PaperScope
LIVE · 2026-09-15 05:40 UTC

New Papers · 2026-09-14 339 submissions

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

#TitleAuthorsCatDate
1Neural-Network Solutions to Real-Space Charge Density and GeneralizationYuxuan Zeng, Taoyuze Lv, Zhicheng Zhongcond-mat.mtrl-sci2026-09-14
2Bridging Control, Inference, Transport, and Thermodynamics: From Theory to Applications in LearningEmmy Blumenthal, Nikolas Claussen, Benjamin Eysenbach +4cond-mat.stat-mech2026-09-14
3Domain Generalization for Smartphone-Based Human Activity Recognition: A Systematic Analysis of Components and InteractionsOtávio Oliveira Napoli, Edson Borincs.AI2026-09-14
#4GGUF-Metadata Prediction of Single-Sequence llama.cpp Throughput Across Three SystemsXinyu Qiu, Chuhong Xu, Bo Su +3cs.AI2026-09-14
#5Externalizing Requirement-to-Repair Artifacts as Observable Traces for LLM-Based Program RepairZewen Tao, Shin-nosuke Ishikawacs.AI2026-09-14
#6Geometric Flow enhanced Graph CoarseningChaoqun Fei, Guoxuan Li, Tinglve Zhou +2cs.AI2026-09-14
#7Towards a knowledge-enhanced single-cell foundation modelHanqing Zhang, Jie Bao, Mei Ma +7cs.AI2026-09-14
#8MemRiskBench: Trace-Aware Risk-Preserving Evaluation for Long-Horizon LLM AgentsJianhua Jiang, Dongbo Yuan, Weihua Lics.AI2026-09-14
#9Converting Sequenced Fuzzy Cognitive Maps to Causal Virtual Worlds with Large Video GeneratorsAkash Kumar Panda, Olaoluwa Adigun, Bart Koskocs.AI2026-09-14
#10Shallow Beliefs: Synthetic document finetuning does not inoculate against emergent misalignment from reward hackingArun Jose, Julian Stastnycs.AI2026-09-14
#11CoMem: Collective-Individual Memory Synergy for Evolutionary Multi-Agent SystemsChengxin Yu, Zhaoxin Fan, Faguo Wu +3cs.AI2026-09-14
#12Semantic-TVM: Structure-Preserving Trustworthy Virtual Memory for Memory-Augmented and Tool-Using AgentsYu Li, Qikun Cai, Tao Huang +1cs.AI2026-09-14
#13Overflip: Repetition-Induced Label Flips in Guardrail ModelsXu He, Chih-Hsuan Lin, Hung-Mao Chen +3cs.AI2026-09-14
#14Four Ledgers, Not One Score: Responsible Communication of LLM-Judge Calibration in Biomedical MLSidi Chang, Peiying Zhucs.AI2026-09-14
#15Horizon-specific Expert Fusion for Photovoltaic Power ForecastingXu Yuqing, Zhou Liguo, Sun Ze +2cs.AI2026-09-14
#16The average-farmer illusion in language-model simulations of agricultural decisionsZhanliang Zhu, Ziwei Li, Yuchen Liu +5cs.AI2026-09-14
#17BusMA: A Bus Communication Substrate for Multi-Agent SystemsYanwen Peng, Delvin Ce Zhang, Xi Wang +1cs.AI2026-09-14
#18Enabling Creative Exploration for Vibe Design AgentsYifan Zhang, Nghi D. Q. Bui, Georgios Evangelopoulos +1cs.AI2026-09-14
#19ER-EDF: A Psychology-Grounded Emotion Regulation Framework for Speech Empathetic Dialogue Generation in Large Audio-Language ModelsHongyu Jin, Wenda Zhang, Runqiu Fei +3cs.AI2026-09-14
#20OpenAI4S: Code as Action, Science as SessionsGongbo Zhang, Hao Li, Yu Wang +15cs.AI2026-09-14
#21Medical Knowledge Simplification for Patients in the Era of LLMs: A Case Study on DiabetesPallika Kafle, Yipeng Zhou, Guanfeng Liu +2cs.AI2026-09-14
#22HazardAuditor: From Executable Threats to Safer Computer-Use AgentsYunhao Feng, Ruixiao Lin, Ming Wen +5cs.AI2026-09-14
#23T-LoopFormer: Token-Level Elastic-Depth Looped Transformers for Latent Reasoning With Dynamic RoutingMingqian Yu, Wenpeng Zhang, Peilin Zhaocs.AI2026-09-14
