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

New Papers · 2026-10-02 441 submissions

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

#TitleAuthorsCatDate
1Time Series Forecasting Benchmarks Need Scenario-Grounded Stress TestingYuyang Zhao, Lian Xu, Hao Xuecs.AI2026-10-02
2VERSE: Verified Self-Evolving Optimizer for Agent HarnessesZekai Wang, Yingqiang Ge, Zekun Wang +6cs.AI2026-10-02
3CuBEs: Culturally-Situated Behavioral Evaluations and the Limitations of Culture-Blind LLM JudgesHoda Ayad, Tanu Mitra, Abhishek Mukherjics.AI2026-10-02
#4Lost in the Request: How Communication Variation Disrupts Retrieval and Action in Email AgentsFeng Chen, Ritam Dutt, Atnaz Taheri +1cs.AI2026-10-02
#5Designing the Future of User Feedback for Generative AIAlisa Frik, Julia Bernd, Amitis Karami +1cs.AI2026-10-02
#6Batched Speech Decisions Without Decoding: Single-Token Supervision Lets a Frozen LLM Hear Beyond the TranscriptJie Jin, Ziyin Ma, Min Yin +4cs.AI2026-10-02
#7Coherence-Driven Belief Formation and Population Dynamics of Contagion in LLM AgentsTathagata Banerjee, Nima Moghaddascs.AI2026-10-02
#8A GHOST in Long-Horizon Agents: Governance Hazard from Overlooked Safety Constraints across TurnsXinPeng Shen, Lan Zhang, Yixiao Huang +4cs.AI2026-10-02
#9Spend Teacher Tokens Where They Matter: Success-Referenced On-Policy DistillationXiang Chen, Futao Su, Kong Wang +2cs.AI2026-10-02
#10DataWeave: Deploying Human-LLM Analytics for Exploratory Structured Data AnalysisRaquib Bin Yousuf, Harith Laxman, Vitaliy Shkremetko +10cs.AI2026-10-02
#11Large language models exhibit unreliable updating of clinical judgment as patient evidence evolvesMin Zeng, Rui Zhangcs.AI2026-10-02
#12Decoupling Memory from Context: Structured Memory for Token-Efficient Test-Time Continual LearningYehya Farhat, Michael Desmond, Anastasios Kyrillidiscs.AI2026-10-02
#13Learning to Revise Reasoning with Segment-wise On-Policy DistillationYuxiang Zhang, Ding Cao, Shuting Cui +3cs.AI2026-10-02
#14Label-Efficient Time Series Classification at Scale: A Dual-Stream OSSE-LSTM with Counterfactual AttributionNguyen Ho, Bach Tung Tran, Trung Ky Nguyen +3cs.AI2026-10-02
#15Ego2World: Compiling Egocentric Cooking Videos into Executable Worlds for Belief-State PlanningQinchuan Cheng, Zhantao Gong, Pengzhan Sun +2cs.AI2026-10-02
#16On the Chain-of-Thought Monitorability of Looped Language ModelsHan Wang, Ishwar B Balappanawar, Huan Zhangcs.AI2026-10-02
#17Dynamic LLM Routers are Often MisguidedSam Wang, Julia White, Sahibzada Allahyar +3cs.AI2026-10-02
#18Law And Order: Tax Law AutoformalizationSophia Simeng Han, Yoshiki Takashima, Anjiang Wei +2cs.AI2026-10-02
#19PAPER2LLM++: Continual Self-Evolution of LLMs from Research PapersHongji Pu, Yilun Zhao, Wenpeng Yincs.AI2026-10-02
#20Modeling Shared and Individual Structure for Cross-Subject Continuous Affect Regression from EEG-fNIRSXuan Wang, Bing Wang, Shuai Chang +3cs.AI2026-10-02
#21BitNest: Bit-Nested Speculative Decoding for Memory-Efficient LLM Inference AccelerationChence Yang, Ningxi Cheng, Arash Akbari +9cs.AI2026-10-02
#22VIGOR: Zero-Shot Visual Generalization via Latent-Space Consistency in Model-Based Reinforcement LearningMingyu Park, Samyeul Noh, Hyun Myung +1cs.AI2026-10-02
#23ROUTEAUDIT: Interaction-Aware Identification for Budgeted Multi-Verifier RoutingMiaobo Hu, Shuhao Hu, Xiaobo Guo +5cs.AI2026-10-02
#24iS-KV: Online Low-Rank KV Cache Compression via Block-Incremental SVDYiren Zhao, Guanghui Song, Tianrui Qin +3cs.AI2026-10-02
#25MetaRubric: Learning to Reward for Rubric-Based Reinforcement LearningYuxuan Fan, Jaehong Yooncs.AI2026-10-02
#26Scaling Trajectories for Complex Tasks through Recursive Self-RewriteZongxia Li, Yucheng Shi, Zhongzhi Li +7cs.AI2026-10-02
#27MLCommons Jailbreak Benchmark v1.0Carsten Maple, Cagatay Yucel, Isaac Holeman +35cs.AI2026-10-02
#28FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Post-TrainingMiaobo Hu, Shuhao Hu, Xiaobo Guo +4cs.AI2026-10-02
#29AMBER: Multi-View Adaptive Budget Allocation for Listwise Vision-Language RerankingWenteng Chen, Jiachen Zhu, Rong Shan +10cs.AI2026-10-02
#30DNAlign: Dynamic Null-Space Safe Alignment for LLMsJisheng Dang, Yushuo Zhao, Dewei Liu +6cs.AI2026-10-02
#31Bounded Reachability & Jailbreak Detection via Contraction-Constrained State Space ModelsOmanshu Thapliyalcs.AI2026-10-02
#32Harness-Aware Distillation for Small Language Model AgentsMoonseok Choi, Taehong Moon, Giung Nam +1cs.AI2026-10-02
#33TACD: Distilling Efficient Text-to-Motion Models via Terminal Amplification ControlWei-Jin Huang, Yuan-Ming Li, Kun-Yu Lin +8cs.AI2026-10-02
#34PsyEvo: A Personalized Counseling Agent That Self-Evolves at Test TimeYuting Yan, Shihao Xu, Junhao Yu +6cs.AI2026-10-02
#35Interpreting at Write Time: A Policy Ablation for Multi-Goal Agent MemoryAlbert Sadowski, Jarosław A. Chudziakcs.AI2026-10-02
#36LUMOS: Tracing Parametric Knowledge from Training Data to Behavioral Outputs in LLMsSeoyeon Ye, Gayoung Kim, Jiyoung Hong +2cs.AI2026-10-02
#37Frequency Is Not Sensitivity Identifying Safety-Sensitive Experts in Sparse MoE LLMMd Nurul Absar Siddiky, Liuwan Zhu, Yingfei Dongcs.AI2026-10-02
#38HASTE: Evolving Agent Harnesses Against Emerging Attacks Using Sparse EvidenceXiqiao Xiong, Moxin Li, Zhixin Ma +4cs.AI2026-10-02
#39Positive-Unlabeled Learning for Agent Safety False Alarm AuditingXichen Yan, Chongyang Gao, Kezhen Chen +3cs.AI2026-10-02
#40When to Compile a Computer-Use Agent? Measuring Payback and Making Compilation Decisions for Token EfficiencyYulong Ming, Jie Xu, Zihan Wu +1cs.AI2026-10-02
#41Continual Graph Memory for Mathematical Research AgentsJunyi Zhang, Jinxi Yu, Eric Hanchen Jiang +14cs.AI2026-10-02
#42Reasoning with Evidence, Not Merely Rationales: Verifiable Preference Proofs for LLM-Based RecommendationYu Hou, Nathaniel Kang, Pengkai Wang +1cs.AI2026-10-02
#43CreateScore: Domain-Theory-Informed Bayesian Routing for LLM-Based CV ScreeningRupsa Roycs.AI2026-10-02
#44Reliable Self-Evolution with Imperfect Proxy RewardsKangjun Noh, Soyu Kim, Kyungwoo Songcs.AI2026-10-02
#45Relevant Evidence Decoding for Audio-Visual Hallucination MitigationHyunjae Ra, Aecheon Jung, Jungin Park +1cs.AI2026-10-02
#46RASPER: Reward-Aligned Summarization of Clinical Notes for EHR Outcome PredictionArya Hadizadeh Moghaddam, Mohsen Nayebi Kerdabadi, Chen Chen +2cs.AI2026-10-02
#47Safeguarding Mutual Correction in Source-Free Domain Adaptation via Cut StatisticsSeongjun Lee, Changhee Leecs.AI2026-10-02
#48PLCWorld: Benchmarking LLM-Generated PLC Programs in Closed-Loop Plant SimulationYunji Kim, Yunseok Lee, Hyunwoo Seo +2cs.AI2026-10-02
#49Personalized Automatic Speech Recognition for a Dysarthric and Tracheostomic Speaker using Artificial ConversationsDavid Nadrchal, Monorama Swain, Florian Schmid +2cs.AI2026-10-02
#50DyadMem: A Long-Term Memory Benchmark of How Agents Work with UsersYifei Tao, Xinyu Zhong, Henry Hengyuan Zhao +5cs.AI2026-10-02
#51Verifiable, Articulable, and Tacit Components of PreferenceAlexander Spangher, Sheldon Huang, Andreas Haupt +4cs.AI2026-10-02
#52SoftGene: Protein Language Model-Enhanced Soft Prompting for Interpretable Gene Set AnnotationDrew Ross, Arya Hadizadeh Moghaddam, Dongjie Wang +2cs.AI2026-10-02
#53When Numbers Start Talking: Numerical Signalling and Strategic Behaviour Among LLMsAlessio Buscemi, Daniele Proverbio, Alessandro Di Stefano +3cs.AI2026-10-02
#54hacktrace: behavior-supervised detection of reward hacking during code generationHao Jiang, Xin Li, Annan Wang +2cs.AI2026-10-02
#55MOF-VERIFY: A Failure-Aware Agentic Harness for MOF Hypothesis VerificationDonghyun Lee, Taehoon Lee, Geonhee Ahn +10cs.AI2026-10-02
#56RIFAR: Reliability and Forgetting-Aware Replay for Continual Robot LearningZirong Song, Zheng Lu, Haoran Liao +4cs.AI2026-10-02
