Video Prediction Policy 2: Predict Better, Act BetterYanjiang Guo, Haodong Yan, Zhide Zhong +15cs.CV2026-10-07
#228$Δ$Representation: Geometry Supervised Representation Learning of Phenotypes via Counterfactual Reasoning for Medical VLMsHao Wang, Qiwei Zeng, Jinghao Lin +6cs.CV2026-10-07
#229TouchScale: 500 Hours of Human Vision and Touch for Visual-Tactile LearningDayou Li, Hao Wang, Qianqian Yang +23cs.CV2026-10-07
#230On the Necessity of Attention-FFN Split in Vision TransformersJunhyeok Kim, Jinyeong Kim, Jae Wan Park +1cs.CV2026-10-07
#231One-Shot Adaptive Segmentation For Scientific ImagesTejaswi V. Panchagnula, Allison M. Davis, Fengqing Zhucs.CV2026-10-07
#232From Digital Human Interactions to Physics-Based Humanoid Skills: Physics-Grounded Post-Training of Interaction GeneratorsKerui Chen, Jianrong Zhang, Kai Lv +1cs.CV2026-10-07
#233Performance at What Cost? A Sustainability-Aware Performance Index for Cell and Nucleus Instance SegmentationEiram Mahera Sheikh, Alaa Tharwat, Wolfram Schenckcs.CV2026-10-07
#234How Private is Private? A Comparative Study for Face De-IdentificationHui Wei, Hao Yu, Hui Kuurila-Zhang +1cs.CV2026-10-07
#235When to Unpair: Regulating Pairing Dependence in Medical Visual In-Context LearningCheng Wan, Chenjun Li, Qingyu Zhaocs.CV2026-10-07
#236Position Forcing: Self-Conditioning 3D GenerationZiheng Ouyang, Zeqiang Lai, Jiarui Chen +7cs.CV2026-10-07
#237Real-Time Joint Audio-Video Generation by Parallel Adapter CompositionJingyu Li, Xiaoxiao Xiang, Yiwen Guocs.CV2026-10-07
#238Explicit Geometric Chain-of-Thought for Vision-Language-Action in Autonomous DrivingXingtai Gui, Yucheng Zhou, Dongqian Guo +3cs.CV2026-10-07
#239MOTIP2: Spatial Priors for End-to-End Multi-Object TrackingBenoît Roussel, Damien Bouet, Liming Chen +1cs.CV2026-10-07
#240Gaussian Density Splatting NetworkMiao Shang, Yabin Wang, Xiaopeng Hongcs.CV2026-10-07
#241Self-correction Optimization for Interleaved Multimodal GenerationXin You, Zhiwei Ning, Zukai Chen +7cs.CV2026-10-07
#242Rubix: Global Correspondence-Free Point Set Alignment through Assignment GeometrySubhransu S. Bhattacharjee, Dylan Campbell, Rahul Shomecs.CV2026-10-07
#243GraphRectify: Graph-Based Transfer of Adversarial Example Detectors Across Neural NetworksArash Vashagh, Roozbeh Razavi-Farcs.CV2026-10-07
#244SGF+: Decoupling Gradient Flows for Autoregressive Video GenerationZihan Su, Junhao Zhuang, Yaowei Li +10cs.CV2026-10-07
#245Detecting Adversarial Images through Response Profiles of Vision-Language ModelsArash Vashagh, Roozbeh Razavi-Farcs.CV2026-10-07
#246ECHO: Embodied Camera Observations of Human Object CarryingXuefei Sun, Lorin Achey, Kali Hamilton +4cs.CV2026-10-07
#247MORCA: Offline-to-Online Reinforcement Learning for Adaptive Cache Reuse in Video Diffusion AccelerationYuxiang Xiong, Ruiyan Wang, Wenqiang Wang +5cs.CV2026-10-07
#248Label-free cell counting and viability prediction with brightfield imaging and deep learningAmir Reza Vazifeh, Christian Zeigler, Sornanathan Meyyappan +2cs.CV2026-10-07
#249Insights from Autoresearch for Solar Panel SegmentationJustinas Lekavicius, Kursat Komurcu, Valentas Gruzauskas +1cs.CV2026-10-07
#250QuadTok: Quadtree Visual Tokenizer for Autoregressive Image GenerationYucheng Mao, Zeyuan Chen, Xiaojun Shan +4cs.CV2026-10-07
#251Video-Conditioned Generative Joint 2D-3D Hand Motion RecoveryChen Xu, Yunqi Li, Binbin Huang +3cs.CV2026-10-07
#252GRACE: Generation-aware latent compression for efficient video generationJiyoung Kim, Paul Hyunbin Cho, Jisu Nam +5cs.CV2026-10-07
#253Never Look Back: Understanding Persistence in 3D Object Memory from Egocentric VideosShravan Chaudhari, William Paul, Suchi Saria +2cs.CV2026-10-07
#254Tetris3D: 3D Scene Generation With Objects That Fit TogetherJaeyeong Kim, Jinhyuk Jang, Jongmin Lee +2cs.CV2026-10-07
#255Comprehension Audits to Mitigate Risks from Automated AI ResearchRonald J. Bodkin, Bahrad A. Sokhansanj, Gillian K. Hadfieldcs.CY2026-10-07
#256When Scientific Cognition Is No Longer ScarceNathan DeBardelebencs.CY2026-10-07
#257CATune: Structural Constraint-Aware Bayesian Optimization for DBMS Configuration TuningFangping Lan, Qi Zhang, Eduard Dragutcs.DB2026-10-07
#258Correspondences as Decisions: JevNexus for Decision-Centric Schema MatchingRunze Li, Hanchen Wang, Ying Zhang +1cs.DB2026-10-07
#259QCATS: Query Context-Aware Transformer Slicing for Efficient Predictive Query ProcessingYueying Li, Zhongle Xie, Ke Chen +1cs.DB2026-10-07
#260Democratizing MoE inference on commodity GPUs with CoMoERuwen Fan, Yuezhi Zu, Junru Li +5cs.DC2026-10-07
#261Attention via Black-Box Vector SearchStepan Zharkov, Krish Singal, Ashwin Padaki +1cs.DS2026-10-07
#262On the Cyclic Assumption of the Cow-Path Search AlgorithmYuan Ma, Yiqun Lisa Yincs.DS2026-10-07
#263emg2face: Expressive Facial Animation with High-Density Surface EMGGanidhu Abey, Wendy Greening, Ashika Kamboj +5cs.GR2026-10-07
#264ScribbleEdit: A Benchmark for Scribble-Only Image EditingJie Ren, Hao Kang, Kai Guo +9cs.GR2026-10-07
#265TRACK: Telemetry-Based Racing Analysis and Coaching Kit in Sim Racing GamesEfe Çangırılı, Murat Kurtcs.GR2026-10-07