#24STHMoE: Hypergraph-Enhanced Heterogeneous Dependency Coordination for LLM-Based Urban Traffic Data ForecastingJiawen Chen, Qi Shao, Yongjian Chang +3cs.AI2026-09-14
#25VisInteract: Towards Dynamic Interactive Text-to-Visualization under Imperfect QueriesWenxin Xu, Jinwei Lu, Hwanhee Kim +4cs.AI2026-09-14
#26Issue Bias in Generative AI Writing Assistance: Political Issues and LLMs in the Swedish 2026 ElectionBastiaan Bruinsma, Annika Fredén, Paul Röttger +2cs.AI2026-09-14
#27From Ideas to Actions: A Public-Data Decision-Support Toolchain Across the Venture LifecycleLei Qucs.AI2026-09-14
#28CWM: Controllable White-Box Meta-Prompting for Adaptive Retrieval-Augmented Generation and Reasoning AbilityKeuntae Kim, Eunhye Jeong, Yong Suk Choics.AI2026-09-14
#29Empirical Evaluation of Open-Source Large Language Models for Retrieval-Augmented Generation in ESG DomainMotaz Saad, Anna Borrelli, Ivan Gentile +3cs.AI2026-09-14
#30ProIQA: A Process-Based Framework for Fine-Grained Math Item Quality AssessmentJunkai Tong, Mingjia Li, Haoran Chen +4cs.AI2026-09-14
#31Why LLM Agents Collapse Without Oversight: The Enforcement Gap as the Mechanism Behind Emergence World FailuresYuhang Wangcs.AI2026-09-14
#32Reason What Matters: Retrieval-Grounded Reasoning for Universal Multimodal EmbeddingsMingzhou Jiang, Peixi Wu, Hang Cheng +7cs.AI2026-09-14
#33Evaluation Metrics for Safe Reinforcement LearningLindsay Spoor, Aske Plaat, Thomas Moerlandcs.AI2026-09-14
#34Parameter-Efficient Adaptation of Pretrained Language Models for Time-Series ForecastingTamanna Kumavat, Georg Brunner, Kyriakos Flouriscs.AI2026-09-14
#35MAPS: Memory-Aware Predictive Scheduling Framework for Large Language Model ServingTiancheng Zhang, Yulin Chen, Yunfeng Zhao +3cs.AI2026-09-14
#36RSIAgent: Autonomous Exploration for Recursive Self-improvement in New EnvironmentsSibo Zhu, Shicheng Fan, Xinyue Wang +3cs.AI2026-09-14
#37SkillLift: Learning Dense Rubrics from Sparse Oracles for Efficient Skill EvolutionHaoxiang Kang, Ming Wencs.AI2026-09-14
#38When Tool Calls Succeed but Workflows Fail: Anomalies at the Agent-Tool BoundaryArtem Trofimov, Boris Novikovcs.AI2026-09-14
#39Who Teaches Which Token? Verifier-Gated Multi-Expert On-Policy Distillation for Scientific ReasoningXun Xu, Zaixi Zhangcs.AI2026-09-14
#40Can AI systems have free will?Christian Listcs.AI2026-09-14
#41Empirical Evaluation of Task-Based Permission Scoping Architecture for AI AgentsHalil Burak Noyancs.AI2026-09-14
#42HISPO: Hierarchical Importance-Sampling Policy Optimization with Entropy-Derived SegmentsQuoc-Vinh Lai-Dang, Hyo-Sang Shincs.AI2026-09-14
#43The Troy Moment of AI: Why SomeWill Cheat and SomeWill Follow?Ivy Zhangcs.AI2026-09-14
#44Beyond Safe Answers: Segment-Aware Listwise Alignment for Reasoning Safety in Large Reasoning ModelsJungMin Yun, Junehyoung Kwon, Hayeong Ryu +3cs.AI2026-09-14
#45Option-Aware Retrieval and Task-Specific VLM Adaptation for Medical VQATristan Kirscher, Niklas C. Koser, Soren Pirkcs.AI2026-09-14
#46GRIN+: Towards Fast Yet Effective Machine Unlearning for Imbalanced Medical DataMinghui Huang, Junxiao Wangcs.AI2026-09-14
#47Diversified and Perceptible Counterfactual Examples Leveraging Expert KnowledgeAkram Bensalem, Fahima Djelil, Marie-Jeanne Lesot +1cs.AI2026-09-14