#57Peer Influence across Heterogeneous AI ModelsFrida Nøhr Laustsen, Marie Haahr Petersen, Victoria Popa +4cs.AI2026-10-02
#58Predictor-Guided Latent Space Codon Optimization for Maximizing Protein ExpressionAlberto Caron, Tianyu Cui, Dmytro S. Lituiev +13cs.AI2026-10-02
#59Trading Strategy Optimization via Textual GradientChaoqun Yang, Qian Wang, Fengbin Zhu +4cs.AI2026-10-02
#60Keeping JEPA World Models Plannable When Little of the Frame MovesFlorian Strohm, Patrick Wagner, Jannik Schwab +1cs.AI2026-10-02
#61Gains and Collapse in On-Policy Distillation:A Reinforcement Learning PerspectiveHan Cui, Jianhao Yan, Yun Luo +3cs.AI2026-10-02
#62KV$^2$: A Self-Refining KV CacheJohannes Wesch, Danni Liu, Jan Niehuescs.AI2026-10-02
#63Toward SLM-based agentic task-tool intent matchingChiara Troiani, Arash Salarian, Majed El Helou +4cs.AI2026-10-02
#64Learning a Fact Is Not Learning How to Retrieve ItChaemin Jang, Jihee Kim, Dongman Leecs.AI2026-10-02
#65EVOL: Simulator-Guided Evolutionary Expert Synthesis for Deployment-Free Learning Path RecommendationGeonwoo Bang, Dongho Kim, Moohong Mincs.AI2026-10-02
#66JOVE: Joint Execution and Verification for Resource-Aware LLM Task GraphsHaoran Zhang, Dongjun Kim, Seohyeon Cha +4cs.AI2026-10-02
#67Optimal Planning in a Dynamic WorldDevin Wild Thomas, Solomon Eyal Shimony, Wheeler Ruml +3cs.AI2026-10-02
#68Lightweight, Rubric-Guided Trajectory Evaluation for Production AI AgentsLinh-An Phan, MingXue Wang, Guangyu Wu +3cs.AI2026-10-02
#69Multi-Task Evolution for Zero-Shot Cross-Problem Generalization using LLMsZhouliang Xie, Changliang Zhou, Genghui Li +1cs.AI2026-10-02
#70Refinement Buys Intelligibility, Search Buys Identity: What Test-Time Compute Buys in Masked-Diffusion TTSNityanand Mathur, Hamees Sayed, Ayush Pratap Singhcs.AI2026-10-02
#71Preserving Mathematical Reasoning in Compressed Diffusion Language Models via Trajectory-Aware Low-Rank ApproximationTian Liang, Zishan Shao, Yiran Chencs.AI2026-10-02
#72ReFract: Benchmarking Perspective Awareness in Language Model Agents with Text World ModelsHainiu Xu, Vítor N. Lourenço, Mohnish Dubey +7cs.AI2026-10-02
#73Geometry Meets Physics: Data-Efficient Pre-Training for Unstructured Neural PDE SolversLuis Medrano-Navarro, Giacomo Baldan, Qiang Liu +4cs.AI2026-10-02
#74Multilingual GSM-Symbolic: What determines capability transfer across languages?Kenneth Enevoldsen, Riley Herchert, Sofie Mosegaard +22cs.AI2026-10-02
#75CVE2AP: Automated Generation of PDDL-Encoded Attack Paths via Large Language ModelsLin Cui, Vincenzo Scotti, Raffaela Mirandolacs.AI2026-10-02
#76Benchmarking Candidate Coverage in Typed Decision ModelsJiawen Lu, Tongtong Wucs.AI2026-10-02
#77Becoming Suspicious Across Borders: Algorithmic Extraterritoriality and AI-Driven Financial SurveillanceGeorgios Pavlidis, Savvas Chatzichristofis, Eleni Gavriilcs.AI2026-10-02
#78Jumping the Line: Exploiting Length Predictions in LLM SchedulingYuyang Dai, Rana Shahout, Mahmood Sharifcs.AI2026-10-02
#79A Near-Zero Monitor Readout Is Not Evidence of Behavioral ControlZhe Zhou, Tianhua Taocs.AI2026-10-02
#80Efficient Reasoning Training Does Not Always Harm CoT Faithfulness and MonitorabilitySamuel Lewis-Lim, Xingwei Tan, Mario Sanger +2cs.AI2026-10-02
#81Reasoning Models Are Accurate but Unsound on IdentificationArman Behnam, Binghui Wangcs.AI2026-10-02
#82From Benchmarks to Production: A Text-to-SQL System for Complex Financial DataArijit Sehanobish, Bruno Gomes Coelho, Guillaume Michel +3cs.AI2026-10-02
#83Recursive Harness Self-Improvement for Frontier Reasoning Data SynthesisWenlong Zhang, Zhengbo Jiao, Chenxu Zhang +5cs.AI2026-10-02
#84Knowledge or Calculator? Decomposing the Skill Premium in Verifiable Financial Agent WorkflowsJermyn Zhen Yong Bek, Zhuang Qiang Bok, Zhongtian Suncs.AI2026-10-02
#85Learning to Assess Heartbeat Observability for mmWave Heart-Rate SensingYuxuan Hu, Shilin Shan, Jianfei Yang +1cs.AI2026-10-02
#86HyperBrowseComp: A Multilingual and Multimodal Stress Test for Web-Browsing AgentsAlham Fikri Aji, Faiz Rizki Ramadhan, Zayd M. K. Zuhri +14cs.AI2026-10-02
#87HazardWeaver: Scientific Route Selection for Hazard Analysis AgentsWangshu Zhu, Xueqi Cheng, Liang Wu +1cs.AI2026-10-02
#88Low-Cost Video--Time Priors as a Strong Baseline for EEG--fNIRS Emotion Regression on Familiar VideosMinghao Kong, Jiurun Chen, Ying Gao +2cs.AI2026-10-02
#89Depth as Time in One-Step Generative ModelsArnold Caleb Asiimwe, William Yang, Sanghyuk Chun +2cs.AI2026-10-02
#90NeutronGym: Physics-Graded Neutron Instrument Design for LLM AgentsLijie Ding, Changwoo Docs.AI2026-10-02
#91Credit Where It Matters: Dependency-Aware Policy Optimization for Terminal AgentsYu Li, Guangfeng Cai, Long-Fei Li +5cs.AI2026-10-02
#92Do Large Language Models Know Colombian Law? A Reliability Benchmark for the Colombian Legal SystemRubén Manrique, Michelle Castellanos, Jorge Morales +3cs.AI2026-10-02
#93MRVQ: One Resident Index for Dimension- and Rate-Elastic Vector SearchSean Culatana, Shang-En Huang, Kang Lics.AI2026-10-02
#94Transcriptome-informed multi-modal AI for predicting neoadjuvant therapy response from breast cancer biopsiesJungkyu Park, Dhruva Biswas, Joseph Cappadona +22cs.AI2026-10-02
#95Learning When to Commit from Partial Speech for End-to-End Simultaneous Speech TranslationHieu Hoang, Amittai Axelrodcs.CL2026-10-02
#96Large Language Continuous Diffusion ModelsZhihan Yang, Wei Guo, Jean-Marie Lemercier +14cs.CL2026-10-02
#97Silent Dissent: LLM Agents That Yield to the Majority Still Represent Their Original PremiseZiang Ni, Peng Zoucs.CL2026-10-02
#98WakeKV: Reactive, Reversible KV Residency for Heads That Change Their MindsUtkarsh Ranjancs.CL2026-10-02
#99TPBench: A Turning-Point Benchmark for Dialogue CompressionMinji Park, Seunghyun Yoon, Hyuk Limcs.CL2026-10-02
#100Beyond Correctness: Resolving Underspecification in Agentic Text-to-SQLWen-Zhi Li, Yue Gong, Konstantinos Kanellis +1cs.CL2026-10-02
#101EpiWorld: Grounding LLM Policy Agents in Epidemiological World ModelsZeeshan Memon, Yiqi Su, Kai Shu +2cs.CL2026-10-02
#102When History Fails to Become Experience: Action Calibration in Language AgentsJingyu Liu, Zhiwen Wang, Yuxin Jing +2cs.CL2026-10-02
#103AptMQL-Bench: From Text-to-SQL to Text-to-MQL via Access-Pattern Schema Design and Data-Preserving MigrationHy Nguyen, Nabi Rezvani, Robin Vujaniccs.CL2026-10-02
#104Improving Atomic-Fact Recall via Focused Views in Unstructured Knowledge EditingDing Wu, Ye Zhang, Haoyu Wang +1cs.CL2026-10-02
#105Automatic Evaluation of Mental Health Stigma in Online CommunicationNaomi Baes, Jemima Kang, Nick Haslam +4cs.CL2026-10-02
#106Text-Centric Post-Training for Omni-Modal ReasoningZiyang Cheng, Yuhao Wang, Hongcheng Liu +5cs.CL2026-10-02
#107Clinical Concept Centers in LLMsAishik Nagar, Abhishek Vaidyanathan, Arun-Kumar Kaliya-Perumal +2cs.CL2026-10-02
#108How Robust Is Multimodal Claim Verification to LLM Rewriting?Yun-Ang Wu, Xanh Ho, Andre Greiner-Petter +4cs.CL2026-10-02
#109Adaptive Mutual Distillation for Balanced Multi-Task Post-Training of Large Language ModelsBaohang Li, Xiaocheng Feng, Yichong Huang +6cs.CL2026-10-02
#110ConvoDrift: A Multi-Turn Conversational Dataset for Modeling Stylistic Tone EvolutionVihindi Kotalawala, Pamoda Dilranga, Gayani Thoradeniya +1cs.CL2026-10-02
#111Query-aware routing for Cross-lingual performance gains in EncodersAkshay Jain, Edward Kimcs.CL2026-10-02
#112Evaluating LLM-as-a-Judge Beyond Score Alignment: A Psychometric Analysis of Residual Judging DifficultyLongwei Cong, Sonja Hahn, Sebastian Gombert +4cs.CL2026-10-02
#113Evaluating VQA in Vision Language Models using Cooperative PrinciplesMonika Shah, Sudarshan Balaji, Somdeb Sarkhel +2cs.CL2026-10-02