#266The Confidence Game: Strategic Miscalibration in Human-AI DelegationRaghu Arghal, Saswati Sarkar, Shirin Saeedi Bidokhtics.GT2026-10-07
#267Optimal Regret for Online Market Making with Limit Order BookMaria Elena Vischi, Francesco Emanuele Stradi, Alberto Marchesics.GT2026-10-07
#268Marrying Pricing and Advertising with LLMsAlessandro Barro, Francesco Bacchiocchi, Francesco Emanuele Stradi +1cs.GT2026-10-07
#269TutorLoop: Regulating Student Learning Behaviors via Sensor-in-the-Loop Generative FeedbackSonglin Xu, Xinyu Zhangcs.HC2026-10-07
#270Structured pre-generation elicitation versus single-shot prompting in AI-assisted enterprise decision-making: a randomised online experimentWilliam Scott-Jacksoncs.HC2026-10-07
#271Healthy skepticism in AI: a data visualization research agendaG. Elisabeta Marai, Marc Baaden, Michael Behrisch +2cs.HC2026-10-07
#272A Scoping Review and Experimental Study on Reinforcement Learning from Human Feedback for Human-Robot CollaborationAlexandra Coroiu, Andrea Vogt, Viktor Werbilo +3cs.HC2026-10-07
#273EEG and Eye-Tracking Evidence That AI Disclosure Shapes Face EvaluationTeodora Mitrevska, Luise Donat, Andreas Butz +3cs.HC2026-10-07
#274PalmSpace: Towards a Versatile On-Palm Interaction Space through Unified Touch ModelingChentao Li, Mingze Gao, Runze Sun +3cs.HC2026-10-07
#275How assigned AI use before class shapes active student engagement in classDan J. Wang, Neelam Modi Jain, Vanessa Burbano +5cs.HC2026-10-07
#276From Chunks to Functional Evidence: Function-Aware Retrieval for EDA Documentation QAXiaotian Qiu, Kairui Liu, Shi Chenyi +3cs.IR2026-10-07
#277Finding the Right Balance: Relevance and Diversity in LLM RetrievalGuillaume Brouillette, Faustin Kagabo, Usef Faghihi +1cs.IR2026-10-07
#278Towards Explaining Query Expansion Performance in Information RetrievalSourav Saha, Aditya Dutta, Soumajit Pramanik +1cs.IR2026-10-07
#279Inverting Multi-Vector Visual Document IndicesZhuchenyang Liu, Yao Zhang, Yu Xiaocs.IR2026-10-07
#280Training with Missed Targets in Generative Recommendation: Separating Supervision from Probability CompetitionXuesi Wang, Yangbin Shi, Xiaolin Zhengcs.IR2026-10-07
#281Does Document Structure Help Dense Retrieval? A Placebo-Controlled Ablation of Four Mechanisms Across Two CorporaAndrey Kuehlkamp, Priscila Correa Saboia Moreira, Samuel Rundcs.IR2026-10-07
#282Beyond LLM-GA: Secure Fluid Antenna Systems with ReEvo-Designed Memetic AlgorithmHanyong Xu, Zhaolai Dang, Tong Zhangcs.IT2026-10-07
#283Pathwise Information Certificates for Decentralized Adaptive SensingTheodoros Tsiligkaridiscs.IT2026-10-07
#284An Informational Curse of Horizon in Goal-Conditioned Policy LearningJohn L. Zhou, Yuxuan Dong, Jonathan C. Kaocs.LG2026-10-07
#285Efficient Best-of-N policy evaluation for inference-time alignmentJonas Schweisthal, Yuxin Wang, Athiya Deviyani +2cs.LG2026-10-07
#286The Symbol of the Surrogate: Measuring Numerical Provenance in Neural PDE SolversRidham Patelcs.LG2026-10-07
#287Evaluating Trajectory Features for Routing Final-Layer AttentionYupeng Yaocs.LG2026-10-07
#288Twist Flow for Inverse ProblemsShiqin Zeng, Zijun Deng, Felix J. Herrmanncs.LG2026-10-07
#289Self-attention summary networks for subsurface velocity-model building from common-image gathersShiqin Zeng, Yunlin Zeng, Abhinav Prakash Gahlot +2cs.LG2026-10-07
#290LeCuration: A Tiny World Model as a Data Curation Multi-ToolMayank Sengupta, Nirmit Desai, Eric Song +1cs.LG2026-10-07
#291Node-level Graph Neural Architecture Search FrameworkLintao Yanga, Sirui Lia, Yaqing Wang +4cs.LG2026-10-07
#292Kuration SDK: Addressing the Virtual2Real Gap via Data CurationNirmit Desai, Eric Song, Mayank Sengupta +4cs.LG2026-10-07
#293MovieSTAGE: Scene, Transition, and Global Encoding for Movie-fMRI ADHD ClassificationBoseong Kim, Haejun Chung, Ikbeom Jangcs.LG2026-10-07
#294Denoising Blocks, Not Tokens: Efficient Compressed Continuous Diffusion with Branching Token RealizationXinsong Feng, Peng Du, Zhizhuo Yang +3cs.LG2026-10-07
#295Benign Overfitting under Heterogeneous Input FusionHouzhen Liu, Xiaobo Xiacs.LG2026-10-07
#296Shared Low-rank Basis Factorization for Data-free Mixture-of-Experts CompressionTianxiao Cao, Jiahe Shao, Yuning Qiu +3cs.LG2026-10-07
#297Multimodal LLMs Can Learn to Read Brain Signals: A Vision--Language Model for Unified Multi-Task EEG DecodingParastoo Azizeddin, Omid Sharafi, Maryam M. Shanechics.LG2026-10-07
#298Global Exponential Convergence of Two-Layer Linear Network TrainingStephen Y Zhang, Gabriel Peyrécs.LG2026-10-07
#299From Retrieval to Customer Context: Evaluating Frontier-Model Systems for Voice-of-Customer AnalysisRaviraja G, Viraj Bagal, Prabhath Chellingics.LG2026-10-07
#300Noise, Denoise, Correct: MCMC Posterior Sampling with Diffusion Priors in Three StepsSo Takao, Gregory David Bellchambers, Luke Ye +2cs.LG2026-10-07
#301Stability and Diversity of Networked Self-Consuming Generative EcosystemsXiukun Wei, Yang Zhang, Xueru Zhangcs.LG2026-10-07