#48Potential of Artificial Intelligence Algorithms for Identification of Relevant Diagnostic and Prognostic Biomarkers of Early-Stage Liver CancerAli Bou Nassif, Darko Castven, Manar Abu Talib +4cs.AI2026-09-14
#49EEG-Xplain: Decoding Neural Black-Boxes of EEG Foundation ModelsHansong Ma, Junxiao Wangcs.AI2026-09-14
#50NoteVQA: Benchmarking VLMs on Real-Life Questions from Human CommunitiesHaonan Jiang, Guojian Zhan, Jiancong Xie +6cs.AI2026-09-14
#51Beyond Accuracy: Robustness, Cost, and Governance Trade-offs for Vision-Language Models in Templated Document ExtractionKushal Patel, Pushkal Shrivastava, Mackenzie Lees +4cs.AI2026-09-14
#52New Conditions for Philosophers to Catch the Wave of Citizen Deliberation in the Age of Artificial Intelligence in advanceBernard Rebercs.AI2026-09-14
#53Predicting build orientation for SLM dental parts: a comparison of rotation representations and direct vector regressionFelix Schmalzel, Reimar Waitz, Moritz Kronberger +1cs.AI2026-09-14
#54Data storytelling meets interpretable machine learning: Decoding AI decisions for non-experts without revealing sensitive data and model detailsLemen Chao, Zixuan Yang, Anran Fang +2cs.AI2026-09-14
#55Are LLMs Good Financial User Simulators? A Preliminary StudyJiajie He, Jiangyuan Hong, Dongling Ni +2cs.AI2026-09-14
#56Design of a Deep Learning Credit Risk Early Warning System Integrating Multi-source Heterogeneous DataLiYang Wang, Zhen Zhong, Zhen Tian +2cs.AI2026-09-14
#57EvoOntology: A Self-Evolving Ontology Layer for Data AgentsMeiduo Chong, Shaolei Zhang, Ju Fan +1cs.AI2026-09-14
#58KnowBench: Effort Reduction as a Unified, Deployment-Grounded Benchmark for Clinical AIJocelyn Kang, Caroline Zhangcs.AI2026-09-14
#59Navigating Sparse Evidence: Agentic Visual RAG via Explicit Context Selection and ConsolidationYucheng Shen, Lingyong Yan, Jiulong Wu +4cs.AI2026-09-14
#60When Should a World Model Move? Loss-Conditioned State ExecutionJintao Xu, Zhengyu Chen, Ben Zhang +2cs.AI2026-09-14
#61Atria Dawn: The Dawn of Agentic SuperintelligenceHonglin Guo, Tao Gui, Yicheng Chen +140cs.AI2026-09-14
#62AlgoEvo: Self-Evolving Agentic Search for Automated Algorithm DiscoveryJunhao Qiu, Qinglong Hu, Xialiang Tong +3cs.AI2026-09-14
#63LongAgent: History-Guided Agentic Search for Longitudinal Outcome PredictionSiyao Wang, Florian Guitton, Shuojie Fu +3cs.AI2026-09-14
#64Pilot Early, Commit Late: A Real-Options Model of Enterprise AI Adoption under Rapid Technological ProgressGaurav Tewarics.AI2026-09-14
#65Recurrent GraphNeural NetworkswithSet-BasedAggregationBlai Bonetcs.AI2026-09-14
#66Stellar Colosseum: A Many-Agent Harness for Long-Horizon Research in Mathematics and Theoretical Computer ScienceHonghao Lin, David P. Woodruff, Yuan Deng +3cs.AI2026-09-14
#67Corrupt Plans, Clean Traces: Evading Chain-of-Thought Monitoring with Plan InjectionKeertana Chidambaram, Andrew Ilyas, Vasilis Syrgkaniscs.AI2026-09-14
#68Low-Dimensional Embeddings for Gaussian Kernels on ManifoldsSoumik Dutta, Kunal Duttacs.CG2026-09-14
#69Multi-Stage NeRF for Efficient 3D Coronary Artery Reconstruction from Two Narrow-Angle Angiographic ProjectionsDeyu Meng, Mojtaba Lashgari, Yiying Wang +1cs.CG2026-09-14
#70ModularRSI: Modular and Generalizable Recursive Harness Self-ImprovementSiwei Wu, Jincheng Ren, Yizhi Li +11cs.CL2026-09-14
#71Dream-RSI: Recursive Self-Improvement through Evolving WorldsTong Zheng, Xidong Wu, Zheng Zhang +14cs.CL2026-09-14