#114Misinformation Without Triggers: From Factual Answers to Downstream DecisionsLin Tian, Marian-Andrei Rizoiucs.CL2026-10-02
#115Output Language Confusion under Multilingual Prompt ContaminationRiju Marwah, Ritvik Garimella, Khusham Bansal +2cs.CL2026-10-02
#116Enhancing Biomedical Named Entity Recognition via Multiple Programming Languages Instruction Tuning and Ensemble MethodSongtao Li, Yijia Zhang, Jianyuan Yuan +3cs.CL2026-10-02
#117A Guideline-Augmented Multi-Agent Framework for Schema-as-Code Biomedical Named Entity RecognitionSongtao Li, Yijia Zhang, Shidi Zhang +3cs.CL2026-10-02
#118OLMo-Detect: A Multi-Stage, Confounder-Controlled Benchmark for Membership Inference on Large Language ModelsTao Shi, Chaoyi Xiang, Qiongkai Xu +1cs.CL2026-10-02
#119OmniConfess: Eliciting Token Confessions to Mitigate Omni-Modal HallucinationHuiqiang Rong, Haoran Luo, Hui Feng +4cs.CL2026-10-02
#120Recursive Self-Improvement in Unified Multimodal ModelsHuijuan Wang, Chufan Shi, Cheng Yang +3cs.CL2026-10-02
#121HyperThink: Text-to-Parameter Hypernetworks for Efficient ReasoningDonggyun Kim, Jack Lu, Chanwoo Kim +2cs.CL2026-10-02
#122The Geometry of Knowledge Accessibility in Large Language ModelsLihu Chencs.CL2026-10-02
#123HARPO: Hallucination-Aware Reinforcement Learning for Faithful and Creative Language GenerationTiezheng Yu, Yuxin Jiang, Jinpeng Li +4cs.CL2026-10-02
#124Unmasking Propaganda: A Comparative Analysis of Masked and Causal Language ModelsClaudiu Creanga, Ioachim Lihor, Liviu P. Dinucs.CL2026-10-02
#125An automated pipeline for standardised speech-unit annotation in spontaneous dialogueHanlu He, Harald Vilhelm Skat-Rørdam, Ingvi Örnólfsson +1cs.CL2026-10-02
#126Ask, Relax, or Act? Evaluating Actionable Indeterminacy in LLM Preference ReasoningAng Li, Yue Lin, Feifei Kou +6cs.CL2026-10-02
#127Emergent Structure in the Marginal Attention Space of Language ModelsValentino Maiorca, Walter Nelson, Francesco Locatellocs.CL2026-10-02
#128Ontological Instability and Statistical Amplification: The Paradox of "Humanizing" LLM-Generated TextClaudiu Creanga, Liviu Dinucs.CL2026-10-02
#129Building Interpretable Feature Representations for Resume-Vacancy Matching by Distilling Production LLM SignalsIlya Chekin, Vyacheslav Malyugin, Vladimir Chirkov +1cs.CL2026-10-02
#130Investigating the Role of Reasoning-Language Alignment in Monolingual Retrieval-Augmented GenerationOliver Hauck, Mario Sanz-Guerrero, Katharina von der Wensecs.CL2026-10-02
#131Predicting Steering Vectors and Adapter Weights for Few-Shot Author-Style TransferLeonard Popp, Danni Liu, Supriti Sinhamahapatra +1cs.CL2026-10-02
#132Hindsight-Guided Rationale Distillation for Rare Disease DiagnosisAarav Singh, Animesh Pathak, Navyansh Singhcs.CL2026-10-02
#133Not Until the Evidence Says So: Teaching LLM Investigators When to Close a CaseTingzhu Bi, Ping Wang, Meng Macs.CL2026-10-02
#134Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce ItJonghyun Song, Haewon Park, Jeonghoon Shim +2cs.CL2026-10-02
#135StanceEval 2026: The Second Stance Detection Shared TaskRasha Albalawi, Nuha Albadi, Hamzah Luqman +6cs.CL2026-10-02
#136Collective Bias Mitigation via Model Routing and CollaborationMingzhe Du, Luu Anh Tuan, Xiaobao Wu +7cs.CL2026-10-02
#137Shrome at Touché: Soft-Vote Ensembling and Counter-Causal Augmentation for Causality ExtractionRoham Zendehdel Nobari, Shayan Sooratgarcs.CL2026-10-02
#138To Jev or Not? Evaluating the Accuracy and Efficiency of Structured Decision Models for Hate-Speech ModerationDemetris Paschalides, George Pallis, Marios D. Dikaiakoscs.CL2026-10-02
#139SyntaxBench: A Statistical Diagnostic Framework for Character-Level Reasoning in Large Language ModelsMohsen Larni, Sobhan Ebrahimi Azar, Pouyan Nahed +1cs.CL2026-10-02
#140CLIMB: Confidence-Guided Complementary Evidence for Multimodal Retrieval-Augmented GenerationHang Gao, Wujiang Xu, Zhixing Zhang +3cs.CL2026-10-02
#141Single-Pass Uncertainty Heads for Claim-Level Hallucination Detection in Persian Medical Language ModelsMehrdad Ghassabi, Pedram Rostami, Hamidreza Baradaran Kashani +2cs.CL2026-10-02
#142Learning from Repaired Reasoning: Root-Cause-Guided On-Policy DistillationChenglei Shen, Haoyang Yao, Weijie Yu +3cs.CL2026-10-02
#143Structured Composition of Verifiable Atomic Insights for Table-to-Report GenerationTeng Lin, Xinyu Liu, Nan Tangcs.CL2026-10-02
#144Author Representation Strategies for Zero-Shot Authorship Attribution: A Comparative Study of LLM-Based and Embedding-Based ApproachesNudrat Habib, Tosin Adewumi, Sana Sabah Al-Azzawi +2cs.CL2026-10-02
#145Writerslogic at PAN 2026: Process over Content for Robust Detection under Domain ShiftDavid L. Condreycs.CL2026-10-02
#146Writerslogic at the CLEF 2026 SimpleText Track: Multi-Candidate LLM Simplification and Stacked Complexity SpottingDavid L. Condreycs.CL2026-10-02
#147FALCON: A Model and Dataset Agnostic Framework for Synthetic Data Generation for NL2SQL PairsDarian Lee, Shannon Rumsey, Jack St. Clair +3cs.CL2026-10-02
#148Language Models that Play Chess and Explain Their MovesAdithya Bhaskar, Jeffrey Cheng, Danqi Chencs.CL2026-10-02
#149RMCW: A Deletion-Robust Watermark Based on Reed--Muller Codes for Language ModelsYi Wang, Baicheng Chen, Yu Wang +3cs.CR2026-10-02
#150AgentTrap: Stateful Feedback Deception against Autonomous Penetration Testing AgentsYuelin Wang, Jiongchi Yu, Yanbang Suncs.CR2026-10-02
#151Beyond Predefined Sinks: Security-Aware Dependency Analysis for LLM AgentsHang Cuics.CR2026-10-02
#152SecJev: Bringing Security Expertise to System One Decision ModelsZheng Chen, Fei Yu, Haohao Huang +3cs.CR2026-10-02
#153Securing Computer-Use Agents Against Branch Steering AttacksGiulio Zingrillo, Hanna Foerster, Ilia Shumailov +2cs.CR2026-10-02
#154The Fragility of Trigger-Tag Mechanisms for Misuse Detection in Open-Weight LLMsToluwani Aremu, Manit Baser, Mohan Gurusamy +2cs.CR2026-10-02
#155EvoRiskBench: An Evolving Benchmark for Runtime Security Risks in Workspace AgentsShiyi Kuang, Xuemei Luo, Kun Liu +7cs.CR2026-10-02
#156LiBRA: Detection-Aware Image Watermark Removal via Bidirectional Latent OptimizationSaibo Ye, Huajie Chen, Xin Guo +5cs.CR2026-10-02
#157Passing the Test You Trained On: Re-evaluating Prompt-Injection Detectors for LLM AgentsZhuowen Liucs.CR2026-10-02
#158Threat-Preserving Representation Sensitivity in Agent-Security BenchmarksNeeraj Karamchandani, Piyush Nagasubramaniam, Xinhong Xie +2cs.CR2026-10-02
#159PoCoFL: POlicy-COmpliant Federated LearningDominik Roy George, Varesh Mishra, Aysajan Abidincs.CR2026-10-02
#160Imagine the Future, Internalize the Gist: Efficient VLA Reasoning via Internalized Spatiotemporal ImaginationShenglan Li, Zhendong Mi, Hengyi Zhu +6cs.CV2026-10-02
#161Capturing Dynamics: The 4D Facial Expression Intensity DatasetZesheng Wang, Alexandre Bruckert, Pierre Lebreton +3cs.CV2026-10-02
#162SpectralCache: Accelerating Diffusion-Based World Models via Spectral Feature CachingZhendong Mi, Pu Zhao, Ziyu Hu +4cs.CV2026-10-02
#163CHASE-VLA: Post-Training Quantization Framework for Vision-Language-Action Models with Chunk-Aware Scale EstimationJin Hyun, Jung Gyu Min, Gyuhyun Jung +1cs.CV2026-10-02
#164Revisiting Visual Representation Enhancement of VLMs via Kernel Canonical Correlation AnalysisPeilin Yang, Xiaoyu Liu, Jian Sun +1cs.CV2026-10-02
#165SymRegFlow: Symmetry-Regularized Flow Matching for Video World ModelsXi Ye, Yuzhu Wang, Xiaoyang Liu +6cs.CV2026-10-02
#166Correcting Guided Diffusion Trajectories with Spectral AlignmentGihoon Kim, Taesup Kimcs.CV2026-10-02
#167FiberGeoText: A Vision-Language Model for Population- Level Organization of Superficial White MatterYuqian Chen, R. Jarrett Rushmore, Guikun Chen +5cs.CV2026-10-02
#168TRAC: Trajectory-aware Reuse and Adaptive Correction for Efficient Autoregressive Video GenerationJiaxing Song, Weiqi Yan, You Huang +4cs.CV2026-10-02