#302Shared Geometry As A Rosetta Stone: Cross-Modal Alignment Without Paired DataDominik Schnaus, Thomas Dagès, Daniel Cremers +2cs.LG2026-10-07
#303Self-Consuming Generative Models with Co-Evolving Human PreferencesXiukun Wei, Tian Xie, Ding Zhu +1cs.LG2026-10-07
#304What a Reporting Convention Hides: A Matched-Budget Audit of Quantum Natural Gradient with an Exactly Computed MetricLu Wei, Yufeng Wang, Haibin Lingcs.LG2026-10-07
#305An extended deep energy method for thermo-mechanical crack propagationHan Zhang, Mehrisadat Makki Alamdari, Babak Shahbodagh +4cs.LG2026-10-07
#306GeoPrior-Mamba: Structured Process Priors with Mamba for Fine-Resolution XCO2 ReconstructionZhao Meng, Yinan Cai, Siru Zhong +2cs.LG2026-10-07
#307DSReg: Provably Recovering Individual World Latents without ReconstructionYujia Zheng, David Klindt, Randall Balestriero +1cs.LG2026-10-07
#308When Should an In-Context Learner Expand Its Hypothesis Space?Weihan Li, Xinlei Chen, Junhao Wu +1cs.LG2026-10-07
#309MORA: Modeling Observed Changes for Drift-Robust Time-Series Anomaly DetectionXudong Mou, Tiejun Wang, Rui Wang +5cs.LG2026-10-07
#310CHASE: Channel-Aligned Structure Exploitation for Geometry-Aware Model EngineeringWei Wang, Wei Jiang, Ziran Liucs.LG2026-10-07
#311Safe on Average, Unsafe in the Tail: When Is the Episodic-Cost Tail Controllable?Samuel Tetteh, Cody Flemingcs.LG2026-10-07
#312Physics-Informed Neural Plasticity: PDE Solvers That Reshape ThemselvesChun-Wun Cheng, Bingcheng Hu, Angelica I. Aviles-Riverocs.LG2026-10-07
#313Differential Refresh Policies for Models Trained on Lagging Data Snapshots: From a Single-Age Equivalence Limit to an Optimal Per-Segment AllocationAmit Rajulacs.LG2026-10-07
#314Align Before You Combine: Reference Space Calibration for Supervision Without Ground TruthJackson Eshbaugh, Jorge Silveyracs.LG2026-10-07
#315CircuitGate: Logic-Consistent Circuit-Level Functional Modeling for And-Inverter GraphsQifan Zhang, Ruijie Li, Fangzhou Zhang +6cs.LG2026-10-07
#316A Framework for the Systematic Review of ML Assets in AI RegistriesAlexandra González, Quim Motger, Xavier Franch +1cs.LG2026-10-07
#317UniCSI Towards a Universal Wi-Fi CSI Encoder for Ubiquitous Human SensingDaniel Eckhoff, Hua Kang, Zhitang Chen +1cs.LG2026-10-07
#318EvoSignal: LLM-Guided Evolutionary Design of Modular Traffic Signal Control ProgramsLeizhen Wang, Peibo Duan, Zhenlin Qin +5cs.LG2026-10-07
#319Online Resource Allocation with an Endogenous Markov State: Fewer LP Solves Earn MoreZhaohua Chencs.LG2026-10-07
#320Collaborative Reasoning Distillation via Cross-Feedback and Coherent CurationTaehoon Kim, Seunggeun Cho, Dongsu Hancs.LG2026-10-07
#321COPC: Coupled Off-Policy Correction for Asynchronous LLM Reinforcement LearningZicheng Hu, Zhijian Zhou, Xuan Zhang +7cs.LG2026-10-07
#322Lightweight and Versatile Learned Optimization by Recombination of Gradient HistoryMinyoung Choi, Dalta Imam Maulana, Wanyeong Jungcs.LG2026-10-07
#323Decoupled Optimization for Teacher-Student Semi-Supervised Learning via a Pioneer StudentHaorong Han, Jidong Yuan, Chixuan Wei +1cs.LG2026-10-07
#324Sequential Pretraining Favors Large ModelsMohnish Harwani, Yujia Zhengcs.LG2026-10-07
#325The Identifiability and Observability of Deep Normalized AttentionPranav Venkata Kondacs.LG2026-10-07
#326When does a network's training history predict its future learning better than its current state? Evidence from a response probe and a forecasting screenMartin Hofmann, Patrick Mädercs.LG2026-10-07
#327Coding-Agent Benchmarks Should Match Their Users' Task FlowsIgor Slinko, Yaroslav Golubev, Sergey Titovcs.LG2026-10-07
#328When Rank Rises as LLMs DegradeZhaohui Geoffrey Wangcs.LG2026-10-07
#329Closed-Form Noise Calibration Against Membership Inference for Random-Allocation DP-SGDMurat Bilgehan Ertan, Marten van Dijkcs.LG2026-10-07
#330DSTNet: Dynamic Spectral Trajectory Network for Causal Multi-Horizon Financial ForecastingAashish Bohra, Lokendra Vishwakarmcs.LG2026-10-07
#331Gauss-Newton Accuracy and Indefinite Hessians: Uniform Coexistence in Low-Cost SetsKihun Rhee, Hanjoon Byuncs.LG2026-10-07
#332CERO: Where and When to Allocate Rollouts for RL Post-TrainingYiming Zong, Yige Wang, Xing Hu +2cs.LG2026-10-07
#333Few-Shot Learning for Personalised Automated Pain AssessmentHeinke Hihn, Ibrahim Eisawy, Patrick Thiam +2cs.LG2026-10-07
#334Pretraining Shapes Spectral Structure: Architecture- and Strategy-Conditional Prediction of OOD Robustness in Foundation ModelsSangyoon Bae, Sk Miraj Ahmed, Shinjae Yoo +1cs.LG2026-10-07
#335EC-EarthFlow: Probabilistic emulation of daily transient global climate model simulations with flow matchingKirien Whan, Nikolaj T. Mücke, Karin van der Wielcs.LG2026-10-07
#336SoftSEEPS improves ML-based precipitation forecastingJost Arndt, Utku Isil, Noelia Otero +3cs.LG2026-10-07
#337EntroPrefill: Renyi-Guided Context Pruning with Conditional Stability Guarantees for Retrieval-Augmented GenerationInbasekaran Scs.LG2026-10-07
#338Unrolled Flow Models for ReasoningFaissal Izermine, Hanru Bai, Oscar Davis +1cs.LG2026-10-07
