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

New Papers · 2026-10-20 575 submissions

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

#TitleAuthorsCatDate
1Solar System Surface Technosignatures: Searching for Signs of Artificial Design on Extraterrestrial TerrainAna Henrique, Sofia Sheikh, Benjamin Fieldsastro-ph.IM2026-10-20
2A Radiation-Hardened, Fault-Aware Quantized Neural Network That Self-HealsPeter Xiangyuan Ma, Joshua S. Bloomastro-ph.IM2026-10-20
3SIGNN++: Robust Graph Neural Star Identification on EarthJeongbin Sohn, Jina Lee, Max Yen +6astro-ph.IM2026-10-20
#4Learning the Geometry of Materials Space with Trained Neural Tangent KernelsDaniel Kaplan, Gabriel Kotliar, Anirvan M Senguptacond-mat.mtrl-sci2026-10-20
#5GBClaw: An agentic AI framework for atomistic grain boundary research and mechanistic discoveryYazhuo Liu, Kunqing Ding, Xiaoguo Gong +8cond-mat.mtrl-sci2026-10-20
#6KPHarness: Co-Evolving Knowledge and Probing for Long-Horizon Gaming HarnessesZhikang Chen, Yueqing Sun, Sen Cui +6cs.AI2026-10-20
#7Harness Self-Evolution for Long-Horizon Terminal AgentsRuhan Wang, Yucheng Shi, Zongxia Li +6cs.AI2026-10-20
#8Ask to Distill: Learning to Synthesize Data for On-Policy DistillationJiashuo Sun, Hao Zhang, Xueqiang Xu +9cs.AI2026-10-20
#9Recoverability and Verifier Strength: Two Measured Preconditions for Unattended Agent Self-ImprovementDe Wang, Peng Qics.AI2026-10-20
#10Runtime Control for AI Agents: Closing the Evaluation--Execution Gap in Operational WorkflowsJayesh Bhadane, Ramachandra Yerramsetti, Rajesh Gupta +1cs.AI2026-10-20
#11Securing Agentic Commerce Through Behavior-Aware Fraud Detection and Cybersecurity for Trusted AI-Agent Payment AuthorizationKayode L. Ogunsusics.AI2026-10-20
#12The More the Better? A Comparison of Single- and Multi-Agent LLM Setups on a Financial Review TaskPei Liucs.AI2026-10-20
#13Structured-Token Attention for Fine-Grained mmWave Liquid IdentificationJunseo Min, Joongheon Kimcs.AI2026-10-20
#14When Health Assistants Agree Too Readily: A Benchmark of Time-Critical Self-DiagnosisMarilyn Zhang, Tianfeng Chen, Patricia M Pechter +1cs.AI2026-10-20
#15MemDev-Bench: Does Memory Help Code Agents?Benchmarking Memory Systems over Real Repository HistoriesGuorui Chen, Tao Liu, Zhenzhen Huang +9cs.AI2026-10-20
#16Automated Multi-Agent Organization Design: From Architecture Search to Organizational LearningShao-Jun Xia, Yuner Zhang, Huixin Zhang +3cs.AI2026-10-20
#17Act on Your Behalf, Beyond Your Authorization: Benchmarking LLM Agent Authorization AlignmentZhiping Zhang, Franklin Mingzhe Li, Zihao Huang +1cs.AI2026-10-20
#18RaspAssistant as an Agentic Framework for Automating Adsorption Simulation Research in Porous MaterialsMarko Petković, Susanne Gooijer, José Manuel Vicent-Luna +2cs.AI2026-10-20
#19When LLMs Manipulate: Measuring Behavioral, Social, and Temporal EffectsSadia Asif, Israel Antonio Rosales Laguan, Shumaila Asif +3cs.AI2026-10-20
#20The Show-Up Attack: When Subagents Win Over Their SupervisorMaosen Zhang, Jianshuo Dong, Yutong Zhang +3cs.AI2026-10-20
#21DuplexLedger: Benchmarking Transactional Memory in Full-Duplex Speech AgentsYuxuan Li, Xiangchen Guan, Kunrong Li +7cs.AI2026-10-20
#22Beyond Experience: Knowledge-Guided Evolution for NPU Kernel GenerationXi Chen, Ming Shen, Haotian Yan +2cs.AI2026-10-20
#23Meta Expert: Cross-Layer Expert Sharing for Storage- and Retrieval-Efficient MoEErmo Hua, Xiangyu Hong, Baiting Wu +11cs.AI2026-10-20
#24From Encoding to Generation: Towards Empathetic Large Language ModelsSamhita Bollepally, Takashi Yamauchi, Marissa Westcs.AI2026-10-20
#25TriGeoBench: A Multimodal Mathematical Geometry Benchmark with Figures and TikZJing Wang, Yitong Yang, Hao Dou +6cs.AI2026-10-20
#26When Does Feedback Help? Auditing Learned Voltage-Clamp Experimental DesignRayan Nyaupane, Abhiram Bhupatirajucs.AI2026-10-20
#27SCODEL: Shared Canonical Ontology Definitions for Food Entity Linking and Ontology-Grounded Recipe Knowledge GraphsNuhu Ibrahim, Rishi Ravikumar, Ayuba Dauda +3cs.AI2026-10-20
#28CUA-Recovery: Benchmarking Error Recovery in Long-Horizon Computer-Use AgentsXu Hu, Haoming Li, Yuxiang Wang +11cs.AI2026-10-20
#29Does Multi-Agent Collaboration Pay When Agents Serve Users? Testing Agent Scaling in Dual-Control SettingsEthan Yang, Xiangcheng Shics.AI2026-10-20
#30When Can LLM Reasoning Reliably Reuse Intermediate Results?Deyuan Liu, Zecheng Wang, Xuanyi Liu +5cs.AI2026-10-20
#31Inferring continuous cognitive traits from limited neuroimaging data using pairwise convolutional neural networksMarjan Rashidi, Robert Bain, Craig Stark +3cs.AI2026-10-20
#32Reusing Multimodal Agents: Efficient Evaluation of Sound Designs in GamesThai Nguyen Van, Ibrahim Khan, Mury Fajar Dewantoro +3cs.AI2026-10-20
#33Temporal Evidence Allocation For Longitudinal Clinical Retrieval: A Position And Technical ReportSoumya Ranjan Sahoo, Divya Bharti, Sanand Sasidharancs.AI2026-10-20
#34Pattern Intelligence: Unsupervised, LLM-Interpreted Discovery of Systematic Underpayment and Denial Patterns in Healthcare Revenue Cycle ManagementHarshil Lodhiya, Alex McManuscs.AI2026-10-20
#35EASformer: Environment-Action-State Alignment for Industrial Generative RankingBohao Li, Dinglun Cao, Pengcheng Huang +8cs.AI2026-10-20
#36E8-QAT: Efficient 2-Bit Quantization-Aware Training with Implicit Lattice CodebooksXinyu Lei, Hong Huang, Jiebin Zhang +6cs.AI2026-10-20
#37How Fine-Tuning Objectives Shape Layer-Wise Information in LLM Hallucination DetectionKaiyang Wan, Forrest Sheng Bao, Amin Ahmad +1cs.AI2026-10-20
#38When Does Experience Memory Help Closed-Loop LLM Driving Agents? A Controlled Evaluation with Resampled Warmup Pools, Token-Matched Fillers, and Audited BaselinesYingxin Jia, Xuanyi Lics.AI2026-10-20
#39How Language Models Organize Task InformationKaiyang Wan, Yuxia Wangcs.AI2026-10-20
#40RSI Control: Can AI Models Perform Covert Sabotage in the Self-Improvement Process?Kaiwen Zhou, Udari Madhushani Sehwagcs.AI2026-10-20
#41Give the Model a Finger: Developmentally Aligned Evaluation of Counting in Vision-Language ModelsYingxin Jia, Hui Geng, Wenxin Yang +1cs.AI2026-10-20
#42CrystalAR: Autoregressive Modeling for Symmetric Crystal GenerationZiqiao Meng, Rongsheng Chen, Zhi Zheng +4cs.AI2026-10-20
#43RITE: Evaluating End-to-End Resilience to Silent Tool Errors in E-Commerce Agentic SystemsWenshuo Zhang, Yuquan Lin, Yushi Sun +6cs.AI2026-10-20
#44GRADUS: Discovering and Recovering Agent Lessons from the Environment's Latent SyllabusQing Ping, Wei Yang, Panpan Xu +4cs.AI2026-10-20
#45Toward Agentic AI for the 6G Physical Layer: From Algorithm Discovery to Verified Baseband SiliconEric Mittag, Lukas Brechtel, Maximilian Stark +1cs.AI2026-10-20
#46LatBridge: Efficient and Stable Model Replacement in Latent-Communication Multi-Agent SystemsJiajun Zhu, Haobo Li, Zixin Chen +2cs.AI2026-10-20
#47Privacy-preserving inference on hosted models: a learned input-embedding transform for frozen Qwen3.8-27BMahendra Roopa, Srikanth Roopacs.AI2026-10-20
#48COMPASS: Routing via Capability-Oriented Model Profiling with Adaptive Search, Selection, and Tool UseAmin Rezaei, Pouya Parsacs.AI2026-10-20
#49SAPD: Learning from Agent Experience without Environment InteractionJuncheng Diao, Haibin Wang, Wei Shi +4cs.AI2026-10-20
#50Physical Operating-Condition-Guided Vision-Language Matching for Cavitation Diagnosis in Industrial Pipeline SystemsYu Sha, Junqi Tao, Deyu Wang +4cs.AI2026-10-20
#51Automatic Differentiation with Constraints in Forward and Inverse ProblemsNikolay Yavich, Alexander Ryabov, Viacheslav Naumov +4cs.AI2026-10-20
#52Staged Continual Adaptation of Multimodal Foundation Models for Japanese Financial DocumentsGenshin Kakimoto, Atsushi Yanagisawacs.AI2026-10-20
#53MMEnterprise-Bench: Evaluating Enterprise Agents over Evolving Multimodal RecordsSeohyun Lee, Jongha Kim, Dohwan Ko +4cs.AI2026-10-20
#54ACE-Compression: An Ability-Centric Evaluation of Compressed Large Language ModelsJiahui Ning, Liang Chen, Yuchen Liang +2cs.AI2026-10-20
#55Quantum-JEPA: Quantum Born Priors for Latent-Action JEPA World ModelsZhiyuan Liu, Sicheng Liu, Haiyu Wucs.AI2026-10-20
#56From Comparison to Selection: Enhancing Cross-Scale Generalization of Pointer Networks Trained with Reinforcement Learning for Capacitated Drone Delivery RoutingSofiene Lassoued, Devara Tertia, Stefan Lier +1cs.AI2026-10-20
#57HypTI: Hyperbolic Geometry-Aware Multimodal Feature Fusion Framework for Dementia Detection Based on Tabular-Image DataJianfei Xu, Huizhi Liang, Judith Harrison +3cs.AI2026-10-20
#58Lost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action ReplayByeonghun Bang, Sangwoo Park, Jinheon Baek +3cs.AI2026-10-20
#59When Do Humans and Machines Truly Complement Each Other? Formal Conditions and Empirical Evidence for Human-AI SynergyAndrea Campagner, Federico Cabitza, Vincenzo Crupics.AI2026-10-20
#60Building Telecom Language Models with RSOD: Domain Data, Specialist Post-Training, Memory-Conscious Distillation, and Networking EvaluationAnil Srirangapatna Nagesh, Nitin Gupta, Anuj Taneja +5cs.AI2026-10-20
#61Dancing Diffusion: Learning Continuous Programs for Image Generation and EditingCui Enhe, Jinyue Yang, Bojian Yin +1cs.AI2026-10-20
#62Scaling in Games: Continued Pre-Training For Embodied Agents In Diverse Virtual WorldsKuan Zhang, Yukun Chen, Zhihao Yang +8cs.AI2026-10-20
#63TrajEvolve: Trajectory Evolution for Reinforcement Learning with Hindsight Credit AssignmentYi Wen, Hao Chen, Wanyu Wang +9cs.AI2026-10-20
#64Slot-JEPA: Object-Structured Prediction Interfaces for Latent World ModelsPeisong Wen, Qianqian Xu, Minye Lei +3cs.AI2026-10-20
#65IECG: Weakly-Supervised Interpretability-Enhancing Foundation Model for ElectrocardiogramHuynh Dang Nguyen, Trong-Thang Pham, Anh-Thuan Do +4cs.AI2026-10-20
#66InsightRAG: Aggregating Distributed Scholarly Judgments for Scientific Survey GenerationYuquan Lin, Wenshuo Zhang, Yilin Ye +4cs.AI2026-10-20
#67Polyscene: Scenario Planning as Diversity PlanningMustafa F. Abdelwahed, Joan Espasa, Felipe Meneguzzics.AI2026-10-20
#68A Semi-Analytical Inference Framework for Structural Causal ModelsTatiana Boura, Robert Peharzcs.AI2026-10-20