#169FUSEye: Training-Light Fisheye Detection with Overlapping Views and Zero-Initialized AdaptersWenya Su, Kai Luo, Di Wen +5cs.CV2026-10-02
#170TerrainForge: Physics-Grounded road geometry Editing for Counterfactual Autonomous DrivingYang Chen, Yicheng Zhu, zhenning Li +2cs.CV2026-10-02
#171Seeing, Saying, but Not Using: From Reportable Spatial Facts to Usable States in Multimodal Large Language ModelsJinchang Zhang, Guoyu Lucs.CV2026-10-02
#172Found but Not Read: When Extracted Text Closes the Retrieval-Reading Gap in Document Vision-Language ModelsQingtao Xia, Siyao Cheng, Jiahua Bao +2cs.CV2026-10-02
#173Revealing Epistemic Uncertainty in MLLMs via Causal-Invariant MaskingHaoyang Luo, Linwei Tao, Jie Gui +4cs.CV2026-10-02
#174ViTok: Improving Dense Semantics in AM-RADIO-Style Multi-Teacher Distillation with PHI-S and Masked Image ModellingHailun Xu, Kanchan Sarkarcs.CV2026-10-02
#175Custom Forcing: Training-Free Subject Customization for Autoregressive Video GenerationYunseung Ok, Hyunsoo Kim, Minseo Kim +1cs.CV2026-10-02
#176Kinematics-Induced Multimodal 3D Human Pose Estimation with Subject-Level PrivacyKaushik Bhargav Sivangi, Fani Deligiannics.CV2026-10-02
#177When Predicting Nothing Beats SAM 3: Revisiting Evaluation in Video Object SegmentationJihwan Hong, Woohyeon Park, Jaeik Kim +1cs.CV2026-10-02
#178TerraVis: Towards Evaluation of World-Grounded Visual Consistency in Text-to-Image Generation via MLLM WorkflowsShuai Fu, Jing Gu, Jian Zhou +3cs.CV2026-10-02
#179Post-Training Frontier Text-to-Image Models by Composing Preference and Rubric RewardsYuanhao Ban, I-Hung Hsu, Anastasios Angelopoulos +3cs.CV2026-10-02
#180Rethinking Fixed Temporal Grids: Frequency-Disentangled Motion GenerationYunjiao Zhou, Junlang Qian, Gen Li +3cs.CV2026-10-02
#181RYOPO: Bringing End-to-End Category-Level Object Pose Estimation into Real TimeHakjin Lee, Junghoon Seo, Jaehoon Simcs.CV2026-10-02
#182OmniAct3D: Leveraging Foundation Geometry and Evidence-Grounded Reasoning for Panoramic 3D DetectionRuntong Wu, Fei Teng, Di Wen +3cs.CV2026-10-02
#183ReSCUE: Re-translation with Sentence Commitment for Unsegmented Long-Form Simultaneous Sign Language TranslationSihan Ren, Gaozheng Li, Yuanshang Quan +5cs.CV2026-10-02
#184CrowdOcc: Monocular Semantic Scene Completion for Quadruped Robots in Crowded Indoor EnvironmentsFeiyang Chen, Jincheng Hu, Yiduo Chen +5cs.CV2026-10-02
#185Parasitic Co-Denoising: Unlocking 3D Human Motion Generation in a Frozen Video Diffusion ModelYunjiao Zhou, Junlang Qian, Lihua Xie +1cs.CV2026-10-02
#186BeeWhere: Segmenting Bumble Bee Colonies to Quantify Behavioral EffectsRoberta Hunt, August Easton-Calabria, James Crallcs.CV2026-10-02
#187Where to Look Is Not How to Fix: Pre-Denoising Diagnostics and Modality-Dependent Control in Diffusion CompositionFangzheng Wu, Brian Summacs.CV2026-10-02
#188NegT2IBench: When Negation Changes the Picture. A Polarity Benchmark for Text-to-Image ModelsOmar Elfatairy, Maria A. Bravo, Jessica Bader +1cs.CV2026-10-02
#189Beyond Single Videos: Benchmarking and Active Evidence Seeking for E-Commerce Cross-Video ReasoningJinghan Zhao, Yiman Hu, Liang Wu +2cs.CV2026-10-02
#190A Benchmark for Spatially Grounded Gesture GenerationAnna Deichler, Rishabh Dabral, Fethiye Irmak Dogan +2cs.CV2026-10-02
#191In-Distribution Forcing for Long Video Generation at Test TimeJeongwoo Shin, Youngyoon Choi, Sangwoo Jo +5cs.CV2026-10-02
#192Foresight: planning future perception in streaming VLMs without retrainingAshok Prasad Neupane, Dipan Bartaula, Ankit Belbase +5cs.CV2026-10-02
#193Behavior Pack Optimization for Video MLLM Post-TrainingZhaolu Kang, Shiyu Liu, Tailong Luo +12cs.CV2026-10-02
#194CalCErt: Bin-wise Certification of Confidence Calibration in Medical Image ClassificationLeo Fillioux, Stergios Christodoulidis, Stergios Christodoulidis +2cs.CV2026-10-02
#195Does Physics Live in the Activations? Localizing Physical Quantities in Video Diffusion ModelsJonas Kneifl, Jakub Skalski, Bartłomiej Twardowski +1cs.CV2026-10-02
#196Geometry-Aligned Semantic Matching for Cross-Modal Planar Image RegistrationZhiwei Wang, Defeng He, Yuxing Li +2cs.CV2026-10-02
#197PocketSplat: Mobile Gaussian Reconstruction via World-Space Latent AllocatioWenzhi Guo, Xianda Chen, Dongxuan Chen +2cs.CV2026-10-02
#198Bridging Research and Practice: A Systematic Evaluation of Generalist and Dermatology-Specific Models in Clinical Skin Lesion ClassificationEmanoel dos Santos, Kelvin Cunha, Rodrigo Mota +8cs.CV2026-10-02
#199Contextual Flow Matching: Adaptive Step Selection in Flow Models for Efficient Visual GenerationDivya Jyoti Bajpai, Arun Verma, Manjesh Kumar Hanawalcs.CV2026-10-02
#200VisionMX: Unlocking Microscaling Post-Training Quantization for Vision ModelsElad Dror Cohen, Ofir Gordon, Lior Dikstein +2cs.CV2026-10-02
#201VDOT++: Unified Few-Step Video Generation via Unbalanced Optimal Transport DistillationYutong Wang, Xingtong Ge, Enhuai Liu +6cs.CV2026-10-02
#202Uncertainty as a Proxy for Semantic Correctness in Diffusion-Based Medical Image SynthesisYuxuan Ou, Konstantinos Kamnitsas, OxAAA Study +3cs.CV2026-10-02
#203EmbPASS: Towards Cross-Embodiment Open Panoramic SegmentationPujun Guo, Yuanfan Zheng, Fei Teng +5cs.CV2026-10-02
#204COSMI: COmpositional Synthesis of Multi-object InteractionsDaniel Eskandar, Ilya A. Petrov, Gerard Pons-Mollcs.CV2026-10-02
#205Consecutive Posterior Fusion for Diffusive Recovery of Unobservable Image StructuresElena Morotti, Davide Evangelista, Elena Loli Piccolominics.CV2026-10-02
#206Moving Forward with Video Saliency: A New Dataset and Benchmark where Motion MattersSusmit Agrawal, Rebecca Wanner, Juliane Verwiebe +3cs.CV2026-10-02
#207T3lescope: Arbitrary-Resolution High-Fidelity Generative Surface Reconstruction from ImagesAtsuhiro Noguchi, Tianhan Xu, Yiming Liang +5cs.CV2026-10-02
#208A Fully Automatic Pipeline for 3D Dendrite Instance Segmentation in SBF-SEMZewen Zhuo, Ilya Belevich, Eija Jokitalo +2cs.CV2026-10-02
#209LAS-CLIP: A Lightweight Adapter Steering Approach for CLIP's Visual EncoderAnh-Khoa Dinh-Duc, Duc-Tai Dinh, Tam V. Nguyen +1cs.CV2026-10-02
#210EVEWorld: Physical Evolution Supervision for Embodied World ModelsKaiqi Wang, Songxin Zhang, Zejian Xie +7cs.CV2026-10-02
#211Interpretable Deepfake Detection in Videos via Explicit Forensic Features and Temporal ModelingChahira Benhama, Mohand Saïd Allili, Assia Hamadenecs.CV2026-10-02
#212From Patching to Pruning Visual Computation in Vision Language ModelsRahul Chowdhury, Timothy A Rupprecht, Xuan Shen +3cs.CV2026-10-02
#213Native Action-Prior Learning from Videos for World Action ModelsZhaochong An, Fei Zhang, Menglin Jia +10cs.CV2026-10-02
#214Beyond Entropy: Self-Diagnostic Multi-Role Token Optimization for Video ReasoningYudong Han, Yong Wang, Zaiquan Yang +4cs.CV2026-10-02
#215ForestQuery: Boundary-Aware and Spatially Anchored Query Learning for Unified Forest Point Cloud SegmentationZhihao Zhan, Le Tao, Yifei Tian +2cs.CV2026-10-02
#216OuroReward: Sequential Reward Scheduling for Reinforcement Learning in Text-to-3D GenerationBingyang Cui, Yujie Zhang, Yiling Xu +1cs.CV2026-10-02
#217Depth Hypothesis Guided Iterative Refinement for Event-Image Monocular Depth EstimationDaikun Liu, Teng Wang, Changyin Suncs.CV2026-10-02
#218ChromaGS: Text-Driven Semantic Editing of 4D Gaussian AvatarsAntonio Canela, Jordi Sànchez-Rieracs.CV2026-10-02
#219Corrupted but Correct: Why Vision-Language Models Lie to Themselves InternallyArun Josephraj Arokiaraj, Zekun Wu, Adriano Koshiyamacs.CV2026-10-02
#220Preserving Anatomical Continuity: Three-Stage Pipeline for Colon Segmentation in 3D Abdominal CT ScansDeshan Kalupahana, Sonit Singh, Praveen Ravindran +1cs.CV2026-10-02