#72One Example Is Enough to Pass Fairness Benchmarks: Rethinking Fairness Evaluation for Aligned LLMsNaihao Deng, Samee Arif, Shuaichen Chang +2cs.CL2026-09-14
#73Forty Shades of Blue: Quality-Diversity Alignment via Mode-Conditioned Reinforcement LearningJiayi Yuan, Hangoo Kang, James Jihao Liu +4cs.CL2026-09-14
#74Can We Triage LLM Translation Errors in Classical Texts Without Human References? Source Novelty, GEMBA Scoring, and Budgeted Review through Pali-to-English TranslationMáté Metzgercs.CL2026-09-14
#75A Corpus-Aligned Uthmani-to-Standard Quranic Word Mapping and a Deterministic Recitation ValidatorYahya Mohamed Elnawasanycs.CL2026-09-14
#76Online Language Adaptive Sampling for Better Distributed Cross-lingual GainsQuang Phuoc Nguyen, Félix Gaschi, David Anugraha +2cs.CL2026-09-14
#77Biomedical Reference Generation Remains Unreliable across 26 Large Language ModelsMaxim Topaz, Zhihong Zhang, Nir Roguin +3cs.CL2026-09-14
#78Typhoon ASR Streaming: Steerable Low-Latency Thai Speech Recognition with Real-Time Shallow FusionWarit Sirichotedumrong, Tanawin Samutsin, Shah Faisal Wani +2cs.CL2026-09-14
#79MTAC-IFBench: Benchmarking Instruction-Following in Multi-Turn Agentic CodingBosi Wen, Cunxiang Wang, Jiayi Gui +6cs.CL2026-09-14
#80Beyond Depth and Width: The Information-Slack Dilemma in Streaming Test-Time ComputeXiaotian Zhangcs.CL2026-09-14
#81ABSOL: Aggregated Bayesian Subsampling Orchestrated with LLMsJackson Hassell, Chen Shen, Estevam Hruschkacs.CL2026-09-14
#82SALUTE: Benchmarking and Adapting LLMs for the Defense DomainHyeongcheol Park, Sumin In, Suyeon Myeong +5cs.CL2026-09-14
#83Mirror, Mirror on the Wall: Prompt Echoing in Small Instruct Language ModelsInez Okulska, Bartosz Naskręcki, Jan Piotrowski +1cs.CL2026-09-14
#84Salesforce Koa: An Enterprise Language Model for Agentic Tool UseZixiang Chen, Sufeng Niu, Yingchi Liu +22cs.CL2026-09-14
#85DA-DLM: Explicitly Modeling Token Dependencies in Diffusion Language ModelsPengyu Ji, Zichen Zhang, Xiang Hu +1cs.CL2026-09-14
#86Translating the Translator: Decomposing the Cost of English-Forced Inter-Agent CommunicationKushagra Agrawal, Yuming Feng, Man-Fai Leungcs.CL2026-09-14
#87When the Wrong Key Wins: Understanding and Detecting Hallucinations in LLMsXuhan Tong, Jiawei Zhangcs.CL2026-09-14
#88MoME: Mixture-of-Memory Embeddings for Context-Aware Sparse LookupMuchen Li, Leonid Sigal, Renjie Liaocs.CL2026-09-14
#89Improving Mathematical Reasoning Capabilities in Large Language Models via Reasoning Process Error ClassificationRuna Yoshida, Kosuke Nishida, Kyosuke Nishidacs.CL2026-09-14
#90EMR: Self-Evolving Medical Multi-Agent System via Experience Mining and ReuseDongsheng Shi, Yue Li, Xin Yi +1cs.CL2026-09-14
#91CITECHOICE: A Causal Audit of How Document Presentation Redistributes Citation Credit in Agentic SearchSriram Selvam, Anneswa Ghoshcs.CL2026-09-14
#92MUSE: A Theory-Harnessed Story Engine for Vibe NarrativizingJianxiang Ma, Xiaocui Yang, Daling Wang +4cs.CL2026-09-14
#93What Limits Us? Analyzing Self-Reported Limitations in NLP ResearchTawan Thaepprasit, Peeranuth Kehasukcharoen, Ding Wang +3cs.CL2026-09-14
#94Semiotic Relations and Proof Methods: A Cross-Genre Study of Argument Structure with Large Language ModelsEdirlei Soares de Lima, Marco A. Casanova, Antonio L. Furtadocs.CL2026-09-14