#69Robust Representation Learning for Spiking Neural Networks based on Conditional Information BottleneckYuli Zha, Wang Fan, Yixiao Dai +5cs.AI2026-10-20
#70Interruption-Aware Recurrent Reinforcement Learning for UAS Navigation Under Temporary OverridesChristopher Conrad, Deepak Panda, Weisi Guo +1cs.AI2026-10-20
#71MaD-RSI: Model-as-Data for Recursive Self-Improvement of Agent HarnessesYu Cui, Hong He, Ruiqing Yue +8cs.AI2026-10-20
#72ChartEvo: Self-Evolving Agent Harnesses for Long-Tail Chart ReasoningQi Wang, Peijie Wang, Jun Cao +4cs.AI2026-10-20
#73Is Sycophancy a Form of In-Context Updating?Itai Shapira, Myra Cheng, Hadas Orgadcs.AI2026-10-20
#74S-Agent 2.0: Spatial Reasoning with a General Coding AgentRui Gong, Ruoyu Wang, Yalun Dai +9cs.AI2026-10-20
#75FALCA: Falsification-Aware Reinforcement Learning with Hierarchical Credit Assignment for Long-Horizon Deep Search AgentsZijun Dou, Kun Luo, Chaofan Li +2cs.AI2026-10-20
#76RACE: RoPE-Aligned Attention Compression Based on Query-Key Activation EnergiesIrene Tenison, Abdulrahman Alabdulkareem, Daniel Karl I. Weidele +2cs.AI2026-10-20
#77SpecEvo: Speculative Evolution with Large Language Models for Cost-Efficient Scientific DiscoveryHa Minh Hieu, Tongyao Zhu, Do Xuan Long +1cs.AI2026-10-20
#78DIVE: Benchmarking Full-Duplex Interaction with Visual Engagement in Continuous StreamsYuhang Chen, Guangyue Liu, Shilong Liucs.AI2026-10-20
#79Stratified Sparse Attention: Reducing the Sparse-to-Dense Gap at Extreme SparsitySahil Joshi, Prithvi Dixit, Aryan Katiyar +5cs.AI2026-10-20
#80Toolflation: Seller Agents Distort Tool Markets Through Spontaneous Generative Engine OptimizationZhenwei Tang, Di Bai, Jintao Liu +3cs.AI2026-10-20
#81Beyond Trajectory Statistics: Community-Consistent Human Mobility Generation via Evolving User-Location GraphsBo Liu, Tong Li, Jiapeng Zhang +3cs.AI2026-10-20
#82Claims of emergence in AI should be grounded in information decompositionChristoph Riedl, Fernando E. Rosascs.AI2026-10-20
#83Exploring Temporal Context-Aware Physical Grounding in Latent World ModelsYilei Man, Yang Chen, Jingcai Guocs.AI2026-10-20
#84Proof-Carrying Contracts: Commitments AI Agents Cannot BreakCarlo Ciliberto, Alessandro Rudi, Enrico Tassics.AI2026-10-20
#85DecisionPivot: A Diagnostic Benchmark for Decision Models in LLM SystemsXialie Zhuang, Mingcong Lei, Zunhai Su +7cs.AI2026-10-20
#86Beyond 4 bits: Data-Centric Post-training Quantization and RecoveryRhea Sanjay Sukthanker, Riccardo Grazzi, James Hensman +1cs.AI2026-10-20
#87Humans Correct Their Judgments Through Debate, but Weaker AI Models Do NotMaria Victoria Carro, Denise Alejandra Mester, Facundo Nieto +14cs.AI2026-10-20
#88Agentic Ensemble with Vision-Language Models for Visual Anomaly DetectionShangquan Sun, Wenjun Luo, Xu He +2cs.AI2026-10-20
#89OptScientist: Automated Discovery of Optimization LawsMa ZhenYao, Yue Liang, Jian-Qiao Zhucs.AI2026-10-20
#90Evolving Semantic Indexes for Generative RetrievalJinming Nian, Jyun-Yu Jiang, Henry Tsai +2cs.AI2026-10-20
#91Sage-A1.5: From Long-Horizon Execution to Scientific Exploration with Capability CompositionWenjie Lou, Tianshuo Peng, Shiyang Feng +96cs.AI2026-10-20
#92Beyond the Sequentiality Bottleneck: A Hybrid Diffusion-Autoregressive Framework for Efficient Multimodal ReasoningWei Cai, Jian Zhao, Yuchen Yuan +1cs.AI2026-10-20
#93What Do RTL Repair Benchmarks Actually Measure?Yeyin Eva Zhu, Rishabh Ranawatcs.AI2026-10-20
#94Evolving Agent InterfacesSaaket Agashe, Yuzhe Yang, Gonzalo Gonzalez-Pumariega +5cs.AI2026-10-20
#95Value-Rich, Differently Organized: Measuring Value Expression and Organization in AI-Generated DebatesMaoyuan Li, Haoyuan Li, Zhongsheng Wang +1cs.AI2026-10-20
#96Semantic Observability for Autonomous Systems DiagnosticsJitendra Solanki, Anand Todkar, Ziran Mincs.AI2026-10-20
#97Adaptive Multi-Token Prediction: How far should we go?Emile Anand, Mohammed Rehan Parwani, Xinyuan Caocs.AI2026-10-20
#98Automating ML for Science: Can Frontier Agents Climb Scientific Hills in the Wild?Ming Zhong, Stacy Li, Nicholas Carlini +1cs.AI2026-10-20
#99Forging More Tasks into Better Harnesses: Agentic Harness Evolution via Successive Scale RacingJingzhe Liu, Jiliang Tang, Tong Zhao +2cs.AI2026-10-20
#100Decision language models as affordable and rapid alternatives to LLM judges of clinical generative AIRotem Gershon, Seffi Cohen, Dean Ariel +11cs.AI2026-10-20
#101Sketch2Sim: an end-to-end modular framework for hand-drawn circuit analysisMohammad Kawsar, Al Amin Islam Ridoy, Md Rakib Hossain +4cs.AI2026-10-20
#102Speedrunning Relational Foundation Model PretrainingGabriel Wedson Mendonça de Souza Veloso, Luan Borges Teodoro Reis Sena, Denis Oliveira Correa +1cs.AI2026-10-20
#103To Manipulate or Not: Opinion Dynamics in LLM InteractionsMohammad Siahkamari, Phuoc Dat Nguyen, Stephen MacNeilcs.AI2026-10-20
#104Fig: Automated Multiagent Behavior ElicitorAnrui Gu, Zhichao Wang, Nicolai Ouporovcs.AI2026-10-20
#105Hidden Messages Between Diffusion Language Model Agents: Causal Evidence for Latent CommunicationAlan-Barsag Gazzaev, Alexey Gavrilov, Sergey Muravyov +1cs.AI2026-10-20
#106DiffResearch: Accelerating Deep Research with Diffusion Language ModelsAlan-Barsag Gazzaev, Alexey Gavrilov, Mikhail Mozikov +1cs.AI2026-10-20
#107Simply Logical -- The First Three DecadesPeter Flach, Kacper Sokol, Jan Wielemakercs.AI2026-10-20
#108D-Skill: Distilling Teacher Knowledge through Agent SkillsShuo Yuan, Dacheng Li, Joseph E. Gonzalezcs.AI2026-10-20
#109Back Up Before You Regret: Measuring Backup Awareness and Automating Backup in Coding AgentsXu Li, Simon Yu, Minzhou Pan +4cs.AI2026-10-20
#110Self-Improving Agents with World Model Predictive PathsHaori Lu, Tianyu Gao, Yaoyao Liu +1cs.AI2026-10-20
#111Behavior Beyond Text: Evaluating Refusal Transfer Failure in LLM AgentsEkagra Gupta, Raj Saha, Aniekan-Abasi Inyang +1cs.AI2026-10-20
#112PerMIT: Securing Persistent Memory for LLM Agents via Machine-Checked Integrity Theorems and Scalable Community TrustTanqiu Jiang, Min Bai, Sadat Shahriar +2cs.AI2026-10-20
#113AgentPolicyForge: From Executable Environments to Policy Benchmarks and Adaptive GuardsChao Shang, Wanyu Du, Yi Zhang +1cs.AI2026-10-20
#114Two $\operatorname{ReLU}$ Layers is All You NeedFlorestan Brunck, Christoph Hertrich, Kilian Ruess +2cs.CC2026-10-20
#115A Bochner Weitzenböck Decomposition for Cellular Sheaf Laplacians, Curvature and Neural Sheaf DiffusionFrancesco Maria Guadagnuolo, Alessio Borgi, Dorina Thanou +1cs.CG2026-10-20
#116The Optimal Sampler for Diverse TSP Solutions: Characterization, Limits, and LearningSsu-Yuan Lo, Ching-Kai Wang, Kuan-Lun Chen +1cs.CG2026-10-20
#117The Router Already KnowsAndrew Bistras, Marty Johnsoncs.CL2026-10-20
#118Detecting Errors in Large Language Model Responses: The Incremental Predictive Value of Hidden StatesNingzhi Li, Xiaojun Ma, Xiaofei Wangcs.CL2026-10-20
#119Judging the Justification: Decision Certificate Supervision for Generative Reward ModelsGuiquan Sun, Bing Bai, Martin Renqiang Min +1cs.CL2026-10-20
#120EviDial: When Correct Depression Predictions Lack EvidenceJunjie Xu, Jin Zhu, Yuzhe Yang +6cs.CL2026-10-20
#121Exploring Recurrent-Depth Language Models for Multitask Clinical Text ProcessingXi Yang, Guodong Liu, Cheng Peng +7cs.CL2026-10-20
#122Learned Readout Tokens for Extracting Large Language Model ConfidenceNima Seifi, Martin Estercs.CL2026-10-20
#123AudiPsy: Evidence-Grounded Multimodal Reasoning over Spoken Counseling Conversations for Depression AssessmentChuanbo Zhu, Run Luo, Weibo Zhao +6cs.CL2026-10-20
#124Why Static Probes Fail: Context Determines Deception Feature CompositionYao Huang, Siyuan Chen, Zhenghan Zhou +1cs.CL2026-10-20
#125Factual Access States in Diffusion Language Models: From Mechanism to Knowledge Editing and RetrievalYuchen Guo, Zhuoyuan Mao, Yiwen Guocs.CL2026-10-20
#126TeCoP: Accelerating Diffusion Large Language Model Decoding via Tentative Context PipeliningJui-Chien Tsou, Hsuan-Chi Liu, Wei-Chin Wang +2cs.CL2026-10-20
#127Beyond Model Weights: Sampling-Dependent Fairness in Diffusion Language ModelsKoshiro Saito, Diasuke Oba, Danushka Bollegala +1cs.CL2026-10-20
#128Benefit and Cost of Random-Token Replacement under Repeated Data: A Known-Entropy Decomposition and Evidence from Ten Real CorporaWonsup Shin, Jingu Kimcs.CL2026-10-20
#129WORTH Benchmark: Evidence Discovery under Not-Fully-Cooperative Information -- A Two-Episode PilotBo Zou, Chao Xucs.CL2026-10-20
#130Self-Decomposing Diffusion for Code GenerationLize Shao, Zichen Xie, Zhizhen Chen +2cs.CL2026-10-20
#131ABench: Adversarily Benchmarking Large Language Models across Taxonomized ValuesLiping Yang, Yongqi Leng, Jingting Zheng +3cs.CL2026-10-20
#132PAR: Progress-Aligned Recurrence for Length Generalization in State TrackingPan Wang, Yihao Hu, Guangyuan Dong +8cs.CL2026-10-20
#133A Two-Way Street: Surveying the Interplay between Code-Mixing and Native Languages in Text and SpeechDebajyoti Mazumder, Akash Anilcs.CL2026-10-20
#134Speak vs. Know: Balancing Behavior and Knowledge Distributions of Large Language ModelsYang Liu, Masahiro Kaneko, Chenhui Chucs.CL2026-10-20
#135Corpus Quality Improves, Retrieval Utility Does Not: An Ablation of Preprocessing and Refinement in a Speech-to-QA PipelineWonsup Shin, Jingu Kimcs.CL2026-10-20
#136Memory as Code: Declarative Retrieval over Codified Long-Term MemoryAoting Zeng, Yuxin Du, Jianwei Wang +4cs.CL2026-10-20
#137Beyond Calibration: Temporal LLM Confidence Assessment Across Languages and Local SettingsSahil Kalecs.CL2026-10-20
#138Tracing Recurrent and Emergent Hallucination Patterns in Decomposed Text-to-SQL GenerationHayden Moore, Abhinav Verma, Anshuman Duttcs.CL2026-10-20
#139Hearsay or Fact? How Framing and Elicitation Shape LLM Probability UpdatesAn-Sheng Jhangcs.CL2026-10-20
#140Are Linguistic and Arithmetic Circuits Dissociated in LLMs?Riku Kisako, Tatsuki Kuribayashi, Ryohei Sasanocs.CL2026-10-20
#141ProVe: Proposer-Verifier DecodingZiqi Jin, Weiwen Xu, Jiaxi Li +3cs.CL2026-10-20
#142SMART: Semantic Segment Mapping and Assessment of Recognition Transcripts with Contextual RubricsXiaoyu Gu, Chencheng Wang, Fuyang Li +4cs.CL2026-10-20