#221A Vision-Language Model (VLM)-based Pipeline for End-to-End Procedural Modeling of Field-Grown Maize from Point CloudsMozhgan Hadadi, Talukder Z. Jubery, Adarsh Krishnamurthy +1cs.CV2026-10-02
#222UniDynamics: Event-RGB Fusion for Unified Future 4D Dynamic Scene GenerationDaikun Liu, Xin Zhan, Teng Wang +2cs.CV2026-10-02
#223Fed-ADApt: Federated Anytime Depth Adaptation for Resource-Aware Medical Image SegmentationAbhijeet Parida, Zhifan Jiang, Pooneh Roshanitabrizi +6cs.CV2026-10-02
#224Weave Forcing: Compositional Memory Routing for Interactive Long Video GenerationZiyi Wang, Junchi Yao, Heqian Qiu +5cs.CV2026-10-02
#225ProgressNet: Sketching and Prompting with a Frozen Text-to-Image ModelArkaprabha Basu, Chaitat Utintu, Yi-Zhe Songcs.CV2026-10-02
#226Feedforward Novel View Synthesis for Heterogeneous CamerasMeng Wei, Cheng Zhang, Boying Li +4cs.CV2026-10-02
#227DuoMatching: Joint-Marginal Distribution Matching for Few-Step Video GenerationJiahao Zhan, Yan Wang, Yongrui Ma +5cs.CV2026-10-02
#228Rethinking What to Cache in Few-Step Diffusion Transformers: Solver-Aware Target SelectionShuo Yang, Lihao Fang, Yi Zhang +5cs.CV2026-10-02
#229ManifoldSplat: Language-Guided Semantic Shape Editing of 3D Gaussian Head AvatarsAntonio Canela, Jordi Sànchez-Rieracs.CV2026-10-02
#230DEPICT: Scoring Text-to-Image Alignment by Answer AgreementVasco Ramos, Sandra Godinho Silva, Joao Magalhaes +2cs.CV2026-10-02
#231World Embedding BenchmarkYiqi Liu, Ruifeng Yuan, Yang Wang +7cs.CV2026-10-02
#232LoGo: Local-Global Rewards for Consistent Long-Horizon Video GenerationZiqi Ma, Shreya Sharma, Mohamed El Banani +8cs.CV2026-10-02
#233On-Board Anomaly Detection for Efficient Marine Environmental MonitoringThomas Goudemant, Clotilde Szywala, Benjamin Francesconi +4cs.CV2026-10-02
#234ProAR: Learning Prospective Reasoning with Autoregressive Video ModelsLinghui Shen, Tinghui Zhu, Sheng Zhang +1cs.CV2026-10-02
#235SigLIP2 for aerial fire risk classificationYunus Serhat Bıçakçıcs.CV2026-10-02
#236FlowHMR: Physically Plausible Motion Capture from VideoZhanke Wang, Chengfeng Zhao, Qing Shuai +8cs.CV2026-10-02
#237Decoding the Functional Roles of Register and High-Norm Patch Tokens in Vision TransformersNeel Varma, Andrew Rufail, Dipika Khullar +1cs.CV2026-10-02
#2384DCodeBench: Benchmarking Agents on Inverse Graphics of Dynamic ScenesRuihong Shen, Žiga Kovačič, Peter Kulits +6cs.CV2026-10-02
#239MoSE3: Learning World-Space SE(3) at Every PixelJiahuan Cheng, Zhiyi Li, Tian Xia +3cs.CV2026-10-02
#240Less Decoder is More Encoder: Geometric Representation Learning from Novel View SynthesisKeerthi Kaashyap, Dennis Anthony, Akshay Krishnan +5cs.CV2026-10-02
#241TSGuard: A Real-Time Framework for Detecting and Imputing Missing Data in Streaming Time SeriesImane Hocine, Asma Abboura, Soror Sahri +3cs.DB2026-10-02
#242Lightweight and Resource-Efficient Perception for Robotic Guide DogsJinse Kwon, Yoojin Lim, Choonghan Lee +3cs.DC2026-10-02
#243Budgeted-GS: Real-Time Large-Scale Gaussian Splatting via Factoring LODHaipeng Wangcs.GR2026-10-02
#244The Shape of Speech: A Geometric Measure of Coarticulation for Speech-Driven 3D Facial AnimationDanzel Serrano, Przemyslaw Musialskics.GR2026-10-02
#245Normal-Form Correlation in Markov GamesIoannis Anagnostides, Constantinos Daskalakis, Gabriele Farina +3cs.GT2026-10-02
#246Asterism: Exploring and Synthesizing Scattered Observations into Literature-Grounded Hypotheses and TheoriesJoseph Chee Chang, Michael D'Arcy, Amy X. Zhang +15cs.HC2026-10-02
#247Characterizing the Performance Gap in Human Activity Recognition for Older AdultsHossein Khayami, Sungjin Hwang, Eshed Ohn-Bar +4cs.HC2026-10-02
#248Learning Query Encoders Can Be Hard Even When Vector Retrieval Is Geometrically EasyAnders Wikum, Nina Mishra, Amin Saberi +1cs.IR2026-10-02
#249Benchmarking Literature Retrieval for a Model Organism: A Dictyostelium Case StudyYun Wang, Gad Shaulsky, Tomaž Curk +1cs.IR2026-10-02
#250Seer: Maximum Likelihood Regression for Learning-Speed CurvesCarl Myers Kadiecs.LG2026-10-02
#251Scale-Recursive Rectified Flows for Few-Step Precipitation EnsemblesShunya Nagashima, Takumi Bannaics.LG2026-10-02
#252What Is Lost in Post-Training? Default Collapse and the Loss of In-Context Steerability Across Diverse PerspectivesJessica Dierking, Itai Shapira, Niclas Boehmercs.LG2026-10-02
#253Quantifying the Value of Constructive Induction, Knowledge, and Noise Filtering on Inductive LearningCarl M. Kadiecs.LG2026-10-02
#254Online Verification of Language Model Responses Under Cost ConstraintsErfan Hajihashemi, Yanning Shencs.LG2026-10-02
#255Context-Tower Conversion Preserves Generation While Freezing Retains Knowledge: Low-Budget AR-to-Diffusion Conversion of MoE LLMsWentao Lu, Jesse Clark, Tianyu Zhucs.LG2026-10-02
#256Distributed Learning with Selective State Space Models: Architecture-Aware Convergence AnalysisAdam Piaseczny, Md Kamran Chowdhury Shisher, Shiqiang Wang +1cs.LG2026-10-02
#257AIGS: Adaptive Incremental Gating System for Online Representation Learning in Non-Stationary Data StreamsSiRui He, Kai Liang Lew, Chui Zi Ong +1cs.LG2026-10-02
#258Mind the Refinement Gap: When Safe High-Level Robot Plans Produce Unsafe ExecutionsStabak Das, Priyesh Ranjan, Xiangfang Li +1cs.LG2026-10-02
#259LEAP: Learning Efficient Action Proposals For LLM AgentsZhen Xu, Qizheng Zhang, Gerry Wan +2cs.LG2026-10-02
#260RAOA: Alternating-Operator Neural Computation with Programmable Radio PropagationToshiaki Koike-Akinocs.LG2026-10-02
#261Test-time Calibration Learning for Large Language Model ReasoningZizhuo Zhang, Xiong Peng, Jingwei Sun +4cs.LG2026-10-02
#262Learning from Evolving Errors: Adaptive Iterative Repair for On-Policy DistillationRui Li, Liyang He, Zheng Zhang +3cs.LG2026-10-02
#263Conditional Capacity and Routing in Mixture-of-Experts Particle TransformersKaushik Pendiyala, Haris Zia, Trevin Lee +8cs.LG2026-10-02
#264MuonIO: Principled Norm-Aware Descent for Embedding Tables and Language Model HeadsLinkai Ma, Xinyu Luo, Mengbo Wang +3cs.LG2026-10-02
#265Differential Privacy of Gradient Descent on Perturbed ObjectivesAustin Watkins, Raman Aroracs.LG2026-10-02
#266Structural-Functional Brain Connectivity Generation via Multimodal Hypergraph-based Flow MatchingChyong Yi Poh, Hwa Hui Tew, Junn Yong Loo +4cs.LG2026-10-02
#267Bellman Error Minimization Via Linear Programming NormalizationHaining Yucs.LG2026-10-02
#268Inner Momentum for Differentially Private MuonBishnu Bhusal, Minh Vu, Ben Southworth +3cs.LG2026-10-02
#269Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality GapsJiaxin Zhang, Xiangyu Peng, Qinglin Chen +3cs.LG2026-10-02
#270Jumping up and down: Denoiser diffusion models for discrete ordinal dataYair Shenfeld, Ricardo Baptista, Stefano Peluchettics.LG2026-10-02
#271A Two-Stage Cascade for Near-Real-Time Forest Anomaly Detection from Sentinel-1 SAR Time SeriesPann Thinzar Seint, Subas Chhatkuli, Bryan Atwoodcs.LG2026-10-02
#272A Controlled Audit of Personal AI Memory for Rating PredictionShivam Guptacs.LG2026-10-02
#273Exact Memory-Time Optimization for Prefix-Cached Language Model ServingShivam Guptacs.LG2026-10-02
#274No-Free-Graph: Learning When Multimodal Data Should Be GraphifiedZekai Chen, Kai Hu, YuXin Zeng +6cs.LG2026-10-02
#275Nearly Optimal Fixed-Confidence Best-Arm Identification with 1-Bit FeedbackKhang Luong, Dinh Thai Son, Hoang Ta +2cs.LG2026-10-02
#276LatticeSMC: Where to Spend Inference-Time Compute in Chunked Sequence GeneratorsXuanchen Wang, Heng Wang, Weidong Caics.LG2026-10-02
#277Controlling Polar Exposure to Delay Memorization in Diffusion ModelsXuanchen Wang, Heng Wang, Weidong Caics.LG2026-10-02
#278OPD Before RL: Warm-Starting Rubric-Based RL with On-Policy DistillationXinpeng Wang, Wei Shi, Yu-Chia Chen +3cs.LG2026-10-02