#95Artificial entrepreneurial cognition: Locating and causally steering an opportunity recognition dial inside large language models (LLMs)Christian Fisch, Angela Altmeier, Martin Obschonka +2cs.CL2026-09-14
#96When Agents Slow Down: Understanding LLM Agents' Test-Time Strategies via Elo-per-token AnalysisKaiyuan Liu, Qiuyang Mang, Bo Peng +6cs.CL2026-09-14
#97Dynamic Semantic Compression for Efficient Latent-Space Inference in Large Language ModelsPeipei Li, Dongsen Zhang, Yuchen Liu +1cs.CL2026-09-14
#98SlopShape: Identifying AI-Generated Commercial Web ContentJochen Madlercs.CL2026-09-14
#99Turkish MMLU Pro: Traceable Option Augmentation and Its Validity Limits in Turkish Multiple-Choice EvaluationM. Ali Bayramcs.CL2026-09-14
#100Temperature Fragility and the Conditional Benefits of Truncation SamplingFrancesco La Rosacs.CL2026-09-14
#101How Lossless Is Lossless Speculative Decoding? The Role of Numerical Precision in OrthrusIlya Koziev, Leonid Sinev, Ivan Oseledetscs.CL2026-09-14
#102Authorship attribution and aesthetic evaluation of AI poetry: a case study with HaikuLivia Oddi, Simone Scardapane, Toru Sugimoto +1cs.CL2026-09-14
#103Psychosis involves a deficit of information compression in connected speechSamuele Vallisa, Claudio Palominos, Rui He +6cs.CL2026-09-14
#104To Each Language Its Tokenizer: Modular Tokenizers for Efficient Multilingual LLMsFranck Signe, Hippolyte Pilchen, François Yvon +1cs.CL2026-09-14
#105Don't Count the Edits, Judge by the Outcome Alone: Reward-Based Evaluation for Grammatical Error CorrectionHayeong Ryu, Sunhee Jo, Seunguk Yu +1cs.CL2026-09-14
#106Can We Trust the Judges? Validation of Factuality Evaluation Methods via Answer PerturbationSarra Gharsallah, Adele Robaldo, Mariia Tokareva +5cs.CL2026-09-14
#107Through the Eyes of the Beholder: Biometric and Demographic Conditioning for Multimodal Sexism DetectionAna-Maria Luisa Mocanu, Sebastian Mocanu, Ciprian-Octavian Truică +1cs.CL2026-09-14
#108Empathy Is Steerable but Multi-Axial: Mechanism Geometry and Persona Effects in LLMsJuHeon Ha, Byounghan Lee, Yunseo Choi +1cs.CL2026-09-14
#109RESKILL: Explicit Failure Attribution and Structured Repair for Interactive Language AgentsMengyi Deng, Xin Li, Duyi Pan +4cs.CL2026-09-14
#110Merging the Knowledge of LLMs for Automatic Speech RecognitionHayato Futami, Tatsuya Kawaharacs.CL2026-09-14
#111Look Before You Leap: Factual Decoding with Internal Attribution SignalsHayeong Ryu, JungMin Yun, Byeonggeuk Lim +2cs.CL2026-09-14
#112Sequential Adapter Stacking for Cross-Lingual Low-Resource ASRThai Thi Thanh Thao Dang, Mengjie Qian, Kate Knillcs.CL2026-09-14
#113Enabling Streaming User Transcription in Full-Duplex Speech-to-Speech ModelsKe Hu, Nourchene Ferchichi, Edresson Casanova +9cs.CL2026-09-14
#114CiteGuard-RAG: A Validation-Centered AI System for Evidence-Grounded Question AnsweringSumit Barua, Guan Hong, Halil Dursunoglu +2cs.CL2026-09-14
#115Before You Poll with LLMs: A Deliberative Diagnostic FrameworkAhmed Wali, Hassaan Tayyabcs.CL2026-09-14
#116Learning to Coach for Experiential LearningGuanheng Chen, Tianzhu Ye, Li Dong +3cs.CL2026-09-14
#117K-Bench: a clinically calibrated benchmark for evaluating large language models in high-risk mental health conversationsLaura M. Vowels, Matthew J. Vowels, Shivali Sharma +9cs.CL2026-09-14