#143SciDiagBench: A Type-Specific Benchmark for Human-Aligned Evaluation of Scientific DiagramsHao Wang, Zixuan Li, Long Bai +4cs.CL2026-10-20
#144UvA-MT's Participation in the WMT26 General Translation Shared TaskDi Wu, Sergey Troshin, Wafaa Mohammed +4cs.CL2026-10-20
#145Testing Associative Creativity in Humans and Multimodal LLMs with Difficult-to-Name Visual StimuliManar Ali, Lisa Gottschalk, Simeon Junker +6cs.CL2026-10-20
#146CollabSciReM: Aligning Language Models for Scientific Conversations via Science-Aware Reward DecompositionSasi Kiran Gaddipati, Gollam Rabby, Sören Auercs.CL2026-10-20
#147Polarity Blindness in LLM Safety: A Systematic Study of Negation, Antonym Substitution, and Adversarial FramingDiego Miguel Lozano, Erik Derner, Juan Antonio Pérez-Ortiz +1cs.CL2026-10-20
#148Why Do LLMs Accept Generics? Explaining Acceptability using Psycholinguistic and Model-Derived FactorsMervat Abassy, Zhaoxin Feng, Tatsuki Kuribayashi +2cs.CL2026-10-20
#149From DQI to C-DQI: Automatic Codebook Generation and Evaluation for Measuring Computational Discourse Quality IndexEsther Shizgal, Ron Keinan, Daniel Shtauber +8cs.CL2026-10-20
#150Adaptive Stopping of Streamed Reasoning for Language Model AgentsJunHyeok Oh, Byung-Jun Leecs.CL2026-10-20
#151Using Letter Positional Probabilities to Assess French Word ComplexityMichael Dalveancs.CL2026-10-20
#152On-Policy Transition DistillationRunyang You, Yongqi Li, Tiezheng Yu +1cs.CL2026-10-20
#153Same Judgment, Different Yes: Measuring Multilingual Judgment Profiles in Language ModelsHaonan Huang, Yuwei Lu, Chengkun Caics.CL2026-10-20
#154BAIT: Can LLMs Find What Biases a Reader? A Benchmark for Cognitive Bias Triggers in NewsYousra Fettach, Tijl De Biecs.CL2026-10-20
#155Reading Too Much Into It? Interpretive Preferences and Commitment in LLM Mentalisation under AmbiguityStephanie Fong, Yiwen Jiang, Qingyang Xu +7cs.CL2026-10-20
#156Africa-Papers: A 10-Billion-Token Multi-Domain Academic Corpus for African Foundation Language ModelsMich-Seth Owusucs.CL2026-10-20
#157Temporal Evidence-Parameter Co-Alignment for LLM Reasoning over Temporal Knowledge GraphsJiapu Wangcs.CL2026-10-20
#158Can Language Models Get "Aphasia" From Neuronal Ablation?Pratik Worah, Randall Batemancs.CL2026-10-20
#159How Language Models Learn Taste: Brand Preference in LLMsTapan Parikhcs.CL2026-10-20
#160Forty Questions: Identifying a Language Model from One-Word AnswersTapan Parikhcs.CL2026-10-20
#161Adaptive Replay Refinement: Allocating Test-Time Compute Between Revision and ResamplingAhsan Bilal, Muhammad Ahmed Mohsin, Muhammad Umer +3cs.CL2026-10-20
#162Reward Misspecification Degrades Chain-of-Thought MonitorabilityTianyi Lorena Yan, John Hewittcs.CL2026-10-20
#163From Abstraction to Action: DSLs for Natural Language Abstraction Interpretation and ExecutionAmit Lisha, Reut Tsarfatycs.CL2026-10-20
#164Beyond a Single Sentiment Score: Topical and Affective Dimensions of Emoji Meaning on TwitterRohan James, Ioannis Christofilogiannis, Yuuv Jauhari +2cs.CL2026-10-20
#165DeclineCraft: A RAG Abstention Benchmark for Jointly Measuring Combined Retrieval and Parametric KnowledgeAtharva Thakur, Abulhair Saparov, Bruno Ribeirocs.CL2026-10-20
#166Object-Oriented Harness: Evolving Agent Harnesses through Object-Oriented DesignGaotang Li, Bhavana Dalvi Mishra, Yifei Ming +9cs.CL2026-10-20
#167When Copying Is Hard: Copy-Constrained Decoding for Exact Span ReproductionJinghui Zhang, Lang Gao, Zongfang Liu +5cs.CL2026-10-20
#168The Instruction Tax on Factual Recall: Base Models Can Beat Their Instruction-Tuned CounterpartsChristophe Khalil, Aya Mouradcs.CL2026-10-20
#169Every Model Leaves a Trace: Multi-Resolution LLM FingerprintingMohammad Reza Modarres, Armin Tourajmehr, Artin Tavasoli +2cs.CL2026-10-20
#170MythoSemantic: An Interactive System for Discovering Semantic Parallels Across Mythological and Religious TraditionsNikita Ganziuk, Innokentiy S. Humonen, Ilya Makarov +1cs.CL2026-10-20
#171Asymmetric Looped Transformers: Fixed Global Representations for an Iterative DecoderCheng Liang, Tengfei Zhang, Wenjie DU +6cs.CL2026-10-20
#172OptionWorld: A Benchmark for Diagnosing Failures of LLMs as Long-Term Personal AssistantsRuoyu Zhang, Zhaocen Liu, Weiyi Tian +2cs.CL2026-10-20
#173BitMTP: When Multi-Token Prediction Meets Low-Bit Large Language ModelsNing Zhang, Shihao Wang, Jinrui Zhang +2cs.CL2026-10-20
#174Translation and data ethicsJoss Moorkens, Monja Jannetcs.CL2026-10-20
#175Large Flow Language ModelsArnav Chavan, Chanhyuk Lee, Udbhav Bamba +4cs.CL2026-10-20
#176Cache Engineering for AgentsTianyu Fu, Ruoxi Wang, Zihan Min +6cs.CL2026-10-20
#177Capable Teacher, Myopic Scorer: Reward-Free Teacher Repair for Agentic On-Policy DistillationShu Zhao, Tan Yucs.CL2026-10-20
#178Benchmarking Arabic Dialects for Math ProblemsNoor Abo Mokh, Teresa Lynn, Nizar Habash +5cs.CL2026-10-20
#179NarraSpace: Multimodal Scene-Grounded Evidence for Picture-Description Dementia ClassificationQingming Li, Ruiyan Sun, Satoshi Nakamuracs.CL2026-10-20
#180SkillEval: Learning Interpretable Ability Profiles of LLMs via Cognitive Diagnosis ModelsBerke Arda, Peng Cui, Qiaoyuan Zheng +3cs.CL2026-10-20
#181Scaling Therapy Supervision: Assessing Psychotherapy Fidelity Using Large Language ModelsArvind Pillai, Alexis Roach, Jason Holden +11cs.CL2026-10-20
#182Is Anyone Enforcing the Cartel? What Reinforcement Learning Teaches LLM Agents in MarketsHieu Tran, Hong Yucs.CL2026-10-20
#183Where Do Legal Factors Live in LLMs?Li Zhang, Kevin Ashleycs.CL2026-10-20
#184LIFT: Scoped Constraints for Evaluating and Training Instruction FollowingEran Goldstein, Yuval Belfer, Yonatan Belinkov +1cs.CL2026-10-20
#185A Parallel Multi-Dialect Arabic Dependency TreebankNoor Abo Mokh, Mohamed Adel, Jamila El-Gizuli +3cs.CL2026-10-20
#186How to Use Parallel Data for Multilingual PretrainingZhihong Huang, Yao Lu, Derek F. Wong +2cs.CL2026-10-20
#187KIRA: A Full-Stack Reading Screening System with Dual-Pathway Analysis for ChildrenMaggie Dong, Rohit Mekkoth, Zixuan Wang +3cs.CL2026-10-20
#188SANE: Automated Scorer-Specific Metamorphic Testing for LLM JudgesEthan Ludwick, Yu-Chung Hsiaocs.CL2026-10-20
#189Building AI Research Teams for Autonomous Discovery of Linear Attention ArchitecturesYujian Liu, Li An, Zelin He +5cs.CL2026-10-20
#190CSD: Common-Support Distillation for Cross-Tokenizer Knowledge TransferMingyu Yang, Sharath Turuvekere Sreenivas, Adithyakrishna Venkatesh Hanasoge +3cs.CL2026-10-20
#191Is Refusal Direction Universal across Low-Resourced Languages?Anastasiia Ivanovacs.CL2026-10-20
#192Guilt by Association: Semantic Leakage Drives Associative Gender BiasHazel Chen, Peter West, Hila Gonencs.CL2026-10-20
#193Scan or Index? large Evidence Coverage, Answer Quality, and Cost in Long-Document RAGJuan Terven, Diana-Margarita Córdova-Esparza, Julio-Alejandro Romero-González +5cs.CL2026-10-20
#194Language Impairment as a Lens onto Large Language ModelsMuxuan He, Wang Bill Zhu, Yue Chen +5cs.CL2026-10-20
#195Privacy-Preserving Personalized Federated Learning (PPP-FL) for Medical ImagingMd Morshedul Islam, Hossain Shahriar, Alfredo Cuzzocreacs.CR2026-10-20
#196Beyond the Prompt: Recovering Hidden Concepts in Text-to-Image ModelsZhengfeng Zheng, Minghong Fangcs.CR2026-10-20
#197Adversarial Benchmarks and BenchDoor Attacks: Exploiting Benchmark Incentives for Backdoor AttacksYixin Wu, Rachel Hong, Jamie Morgenstern +1cs.CR2026-10-20
#198Local Allow, Global Deny: Why Per-Action Authorization Does Not Compose in LLM AgentsAnmol Pandey, Aditya Jain, Liang Chen +1cs.CR2026-10-20
#199A Unified Attack Framework against Statistical Generative Watermarks for Large Language ModelsRomina Omidi, Nima Naderloui, Yuan Hong +1cs.CR2026-10-20
#200CyberHull: Deterministic Malicious URL Isolation via Convex HullAvijit Gayen, Aniket Ghosal, Durba Chakraborty +3cs.CR2026-10-20
#201Self-Evolving Static Analysis via LLM Pseudo-LabelingRui Melo, Andre Duarte, Aditya Oke +5cs.CR2026-10-20
#202Contextual Candour: Role-Aware Graduated Disclosure for LLMs over Mixed-Sensitivity ContextsDevansh Srivastav, David Pape, Samira Abedini +1cs.CR2026-10-20
#203ClawMMU: Protection-Coherent Virtual Memory for Stateful LLM AgentsJinhao Hu, Bardia Mohammadi, Mofasshara Binte Rafique +4cs.CR2026-10-20
#204Disclosure Begets Disclosure: A Self-Reinforcing Privacy Loop in LLM Agents with Persistent MemoryMasahiro Kaneko, Hiromi Arai, Timothy Baldwincs.CR2026-10-20
#205Context-Aware Prompt Injection Detection via Small Language Models in RAG Pipelines: nokast-secureRAGAbhishek Raics.CR2026-10-20
#206MAS-Guard: Unified Guardrails from Individual Agents to Multi-Agent LLM SystemsMohammad Kachuee, Phu Mon Htut, Sheng Li +5cs.CR2026-10-20
#207After the Attacker Leaves: Benchmarking Carryover Attacks on LLM AgentsZhiyue Xu, Xukai Wang, Zhiyuan Huang +3cs.CR2026-10-20
#208A Digital Twin to Improve Cyber-Social ImpactVita Santa Barletta, Danilo Caivano, Gabriel Cellammare +3cs.CR2026-10-20
#209Combining Long-Term Memory and LLMs Comes at a High Cost: From Prompt Injection to Persistent CompromisePedro H. Barcha Correia, Matheus Azevedo de Sá, Paulo H. Gomes de Senna +4cs.CR2026-10-20
#210Black-Box Red-Teaming of Multi-Agent Systems via Reinforcement LearningYuqi Jia, Hangsheng Zhang, Chenxi Liu +2cs.CR2026-10-20
#211Test-time Adaptation for Point Cloud Denoising under Unseen NoiseKun Jiang, Shida Fu, Fanhao Yi +2cs.CV2026-10-20
#212TokenFlow: Latent Token Rectified Flow Matching for 3D Point Cloud GenerationLinhao Wang, Dongjin Huangcs.CV2026-10-20
#213LoRASpace: A Pool-Wide Shared Substrate for Static and Dynamic Multi-LoRA CompositionThamirawaran Sathiyalogeswaran, Navindu De Silva, Chamikara Siriwardane +4cs.CV2026-10-20
#214FocusOVD: Geometric and Contextual Feature Refinement for Open-Vocabulary Small-Object DetectionHanlin Kou, Beiqi Bai, Li Chen +3cs.CV2026-10-20
#215Cross-Visibility-Gap Identity Persistence for 4D Scene GraphsJiahui Hu, Li Gao, Yu Liu +1cs.CV2026-10-20
#216Progressive Subset Selection and Cascaded Consistency for Unsupervised Vision-Language Model AdaptationHao Yan, Guanghui Wangcs.CV2026-10-20
#217HealBench: A Fine-Grained Benchmark for Evaluating Psychological Comfort in Text-to-Image GenerationJunjie Xu, Yuzhe Yang, Rui Yang +4cs.CV2026-10-20