#279Efficient Memory Crystallization for Graph Learning under Non-Stationary Distribution ShiftsYue Hou, Ruomei Liu, Yingke Su +2cs.LG2026-10-02
#280Muon Learns Facts Better: Understanding the Role of Spectral OrthogonalizationXuheng Li, Qiwei Di, Yuan Cao +1cs.LG2026-10-02
#281Gated Slot Attention-2: Two-Sided Associative Memory Correction in Linear AttentionRuijie Li, Shengnan Ding, Weimin Zhang +6cs.LG2026-10-02
#282Adaptive Spectral-Koopman Dynamics Modeling for Temporal Domain GeneralizationTengxue Zhang, Yu Ke, Yang Shu +4cs.LG2026-10-02
#283All Work And No Play Makes Jack a Dull Boy: Understanding and Preventing Catastrophic Strategy Collapse in RLVRQiyuan Huang, Tianshi Xu, Meng Lics.LG2026-10-02
#284To Explore The Strange New World Beyond Data Distribution: System Behavior, Causality Tax, and Non-causal Base ModelXianzhi Zeng, Jiangneng Li, Gao Congcs.LG2026-10-02
#285Understanding Enrichment in Reinforcement LearningJinwoo Kim, Shraddha Barkecs.LG2026-10-02
#286Counterfactual Action Evaluation, Observation Bottlenecks, and Representation Geometry in Joint-Embedding Predictive World ModelsArjun Subramaniancs.LG2026-10-02
#287NeuroLens: Learning Latent Embeddings of Neural Semantics from Chronic RecordingsHanrui Lyu, Baiyuan Chen, Tianshu Tan +8cs.LG2026-10-02
#288On Unlearning for Time-series ForecastingZeyu Shi, Yanhui Luo, Ziming Hong +4cs.LG2026-10-02
#289DIVINE: Simple Cross-Market Stock Pretraining via Diverse Indicator ReconstructionKuan-Yu Chen, Shu-Cheng Zheng, Yu-Chen Den +2cs.LG2026-10-02
#290Distributionally Robust Survival Models under Subpopulation Shift and Outlier ContaminationSeonghwi Kim, Sung Ho Jo, Minwoo Chaecs.LG2026-10-02
#291Peer Effects in Signed Networks: Separating Influence Through Positive and Negative TiesXiaojing Du, Jiuyong Li, Lin Liu +3cs.LG2026-10-02
#292Toward Omni Multimodal Graph Foundation Model: A Topology-Driven Binding ApproachXunkai Li, Chenxi Wan, Yinlin Zhu +4cs.LG2026-10-02
#293DyRA: Dynamic Residual Approximation for Efficient Matrix Multiplication in DNNsDaewon Chae, Hyunwon Chung, Changwoo Lee +1cs.LG2026-10-02
#294When Can We Trust the Matching Principle? Robust Deployment Geometry Under Finite-Sample and Model UncertaintyVishal Rajputcs.LG2026-10-02
#295Tangent Schrödinger Bridge Matching: Learning Stochastic Transport with Mechanistic SensitivitiesJowaria Khan, Elizabeth Bondi-Kellycs.LG2026-10-02
#296Do ResNets Route? Sparse Interaction Experts in Residual NetworksLiang Yan, Siying Chen, Kaijie Chen +3cs.LG2026-10-02
#297Constraint-Aware TrainingJinwoo Kimcs.LG2026-10-02
#298Probe the Harness: Setup Checks for Stale-Data RL Comparisons in Language ModelsTaiheng Pancs.LG2026-10-02
#299Dynamic Expert Pruning for Multi-Agent SystemsJabin Koo, Soheil Abbasloo, Sungjae Lee +1cs.LG2026-10-02
#300SlimKV: Joint Token-Feature KV Cache Compression with Reconstruction-Free Beacon AttentionZihan Teng, Jiayu Zhao, Wentao Ren +4cs.LG2026-10-02
#301Hyperparameter selection for equation learning with biologically-informed neural networksWilliam Lavery, Jodie A. Cochrane, John T. Nardini +1cs.LG2026-10-02
#302Understanding Trajectory Heterogeneity in Federated World Model LearningYipan Wei, Zhaokun Yan, Ziming Hong +2cs.LG2026-10-02
#303Dirac-Interconnected Neural Elements: Discovering Modularity in Physical Systems Without ReductionReiho Li, Razmik Arman Khosrovian, Takaharu Yaguchi +2cs.LG2026-10-02
#304Differentiable Koopman Operator for Contrastive Learning on Dynamic GraphsMd Abrar Jahin, Taufikur Rahman Fuad, Md Rizwan Parvezcs.LG2026-10-02
#305Sentry: Learning to Recover from LLM Agent Failures at Test TimeChangxiu Ji, Amy Lu, Qizheng Zhang +1cs.LG2026-10-02
#306Temporal Geometry of Deep Networks: Hyperbolic Representations of Training Dynamics for Intrinsic ExplainabilityAmbarish Moharilcs.LG2026-10-02
#307Neural Data Needs Semantic Tokenization: Behavioral Events as Boundaries of Session-Transferable TokensSangyoon Bae, Jiook Chacs.LG2026-10-02
#308AvoKV-E: Payload-Aware KV Cache Eviction for Long ReasoningHan Yu, Wenhui Zhu, Xiwen Chen +9cs.LG2026-10-02
#309Signal Simplification Is Not Predictive Simplification: Diagnosing Residual Neural Forecasting in Short-Horizon VolatilityBingqi Lian, Linfeng Cheng, Mei Lu +1cs.LG2026-10-02
#310Tailoring the Quantization Space for 1-Bit KV Cache CompressionMinsoo Cheong, Donghyun Son, Sungjoo Yoocs.LG2026-10-02
#311Adaptive Second-Order Solvers for Fast Stochastic Diffusion SamplingElla Kemperman, Luca Ambrogionics.LG2026-10-02
#312Balancing Multimodal Learning via Functional ProgressZhongjing Gu, Fengqiang Wan, Yiming Cui +2cs.LG2026-10-02
#313WebFovea: When the Model Is Right but the Click Is Wrong -- Reliable Round Trips for Vision-Based Web Agents on Live WebsitesJiangang Hancs.LG2026-10-02
#314RIPPLE in Still Water: Zero-Shot Clustering in Federated Learning with Wavelet Scattering TransformAlessandro Licciardics.LG2026-10-02
#315When Does Synthetic Relational Data Teach Models to Use Relations? Tracing Predictive Structure from Pretraining Data to Model BehaviorShivam Dubey, Mohamed Bouadi, Nassim Bouarour +3cs.LG2026-10-02
#316Learning Transferable Policies from Action-free Time Series Through Dynamical EmbeddingsNiklas Emonds, Georgia Koppecs.LG2026-10-02
#317Learn Feasibility Once, Optimize All Objectives: Derivative-Free Diffusion Models for Chance-Constrained ProgrammingZiwen Liu, Yan Liu, Congying Han +3cs.LG2026-10-02
#318Smart Sensing for Safer Bridges: From Sensor Signals to AI-Driven Anomaly DetectionRahul Jaiswal, Joakim Hellum, Halvor Heibergcs.LG2026-10-02
#319Light Entropic Optimal Transport on Riemannian ManifoldsXavier Aramayo-Carrasco, Petr Mokrov, Alexander Korotincs.LG2026-10-02
#320Zephon: Elastic Determinism for Online, Stateful Foundation Model Data Loading PipelinesMaximilian Böther, Josh Wills, Ties Robroek +14cs.LG2026-10-02
#321ULTRADISCOVERY: Abductive Exploration in an Interconnected, Epistemically Open UniverseWeihan Li, Tianshi Zheng, Yangqiu Song +2cs.LG2026-10-02
#322LS-AR: Future-Predictive Latent Steering in Autoregressive LLMsAnubha Gupta, Eduardo Pignatellics.LG2026-10-02
#323Exploring the Trade-Off Between Structured Pruning and Fault Tolerance in Deep Neural Networks for Space ApplicationsToon Vinck, Naïn Jonckers, Jaro De Roose +2cs.LG2026-10-02
#324How to Find and Reuse Policies for Continuous Adaptation in Lifelong Reinforcement LearningSaptarshi Nath, Inish M. D'Souza, Antonio Carta +2cs.LG2026-10-02
#325Coverage You Can Steer: Online Conformal Calibration for RL-Driven Hardware-Aware NASPedro Brandimarte, Nerea Aranjuelo, Marcos Nieto +1cs.LG2026-10-02
#326Page-EntroKV: Hardware-Aligned, Entropy-Weighted KV-Cache Eviction under Grouped-Query AttentionInbasekaran Scs.LG2026-10-02
#327Sample complexity of variance-reduced policy gradient: weaker assumptions and lower boundsGabor Paczolay, Matteo Papini, Alberto Maria Metelli +2cs.LG2026-10-02
#328Predicting and Repairing Merge Collapse in Large Language ModelsJungseob Lee, Seungyoon Lee, Sugyeong Eo +3cs.LG2026-10-02
#329HyperFuse: Fast Self-Supervised Node Embeddings for Attributed HypergraphsMegha P, Harshit Kumar, Srajan Agarwal +3cs.LG2026-10-02
#330Kernel Singular Value Decomposition with Extension to Multiple Data SourcesXinjie Zeng, Qinghua Tao, Johan Suykenscs.LG2026-10-02
#331AdaStep: Adaptive Step Credit Weighting for Agentic Reinforcement LearningXin Wang, Wenhao Wu, Menghao Zhang +3cs.LG2026-10-02
#332The Neuro-Physical Inverter: A Modular Framework for Magnetotelluric Inversion Coupling Ensemble Conditioning with Residual LearningJae Deok Kim, Sai Ravela, Rob. L. Evanscs.LG2026-10-02
#333D2K-Bench: Can LLM Agents Turn Expert Designs into Efficient GPU Kernels?Daifeng Li, Huiqiang Jiang, Chengruidong Zhang +6cs.LG2026-10-02