#118Inoculation Midtraining with Learned NeologismsKyle O'Brien, Edward James Young, Puria Radmard +4cs.CL2026-09-14
#119HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific HypothesesJieyuan Liu, Mengzhou Hu, Jefferson Chen +10cs.CL2026-09-14
#120Verifiable by Construction: Claim-Level Evaluation of Verbatim Citation in Clinical Question AnsweringJiashuo Zhang, Yuling Chen, Yvonne Commodore-Mensah +1cs.CL2026-09-14
#121Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental StatesZixuan Wang, Yufan Zhou, Jinzhou Tang +16cs.CL2026-09-14
#122Discovery Foundation Models: Toward Open-Ended Discovery IntelligenceLing Yang, Zhenfei Yin, Yingcheng Wucs.CL2026-09-14
#123Disentangling Representation Evolution in Transformers through Directional DecompositionShwai He, Haichao Zhang, Shen Yancs.CL2026-09-14
#124ActGuard: Pre-execution Action Auditing against Indirect Prompt Injection in LLM AgentsBingzheng Wang, Xiaoyan Gu, Wentao Wang +3cs.CR2026-09-14
#125PIDS-Bench: Evaluating Prompt-Injection Detectors Under Over-Defense, Obfuscation, and Distribution ShiftYusuf Khalid Shire, Sang-Chul Kimcs.CR2026-09-14
#126SpliTEE: Improving LLM Inference on Trusted Hardware with Differentially Private GPU OutsourcingShashie Dilhara Batan Arachchige, Robin Carpentier, Hassan Jameel Asghar +1cs.CR2026-09-14
#127Divide, Consult, Conquer: Capability Laundering Through Aligned LLMsMark Russinovich, Blake Bullwinkel, Giorgio Severi +2cs.CR2026-09-14
#128Automating Attack Graph Construction for Agentic Pentesting. Towards Neuro-Symbolic Vulnerability HuntingOliver Stevanovic, Jasmin Wachtercs.CR2026-09-14
#129CiteShade: Citation Laundering in Multi-Source Retrieval-Augmented Generation and Its Counterfactual DefenseGuo Fuzhengcs.CR2026-09-14
#130When the World Lies: Backdoor Attacks on Latent World Models for Downstream ControlRoberto Riaño, Gorka Abad, Stjepan Picek +1cs.CR2026-09-14
#131Vulnerability Localization Benchmark: Measuring Agentic Security Analysis at Repository ScaleAman Priyanshu, Supriti Vijay, Kimia Majd +8cs.CR2026-09-14
#132RAIN: Region-Aware Inversion Network for Semantic Watermark ExtractionZilai Lics.CV2026-09-14
#133What Makes a 3D Scene Editable? A Factorized Benchmark of Fidelity, Locality, Consistency, and PreservationSariah Patro, Arjun Mehra, Nikhil Bhatiacs.CV2026-09-14
#134ThreshGuide: Class-Aware Labeled-Guided Thresholding for Semi-Supervised 3D Abdominal Multi-Organ SegmentationHongyu Liu, Yinlong Wang, Lusha Li +1cs.CV2026-09-14
#135MoVT: Video-Augmented Motion Tokenizer for Text-to-Motion GenerationBeibei Jing, Tianle Guo, Youjia Zhang +5cs.CV2026-09-14
#136PhysBrain 1.5: From Vision-Language Models to Physical Foundation ModelsDeepCybo Team, Yu Bin, Haipeng Cao +51cs.CV2026-09-14
#137G-ray: Ray-Level Relative Geometric Position Encoding in Multi-View Vision Transformers under Camera HeterogeneityShuo Zhang, Xin Su, Wei Wang +8cs.CV2026-09-14
#138TwinICL: Diagnosing Multimodal In-Context Learning through Paired CounterfactualsZihan Xue, Po-Yi Lu, Serhii Honcharenko +5cs.CV2026-09-14
#139Tele360: Real-Time Feed-Forward Human Reconstruction from Sparse Unposed CamerasHanzhang Tu, Zhanfeng Liao, Wei Min +2cs.CV2026-09-14
#140LG-VLN: A Zero-Shot Vision-and-Language Navigation Framework with LangGraph State OrchestrationJianhe Zhao, Yanhua Qiu, Zhiyu Zhang +2cs.CV2026-09-14