#218Multiscale Temporal-Spectral-Spatial EEG Learning With Modality-Specific and Modality-Invariant Representations for Emotion RecognitionJian Zhang, Manrong Liu, Yilei Huang +3cs.CV2026-10-20
#219OmniVLoc: Topo-metric Visual Localization for Omnidirectional CamerasZhuo Yu, Shuyang Zhang, Huihua Zhu +6cs.CV2026-10-20
#220Less is More: Concise Retrieval and Critic-based Re-ranking for Composed Image RetrievalYuqian Zheng, Hyoju Ahn, Hyeongjin Ahn +1cs.CV2026-10-20
#221SynCalib: Breaking Dataset Shortcuts in LiDAR-Camera Calibration via Extrinsic-Controllable SynthesisHuihua Zhu, Shuyang Zhang, Dongqing Chen +6cs.CV2026-10-20
#222CityPaint: A Free Lunch from 2D Diffusion for City-Scale 3D TexturingYuchen Zou, Lihuang Fang, Siyu Zhu +1cs.CV2026-10-20
#223AnomalyJev: Towards Evaluating Image Anomaly Explanations via Claim-Level VerificationQizhou Wang, Jiawen Zhu, Guansong Pang +1cs.CV2026-10-20
#224Text-Anchored Modality Experts with Uncertainty-Guided Routing for Multimodal Sentiment AnalysisXiaohua Huang, Bingrui Lei, Xiuyan hao +4cs.CV2026-10-20
#225Real In, Real Out: What If We Only Use Real Data for Scene Text Editing?Xingsong Ye, Yongkun Du, Jiaxin Zhang +2cs.CV2026-10-20
#226Causal Spatiotemporal State Evolution for Monocular 4D ReconstructionQiaowei Miao, Yijing Guo, Lipei Zhang +4cs.CV2026-10-20
#227HiQGS: Hierarchical Spatiotemporal Querying for Feed-Forward Gaussian ReconstructionQiaowei Miao, Qifeng Cheng, Yijing Guo +3cs.CV2026-10-20
#228DART: Scaling a Shape Representation Across Anatomical Classes and Imaging ModalitiesKoushik Swarna, Pedro R. A. S. Bassi, Lam Ngo +4cs.CV2026-10-20
#229WaveSpec: Multi-Spectral Iris Presentation Attack Detection via Wavelength-Conditioned Spectral Coherence AdaptationRaghavendra Ramachandracs.CV2026-10-20
#230Provisioning Robust and Efficient LiDAR Perception for Autonomous DrivingTingxu Han, Zijie Shen, An Guo +4cs.CV2026-10-20
#231PACE-MoE: Adaptive Domain Sampling and Domain-Specific LoRA for Medical Visual GroundingZhenxuan Wang, Jisheng Dang, Ronghao Lin +6cs.CV2026-10-20
#232Reusing Assurance Evidence in AI Pipelines: Validity Conditions, a Fail-Closed Release Gate, and a Replay of 714 Public Data Version Control PipelinesAtanu Mukhopadhyay, Shravya Reddy Nallacs.CV2026-10-20
#233NeoWorld-3: From Pixels to Code-Defined Physical WorldsEachen Soong, Zijian Niu, Haoran Xu +3cs.CV2026-10-20
#234A Principled Optimal Transport Framework for Frame Selection in Long Video UnderstandingZiwei Zhao, Yuhang Liucs.CV2026-10-20
#235PanoGraphGS: Unifying Panoptic Segmentation and Hierarchical 3D Scene Graphs with Gaussian SplattingJinghan Gao, Siyu Wang, Dongyu Feng +2cs.CV2026-10-20
#236VLA-Retain: Benchmarking Cross-Dimension Effects of Vision Tuning in VLAsBorui Xu, Han Chen, Bingsheng He +3cs.CV2026-10-20
#237VEOcc++: Learning Persistent Voxel Feature Maps for Embodied Online Semantic Occupancy Mapping and Offline RefinementRuoyu Wang, Jiahan Li, Yong Liu +1cs.CV2026-10-20
#238RLSplat: Resource-Linear Budget Control for Feed-forward 3D Gaussian SplattingInjae Kim, Minseok Joo, Jihwan Park +3cs.CV2026-10-20
#239Push-Pull Attentional Anchoring for Diffusion Concept ErasureNattanat Chatthee, Tagon Sompong, Ekapol Chuangsuwanich +1cs.CV2026-10-20
#240World2HOSI: A Multi-Expert Harness for Long-Horizon Human-Object-Scene Interaction GenerationJiushu Li, Haoran Wang, Yumeng Liu +4cs.CV2026-10-20
#241CILA: Confusion-based Instance-wise Logit Adjustment for Long-Tailed RecognitionJiyoung Lim, Jee-Hyong Leecs.CV2026-10-20
#242Revealing Inter-Channel Modality Discriminability: Channel Selective Interaction Fusion Network for Optical-SAR Object DetectionHaojie Li, Yuanfei Huang, Lingfei Song +2cs.CV2026-10-20
#243PixelSR: Pixel-Space Orthogonal Flow Decoupling for Real-World Image Super-ResolutionXiang Lv, Kai Zhao, Qiang Wang +3cs.CV2026-10-20
#244Radar-Based 3D Human Pose Estimation via Motion-Aware Pose Initialization and Observation-Guided RefinementWoo-Jin Jung, Chan-Bin Lim, Seung-Hyun Kongcs.CV2026-10-20
#245Geometry Regularization for Vanilla NeRF via Self-Supervised Cross-Ray ConsistencyZongji Wangcs.CV2026-10-20
#246RoboJudge: Multimodal Language Models as Judges for Embodied Video GenerationSiyuan Ma, Yu Qi, Cheng Ye +8cs.CV2026-10-20
#247Decoupled Representation Learning for Face Presentation Attack Detection under Smart Glass CaptureRaghavendra Ramachandra, Narayan Vetrekar, Neha Naik +1cs.CV2026-10-20
#248GARRET: Generative Feedback for Region Retrieval in Visual DocumentsWeijian Jian, Siyang Chen, Yuguang Yang +4cs.CV2026-10-20
#249LaLa-World: Scaling Latent World Models with Natural Language ActionsJunha Song, Geonmo Gu, Jeongeun Park +5cs.CV2026-10-20
#250Manifold Prior Guided Deep Unfolding for Hyperspectral Image ReconstructionShuqi Liu, Yingkai Zhang, Lin Gu +2cs.CV2026-10-20
#251Gaze2HOI: Gaze-Aware Intention Disambiguation for Egocentric Hand-Object Interaction ForecastingChuanyang Ma, Chenye Wang, Yixuan Wang +6cs.CV2026-10-20
#252S$^3$E-Det: A Strict Spatial-Spectral Equivariant Detector for Multispectral Object DetectionPeng Zhang, Tingfa Xu, Jinrui Sui +2cs.CV2026-10-20
#253SGLDet: Spectral-aware Global-Local Dynamic Modeling for Multispectral Aerial Object DetectionPeng Zhang, Shuaihao Han, Tingfa Xu +1cs.CV2026-10-20
#254EndoWorld-JEPA: Motion-Guided Global-Local Latent World Modeling for Endoscopic Video Representation LearningJie Wang, Shilong Yang, Tao Zhou +5cs.CV2026-10-20
#255ICIBS: Increasing the Context for Ice Boundary SegmentationMarcel Dreier, Dakota Pyles, Nora Gourmelon +6cs.CV2026-10-20
#256World Models with Configurable PerceptionYijun Shen, Delong Chen, Xianming Hu +2cs.CV2026-10-20
#257In PRAISE of Attributes: Grounding Retrieval Geometry with Query-Conditioned Subspaces for Person Re-IdentificationRajarshi Bhattacharya, Aryan Shukla, Shakeeb Murtaza +4cs.CV2026-10-20
#258Decoupling Action from Egocentric Observation for World SimulationYue Ma, Pengjie Song, Xinyu Wang +10cs.CV2026-10-20
#259Edit in Sync: Unified End-to-End Audio-Visual Editing for Human-Centric VideosZiye Yuan, Minghong Cai, Xu He +8cs.CV2026-10-20
#260From Proper Scoring Rules and Edge Biases to Mumford-Shah Models: Robust Unsupervised Hyperspectral Image SegmentationFabian Conrad, Benjamin Berkelscs.CV2026-10-20
#261Efficient SAM3 Adaptation for Multi-Class Semantic Segmentation via Dense Competitive RepresentationsWenbin Liao, Hao Zhu, Yike Ma +2cs.CV2026-10-20
#262Media Intelligence Platform: Multimodal Detection of Synthetic and Manipulated ContentDavid Fischinger, Marcel Hasenbalg, Silvia Poletti +7cs.CV2026-10-20
#263Beyond the Frame: Redundancy, Not Trajectory, Carries the Privacy Leak in Video UnlearningKavyansh Tyagi, Paolo Russocs.CV2026-10-20
#264Recast the Past: Stable Long Video Generation with Full Context MemoryYukuo Ma, Cong Liu, Junke Wang +4cs.CV2026-10-20
#265Matrix-Game 4.0: Harnessing Video Models for Real-Time Playable Game WorldsJihai Zhang, Runjia Qian, Kaiqin Kong +15cs.CV2026-10-20
#266Beyond the Evidence Boundary: Behavioral Mirage Under Progressive Degradation in Medical VLMsEdric Castel C. Hao, Rez Samantha Z. Florescacs.CV2026-10-20
#267Differentiable Task-Driven Coded Aperture Camera Design with 3D Gaussian Scene RepresentationsChengyang Yan, Donald G. Dansereaucs.CV2026-10-20
#268AdaptMIL: Domain Adaptation for Multiple Instance Learning in Digital PathologyBen Vardi, Dana Schonberger, Yuval Friedmann +4cs.CV2026-10-20
#269P$^3$-VLM: A Point-based Alternative for Grounded 3D Vision-Language ModelsAnna-Maria Halacheva, Jan-Nico Zaech, Sombit Dey +2cs.CV2026-10-20
#270Spherical Geometry-Aware Panoptic Scene Graph Generation for Equirectangular PanoramasZhe Wu, Xiaoyan Fei, Xinyi Jiang +4cs.CV2026-10-20
#271A Process-Informed, Photorealistic Digital Twin for Vision-Based Inline Inspection of C-SMC Strip DepositionPatrick Flore, Fabian Röder, Kevin Chen +1cs.CV2026-10-20
#272Assessing Representation Semantics Under Language Pretraining in Fine-Grained ClassificationMd Raisul Kibria, Sébastien Lafondcs.CV2026-10-20
#273Auditing Where Concept Bottleneck Accuracy Comes From on CUBSascha Saralajew, Eleonora Poeta, Eliana Pastor +1cs.CV2026-10-20
#274MoDDiT: Simple Token Routing in Diffusion TransformersJarek Liesen, Matthew T. Jackson, Benjamin Ellis +2cs.CV2026-10-20
#275WildAIGC-Bench: Can AI Image Detectors Handle the Wild? A Benchmark of Generated and Edited Images in Online CirculationZijian Yu, Hangwei Zhang, Jun Lan +3cs.CV2026-10-20
#276LatticeRank: Spacing-Ranked Consistency for Native-Grid 3D Medical Image SegmentationJingjia Yan, Yue Zhuo, Zhonghua Xiecs.CV2026-10-20
#277Reliability-Guided Vision-Language Decoding with Text-Aware Skip Refinement for Medical Image SegmentationSivan Talaei, Fatemeh Daneshfar, Mustaqeem Khan +2cs.CV2026-10-20
#278PointForward V2: Point-Aligned Interaction for Feedforward Driving ReconstructionXianqi Wang, Cheng Chi, Yuechuan Pu +6cs.CV2026-10-20
#279GAMF-Net: Grouped Availability-Aware Multimodal Fusion for Smartphone Skin Lesion ClassificationYue Zhuo, Jingjia Yan, Fangyu Liu +4cs.CV2026-10-20
#280OV-Foam: How 3D Representations Shape Semantic Feature LiftingYousef Rajeh, Alejandra Esparza Pelcastre, Ivan Viola +1cs.CV2026-10-20
#281DocLayout-YOLO: Axis-Attentive Document Layout Detector with Mesh-Guided Synthetic PretrainingZhiyuan Zhao, Hengrui Kang, Guang Liang +2cs.CV2026-10-20
#282CrossFit-GS: Out-of-Fold Pose Estimation for COLMAP-Free 3D Gaussian SplattingZijian Wu, Jinliang Wang, Mingfeng Jiang +3cs.CV2026-10-20
#283Unified RAW Image Exposure Correction and Restoration via Linear Illumination and Frequency-Adaptive EnhancementYingkai Zhang, Yunhao Zou, Ying Fucs.CV2026-10-20
#284Offline Makes Online Better: Calibrated Cache Compression for Video GenerationZhen Wang, Ning Lai, Qingtao Yucs.CV2026-10-20
#285Attractive Faces Skew Text-to-Image Reward Models and LeaderboardsHarvey Mannering, Zhiwu Huang, Adam Prügel-Bennettcs.CV2026-10-20
#286Learn to Modify: Self-evolving Multi-agent Refinement Framework for Conversational Text-to-Motion GenerationJianan Li, Jiawei Zhao, Yangtao Zhou +6cs.CV2026-10-20
#287Region-Guided Food-Package Evidence Extraction and Abstention-Aware Draft R3337 Screening with Selective VLM ReviewMayimunah Nagayi, Alice Scaria Khan, Tamryn Frank +2cs.CV2026-10-20