#339Leaner Transformers Can Easily Learn to ClusterCharlotte Park, Kenneth L. Clarkson, Lior Horesh +2cs.LG2026-10-07
#340Beyond Policy Support: Interaction Constrained Offline Reinforcement Learning for Autonomous DrivingMahmoud Selim, Cristina Cipriani, Karl Henrik Johanssoncs.LG2026-10-07
#341Fluctuations of Nonlinear Observables in Mean Field Neural Network TrainingArnaud Descours, Geoffrey Lacourcs.LG2026-10-07
#342AdaPS-LiNGAM: Adaptive Predecessor Selection for Linear Non-Gaussian Acyclic Models under Small-Sample SettingsShun Yanashima, Kentaro Kanamori, Hirofumi Suzukics.LG2026-10-07
#343A Proof-of-Concept Study of Weakly Supervised Labeling of Fine-Grained EEG Components for Artifact AttenuationLu Wang-Nöth, Hai Huang, Philipp Heiler +3cs.LG2026-10-07
#344BoT-GRPO: Efficient Process-Reward RL for Reasoning via Bag-of-Token AggregationYingxiang Yang, Weihang Xiao, Zhunxuan Wang +2cs.LG2026-10-07
#345Homogenization in Multi-Agent SystemsPrakhar Ganesh, Kyra Wilson, Luca Zappella +4cs.LG2026-10-07
#346Dual-QK: Sharp Queries and Flat Keys for Prunable 2-bit KV CachesSunjoo Whang, Jungjun Oh, Minsung Kim +5cs.LG2026-10-07
#347Fully Interpretable Minimal Transformers: From Geometry to AlgorithmRaneem Mahajne, Toviah Moldwincs.LG2026-10-07
#348For Those Who Believe in Faithfulness: Optimizing the Area Under Insertion and Deletion Curves for Ranking Relative Feature ImportanceBjørn Leth Møller, Bulat Ibragimov, Christian Igelcs.LG2026-10-07
#349Stream-Based Active Learning with Cooperative Neural Networks for Data-Efficient Partial Inverse Design: An Automotive Glass Run Channel Case StudyAgung Nugraha, Hyerin Kwon, Heungjun Im +2cs.LG2026-10-07
#350MUNITE: Unified Multimodal Latent Inference for Any-to-Any Multimodal GenerationKyeongmin Yeo, Minhyuk Sungcs.LG2026-10-07
#351Layerwise Error Attribution for Fast and Robust Mixed-Precision Post-Training QuantizationSamy Houache, Yann Traonmilin, Jean-François Aujolcs.LG2026-10-07
#352Identifiability of a dissipative knowledge-dynamics model: exact recovery under designed excitation, degeneration on observational dataArman Kostanian, Armen Beklaryancs.LG2026-10-07
#353RollVerify: Bridging Efficiency and Accuracy in Long-Tail Rollout Reinforcement LearningYongqiang Yao, Jinru Tan, Kaihuan Liang +5cs.LG2026-10-07
#354NeuralZip: Reusable Setup for Fast Lossless CompressionMartín Bravo, Samuel Horváth, Gonzalo Navarro +1cs.LG2026-10-07
#355Eigenvalues of the Hessian in Deep Learning: The Origin of Symmetry and Its BreakingYossi Arjevanics.LG2026-10-07
#356KGATE : a Knowledge Graph Embedding Training EnvironmentBenjamin Loire, Galadriel Brière, Célia Brahimi +2cs.LG2026-10-07
#357Expected Sample Complexity in Multi-Armed BanditsNadav Sukenik, Nadav Merliscs.LG2026-10-07
#358Learning Traffic Flow Dynamics with Stochastic Physics-Informed Neural Cellular AutomataFederica Bragone, Matthieu Barreaucs.LG2026-10-07
#359Force without transmission: a depth-induced rank collapse that no loss on the representation reopensMartin Hofmann, Patrick Mädercs.LG2026-10-07
#360TR-PTQ: High-Accuracy Integer-Only Transformer Post Training Quantization via Taylor Region ReformulationEliyahu Levy, Adam Teman, Yoni Pugachovcs.LG2026-10-07
#361Efficient Patch-Based Anomaly Detection Fused with Diffusion Driven Generative Modeling for Semiconductor Wafer Bin Map Open Set Anomaly DetectionLimon Bin Hossain, Md Sadib Rahman Anantacs.LG2026-10-07
#362Temporal Predictive Multiplicity: Equally Accurate Time Series Models Yield Different Forecast TrajectoriesEmanuele Albini, Francesca Toni, Saumitra Mishra +1cs.LG2026-10-07
#363Beyond Reward Suppression: Near-Optimal Offline Attacks on Warm-Start Bandits with Bounded RewardsQirun Zeng, Manhin Poon, Xiangxiang Dai +2cs.LG2026-10-07
#364A Drosophila Whole-Connectome Network Can Learn Human-Designed Cognitive TasksJoonghui Cho, Minchan Kang, Daeshik Kimcs.LG2026-10-07
#365Oscillatory Neural Dynamics over SheavesJan-Willem Van Looy, Alessandro Trenta, Alessio Gravina +5cs.LG2026-10-07
#366Matching of signal, noise and hardware timescales for filtering and forecasting of correlated noise signalsJoshua Donald, Alex Gabbitas, Arthur G. T. Coveney +2cs.LG2026-10-07
#367WxFM-XL: Adapting Univariate Foundation Models to Multi-Station Weather ForecastingXiao Wang, Changjian Chen, Zhuo Tang +3cs.LG2026-10-07
#368Efficient Provably Private Classification with a Tabular Foundation ModelTalal Alrawajfeh, Cristiana Diaconu, Ossi Räisä +5cs.LG2026-10-07
#369Activation-Aware Weight Tensorization: A Calibration-Time Preconditioner for Tensor-Network LLM CompressionAlessandro Beatini, Marco Maronese, Emanuele Rodolàcs.LG2026-10-07
#370Multi-Agent Coordination via Support-Preserving DistillationSangmin Lee, Youngju Na, Chanmi Lee +1cs.LG2026-10-07
#371CAFE+FNO: Fourier Kernel Generation via Multiplicative Feature CompositionHyungjoon Juen, Minwoo Shincs.LG2026-10-07
#372YANchor-4B: Effective Long-Horizon Reasoning in O(N) Time with O(1) MemoryHuishan Ji, Hua Xu, Weiming Zhang +1cs.LG2026-10-07
#373What Can a Gaussian Process Design TestIvan De Boi, Marnix Van Soomcs.LG2026-10-07