#334Cross-cohort TB classification using clinical data gathered in Uganda and South AfricaJoshua M. Jansen van Vüren, Devendra S. Parihar, Daphne Naidoo +8cs.LG2026-10-02
#335Mapping and Advancing the Scalability-Accuracy Frontier of Nonlinear Causal DiscoveryHendrik Suhr, Sascha Xu, Jilles Vreekencs.LG2026-10-02
#336PaMIR: Open Benchmark of Public Credit-Default DatasetsMikhail Liashkov, Ilyas Varshavskiy, Shuhratjon Khalilbekov +2cs.LG2026-10-02
#337SPEAR: A Spectral-Disentangled MoE Neural Operator with Knowledge-Guided Expert Aggregation for Large-Scale PDE PretrainingDengdi Sun, Xiaoya Zhou, Xiao Wang +3cs.LG2026-10-02
#338Architecture-Dependent Fusion Pathways in MLLMsHebao Zhu, Dongxia Wucs.LG2026-10-02
#339S$^{2}$-PINN: Stochastic Separable Physics-Informed Neural NetworksZhendong Li, Akwum Onwuntacs.LG2026-10-02
#340Training-Loss Guarantees for Muon with Finite-Step Newton--Schulz OrthogonalizationAmartya Roy, Souvik Chakrabortycs.LG2026-10-02
#341Cordial Learning: Distributed Training with Correlated DataSarah Shitrit, Ilai Bistritzcs.LG2026-10-02
#342Follow the Winners: Conservative Policy Improvement with the Cross-Entropy Method for Critic-Free RFTJoery Ariën de Vries, Neil David Lawrence, Zhenwen Daics.LG2026-10-02
#343SCAD: Structured Credit Assignment and Distillation for Long-Horizon AgentsShangyang Wu, Shuai Zhao, Ziyue Zhu +3cs.LG2026-10-02
#344Operator-informed initialization for Fourier features physics-informed neural networksJuan Molina, Paris Perdikaris, Mircea Petrache +2cs.LG2026-10-02
#345Bidirectional Voronoi-biased Exploration Curriculum for Reinforcement LearningJuri Pfammatter, Kaixian Qu, Clemens Schwarke +2cs.LG2026-10-02
#346A Unified Framework for Bayesian Data Assimilation with Generative Models and Observation InterpolantsNikolaj T. Mücke, Benjamin Sandersecs.LG2026-10-02
#34716-bit Precision of Convolutional Neural Networks on Microcontroller Units for 8-bit CostsRui Liu, Benjamin Paaßencs.LG2026-10-02
#348AIBL: Augmented Instance-Based Learning with Structured Memory and Neural EmbeddingsRadha Poovendran, Andrea Stocco, Linda Bushnellcs.LG2026-10-02
#349Rethinking Epistemic Uncertainty in Node Classification through Information GrowthEmma Meneghini, Francesco Ferrini, Bruno Lepri +2cs.LG2026-10-02
#350Deep Bayesian REFoCUSSimon Penninga, Ruud van Slouncs.LG2026-10-02
#351OptiSelect: How does the Optimizer Shape Data Curriculum?Simin Fan, Alireza Abdollahpoorrostam, Martin Jaggics.LG2026-10-02
#352Causal Representation Learning with Instantaneous and Lagged Relations via NonstationarityTatsuya Yamada, Hiroshi Morioka, Yoshinobu Kawaharacs.LG2026-10-02
#353Measure Less, Know More: Self-Supervised Test-Time Feature AcquisitionEeshaan Jain, Linus Bleistein, Bart Deplancke +1cs.LG2026-10-02
#354Beyond Random Splits: Evaluating Drug-Target Affinity Models Under Chemically and Biologically Motivated Distribution Shifts CopyMinjae Chung, Clara Li, Malar Paavai Muthukumaran +8cs.LG2026-10-02
#355Single or Multiple Policies for Phase-Structured Reinforcement Learning?Guilhem Loussouarn, Nancy Nayak, Kin K. Leungcs.LG2026-10-02
#356Metropolis-Hastings Dominates Importance Resampling for Policy CompositionAlexey Kurennoy, Ramil Yarullin, Fergal Reidcs.LG2026-10-02
#357Dual-Context Analog Retrieval for Time Series ForecastingJung Min Choi, Ngoc Son Le, Ibram Abdelmalak +2cs.LG2026-10-02
#358Most-Recent Anchoring with Recurrent Ordering for Time Series ForecastingJung Min Choi, Ngoc Son Le, Ibram Abdelmalak +2cs.LG2026-10-02
#359Below what training size do deep tabular generators stop beating trivial baselines? A preregistered benchmark on a size ladder of clinical and standard datasetsShivam Shrivastavacs.LG2026-10-02
#360Certified Mechanistic Edits: Behavioral Guarantees for Skill Removal and PreservationMd Sazid Uddin, Md. Khairul Alam Mazumder, M. F. Mridhacs.LG2026-10-02
#361Getting Your Guidance Weights Right in diffusion and flow-matching posterior samplingLiam Moroy, Jean-François Giovannelli, Yoann Altmann +3cs.LG2026-10-02
#362An Automated and Reproducible Workflow for Crack Identification and Damage Assessment of Fusion MaterialsRinkle Juneja, Viktor Reshniak, Richard K. Archibald +4cs.LG2026-10-02
#363Beyond Trained Models: Compiling GNNs for a Sound Explainer BenchmarkSteve Azzolin, Francesco Paolo Nerini, Stefano Teso +4cs.LG2026-10-02
#364Divergence controls entropy in distillationNicolas Zucchet, Scott W. Lindermancs.LG2026-10-02
#365ZeroMAG: Zero-Shot Multimodal Adapter Generation for Plug-and-Play EEG Foundation ModelsYubo Wang, Jingying Ma, Xinliang Zhou +8cs.LG2026-10-02
#366Objects Without Morphisms: What LLMs for Mathematics Do Not RepresentYanli Wang, Suijin Wang, Xiaopeng Yuan +1cs.LG2026-10-02
#367Get a GRIP, this will be a long TRIP: A Quantifiable Long-Range Framework for Verifying Over-squashingFerran Hernandez Caralt, Simon Heilig, Adrián Bazaga +3cs.LG2026-10-02
#368Cephalonauts One: A deep fMRI dataset for decoding naturalistic speech in the human brainAntoine Collas, Louis Jalouzot, Géraud Ilinca +11cs.LG2026-10-02
#369A Path Integral Surrogate for Multi-Step Gradient Inversion in Federated LearningAgnivo Ghosh, Saumik Bhattacharyacs.LG2026-10-02
#370Mastering Atari 2600 Games with Discovered OptionsErik M. Lintunen, Marlos C. Machadocs.LG2026-10-02
#371UniIntervene++: An Adaptive Intervention Agent for Efficient Real-World Reinforcement LearningYudong Lin, Haoyuan Deng, Zhuoxuan Yuan +3cs.LG2026-10-02
#372Broken scale symmetries in undercomplete linear autoencodersFarhad Pashakhanloo, Jacob A. Zavatone-Vethcs.LG2026-10-02
#373IDRF: Inverse-Distilled Reward Fine-tuning of Masked Discrete Diffusion ModelsVladislav Gromadskii, David Li, Samson Gourevitch +4cs.LG2026-10-02
#374On the Convergence of Success Conditioning for Policy OptimizationMatthew Brun, Xu Andy Suncs.LG2026-10-02
#375When May a Bandit Leave Its Anchor? E-Process-Authorized Thompson Sampling under Non-stationarityMayand Gulati, Kerong Wang, WeiChen Aucs.LG2026-10-02
#376Forecasting from Counterfactual Simulator Rollouts: A Sim2Real EvaluationAngel Wang, Dominique Perrault-Joncas, Alvaro Maggiar +2cs.LG2026-10-02
#377Pivot-SD: Efficient Self-Distillation for Masked Diffusion Language ModelsSeo Hyun Kim, Sunwoo Hong, Younwoo Choi +3cs.LG2026-10-02
#378Planning to LearnIan Osbandcs.LG2026-10-02
#379Simulation-Free Learning of Population Dynamics with Wasserstein Lagrangian ResidualsFedor Sergeev, Markus Heinonen, Daniel Waxman +4cs.LG2026-10-02
#380LESSER: Post-Training Data Selection with Output-Layer GradientsLyuxin David Zhang, Eric Wong, Surbhi Goel +1cs.LG2026-10-02
#381RNADyn: A Benchmark for Generating and Understanding RNA DynamicsYiming Huang, Lennart Bastian, Hanqun Cao +2cs.LG2026-10-02
#382What Should World Models Forget? Stratified Retention for Continual AdaptationNishit Anand, Ramani Duraiswami, Dinesh Manochacs.LG2026-10-02
#383Turnover-Orthogonal Credit Assignment for Open-Team Multi-Agent Reinforcement LearningAmit Thakur, Mukesh Singhalcs.MA2026-10-02
#384From Expression to Reaction: Role-aware Visual Transfer and Stimulus-guided Reasoning for Interlocutor Emotion RecognitionWei Wang, Zhaowu Li, Jianjie Luo +3cs.MM2026-10-02
#385Evolving Hybrid Quantum-Classical Architectures for Image ClassificationDevroop Kar, Daniel Krutz, Travis Desellcs.NE2026-10-02
#386FrugalEvo: Towards Cost-Aware LLM-Guided Program EvolutionHui Chen, Xuan Qi, James Xu Zhao +5cs.NE2026-10-02
#387WAMpy: Efficient Synthesis of Prolog Programs in PythonDominik Magiera, Lukas Röhrig, Frank Jäkelcs.PL2026-10-02
#388GeoScaffold: Learning Compact Geometric Latents via Reconstruction for Efficient Vision-Language NavigationYixuan Jiang, Wentong Li, An Liu +5cs.RO2026-10-02
#389Localized Conformal Safety Monitoring with Vision-Language Models for Autonomous DrivingLuís Marques, Rong Fang, Disha Kamale +1cs.RO2026-10-02