#288Convergent Performance, Divergent Mechanisms in LoRA-Adapted Vision Foundation Models for Brain MRICecilia Diana-Albelda, Fiona Kekwick, Raghav Mehta +6cs.CV2026-10-20
#289SplatFlux: Feed-Forward 4D Gaussian Reconstruction and Generation from Video LatentsRunmin Zhang, Binglin Ren, Zhu Yu +6cs.CV2026-10-20
#290Reliability-Aware Reconstruction of V-Shaped Surfaces with a Low-Cost Multi-Zone SPAD SensorYohanssen Pratamacs.CV2026-10-20
#291PI-MLLM: Psychophysics-Inspired Multimodal Large Language Model for Oddly Satisfying Video Emotion AnalysisYuheng Zhang, Jie Zhang, Yuecong Min +4cs.CV2026-10-20
#292VGL-stGen: Learning a shared multimodal model for lung histology and spatial transcriptomicsHaenara Shin, Dongjoo Lee, Sungwoo Bae +3cs.CV2026-10-20
#293HRoPE: Homography Relative Positional EncodingHuachen Gao, Yang Yang, Xiaoqian Liang +6cs.CV2026-10-20
#294CPVB-RG: Cross-Prior Visual Bridging for Prior-Aware Chest X-Ray Report GenerationSike Xiang, Shuang Chen, Julie Cox +1cs.CV2026-10-20
#295AGGR-Mamba: Mamba-based Network with Attention-Guided Gated Residual Refinement for Undersampled MRI ReconstructionYue Zhuo, Wenbin Deng, Lingjun Liu +2cs.CV2026-10-20
#296Towards Consistent Geospatial Representations: Aligning One Encoder to Many Foundation ModelsArthur Ouaknine, David Rolnickcs.CV2026-10-20
#297ABACUS: A Benchmark for Image Editing Models to Assess Object Category and Counting Under Scene ConservationAymen Lassoued, Angelique Loesch, Romaric Audigiercs.CV2026-10-20
#298PACE: Plan, Attend, Check, and Emit for Training-Free Response Timing in Streaming Video UnderstandingSiqi Guo, Yuxia Chen, Wenbo Zhu +4cs.CV2026-10-20
#299HistoLoop: Iterative Contextual Inference with a Looped Transformer for Histology-Based Spatial Gene Expression PredictionZiang Liu, Jie Liu, Shuai Li +2cs.CV2026-10-20
#300Auto-Director: Leveraging Multi-Agent Collaboration for Autonomous Video EditingYuxia Chen, Wenbo Zhu, Yangguang Ji +3cs.CV2026-10-20
#301Gated Prototype Transfer for Zero-Support Medical Vision Language ModelSumaiya Fazal, Rizwan Qureshi, Laleh Behjat +1cs.CV2026-10-20
#302RayCo4D: Ray-Conditioned Continuous Motion Model for Monocular 4D Dynamic ReconstructionYuanxiang Ni, Xianliang Huang, Ruihan Hou +2cs.CV2026-10-20
#303CountVideoBench: A Benchmark to Evaluate Prediction Biases on the Object Counting task by Video-Language ModelsMarc Chapus, Carlos Crispim-Junior, Véronique Eglin +1cs.CV2026-10-20
#304RACE: Learning Multimodal Search through Referential Abstraction and Compositional EvidenceEric Tao, Minhao Sun, Liyan Liu +9cs.CV2026-10-20
#305VisualEvolve: A Skill Self-Evolution Framework for Visual ReasoningJiawei Wang, Yucun Li, Xueqi Li +9cs.CV2026-10-20
#306StreamEval: Evaluating Interactive Streaming Video Generation ModelsStreamEval Teamcs.CV2026-10-20
#307A Multi-Agent Framework for Automated Machine Learning with Evidence-based Planning for Medical Image AnalysisYiqing Shen, Mathias Unberathcs.CV2026-10-20
#308Brain2Vec: A Self-Supervised 3D Foundation Model for Structural Brain MRISpiros Maggioros, Guray Erus, Gareth Harman +4cs.CV2026-10-20
#309Code2Video-Compass: A Comprehensive Benchmark for General-Purpose Code-Based Video Generation across T2V, I2V, and V2VZhenghan Chen, Zekai Shao, Xin Lin +2cs.CV2026-10-20
#310DISTRACT: Degradation-Indexed Study of Textual Reference Across Competing TargetsDan Zlotnikov, Ohad Ben-Shaharcs.CV2026-10-20
#311WorldSR: Harnessing World Knowledge Search for Grounded Image Super-ResolutionJunyuan Deng, Xinyi Wu, Zhenyao Wu +3cs.CV2026-10-20
#312EvaOmni: An Evidence-Grounded Benchmark for Audio-Visual ReasoningXiaoxing Hu, Wenxi Yao, Chaoyuan Shi +17cs.CV2026-10-20
#313Answering in the User's Variety: Calibrated Accommodation Pairs for Post-TrainingZhizhuo Kou, Heming Li, Jian Yang +4cs.CV2026-10-20
#314CLOSER: Evidence-Aware Active Visual Verification for Embodied Object-Goal NavigationPengying Wu, Mingye Jiang, Yunze Hu +5cs.CV2026-10-20
#315Learning from Automatic 3D Gaussian Splatting Edits for Online Bayesian Scene Change DetectionChangrui Zhu, Simon Juliercs.CV2026-10-20
#316GazeLens for Efficient Egocentric Video Question Answering with Simple Gaze-Driven Adaptive Token ReductionTrong-Thang Pham, Anh Nguyen, Hien Van Nguyen +1cs.CV2026-10-20
#317Deep Learning-Based Road Lane Quality Assessment from Egocentric Dashcam VideoShaif Chowdhury, Akhila Yeruvasu, Moshiur Rahman Tonmoy +2cs.CV2026-10-20
#318SenseAlign: Understanding Vision and Touch through Language at Test TimeChuyang Ye, Qinting Jiang, Jingyan Jiangcs.CV2026-10-20
#319Touch-JEPA: Tactile Representation Learning from Hand-Object Video with Limited Tactile SupervisionMinseong Kweon, Qiao Feng, Yiming Huang +1cs.CV2026-10-20
#320Latent Bridge: From Video Latents to 3D Geometry via Feature AlignmentShuai Zhang, Zhanpeng Ouyang, Zhengqing Chen +7cs.CV2026-10-20
#321Copyright Leakage Detection in AI Generated VideosShaif Chowdhury, Moshiur Rahman Tonmoycs.CV2026-10-20
#322CoGaussian: Open-Vocabulary Gaussian-based Collaborative 3D Scene UnderstandingOm Shivam Verma, Shaya Farahmand, Lingjun Zhao +1cs.CV2026-10-20
#323Predictive Latents for Autoregressive Language Models: Possibility, Gauge, and ObstructionYuzhou Hongcs.CV2026-10-20
#324OverSeer: Multi-Agent World Models Beyond What Agents SeeRunjia Li, Kam Woh Ng, Minghao Chen +6cs.CV2026-10-20
#325Continual Concept Personalization in Diffusion Models via Residual-Space AdaptationYuzhi Liu, Enis Simsar, Giulia Lanzillotta +1cs.CV2026-10-20
#326Can a Display Be Used for Rapid LiDAR-Camera Extrinsic Calibration?Zuhao Zou, Xiangcheng Hu, Jianhao Jiao +1cs.CV2026-10-20
#327WildMAE: Structure-Aware Masked Autoencoding for Wildlife Image ReconstructionYicheng Zhang, Yujie Jin, Ke Zhang +1cs.CV2026-10-20
#328Learning the 4D World through Point Trajectory ForecastingByungwoo Jeon, Sunghwan Hong, Dohyeon Kim +10cs.CV2026-10-20
#329Neural Implicit Energy Optimization for LiDAR MappingHrishikesh Viswanath, Md Ashiqur Rahman, Chi Lin +2cs.CV2026-10-20
#330KoalaGS: Complexity-Aware Continuous Level of Detail for Gaussian SplattingRadu Beche, Raoul de Charettecs.CV2026-10-20
#331MindView: Benchmarking Generative Multi-View Spatial IntelligenceYanbo Wang, Siqi Luo, Siyu Zhang +9cs.CV2026-10-20
#332PsycheMME: A Psychology-Informed Benchmark for Social Understanding and Interaction in VideosHeran Hu, Yuhang Dong, Zhucun Xue +3cs.CV2026-10-20
#333SolarRenderer: Few-Step Generative Reference RenderingGuian Fang, Shengju Qian, Dongyue Lu +6cs.CV2026-10-20
#334AEON: Unifying Video and 3D World ModelsWeiqi Zhang, Wenyuan Zhang, Yu-Shen Liu +1cs.CV2026-10-20
#335Joints, Camera, Action! Co-Generating 3D Motion and Video for Arbitrary RigsNoam Rotstein, Yoad Tewel, Chen Tessler +5cs.CV2026-10-20
#336Different Defects, Different Effects: A Controlled Audit of Face Recognition Training DataAna Dias, João Ribeiro Pinto, Hugo Proença +1cs.CV2026-10-20
#337Complexity-Aware Surgical Video Reasoning Segmentation with Digital Twin and Context MemoryYiqing Shen, Mathias Unberathcs.CV2026-10-20
#338JUICE: Unified Multimodal Modeling in Pretrained Representation SpacesJiahan Li, Huangyuan Su, Shengbang Tong +9cs.CV2026-10-20
#339SAIL: A Learnable Generalisation of Spatial Autocorrelation over Graph-Structured DataPiotr Keller, Fayyaz Minhascs.CV2026-10-20
#340Register Anything Model for Generalizable and Robust Point Cloud RegistrationZheng Qin, Junhua Xi, Yan Huang +5cs.CV2026-10-20
#341WorldStream: Streaming Interactive 3D Worlds with Hierarchical Planning and Persistent StateXiaoxiao Ma, Weiyang Jin, Yanwen Ma +11cs.CV2026-10-20
#342HorizonComposer: Spatiotemporally Consistent Driving Video Editing with Enriched Traffic SemanticsMauricio Soroco, Yuqiu Liu, Zaid Tasneem +5cs.CV2026-10-20
#343Conditional Imaging for Privacy-Preserving Visual SensingHengyu Lian, Debabrata Mandal, Anzhou Wen +3cs.CV2026-10-20
#344Beyond Correct Answers: How Compositional Cues Shape Visual JudgmentsXiaoyu Ma, Zheyuan Zhang, Kaiwen Shi +1cs.CV2026-10-20
#345Depth-guided Geometric Adaptation for Few-shot Image ClassificationZhiqi Miao, Estefanía Talavera, Weichuan Zhang +1cs.CV2026-10-20
#346DualHeads: Reward-tilted few-step diffusion made simpleYuanzhi Zhu, Eleftherios Tsonis, Simo Alami Chehboune +3cs.CV2026-10-20
#347Policy-Mask: Budget-Aware Adaptation of Diffusion Features to Discriminative TasksIvan Listopadov, Maksim Nakhodnov, Aibek Alanovcs.CV2026-10-20
#348Data-Driven Glyph Positioning for Handwritten Music SynthesisElona Shatri, Jiří Mayer, Jan Hajičcs.CV2026-10-20
#349MINER: Modeling Inter- and Intra-Person Variance for ReidentificationOron Nir, Eliyahu Strugo, Ariel Shamircs.CV2026-10-20
#350Pair-Free Coarse-to-Real Video Generation via Real-to-Coarse Image SupervisionGonzalo Gómez-Nogales, Daohan Lu, Peiye Zhuang +2cs.CV2026-10-20
#351RoPT: Robust 6DoF Object Pose Tracking in VideoYongqing Liang, Yuzhong Chen, Sihang Li +7cs.CV2026-10-20
#352TEMPL: A Resource-Efficient and Transparent Model-Free Framework for Pseudo-Label Generation in Material CT ScansAshiqur Rahman, Venkata Devesh Reddy Seethi, Austin Yunker +2cs.CV2026-10-20
#353MedBOE: Optimization-Based Estimation of Complete Patient Body Models from Whole-Body Medical ImagingHoijoon Jung, Yuhao Wei, Mingxiao Tu +3cs.CV2026-10-20
#354Local Inference of LLMs on Long Contexts: A Data Systems PerspectiveMattias Dürrmeier, Alberto Lernercs.DB2026-10-20
#355GPU-Accelerated Construction of the Gabriel Graph: Parallelization Strategies and Applications to Large-Margin Classification and Graph-Based ClusteringDiego Sanches Nere dos Santos, Luiz Carlos Bambirra Torrescs.DC2026-10-20
#356GALA: Geometry-Aware Language Model for Controllable Object ArrangementChucheng Xiang, Runze Wang, Zhi Deng +10cs.GR2026-10-20
#357Fixed Sets and the Hardness of Computing Correlated EquilibriaIoannis Anagnostides, Constantinos Daskalakis, Gabriele Farina +3cs.GT2026-10-20
#358Baseline and Incremental: User, Item, and Request Debiasing in Instagram Feed RankingHsin-Chiang Chen, Hao Wang, Gedi Zhou +23cs.IR2026-10-20
#359Certified Adaptive List Decoding for Error-Correcting CodesJaeho Hwang, Byung-Sun Won, Uiwon Hwangcs.IT2026-10-20