#374m-Set Adversarial Bandits with Winner FeedbackNicolò Cesa-Bianchi, Matteo Papinics.LG2026-10-07
#375A Unified Information-Theoretic Approach to Constrained Multi-Fidelity Multi-Objective Bayesian OptimizationRikuto Matsumoto, Masanori Ishikura, Masayuki Karasuyamacs.LG2026-10-07
#376Pre-training of Bayesian Optimization Algorithm through Bayesian OptimizationSatoshi Katayama, Shoyo Hunt, Shintaro Masuda +1cs.LG2026-10-07
#377Robust Decentralized Fairness AuditingSayan Biswas, Jade Garcia Bourrée, Anne-Marie Kermarrec +2cs.LG2026-10-07
#378How to train your model organismXilin Wang, David Bau, Byron C. Wallacecs.LG2026-10-07
#379OrthoGen: A Generative Orthogonal Learner for Time-Varying TreatmentsTomàs Garriga, Valentyn Melnychuk, Konstantin Hess +4cs.LG2026-10-07
#380Edge Accuracy Is Not Enough: Why Dynamics-Learned Structure Fails to Transfer to Inverse ProblemsNicholas Tan Jerome, Fangnian Wangcs.LG2026-10-07
#381Finite-Sample Approximation of Hessian-Guided Perturbed Wasserstein Gradient FlowsRyotaro Kawata, Atsushi Nitanda, Taiji Suzukics.LG2026-10-07
#382Evaluating Sequence Assembly Strategies for Differentially Private Synthetic Time-Series ForecastingGuoxiong Long, Huizhen Huang, Qikun Cai +2cs.LG2026-10-07
#383From Prompts to Trees: Effective LLM-Guided Tree Generation for Few-Shot Tabular ClassificationYue Qiu, Zekang Du, Yiqun Diao +2cs.LG2026-10-07
#384ProtocolMatch: Protocol-Dependent Model Selection for Scientific Dynamics ForecastingLu Wei, Yufeng Wang, Haibin Lingcs.LG2026-10-07
#385MorphCL: Morphological Contrastive Learning for Inertial-based Human Activity RecognitionMarius Bock, Yuwei Zhang, Juergen Gall +3cs.LG2026-10-07
#386Stationary Bias and Extrapolation in Nonlinear Two-Timescale Stochastic ApproximationA. Ch. Madhusudanarao, Rahul Singhcs.LG2026-10-07
#387Logarithmic Regret via Passive Change Detection in Piecewise-Stationary Self-Tuning RegulationA. Ch. Madhusudanarao, Rahul Singhcs.LG2026-10-07
#388PairAudit: Guiding Human Review with Graph Tokens under Distribution ShiftJiran Tao, Binyan Jiangcs.LG2026-10-07
#389A Closed-Loop Non-Asymptotic Convergence Analysis of PPO with Learned Critics and ClippingJunwei Su, Mengfan Liu, Yanyong Zhang +1cs.LG2026-10-07
#390Sparse Planning in Visual World Models via Cost GradientsYingchen Xu, Edward Grefenstettecs.LG2026-10-07
#391PatchBench: Measuring Collateral Damage in Activation PatchingAlexi Canesse, Mathis Le Bail, Maël Jenny +3cs.LG2026-10-07
#392Physics-Aligned Electronic Ground-State Learning Improves GeneralizationEike S. Eberhard, Xaver Kainz, Viktor Kotsev +2cs.LG2026-10-07
#393Shared Gaussianization: What Gaussian Regularizers Certify About Contrastive Learning, and What They MissRuoyu Zhao, Yuting Chen, Jinheng Zhang +2cs.LG2026-10-07
#394Revisiting Explainable AI through Model-Independent Concept DictionariesThomas Schnake, Doreen Schöppenthau, Alexander Meyer +3cs.LG2026-10-07
#395Continual Graph Multi-Agent Reinforcement LearningTommaso Marzi, Ahmed Hendawy, Jan Peters +3cs.LG2026-10-07
#396SemanticFold: Latent Sequence Compression SeparatesLanguage Modeling, Decodability, and ReasoningMingyan Liu, Min Huangcs.LG2026-10-07
#397How Do Transformers Learn to Represent Symmetries?Eduardo Santos-Escriche, Valerie Engelmayer, Ya-Wei Eileen Lin +1cs.LG2026-10-07
#398RSIGym: A Flexible Environment for Recursive Self-ImprovementFanqing Meng, Lingxiao Du, Haocheng Lu +6cs.LG2026-10-07
#399Fault-tolerant foundation modelsTrevor McCourt, Ila R. Fiete, Isaac L. Chuangcs.LG2026-10-07
#400PoreML: A Data-Driven Framework for Learning Multiphase Flow in Porous MediaChunyang Wang, Mingrui Zhang, Yuyan Zhang +5cs.LG2026-10-07
#401Thinking in Depth: Retrospective Inference for Tabular Foundation ModelsHao-Run Cai, Si-Yang Liu, Zi-Jian Cheng +8cs.LG2026-10-07
#402HAN-Mamba: Hierarchical Selective State Space Networks for Multi-Scale Financial Volatility ForecastingMihai Bogdan Deaconu, Ioan Daniel Popcs.LG2026-10-07
#403Average-Reward Reinforcement Learning for Multichain MDPs: A Hierarchical Decomposition ApproachHuizhen Yu, Isaiah Heidtcs.LG2026-10-07
#404AutoAdapt: Automatic Domain Discovery Enables Low-Cost ExtensibilityJosh McGiff, Salma Mekaoui, Robert Shanahan +1cs.LG2026-10-07
#405ORDERS: An Empirical Study of Norm-Rank Aggregation for Personalized Federated LearningKoffka Khancs.LG2026-10-07
#406Koopman Observers for Diffusion Acceleration: Correcting Feature Forecasts with Shallow MeasurementsHanru Bai, Yuanchao Xu, Fengyi Lics.LG2026-10-07
#407Temporally Interpretable Differentiable Decision TreesEisuke Hirota, Aarav Sane, Rohan Palejacs.LG2026-10-07
#408Input-Blind Controls Produce Substantial Oracle Headroom for Layer Programs in Multiple-Choice EvaluationYibei Guo, Rui Liucs.LG2026-10-07
#409Continual Learning without Continual TrainingNikita Narayanan, Ritham Majumdarr, Sonali Parbhoocs.LG2026-10-07
#410ResidualQuant: KV Cache Quantization for Looped Transformers with 2-Bit ResidualsHeejun Kim, Junyoung Lee, SangLyul Cho +3cs.LG2026-10-07