#390FastOPD: On-Policy Distillation for Lightweight VLA DeploymentYoojin Oh, Jeongsol Kim, Yeonwoo Seo +7cs.RO2026-10-02
#391PointWAM: 3D World Action Modeling for Dexterous Robotic ManipulationChunghyun Park, Beomjun Kim, Seungcheol Park +5cs.RO2026-10-02
#392Permutation Robustness Is Not Enough: Action Collapse in Multi-Agent Transformer PoliciesAmit Thakur, Mukesh Singhalcs.RO2026-10-02
#393From Language Priors to Field Adaptation: Preference Learning for Traversability EstimationSimon Schwaiger, David Seyser, Alessandro Scherl +3cs.RO2026-10-02
#394Safe Streaming Flow Planning by Aligning Sampling Dynamics with Execution DynamicsSeunghwan Jang, Jeongyong Yang, Siddharth Ancha +1cs.RO2026-10-02
#395HexVIO: Towards All-Day Stereo-Inertial Tracking Through Commodity DSPsPatrick Wolf, Mateo de Mayo, Daniel Cremerscs.RO2026-10-02
#396Equivariant Visual-Tactile Diffusion Policy for Contact-Rich ManipulationLik Hang Kenny Wong, Yiyao Ma, Xiu-Shen Wei +5cs.RO2026-10-02
#397I2CD: Direct Image-to-Convex Decomposition for Simulation-Ready Collision GeometryQian Wang, Liam Merz Hoffmeister, Brian Scassellati +1cs.RO2026-10-02
#398MobiAgent: Dual-Loop Recursive Policy Self-Improvement for Long-Horizon Mobile ManipulationChenzhi Liu, Yue Zhang, Jiehong Lin +4cs.RO2026-10-02
#399Detect and Suppress: A Mechanistic Defense against Adversarial Patches in VLA ModelsYukiya Horiba, Koshiro Aoki, Shunsuke Yasuki +2cs.RO2026-10-02
#400XGenAct: Geometry-Enhanced World Action Models through Cross-Task GenerationTingting Du, Ziyao Wang, Guoheng Sun +1cs.RO2026-10-02
#401Autonomous Robotic Navigation for Endovascular Brain-Computer Interface AccessHarry Robertshaw, Weijie Qi, Nikola Fischer +3cs.RO2026-10-02
#402EyeRobot 2.0: Active Gaze for Precise Manipulation without Wrist CamerasKush Hari, Justin Kerr, Nidhya Shivakumar +7cs.RO2026-10-02
#403Learning Jazz Pianist Style with Cross-Attention ConditioningDrew Edwards, Akira Maezawa, Simon Dixoncs.SD2026-10-02
#404ParaGeo: Decomposing Paralinguistic Variation into a Shared Latent GeometryYuhan Liu, Yuxuan Ou, Ruoxi Su +2cs.SD2026-10-02
#405DriftTTS: Few-Step Text-to-Speech Without Distillation via Distribution-Matching DriftMohammad Nur Hossain Khan, Subrata Biswas, Bashima Islamcs.SD2026-10-02
#406Revisiting Input Time-frequency Representations in Multi-pitch Estimation for Vocal EnsemblesJunyoung Koh, Hao-Wen Dongcs.SD2026-10-02
#407WebUIProof: Benchmarking WebUI Code Generators with UI-Agent Execution HarnessYun-Yun Tsai, Yuning Mao, Shiqi Wang +2cs.SE2026-10-02
#408Self-Supervised Scaling of Terminal Environments for Scientific DomainsZhongzhi Li, Yucheng Shi, Zongxia Li +8cs.SE2026-10-02
#409Discriminating Fixture Coverage in Agent-Infrastructure Verification SuitesXin Xu, Siru Taocs.SE2026-10-02
#410GTDD: Generative Test-Driven Development for AI Coding Agents with Adversarial TestingMasahiro Katocs.SE2026-10-02
#411MintEval: Do LLMs Implement the Trading Strategy You Asked For? A Behavioural-Equivalence Benchmark for Natural-Language-to-Strategy CodeSiyu Wang, Yifan Wang, Yuecheng Hecs.SE2026-10-02
#412FASTDIAR: Frame-level speaker encoder for Streaming DiarizationNikita Torgashov, Okan Köpüklüeess.AS2026-10-02
#413One Photon, Many Worlds: Posteriors and Predictions with Single-Photon CamerasHaejoon Lee, Mohit Gupta, Vijayakumar Bhagavatula +1eess.IV2026-10-02
#414Wrong Organ, Right Physics: Transferring Echocardiography Pretraining to Lung Ultrasound for Tuberculosis ScreeningChristiaan M. Geldenhuys, Joshua M. Jansen van Vüren, Véronique Suttels +6eess.IV2026-10-02
#415A hybrid CNN-adjoint optimization framework for reconstruction of viscoelastic tissue properties in magnetic resonance elastographyAnwesa Dey, Johann Rudi, Elena Cherkaevmath.OC2026-10-02
#416Near-Optimal Convex Optimization with Lazy Second-Order OraclesXinliang Zhang, Lesi Chen, Chengchang Liu +1math.OC2026-10-02
#417Information Limits of Low-Rank Approximation CertificationKang Liu, Bohao Qumath.OC2026-10-02
#418From Mixing to Tearing: Graph Decomposition in Decentralized Optimization via Message PassingKuangyu Ding, Gesualdo Scutarimath.OC2026-10-02
#419S2S-JEPA: Predicting the Predictable at Subseasonal-to-Seasonal TimescalesChenyu Dong, Gianmarco Mengaldophysics.ao-ph2026-10-02
#420Equivariant Flow Matching for Electron Density PredictionChenxing Liang, Chengdong Wang, Yuchao Lin +2physics.chem-ph2026-10-02
#421Explainable Molecular Structure Inference from GC--MS with Diffusion Models and LLM RerankingChanglin Liu, Tianyu Yi, Chengchun Liu +2physics.chem-ph2026-10-02
#422Electronic Density versus Geometry for Machine-Learned Molecular Absorption SpectraSiddharth Dhanpal, Peter Elliott, Paolo Emilio Trevisanutto +2physics.chem-ph2026-10-02
#423Contrastive Neural Embeddings Reveal Individual Traits Beyond Conversational RoleHubert Huang, Michelle McCleod, Brendan Ames +1q-bio.NC2026-10-02
#424Multimodal reasoning for broadly neutralizing antibody discovery from label-free human B cell repertoires across virus familiesHantao Lou, Jianqing Zheng, Can Yue +21q-bio.QM2026-10-02
#425Mixture-of-Experts for Cryptocurrency Order Execution: Training Stability, Tail Risk, and Failure ModesAlexander Ardaiz, Varun Budati, Ali Habibniaq-fin.TR2026-10-02
#426When a Correct Reward Is Not Enough: Diagnosing and Guiding PPO in an Analytically Solved Broker-Trader GameSiu Tung Wong, Carlo Campajolaq-fin.TR2026-10-02
#427Where Quantum Fourier Sampling Stops Short: A Three-Gate Audit Protocol for Delay-PUF Security ModelsOwen Friedewald, Ali Shiri Sichani, Chi-Ren Shyuquant-ph2026-10-02
#428When Normalization Selects the Sign: Auditing Robustness Ablations in Quantum AttentionOwen Friedewald, Srikar Alla, Ali Shiri Sichani +1quant-ph2026-10-02
#429Landscape-Dependent Performance of Photonic Quantum Solvers in QUBO Feature Selection for Financial Risk DetectionNirvik Sahoo, Paul Robert Griffinquant-ph2026-10-02
#430Hamiltonian locality testing and certification do not achieve the Heisenberg limitFrancisco Escudero Gutiérrez, Junseo Lee, Sebastian Zurquant-ph2026-10-02
#431Generalization of Transformer-Based Neural Quantum States via In-Context LearningZhen Qin, Qing Qu, Alfred O. Heroquant-ph2026-10-02
#432Generalization Properties of Score-matching Diffusion Models for Intrinsically Low-dimensional DataSaptarshi Chakraborty, Quentin Berthet, Peter L. Bartlettstat.ML2026-10-02
#433Hold-Out Scoring for Efficient Gaussian DAG LearningDonguk Shin, Byeongguk Kang, Inseol Lee +1stat.ML2026-10-02
#434Invariance of Clustering Operations in Causal Effect IdentificationJani Nykänen, Otto Tabell, Santtu Tikka +1stat.ML2026-10-02
#435Predictively Oriented Gaussian Process PosteriorsCallum Lau, Jeremias Knoblauch, Louis Sharrockstat.ML2026-10-02
#436SDECast: Probabilistic Weather Forecasting in Continuous Time with Neural SDEsMaria Marchenko, Martin Andrae, Fredrik Lindsten +1stat.ML2026-10-02
#437DAWIS: Data Assimilation with Windowed Inverse Sampling via Multitask InterpolantsErik Wikingsson, Martin Andrae, Tomas Landelius +1stat.ML2026-10-02
#438Iterating Consistency Models: Stability, Error Bounds and Noise SchedulesAlessio Spagnoletti, Abdul-Lateef Haji-Ali, Andrés Almansa +3stat.ML2026-10-02
#439When Is Accuracy Evidence? A Unified Theory of Generalisation, Validation, and Information FusionJM Gorrizstat.ML2026-10-02
#440AREX: Affine-Residual Exponential Integrator for Few-Step Sampling in Flow MatchingShizheng Lin, Soon Hoe Lim, N. Benjamin Erichsonstat.ML2026-10-02
#441Amortized Structured Stochastic Variational Inference for Gaussian Process Latent Variable ModelsMaksym Tretiakov, Sarah Lucie Filipp, Vincent Fortuin +3stat.ML2026-10-02

latest · trends · arXiv announcement batches follow US Eastern weekdays