#360From Common Information to Canonical Correlation Analysis and Beyond: Bridging Information Theory, Signal Processing, and Machine LearningParis A. Karakasis, Walid Saadcs.IT2026-10-20
#361MLIPS: Multi-Layer Indexer Pool SharingSamkit Jain, Sai Kishan Pampana, Shlok Agarwalcs.LG2026-10-20
#362Scaling Graph Reasoning in Language Models with Learnable Graph Positional EncodingsJavier Porras-Valenzuela, Arush Arora, Alejandro Ribeirocs.LG2026-10-20
#363Learning-Theoretic Foundation for General Coded Computing: The Adversarial SettingParsa Moradi, Hanzaleh Akbarinodehi, Mohammad Ali Maddah-Alics.LG2026-10-20
#364Using Set Learning to Improve Set-Valued Classifiers on Long-tailed DataKevin Kasa, Scott C. Lowe, Graham W. Taylorcs.LG2026-10-20
#365Decision Sufficiency of Learned Representation Interfaces for Safe Generative ControlJipeng Li, Yanning Shencs.LG2026-10-20
#366Projected Distillation: On Learning to Solve Hard Problems from Close, Correct TargetsShripad V. Deshmukh, Christian Bock, Kangrui Ruan +4cs.LG2026-10-20
#367Training-Free Continual Learning for Multimodal Forecasting via Prompt EvolutionLaurent Mombaerts, Jonathan Taws, Jacopo Gargano +4cs.LG2026-10-20
#368When Parameter Gradient Flows Close in Representation SpaceShengye Taocs.LG2026-10-20
#369Orthogonal Boundary Unlearning for Dual-Use Concepts in Large Language ModelsNiccolò Ronchettics.LG2026-10-20
#370Self-Evolving Agents through Privileged Retrospective DistillationYuhang Zhou, Yifan Wu, Bo Peng +5cs.LG2026-10-20
#371BEACON: Bridging Multimodal Semantics and Asynchronous Propagation for Cloud System Anomaly DetectionZhe Li, Tengxue Zhang, Yang Shu +4cs.LG2026-10-20
#372Timing-Aware and Interpretable Self-Attention for Event-Based Wearable Task Transition DetectionAnda Ouyang, Siyuan Chen, Julien Eppscs.LG2026-10-20
#373Lower Bounds for Smooth Nonconvex Zeroth-Order Optimization: The Price of Determinism under Low Curvature TraceYuxing Peng, Zhiqing Tang, Weijia Jiacs.LG2026-10-20
#374Can Native Safety Travel? Reusing Safety Pretraining Across Models via On-Policy DistillationBingqi Shang, Yang Zhang, Yiwei Chen +4cs.LG2026-10-20
#375AnchorRM: Parallel Intra-Batch State Reconstruction with Anchor-Based Residual Memory for Temporal Graph Neural NetworksHaroon Gharwi, Kai Shu, Yue Daics.LG2026-10-20
#376TRCM: Topology-Aware Route-Consistency Modeling for Robust Neural Vehicle RoutingPeiheng Jian, Zhenwei Wang, Tiehua Zhang +4cs.LG2026-10-20
#377Two Is Enough: Binary Classification Priors Suffice for Multi-Class In-Context Tabular PredictionZhixiong Cheng, Shiyuan Han, Jingjing Suo +1cs.LG2026-10-20
#378From POMDP Theory to Deep RL with Particle FiltersKevin Tan, Ziping Xucs.LG2026-10-20
#379Bridging Digital Deception and Physical Fidelity: A Spatio-Temporal Attack on Cognitive RadarsTongrun Xing, Yongjun Dai, Xuan Liao +4cs.LG2026-10-20
#380Auditing the Product, Not the Recursion: The Evaluation Evidence Behind Recursive Self-Improvement ClaimsZihan Chen, Di Zhu, Lei Nico Zhengcs.LG2026-10-20
#381Learning Inter-Graph Interactions Between Heterogeneous Substructures of Chemical SystemsGyoung S. Nacs.LG2026-10-20
#382From Outcomes to Steps: Reliable Success-Aware Critic Learning for Long-Horizon Language AgentsJiaxi Liu, Shixiong Kai, Zhentao Tang +4cs.LG2026-10-20
#383Ensemble-Aware Structural Encoding (EASE): Conditioning Protein Encoders on Peptide Conformational EnsemblesRuoyao Zhang, Hongxuan Li, Jie Peng +1cs.LG2026-10-20
#384BCT: Bayes-Consistent Tempering for Flow Language ModelsDaisuke Oba, Hiroki Furuta, Naoaki Okazakics.LG2026-10-20
#385Pairwise Learning Increases Data Efficiency in Deep Neural NetworksRobert Bain, Marjan Rashidi, Elizabeth Chrastilcs.LG2026-10-20
#386Neural Operator Splitting for Fluid Dynamics in Complex GeometryJianxiang Li, Xi Deng, Hong Chul Nam +1cs.LG2026-10-20
#387Hybrid Momentum Methods for Optimizing Deep Learning ModelsHaifeng Xu, Yijin Ren, Qi Deng +3cs.LG2026-10-20
#388Influence Is the Target-Response Jacobian Times ResidualsPaul Geertsema, Simon Geertsemacs.LG2026-10-20
#389Understanding Data Augmentation under Label NoiseHong Zheng, Fei Tengcs.LG2026-10-20
#390Multi-Objective Evolutionary Semi-Supervised Learning for Resource-Aware Smart City ClassificationFrancisco José Sedeño, Jamal Toutouhcs.LG2026-10-20
#391Privacy Accounting for Empirical DenoisersWilliam Cheng, Mijung Park, Dongjun Kimcs.LG2026-10-20
#392EEG-Based Classification of Hypnotic Susceptibility Using Two-Dimensional Convolutional Neural NetworksKrzysztof Wrobel, Grzegorz M. Wojcik, Filip Postepski +3cs.LG2026-10-20
#393Constant Step Sizes for Muon-Type Spectral Optimizers on Strongly Convex QuadraticsPratik Jawanpuria, Bhabatosh Garai, Bamdev Mishracs.LG2026-10-20
#394Detection of Memorization in Diffusion Models Through Thermodynamic SingularityIljung Kim, Kangwoo Park, Yung-Kyun Noh +1cs.LG2026-10-20
#395AC/DC on a Budget - Alternating Sparse PhasesRahul Nittala, Advait Gadhikar, Tom Jacobs +1cs.LG2026-10-20
#396Foundation-Style Pretraining for Scalable and Transferable Distributed PV ForecastingDayin Chen, Xiaodan Shi, Xin Xu +6cs.LG2026-10-20
#397Engram Memory Network: Brain-Inspired Prototype ExplanationsHyunjun Kim, Myoung Hoon Hacs.LG2026-10-20
#398How Much Do $\ell_1$ Attacks Need Concentrated Perturbations?Melika Shirian, Kianoosh Vadaei, Arshia Hemmatcs.LG2026-10-20
#399Foundations of the Scaling LawTianyu Zhao, Zhixiang Rencs.LG2026-10-20
#400SliMOO: Interpretable Multi-Objective Evolutionary Search for LLM Depth PruningGuanchen Li, Yixing Xu, Xuanwu Yin +2cs.LG2026-10-20
#401From Generic to Dedicated: A Novel Optimizer for Online Continual LearningYongyi Wu, Zheng Wang, Sen Lincs.LG2026-10-20
#402Interaction-Gated Time-Frequency Learning for Parameter-Efficient PPG-Based Heart Rate EstimationAnh Khoi Pham, Phat Lam, Thien Truong Nguyen Ly +1cs.LG2026-10-20
#403Elicitation or Expansion? Demystifying Gains from Agent Harness OptimizationYounghyun Kim, Wooseok Seo, Minseo Kim +6cs.LG2026-10-20
#404Physical-Variable-Informed Deep Learning for Robust Diagnosis in Industrial Fluid Transport SystemsYu Sha, Junqi Tao, Dixin Zhou +4cs.LG2026-10-20
#405The Shape of the DPO Hyperparameter Landscape: What to Measure, How It Moves with Scale, and When Not to Transfer ItHannan Mahadik, David Salinas, Jacek Golebiowski +1cs.LG2026-10-20
#406Near-Duplicate Image Selection Transfers Preferences in Vision-Language ModelsJaeyoung Kim, Eunseok Kim, Dongsuk Jang +1cs.LG2026-10-20
#407Unsupervised Head Network Personalization for Split Computing via Federated LearningYutaro Horikawa, Takayuki Nishiocs.LG2026-10-20
#408On Johnson-Lindenstrauss Transforms for Byzantine-Robust OptimizationAleksandr Shestakov, Vladimir Aletov, Aleksandr Beznosikovcs.LG2026-10-20
#409When Momentum Helps Polyak--Ruppert AveragingAlexandra Suvroikova, Darina Dvinskikh, Yuriy Dorn +1cs.LG2026-10-20
#410RANGER: Retrieval Agent for Navigating Graphs with Semantic Evaluation RewardsArtem Mikhaylov, Pavel Konoplev, Nikolay Efanov +2cs.LG2026-10-20
#411Reinforcement learning for hardware acceleration and system-level optimization on FPGA and integrated-circuit platforms: A surveyHamza Kheddarcs.LG2026-10-20
#412From RL Papers to Framework Code: Inclusion and Review in Seven Open-Source Training FrameworksTaiheng Pancs.LG2026-10-20
#413When Does Training on Synthetic Data Provably Work?Leroy Odunlami, Tobias Riedlinger, Hanno Gottschalkcs.LG2026-10-20
#414Poisoning-Based Backdoors Are Not CryptographicMasahiro Kanekocs.LG2026-10-20
#415Universal Online Convex Optimization With Delayed FeedbackHao Qiu, Andrew Jacobsen, Emmanuel Esposito +1cs.LG2026-10-20
#416MuPACE: Learning to Pace Muon for LoRA Fine-TuningJan Kobiolka, Christian Frey, Josif Grabockacs.LG2026-10-20
#417PULSE: Personalized Opportunistic Learning for Wearable DevicesMattia Giovanni Campana, Dariush Salami, Hüseyin Yiğitler +1cs.LG2026-10-20
#418From Complex Histories to Simple Predictors: Predictive Dimension in Dynamic Graph LearningHantong Feng, Duxin Chen, Wenwu Yucs.LG2026-10-20
#419Causal Discovery for Linear Models with Latent Confounding via Multi-domain Identifiable Representation LearningDanru Xu, Aapo Hyvärinen, Sara Magliacanecs.LG2026-10-20
#420Curriculum Learning for Generative Flexible DockingWenyin Zhou, Hossein Azizpourcs.LG2026-10-20
#421Scalable Stress-Constrained Topology Optimization: A Super-resolution and Simultaneous Approach Based on Machine LearningXiangyu Sun, Shirin Hosseinmardi, Ramin Bostanabadcs.LG2026-10-20
#422Coincidence-Maximizing Customer Clustering Using Smart Meter DataRamiro H. Gálvez, Gabriel Martos Venturini, Iván Mondrzakcs.LG2026-10-20
#423Adaptive Pullback: Reweighting Supervision at Penalty Jumps in On-Policy DistillationGuangyu Liu, Siyuan Gan, Shilong Zhou +3cs.LG2026-10-20
#424Reframing Object-Centric Reinforcement Learning: From Absolute to Relative RepresentationsCedric Derstroff, Jannis Blüml, Janosch Moos +4cs.LG2026-10-20
#425Parameter-Efficient Adaptation of Time Series Foundation Models for Electrical Load ForecastingAliullah, Julian Oelhaf, Edouard Fouché +4cs.LG2026-10-20
#426JAXbounce: A Continuous-Control Pong-Like Benchmark for Active Inference Beyond Low Dimensional EnvironmentsChaitanya Kaul, Markus Klar, Sebastian Stein +3cs.LG2026-10-20
#427TPO: Tri-level Distributionally Robust Learning for OOD Direct Preference OptimizationChengtao Jian, Kai Yangcs.LG2026-10-20
#428Learning Normal Coordinates on Riemannian Manifolds with Flow ChartsEdmond Cunninghamcs.LG2026-10-20
#429Recommending Bacterial Cultivation Conditions from 16S rRNAJuntang Wang, Hao Wu, Yihan Wang +3cs.LG2026-10-20
#430Manifold-Informed Neural Networks for Low-Label ECG Electrolyte InferenceJuntang Wang, Hao Wu, Yihan Wang +2cs.LG2026-10-20
#431Observation Assimilation Transformer: Probabilistic Weather Analysis from Sparse Station ObservationsChristian Donner, Michele Cattaneo, Maxim Samarin +4cs.LG2026-10-20
#432Identifying Dependent Components from Multi-domain Linear MixturesDanru Xu, Lauri Parkkonen, Sara Magliacane +1cs.LG2026-10-20
#433Characterizing Cross-Relay Generalization Failure in Machine Learning-Based Power System ProtectionNithin Pradeep Nadayil Kizhakkethil, Julian Oelhaf, Christian Bergler +2cs.LG2026-10-20