#411Boosting and the Expressive Power of Simple Weak Learners via the $γ$-VC DimensionArthur da Cunha, Kasper Green Larsen, Liang-Yu Zoucs.LG2026-10-07
#412OrBIT: Structure-Guided Embedding CompressionYunied Puig, Amit Kumar Jaiswalcs.LG2026-10-07
#413Kernel Autoresearch for Open-Ended Model DiscoveryRichard Cornelius Suwandi, Feng Yin, Kevin Murphycs.LG2026-10-07
#414Executing Causal Structure Learning with Linear-Attention TransformersAmartya Roy, Sayar Karmakarcs.LG2026-10-07
#415Cross-Domain Pretraining for Steady-State Neural CFD SurrogatesAnthony Zhou, Amir Barati Farimani, Shirley Ho +1cs.LG2026-10-07
#416Training Parallel Speculative Draft Models by Directly Minimizing Expected Decoding RoundsYunxiao Zhao, Changxiao Caics.LG2026-10-07
#417Which Rollout Taught It That? BehaviorTrace and the Limits of Training-Data Attribution in Online RLAmit Nautiyalcs.LG2026-10-07
#418Q-Learning with Scalar Adjoint MatchingYonghoon Dong, Minsung Yoon, Jaehyuk Kim +3cs.LG2026-10-07
#419Seq-Flow: Efficient Probabilistic Forecasting with Self-Rollout Error ControlYinan Huang, Shitij Govil, Bo Dai +1cs.LG2026-10-07
#420A Good Self-Teacher Meets the Student Where They Are: Joint On-Policy Learning and TeachingRandy Ardywibowo, Arnav Dalal, Jiantao Jiaocs.LG2026-10-07
#421NeuralBES: A Differentiable, Control-Aware Emulator for Scalable Building Energy ModelingTing-Yu Dai, Takuya Kurihana, Wing Yee Au +1cs.LG2026-10-07
#422Composing What Each Teacher Learned: Multi-Teacher On-Policy Distillation through Teacher-Relative ShiftsHejian Sang, Zhengze Zhou, Shayan Mohajer Hamidi +3cs.LG2026-10-07
#423Two-Level Softmax Sampling Done Right: Correcting Bias from Size Imbalance and DispersionWalid Bendada, Guillaume Salha-Galvancs.LG2026-10-07
#424Oracle-Efficient and Parameter-Free Agnostic Smoothed Online LearningSasha Voitovych, Adam Block, Alexander Rakhlin +1cs.LG2026-10-07
#425Why Forget-Only Unlearning Needs MemorizationLuka Radić, Vikrant Singhal, Amartya Sanyalcs.LG2026-10-07
#426Distilling Graph Geometry: Knowledge Gap from GNNs to MLPsZhewei Chen, Hao Zhu, Jiaojiao Jiang +1cs.LG2026-10-07
#427Decoupling Exploration from Optimization in RLVRSaif Punjwani, Micah Goldblumcs.LG2026-10-07
#428Know the Shape, Find the Fault: Topology-Conditioned Diagnosis of Multi-Agent LLM FailuresXinwen Liu, Zhuocheng Pan, Isabella Zhu +3cs.MA2026-10-07
#429A Society of Researchers: Designing Institutions for Populations of Autonomous Research AgentsAli Asaria, Deep Gandhi, Tony Salomonecs.MA2026-10-07
#430MemoCare: An Interactive Multimodal Mobile System for Automated Cognitive ScreeningDuy-Cat Can, Mau Minh Phuc Le, Tuan-Khoa Hoang +10cs.MM2026-10-07
#431Evolutionary Architecture Search for Chlorophyll-$a$ Prediction in Lakes using Sentinel-2Kursat Komurcu, Linas Petkeviciuscs.NE2026-10-07
#432Deadline-Aware Multi-Agent Reinforcement Learning for TSN-Based Vehicular Edge NetworksBernardo A. C. Pereira, Marcos Carvalho, Fatih Temiz +5cs.NI2026-10-07
#433Reproducible LLM Inference Benchmarking: A Sequential Isolation Protocol for Regression TestingArnold Olympio, Juan Manuel Servera Bondroit, Wael Abdelmalek +2cs.PF2026-10-07
#434Learning Unknown Constraints without Unsafe Data via Optimality and Counterfactual RegularizationZhouyu Zhang, Chih-Yuan Chiu, Glen Choucs.RO2026-10-07
#435Immiscible Diffusion Policy: Preserving Multimodal Robot Actions through Label-Free Noise AssignmentXiao Zhang, Yuxin Chen, Zhixuan Liang +5cs.RO2026-10-07
#436Sparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action ModelsJiho Lee, Jeongeun Park, Heayoun Choi +2cs.RO2026-10-07
#437Not All Uncertainty Matters: Simulation-in-the-Loop Fast-Slow Reasoning for Decision-Critical Autonomous Driving SystemJiayi Chen, Shuai Wang, Guangxu Zhu +3cs.RO2026-10-07
#438Adaptive Code Generation for Controlling RobotsJustus Flerlage, Thorsten Wittkopp, Alexander Acker +1cs.RO2026-10-07
#439NAViLoss: An Underwater Navigation-Aware Dual-Residual Objective for Physics-Consistent LearningArup Kumar Sahoo, Itzik Kleincs.RO2026-10-07
#440Do Better Visual Representations Always Lead to Better End-to-End Autonomous Driving?Zihao Zhang, Haochen Tian, Tianyu Li +5cs.RO2026-10-07
#441YUBI-STAG: Contact and Semantic-Rich Alignment for VLAs via Automated Video-Language GroundingMasatoshi Tateno, Takehiko Ohkawa, Yueh-Hua Wu +4cs.RO2026-10-07
#442Juno: Taming Predictive Latents for Vision-Language-Action ModelsYuchen Zhu, Chenyi Xu, Yulin Zhang +2cs.RO2026-10-07
#443Many Ways to Succeed: Diversity-Driven RL Fine-Tuning for VLA GeneralizationHaoru Li, Jinmei Liu, Zhiyong Wang +5cs.RO2026-10-07
#444Lifelong small-object navigation in changing object layouts: a benchmark and methodJiagan Huang, Zikun Zhou, Zijian Ni +4cs.RO2026-10-07
#445Temporal Visuo-Tactile Learning for Dexterous Grasp StabilityKen Nakahara, Aleksei Buvailik, Prokhor Kotov +1cs.RO2026-10-07
#446Energy-Efficient Gait Adaptation via Hierarchical Reinforcement Learning for Quadrupedal Locomotion Across Diverse TerrainsAmmar Issa, Anubhav Singh, Anton Tsaritsin +1cs.RO2026-10-07
#447MultiFly: A Real-World Multimodal Aerial Dataset with Annotation-Efficient Label Transfer and Cross-Modal Semantic ConsistencyMarkus Gross, Andreas Greiner, Taehyoung Kim +12cs.RO2026-10-07
#448RoboQuest: Generalist Physical Agents that Search, Inspect and TestLiu Renhang, Navonil Majumder, Tej Deep Pala +1cs.RO2026-10-07
#449RobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and EmbodimentsZhiqin Yang, Chenxin Li, Xiaomeng Hu +30cs.RO2026-10-07
#450FoldBack: Self-Correcting Masked Generative Policy for Long-Horizon Garment FoldingLipeng Zhuang, Shiyu Fan, Yingdong Ru +4cs.RO2026-10-07
#451Agentic RSR: Real-to-Sim-to-Real through Scene Reconstruction and Execution-Grounded Robot PoliciesYihan Li, Yating Feng, Shengjiu Sun +7cs.RO2026-10-07
#452Rephrase Before You Act: Characterizing and Mitigating Language Sensitivity in Vision-Language-Action ModelsMikey Watts, Yuchen Cuics.RO2026-10-07
#453Long-WAM: Scaling the Context of World-Action ModelsWei Huang, Bohan Zhang, Chenzhi Liu +13cs.RO2026-10-07
#454Tracing Inputs, Verifying Outputs: Validating Attribution in Music GenerationTaejun Kim, Wonil Kim, Jongmin Jung +10cs.SD2026-10-07
#455Backdooring Acoustic Foundation Models for Physically Realizable TriggersZebin Yun, Eyal Ronen, Mahmood Sharifcs.SD2026-10-07
#456CARES: A Controlled Synthetic Benchmark of Speaker Reactions to SoundMarcel Gibier, Thomas Thebaud, Olivier Boëffard +1cs.SD2026-10-07
#457MIRA: A Musical Intent Refinement Agent for Aligning Text-to-Music Generation with User IntentZekai Liu, Zhilin Wang, Xuzheng He +2cs.SD2026-10-07
#458Steerspeech: Activation Steering For Emotion Control In Generated SpeechAfsara Benazir, Darius Pétermann, Felix Xiaozhu Lin +1cs.SD2026-10-07
#459Why Software Engineering Is Indispensable in the Age of Coding AgentsAlfonso Fuggettacs.SE2026-10-07
#460TestGRAD: Evolving Test Suites via Failure Pattern Momentum for SWE-Agent EnsemblePengfei He, Jiayuan Zhou, Shaowei Wang +1cs.SE2026-10-07
#461QuSema: Detecting Silent Bugs in Quantum Libraries via Quantum-knowledge-enhanced AgentsYujin Song, Kaining Zhang, Qixin Zhang +3cs.SE2026-10-07
#462Using Small Language Models to Reverse-Engineer Machine Learning Pipelines StructuresNicolas Lacroix, Frederic Precioso, Mireille Blay-Fornarino +1cs.SE2026-10-07
#463TaoD2C-Bench: Benchmarking MLLMs for Industrial UI Code Generation Beyond Visual FidelityChengwei Shi, Yunnong Chen, Tingting Zhou +5cs.SE2026-10-07
#464VM-ARRAYDPS: Virtual Microphone Augmented Diffusion Posterior Sampling for Unsupervised Blind Speech SeparationJingqi Sun, Haozhan Tang, Shulin He +1eess.AS2026-10-07
#465Boundary-Free Contextual Biasing: Depth-Adaptive Gating and Reading-Space Matching for Unsegmented LanguagesMuhammad Huzaifah, Yu Pan, Zachary Yeo +2eess.AS2026-10-07
#466Mitigating Accent-Language Confusion in Self-Supervised Speech Representations for Language IdentificationMinu Kim, Jihwan Lee, David R. Mortensen +1eess.AS2026-10-07
#467A Strength-Monotonic Law for Domain Alignment in Frozen-Embedding Bioacoustic ClassificationYucheng Gong, Rui Zhou, Binbin Zeng +2eess.AS2026-10-07
#468Second-order optimization of variable projection SVM models and road abnormality detectionAndrea Angino, Matthias Voigt, Rolf Krause +1eess.SP2026-10-07
#469Transition Path Sampling Using Koopman Operators and Exit-Time Optimal ControlBoya Hou, Shane Wang, Siddharth Ambekar +2eess.SY2026-10-07
#470Fast holographic inversion of superconducting domesSejin Kimhep-th2026-10-07
#471Computations of the slice genus and the unknotting number of links via machine learningYutong Dai, Oliver Hayman, András Juhász +1math.GT2026-10-07
#472Neural Sampling with Reweighted Normalizing Flows via the Wasserstein--Fisher--Rao JKO SchemeChenguang Duan, Johannes Hertrich, Gabriele Steidlmath.NA2026-10-07
#473Beyond Nominal Equilibria: Risk-Averse Multi-Population Mean-Field GamesBhavini Jeloka, Siddhartha Ganguly, Panagiotis Tsiotrasmath.OC2026-10-07
#474Boundary-aware Reinforcement Learning for Hypercube State Spaces via Deterministic Policy GradientLijun Bo, Yijie Huang, Chenhao Lumath.OC2026-10-07
#475Decentralized SGD under Heavy-Tailed Noise: Optimal Convergence Rates and the Role of Gradient ClippingAleksandar Armacki, Haoyuan Cai, Ali H. Sayedmath.OC2026-10-07
#476The Silhouette Operator: Identifiability of Low-Rank Measures from One-Dimensional ProjectionsRobert A. Vandermeulenmath.ST2026-10-07
#477Unbounded Characteristic and Universal KernelsJose Cribeiro-Ramallo, Florian Kalinke, Zoltán Szabómath.ST2026-10-07
#478Sharp Asymptotic Theory of Maximum Likelihood Estimation for Gaussian Processes with an RBF KernelAmeer Qaqish, Didong Limath.ST2026-10-07
#479Artificial intelligence pathways from weather to climateTom Beucler, J. David Neelin, Hui Su +10physics.ao-ph2026-10-07
#480PEACE: Covariant learning of nonadiabatic manifolds with parity-resolved HamiltoniansRongzhi Gao, Shuguang Chen, Yang Zhou +3physics.chem-ph2026-10-07
#481LLM-Assisted Generation of Transparent, Open-Source Multiphysics Models of Electrochemical DevicesSebastian Castro, Maya F. Schuchert, Spencer A. McCluskey +2physics.chem-ph2026-10-07