#434Beyond the Point Mass: Acceptance-Derived Weights and Distributional Losses for Speculative DecodingTianyu Wu, Zhuohan Wang, Jonathan Geuter +5cs.LG2026-10-20
#435Relative Representations Enable Portable White-Box Monitoring Across Language ModelsTim Bakker, Christos Louizoscs.LG2026-10-20
#436Don't Skip the Baseline: A Controlled Comparison of Dynamic Expert Skipping in MoEsJakob Steimle, Thomas Elsken, Daniel Ehrhardt +3cs.LG2026-10-20
#437Self-Credit: Credit Assignment for Long-Horizon Agentic RL via Intra-group RescalingFangcong Yin, Ming Yin, Tanvi Bhandarkar +7cs.LG2026-10-20
#438Rewards for Budget-Aware Multi-Turn Agents That Adapt to Arbitrary Test-Time ConstraintsTom A. Lamb, Adam Golinski, Eleonora Gualdoni +2cs.LG2026-10-20
#439Region-Specific EEG Classification of Hypnotic Susceptibility Using a Sliding-Window 2D CNN: A Subject-Independent EvaluationKrzysztof Wrobel, Grzegorz M. Wojcikcs.LG2026-10-20
#440SimHack: Predicting the onset of detectable reward hacking before RL trainingJunwei Deng, Alex Bie, Natalia Ponomarevacs.LG2026-10-20
#441Do Neural Models Prefer Their Submodels?Alvaro Ribot, Yulia Alexandr, Anna Seigalcs.LG2026-10-20
#442CNN-based classifier for subject-independent MBTI Extraversion/Introversion preference classification from short-time EEG signalsFilip Postepski, Grzegorz M. Wojcikcs.LG2026-10-20
#443LocaLeJEPA: Maximum Entropy Representations under Geometric PriorsKartik Tandon, Alessio Borgi, Pavel Snopov +8cs.LG2026-10-20
#444Geometry-Agnostic Data-Driven Discovery of Extreme ScenariosAngeline Hu, Ava K. Tse, Kaitlyn S. Yasumura +8cs.LG2026-10-20
#445STAR-XPC: Set Transformer for Estimating X-ray Transmission in Polymer CompositesCan Erer, H. Birkan Yilmaz, Nebahat Aralcs.LG2026-10-20
#446Model- and Layer-Level Closed-Loop Forecasting with SSM-Based Spiking Neural NetworksErik Stolt, Sanja Karilanova, Ayca Ozcelikkalecs.LG2026-10-20
#447Present but Hard to Read: Probing Latent Reasoning with Minimal PairsAur Shalev Merincs.LG2026-10-20
#448ECG for laboratory values:A comprehensive physiological and technical analysisWalentin Palanchukcs.LG2026-10-20
#449GraphCast-Mamba: Learning Non-Markovian Corrections for Weather ForecastingIlya Vilkoviskiy, Liang-Hong Mo, Suozhi Huang +1cs.LG2026-10-20
#450Binary Discrete Diffusion: Candidate-Set Diffusion for Logic and Planning TasksRodrigo Casado Noguerales, Dimitri von Rütte, Bernhard Schölkopf +2cs.LG2026-10-20
#451Discount Yourself: Self-inclusive Freshness-weighted Gossip for Decentralised Learning under Client OutagesQiyuan Wang, Ke Xiao, Christos Anagnostopouloscs.LG2026-10-20
#452Learning Computational Structure for Sample-Efficient PredictionHangyu Zhou, Constantine Dovrolis, Stephen Mussmanncs.LG2026-10-20
#453When Do LLMs Help with Feature Selection? A Systematic Empirical StudyFateme Memar, Dongjie Wang, Arvin Agahcs.LG2026-10-20
#454Convergence of stochastic gradient descent for learning linear neural networksGabin Maxime Nguegnang, Bubacarr Bah, Holger Rauhut +1cs.LG2026-10-20
#455Asymmetric Bidirectional Predictive Dynamics in Google Search and COVID-19 Time Series: A Multi-Horizon Forecast-Error AnalysisAndrei Velichko, Imen Mahmoudcs.LG2026-10-20
#456The Dynamics of Collapse and Recovery in Clustered Federated LearningPriyanka Sinha, Snigdhansu Chatterjeecs.LG2026-10-20
#457The Token-Energy Law of LLM Decode: Active Bytes and Realized Time Account for Joules per TokenChenxu Niu, Batuhan Sencer, Wei Zhang +1cs.LG2026-10-20
#458Continuous-Time Policy Gradient from Discrete Data: Convergence Analysis and Model-Free AlgorithmsMartin Hernandez, Xinyan Qing, Mo Zhou +1cs.LG2026-10-20
#459PaPi: Parallel Picard-Duhamel Integration for Fast Neuro-Spectral ArchitecturesArthur Bizzi, Márcio Marques, Kleyton Da Costa +4cs.LG2026-10-20
#460Turning TS2Vec into a Foundation Model for Time Series ClassificationVasilii Feofanov, Zhenghan Tai, Andrei Ermakov +1cs.LG2026-10-20
#461Big Claims, Small Margins: Do Reported GraphLLM Gains Survive Simple Baselines?Michal Podstawskics.LG2026-10-20
#462Efficient Edge-aware Attention Network for Graph GenerationVincent Jung, Alba Carballo-Castro, Yiming Qin +2cs.LG2026-10-20
#463Offline Apprenticeship Learning for Human-Centric EnvironmentsMd Mirajul Islamcs.LG2026-10-20
#464Planning under Noise with Neural OperatorsMichael Chen, Hong Chul Nam, Xi Deng +1cs.LG2026-10-20
#465ReAPO: Retry-Aware Policy Optimization for Efficient Exploration in LLM ReasoningNghi Dao, Calder Morton-Ferguson, Noah Golowich +1cs.LG2026-10-20
#466Motion Equivariant Convolutional LSTM: When Motion Becomes a Gauge SymmetryVahid Hosseinzadeh, T. Anderson Keller, Michael Puthawalacs.LG2026-10-20
#467Building a Nested LADDER for LLM Unstructured Post-Training PruningNicolás Mauricio Cuadrado Ávila, Ivo Gollini Navarrete, Martin Takáč +1cs.LG2026-10-20
#468Second Thoughts: Exploring and Planning through Comparative Imagination in World ModelsHieu Tran, Hong Yucs.LG2026-10-20
#469Extreme Low-State Quantized Transformer for Electricity-Load ForecastingMuhammad Sabbir Alam, Harindra Sandun Mavikumbure, Victor Cobilean +2cs.LG2026-10-20
#470Measure First, Then Allocate: Calibrated Rollout Budgets for MCP Agents in Reinforcement LearningHieu Tran, Zonghai Yao, Sunjae Kwon +1cs.LG2026-10-20
#471ArcFlow: Training Flow Policies for Multiple Solver BudgetsHieu Tran, Hong Yucs.LG2026-10-20
#472CALLIOPE: Private Insights into AI Use, Without EmbeddingsEdith Cohen, Vadym Doroshenko, Badih Ghazi +11cs.LG2026-10-20
#473An Explicit Feedback Contract for Iterative ML-Agent HarnessesKehui Yao, Chuanbo Hu, Jiao Chen +8cs.LG2026-10-20
#474Towards Realistic Models of Change: A Causal Perspective on Decision-Making and Dynamical SystemsIsacco Berettacs.LG2026-10-20
#475A Mechanistic Study of Automated Failure Attribution in LLM-based Agentic SystemsWendy Zheng, Liang Wu, Yinhan He +3cs.LG2026-10-20
#476When Do Gaussian Priors Fail? A Latent Geometry Investigation of RL Fine-TuningWang Rucs.LG2026-10-20
#477A General Topological Symmetry Index for Critical Orbits In Neural Network Loss LandscapesJingzhou Liucs.LG2026-10-20
#478How Much Gradient Does Truncated Backprop Lose in Looped Transformers?Aur Shalev Merincs.LG2026-10-20
#479LEAN: Loss-Engineered Modulation of the Model Weight-Sensitivity Distribution for Efficient, Error-Tolerant Neural NetworksHabibur Rahaman, Swarup Bhuniacs.LG2026-10-20
#480Actually, All Learnable Distribution Classes Are Privately LearnableMohammad Afzali, Hassan Ashtiani, Alex Bie +4cs.LG2026-10-20
#481RL-IF: Tracking Non-local Training Data Influence for Online Reinforcement LearningShixuan Liu, Cheng Tang, Yuzheng Hu +3cs.LG2026-10-20
#482Combating Catastrophic Forgetting in Continual Domain Adaptation via Knowledge RecastingZijie Liu, Zhen Tan, Charles Fleming +1cs.LG2026-10-20
#483Minimax-Optimal Predictive Flow Matching under Distribution DriftAadithya Srikanth, Vaneet Aggarwalcs.LG2026-10-20
#484A Model-Free Continuous-Time RL Algorithm from Discrete-Time Off-Policy Data with End-to-End GuaranteesChaorui Yao, Yuming Paul Zhang, Lin Yang +1cs.LG2026-10-20
#485Query Feedback and Teaching for Stable and Certifiable Language GenerationFarnam Mansouri, Alireza F. Pour, Grigoris Velegkas +1cs.LG2026-10-20
#486The Data Differentiator Framework (DDF): Quantifying Marginal Data Value with Information-Theoretic and Game-Theoretic Measures in an Agentic Evaluation Pipeline (SDSAE)Sukesh Kumar, Dilip Singhcs.LG2026-10-20
#487Auditing Conformal Prediction for Language Models Under Inference-Time Model ShiftAchref Doula, Max Mühlhäusercs.LG2026-10-20
#488Multi-Objective Protein Optimization via Modular Diffusion SteeringMeir Roketlishvili, Felix Huber, Wenda Chu +2cs.LG2026-10-20
#489Is 2:4 Sparsity Still Worth It? Semi-Structured Sparsity versus Quantization in LLM InferenceXiuyi Qincs.LG2026-10-20
#490Online Open-World Wafer Defect Discovery using Hyperdimensional ComputingQuanling Zhao, Ava Emami, Tsuyoshi Idé +4cs.LG2026-10-20
#491Transformers as Generic Deep Neural Networks: Exact Compilation, the Cost of Removing Activation-Activation Products, and Multi-Agent Attention ClusteringSergey Salishev, Zeev Volkovich, Oleg Granichincs.LG2026-10-20
#492Unit-Aware Differentially Private Quantum Machine Learning for Clinical and Wearable Health DataMd Khalid Syfullah, Alvi Ataur Khalilcs.LG2026-10-20
#493From Weather to Enhanced Weathering: Weather Foundation Models for Carbon Dioxide Removal at Operational ScaleSasankh Munukutla, Felipe Oviedo, Danrong Zhang +2cs.LG2026-10-20
#494How Does Orthogonalization Adapt to the Neural Network Hessian Structure? A Gradient Self Outer-Product Analysis at InitializationShenyang Deng, Garvit Goyal, Tianyu Pang +2cs.LG2026-10-20
#495SSMCGM-Stream: A Streaming State-Space Model for Personalized Diabetes ManagementShakson Isaac, Chirag Patelcs.LG2026-10-20
#496Attention-based Classification for Indirect Prompt InjectionAmelia Kawasaki, Stefan Leecs.LG2026-10-20
#497Doob-Based Generative Policy OptimizationMaojiang Su, Qijie Zhu, Yu Xiao +4cs.LG2026-10-20
#498Rethinking Time Series Tokenization from a Frequency PerspectiveZelong Tian, Ming Jin, Bo Du +1cs.LG2026-10-20
#499FlashNext-RL: A System Optimization Study for Long-Horizon Agentic RL of Qwen3.8-Flash-NextZhewei Yao, Yuxiong Hecs.LG2026-10-20
#500S$^2$-MAS: A Society-Scale Multi-Agent Simulation Framework with 500 Million Household Persona AgentsYang Li, Di Wan, Yike Wang +12cs.MA2026-10-20
#501Local Work, Global Progress: A Convergence Theory of AI Agent CollaborationIvan Ilin, Peter Richtárikcs.MA2026-10-20
#502JaxMARL-BC: Multi-Agent Reinforcement Learning for Macroeconomic Modelling, in SecondsDaniele Montagnani, Andrea Coletta, Antonietta Mira +1cs.MA2026-10-20
#503Agent AI Zarządzający Siecią Open RAN Zorientowana na UżytkownikaMarcin Hoffmanncs.NI2026-10-20
#504Sensitivity-Orthogonal Residual Learning for Adaptive Sideslip and Cornering Stiffness EstimationKyoungtae Ji, Dongyeol Won, Kyoungseok Hancs.RO2026-10-20
#505A Head Camera Is (Almost) All You Need: An Electronics-Free UMI Glove Labelled and Observed by One Moving CameraYosub Shin, Yuan Liu, Igor Molybogcs.RO2026-10-20