#482Conditional Flow Matching for Generation of 3D Multi-variable Instantaneous Urban Microclimate FieldsPeng Liu, Shaoxiang Qin, Theodore Potsis +3physics.flu-dyn2026-10-07
#483Real-world application of deep learning in large-scale seismic interference attenuation: A case study in the Camie field of AngolaJing Sun, Song Houphysics.geo-ph2026-10-07
#484An AI-assisted conditioning and geological interpretation workflow for usage in implicit geological modelingStefan Carpentier, Jan Diederik van Wees, Eva de Boever +5physics.geo-ph2026-10-07
#485Structure alone supports efficient visual computation in the Drosophila visual systemEudald Correig-Fraga, Roger Guimerà, Marta Sales-Pardoq-bio.NC2026-10-07
#486FaceKit: a Toolkit for Interpretable Facial Phenotyping, Synthetic Image Generation and Privacy Analysis in Rare DiseasesHongzhuo Chen, Zhanliang Wang, Florent Pollet +9q-bio.QM2026-10-07
#487CircuitATLAS: Agentic reasoning over a systems neuroscience knowledge graph for target discovery in circuitopathiesGabriel Ocana-Santero, Marko Tvrdicq-bio.QM2026-10-07
#488Residual Learning in Empirical Asset PricingDexin Peng, Xiaoyu Wangq-fin.ST2026-10-07
#489Quantum anomaly detection in real scarce dataEmanuele Casciaro, Fabio Mascherpa, Alfonso Amendola +1quant-ph2026-10-07
#490Q-PhotoMarket: A Design Space Exploration Framework for Photonic Hybrid Quantum Neural Networks in Financial Market PredictionAlberto Marchisio, Hanzalah Mohamed Siraj, Muhammad Kashif +2quant-ph2026-10-07
#491Pareto-optimal quantum kernel selection for unsupervised anomaly detection on real malware beaconing dataBoaz Micah, Nadia Milazzo, Maissa Beji +8quant-ph2026-10-07
#492Measurement-Efficient Differentiable Quantum Architecture Search for Combinatorial OptimizationLukas Theißinger, Thore Gerlach, Christian Bauckhagequant-ph2026-10-07
#493Learning joint probabilistic weather forecasts from station observations aloneChaeyeon Yi, Yun Am Seostat.AP2026-10-07
#494Estimating Uncoded Crash Factors with Tabular Foundation and System One Models: Kumo Tabular and JevAmir Rafe, Subasish Dasstat.AP2026-10-07
#495Policy Learning with Weak SignalsBenedikt Koch, Winston Chou, Aurélien Bibaut +1stat.ME2026-10-07
#496Adjoint-Based Calibration and Optimal Control of Stochastic Multiscale Bioprocess Digital TwinsKeilung Choy, Wei Xiestat.ML2026-10-07
#497Reflected Anchored Langevin AlgorithmsChangwei Tu, Xiaoyu Wang, Yingli Wang +2stat.ML2026-10-07
#498Unpaired Canonical Correlation AnalysisNir Ben-Ari, Ronen Talmon, Uri Shahamstat.ML2026-10-07
#499Certified by Abstention: Distribution-Free Guarantees for Chain-of-Thought Verifiers at Small Calibration BudgetsArjun Balajistat.ML2026-10-07
#500Scalable Logistic Gaussian Process Density Regression with Kinetic Langevin SamplingDaniel Paulin, Ádám Jung, András A. Benczúrstat.ML2026-10-07
#501Sparsifying Stochasticity, Not Capacity: Partial Stochasticity via Deep Weight Factorization of Prior ScalesMarius P Linhard, Maurizio Filipponestat.ML2026-10-07
#502Possibilistic Radial Transport for Approximate IM InferenceJungeum Kim, Percy Zhaistat.ML2026-10-07
#503Extreme Binary Classification: Extreme Value Theory for Extreme Constraint on False NegativeSamuel Gruffaz, Muhammad Fawad, Jaakko Nevalainenstat.ML2026-10-07
#504Controlling Dependence in Implicit Generative Models via Spread Mutual InformationJiahao Yu, Song Liu, José Miguel Hernández-Lobato +1stat.ML2026-10-07
#505Gaussian Equivalence for Multi-Head Self-AttentionTomohiro Hayase, Ryo Karakidastat.ML2026-10-07
#506Towards Calibrated Probabilistic Forecasts for Events of Interest via Outcome-Conditional RecalibrationJakob Benjamin Wessel, Sam Allenstat.ML2026-10-07
#507Conformal Prediction for Spatially Dependent Data via Sequential WhiteningAyush Baran Sen, Arkajyoti Sahastat.ML2026-10-07
#508Kinetic Langevin Meets Split Gibbs: Accelerated Posterior Sampling for Imaging Inverse Problems with Diffusion PriorsDai Hai Nguyen, Duc Dung Nguyenstat.ML2026-10-07
#509Universal Local Error and Realized Amplification for the First-Order EDM PredictorNicolas Brosse, Arnak S. Dalalyanstat.ML2026-10-07
#510Broadly Applicable Approximate MCMC for Switching Stochastic Differential Equations Using Uniformization and Time-Conditioned Factorized Neural Likelihood EstimationShion Hosoda, Michiaki Hamadastat.ML2026-10-07
#511RoBART: Bayesian Additive Regression Trees with Tree-Specific RotationsJeongung Heo, Seonghyun Jeongstat.ML2026-10-07
#512Data Reuse in Non-Stationary LearningTomer Gafni, Garud Iyengar, Assaf Zeevistat.ML2026-10-07
#513Dataset Pruning from First Principles: A Label-Free Linear Programming ApproachRodrigo Schuller, Francisco Ganacimstat.ML2026-10-07
#514Safe Meta-Policy Design with Risk ControlWenbin Zhou, Michael Lingzhi Li, Shixiang Zhustat.ML2026-10-07
#515Derivative Gaussian Processes on a Two-Direction BudgetHyunseok Seung, Matthias Katzfussstat.ML2026-10-07
#516Best Arm Identification for Bandits with Shifting MeansLukas Zierahn, Wouter M. Koolen, Shubhada Agrawal +2stat.ML2026-10-07

latest · trends · arXiv announcement batches follow US Eastern weekdays