#506PLaCA: Learning Patch-Level Future Latent Change for Action GenerationZhan Yi, Yuchen Wang, Chao Li +2cs.RO2026-10-20
#507CovNav: Conformal Prediction-Guided Adaptive Inference for Object Goal NavigationPengying Wu, Zhejia Wen, Kang Ding +5cs.RO2026-10-20
#508Enumeration-Guided Training of Neural Hamilton-Jacobi Safety CertificatesMihaela-Larisa Clement, Tosca Pierro, Ezio Bartocci +1cs.RO2026-10-20
#509Learning Tactile-Aware Hand Representations from Human Hand-Object Interaction DataYeonguk Yu, Jaehong Kim, Byungok Hancs.RO2026-10-20
#510De-Diffusing WAMs: Action-Sufficient Direct Prediction for Robot ControlShaoyi Zheng, Zhongtao Jiang, Yue Peng +4cs.RO2026-10-20
#511Perceives but Doesn't Brake: A Perception-Action Binding Gap in Reasoning Driving VLAsMatteo Cercola, Katie Z Luo, Simone Formentin +1cs.RO2026-10-20
#512CAPSafe: A Benchmark for Contextual Action and Plan Safety Reasoning in Embodied AgentsYoumna Farag, Svetlana Stoyanchev, Simon Keizer +2cs.RO2026-10-20
#513Plausible Future, Wrong Choice: Steering World-Action Models toward Intended FutureZhuohao Li, Jiawei He, Yuxuan Yan +11cs.RO2026-10-20
#514GPT-6-Astra Understands Touch and Outperform Vision--Tactile--Language--Action ModelsZiyong Wang, Yupei Lin, Runxuan Huang +3cs.RO2026-10-20
#515VLM-Guided Contact Retargeting and Generative Partner Modeling for Humanoid-Human InteractionYuto Shibata, Kotaro Amaya, Kashu Yamazaki +4cs.RO2026-10-20
#516SceneRig: An Agentic System for Simulation-Ready 3D Scene Reconstruction from Single ImagesRundong Luo, Yunong Liu, Di Cao +4cs.RO2026-10-20
#517Industrial ReMEmbR: Scaling Spatiotemporal Memory to Robot FleetsJad Yammine, Malek Wahidi, Abrar Anwar +3cs.RO2026-10-20
#518UniWALM: Unified World Action Language Model for Embodied Robot ControlRahul Sajnani, Diego Romeres, Mingyuan Zhang +9cs.RO2026-10-20
#519Learning Adaptable Dexterous Skills via Hybrid Dexterous MimickingYuxuan Kuang, Jiashun Wang, Yixuan Sun +5cs.RO2026-10-20
#520Real2Sem2Real: 3D Semantic Augmentations for Robot Learning from a Single Human RGB DemonstrationMatthew Strong, Ankush K. Dhawan, Julien Poffet +3cs.RO2026-10-20
#521inr2action: Encoding Robot Episodes as Neural Implicit Representations for Recall and ActionLeann Alhashishi, Christos Margadji, Sebastian William Pattinsoncs.RO2026-10-20
#522One Policy, Many Styles: Where to Aggregate Preferences for Steerable Humanoid Control?Ziqian Huang, Yuzhuo Chen, Shimin Zhang +3cs.RO2026-10-20
#523HyperDrone: Simulation-to-Reality Transfer at Millions of Frames per SecondJonas Eschmann, Giuseppe Loiannocs.RO2026-10-20
#524SLoSa: Small, Low-Power, and Safe Foundation Models for Robotic Task PlanningWeizhe Xu, Jialiang Fan, Essien Taylor +3cs.RO2026-10-20
#525Racer: Hunting GPU Kernel Bugs with Symbolic Equivalence CheckingTuan Truong Vu, Cheng Tancs.SC2026-10-20
#526MiCLA: Mixture-to-Constituent Latent Alignment for Polyphonic Audio Representation LearningKohei Yamamoto, Kosuke Okusacs.SD2026-10-20
#527PhonoBridge: Error-Aware Phoneme-Mediated EMG-to-Text ReconstructionWen Qiu, Jiacheng Zhang, Xuanda Chen +2cs.SD2026-10-20
#528SLM-SS: Token-Based Speech Separation with Speech Language ModelsChenda Li, Tianhua Li, Yiming Chen +4cs.SD2026-10-20
#529APRIL: Ambiguity-Aware Expert Routing for Respiratory Sound Domain-Incremental LearningXinhong Li, Weiping Tucs.SD2026-10-20
#530Slots Are Not Speakers: Training-Free Speaker Linking for Frozen Streaming DiarizersAditya Srinivas Menon, Kumarmanas Nethil, Kavya Manoharcs.SD2026-10-20
#531Uncovering Audio-Text Alignment in Large Audio-Language Models through Cross-Modal Concept NeuronsTzu-Quan Lin, Chih-Kai Yang, Yi-Cheng Lin +2cs.SD2026-10-20
#532Qwen-Audio-3.1-ASR Technical ReportChuanmeng Bian, Daren Chen, Peixin Chen +45cs.SD2026-10-20
#533StyleStream 2.0: Fast and Controllable Streaming Voice Style ConversionYisi Liu, Nicholas Lee, Gopala K. Anumanchipallics.SD2026-10-20
#534RELAY: Scaling Historical Build Restoration through Rule Reuse and Agentic RepairOlivier Nourry, Yoshiki Higocs.SE2026-10-20
#535RAG-NIMBF: A Non-Invasive, Modular Benchmarking Framework for Automated RAG Configuration AnalysisNiclas Hart, Nicolas Weegercs.SE2026-10-20
#536From Tokens to Files: Multi-Granularity Detection and Localization of AI-Involved CodeYue Xu, Xiyang Wang, Hui Liu +1cs.SE2026-10-20
#537Hallucinations of Large Language Models in Cross-Language Code Translation: Phenomena and MitigationYali Du, Yunji Zhang, Ming Lics.SE2026-10-20
#538From Code Generator to Engineering Companion: A Plant-aware Agent for PLC ProgrammingJoschka Kersting, Gesa Benndorfcs.SE2026-10-20
#539Foreword: Pre-Generation Prediction and Characterisation of LLM Test Failures using the Jacobian LensSomin Kim, Robert Feldt, Shin Yoocs.SE2026-10-20
#540ExeBench-FHD: Addressing Fidelity Issues in Decompiler EvaluationAkarsh Ashok, Dinil Mon Divakaran, Vivek Balachandrancs.SE2026-10-20
#541Agentic Verified Optimization of Real-World SoftwareZhe Ye, Udaya Ghai, Zhizhen Qin +2cs.SE2026-10-20
#542Where Should a Stuck Agent Spend Its Next Tokens? Causal Attribution of Inference-Time ResourcesSaiyue Lyu, Jerrold Huang, Yunbei Zhang +4cs.SE2026-10-20
#543Occupational Uniqueness and Wage GrowthR. Vestrelli, A. Fronzetti Colladonecon.GN2026-10-20
#544VISH-ASR: Viterbi-Guided Selection of Hotwords for Speech-LLM Contextual ASRXiaoyu Gu, Yu Xi, Chencheng Wang +4eess.AS2026-10-20
#545CAPS: Clinically-Verifiable Anatomy-Prioritized Synthesis for Missing MRI Imputation in Brain Tumor SegmentationCecilia Diana-Albelda, Arthur Longuefosse, Mario Rubén Paz Campos +2eess.IV2026-10-20
#546Stabilizing Filters for Graph Signal GenerationMartin Schmidt, Gonzalo Mateoseess.SP2026-10-20
#547Anytime-Valid Runtime Monitoring of Learned Barrier CertificatesZhipeng Cao, Taoran Wu, Weiru Cui +2eess.SY2026-10-20
#548Neural Closed-Loop Identification of Nonlinear Systems with Stability and Generalization GuaranteesLaura Meroi, Mahrokh G. Boroujeni, Leonardo Massai +1eess.SY2026-10-20
#549Brittle by Design? Multi-Scenario Reinforcement Learning for Robust Mission Coordination in Systems of Systemsİbrahim Oğuz Çetinkaya, Sajad Khodadadian, Taylan Topcueess.SY2026-10-20
#550Soliton Profiles in 1D: Enhanced Neural-Network Solvers and Constrained Deep Ritz MethodsChandler Haight, Alex D Rodriguez, Svetlana Roudenkomath.NA2026-10-20
#551Weak-$L^α$ Noise, Strong Guarantees: Gradient Clipping under Affine Heavy TailsAlyona Nekrasova, Makar Sidorov, Savelii Chezhegov +4math.OC2026-10-20
#552Variance Reduction with Delayed Feedback for Non-Convex OptimizationWei Jiang, Dingzhi Yu, Zechao Limath.OC2026-10-20
#553Self-Supervised Tuning of Low-Fidelity Optimization Models via High-Fidelity FeedbackGonzalo E. Constante-Flores, André H. Quisaguano-Paredes, Asha Ramanujam +2math.OC2026-10-20
#554TerraNostra-Bench: Benchmarking Spatial Downscaling and Temporal Rollout for Global 1-km Land-Use ReconstructionAmirpasha Mozaffari, Marina Castaño, Stefano Materia +6physics.ao-ph2026-10-20
#555Tropical Cyclone Attributes in Sparse Autoencoder Features of an AI Weather ModelJiapei Liu, Ruidong Li, Ting Sun +1physics.ao-ph2026-10-20
#556HypoNet Nankai PS: rapid hypocenter determination for the Nankai Trough using physics-informed neural networks with three-dimensional P- and S-wave velocity modelsRyoichiro Agata, Ayako Nakanishi, Dan Bassett +3physics.geo-ph2026-10-20
#557Spatially Informed and Direction Sensitive Representation Learning for Spatial TranscriptomicsAzim Dehghani Amirabad, Ali Khodabandeh Yalabadi, Artem Moskalev +4q-bio.QM2026-10-20
#558Understanding the Inner Workings of a State-Space Foundation Model for Limit Order BooksValentin Mohl, Alexandre Bismuth, Aramis Marti-Shahandeh +6q-fin.TR2026-10-20
#559Can Quantum Layers offer Performance and Security Advantages in Vision-Language Models?Md Khalid Syfullah, Alvi Ataur Khalilquant-ph2026-10-20
#560Quantifying the Threat: A Bayesian Probabilistic Framework for Heavy Metal Health Risks among Children in the Densu Basin, GhanaT. Ansah-Narh, G. Y. Afrifa, J. B. Tandoh +4stat.AP2026-10-20
#561Backtracking Direct, Indirect and Total EffectsJose M. Peñastat.ME2026-10-20
#562Beyond Scalar Leaderboards: Adaptive Sampling for Pareto Frontier Identification in Multi-Objective LLM ArenasLiang Twist Shan, Jiahao Ai, Zhimei Renstat.ML2026-10-20
#563What Moved the Alarm Score? Causal Attribution with Exact Computation and Scarce-Incident EstimationMasaaki Takada, Ryusei Shingakistat.ML2026-10-20
#564Bayesian Neural Networks via Dirichlet Process Priors on the Data-Generating Distribution for Randomized Value Functions in Deep Reinforcement LearningSumit Vashishthastat.ML2026-10-20
#565Ask to Learn: Query-Based Collaborative Reinforcement LearningKaicheng Zhang, Hongqian Niu, Laixi Shi +3stat.ML2026-10-20
#566Annealed correlation and quenched noise sensitivity in biased deep neural networksJohan Jonassonstat.ML2026-10-20
#567Near-Optimal Regret Bounds for UCB-Style Gaussian Process Bandits via Data ThinningShion Takeno, Shogo Iwazaki, Ichiro Takeuchistat.ML2026-10-20
#568Predicting silent failures of learned inference under restricted access: what measurement physics and prior information explainMario Giannistat.ML2026-10-20
#569Geometry-Aware Block Selection for Sparse Variational Gaussian ProcessesMatteo Hoxhastat.ML2026-10-20
#570Debiased Prior-Data Fitted Networks for Amortized Bayesian Semi-Parametric InferenceValentyn Melnychuk, Emil Javurek, Stefan Feuerriegelstat.ML2026-10-20
#571Confessions of a Masked MDPSebastian Reboul, Lorenzo Croissant, Hélène Halconruystat.ML2026-10-20
#572Borrowing Strength Across Stores: Transfer Learning for Choice-Based Revenue ManagementRecep Yusuf Bekci, Stefanus Jasin, Joline Uichancostat.ML2026-10-20
#573A Reverse-Gold Theorem: Positive-Data Identification by Substrate-Bounded Contrastive LearnersRakesh Senguptastat.ML2026-10-20
#574Depth Separation for Neural Networks under Gaussian MeasureCynthia Bortolotto, Francisco Ganacim, Roberto I. Oliveirastat.ML2026-10-20
#575Is In-Context Reinforcement Learning A Posterior Sampler? An Empirical StudyWeiqin Chen, Xinlong Du, Gesualdo Scutari +1stat.ML2026-10-20

latest · trends · arXiv announcement batches follow US Eastern weekdays