#141ChatGPT Images 2.5 in the Wild: A Launch-Period Dataset and Detector EvaluationDennis Ng, Xingyu Shen, Ankit Raj +6cs.CV2026-09-14
#142DNF-SR: Dual-Input and Negative-Aware Feature Fine-Tuning for Real-World Image Super-ResolutionShuhao Han, Wenjie Liao, Hayden Vance +4cs.CV2026-09-14
#143AdaVSkip: Adaptive Visual Token Skipping Across Layers For Efficient MLLMs InferenceYuyao Sun, Tao Deng, Shuang Li +1cs.CV2026-09-14
#144SparseTalk - Sparsifying 3D Gaussian Language Fields for Efficient 3D Visual Question AnsweringDavit Soselia, Joseph JaJa, Amitabh Varshneycs.CV2026-09-14
#145Automated Perceptually-Motivated Assessment of Photographic Consistency in Paired Clinical Photographs: Pipeline Development and Internal EvaluationDerrick Lin, Samantha Rabinovich, Joclin Rabinovich +5cs.CV2026-09-14
#146Weakly Supervised Spatial Grounding for Discriminative Attention-Based Ultrasound-Histopathology Alignment in Prostate Cancer GradingObed Korshie Dzikunu, Emma Willis, Mohammad Mahdi Abootorabi +7cs.CV2026-09-14
#147PACE: Progressive Angular-to-Norm Contrastive EmbeddingYanping Li, Wei Zhou, Yawen Liu +7cs.CV2026-09-14
#148GRAVA: Grounded Reasoning-to-Action Representation and Learning for Autonomous DrivingXiao Liu, Haoyu Li, Jianghao Leng +2cs.CV2026-09-14
#149EECTracker: Swarm Motion Prior-Guided Feature Compensation for Airborne Optical UAV Swarm TrackingZhaochen Chu, Tao Song, Ren Jin +2cs.CV2026-09-14
#150Does Attention-Guided Masking Really Help Object Discovery in Object-Centric Learning?Youliang Tao, Yanhua Han, Bin Zhao +3cs.CV2026-09-14
#151Reconstructing Is Not Acting: Action-Centric Latent Dynamics ModelingDingjie Fu, Dianxing Shi, Yangyang Xu +1cs.CV2026-09-14
#152Long-to-Short Video Evidence Reasoning for Grounded Question AnsweringKaiyan Chen, Junbin Xiao, Xun Yangcs.CV2026-09-14
#153Deep Learning-based Intelligent Diagnosis of Congenital Uterine Anomalies in 3D UltrasoundYueyue Xu, Yuhao Huang, Jiaxiao Deng +10cs.CV2026-09-14
#154Closed-form Bayesian homography estimation from noisy point correspondencesHanne Beuter, Sebastian Dorncs.CV2026-09-14
#155Unsupervised Point Cloud Registration via Training-Time Semantic GuidanceKezheng Xiong, Shiyun Xu, Sheng Ao +3cs.CV2026-09-14
#156Pre-PEFT Probing: Weight Statistics and Perturbation Robustness for Layer Selection in VLM Vision EncodersQingtao Xia, Jiahua Bao, Siyao Cheng +1cs.CV2026-09-14
#157A 25-$μ$s/inf Event-driven Graph Neural Network Processor with Spatiotemporal Caching and Spline Convolution for Ultra-low-latency AI at the EdgeAdrian Kneip, Martin Lefebvre, Daniel Gehrig +4cs.CV2026-09-14
#158AlignUS: MRI-Guided Ultrasound Representation Learning for ALS Classification from Tongue ImagesKadija Abdel Ghader, Emani Babe, Lorenzo Pettinari +2cs.CV2026-09-14
#159Learning from Reliable Negatives: Confidence-Anchored Test-Time Adaptation for GUI GroundingYizhou Liu, Fei Tang, Yuchen Yan +8cs.CV2026-09-14
#160Hypergraph-Regularized Gramian Volumes for Multimodal RetrievalAnindya Nag, Ambuj Mehrish, Sebastiano Vasconcs.CV2026-09-14
#161Query-Conditioned Spherical Centroid Aggregation for Multimodal RetrievalAmbuj Mehrish, Anindya Nag, Sebastiano Vasconcs.CV2026-09-14
#162Concept-Grounded Reasoning with Prompt-Driven Localization for Interpretable Structured Report GenerationXinyue Xu, Hongbin Lin, Juangui Xu +6cs.CV2026-09-14
#163Robust Multi-Model Fitting through Learning Neighbor RegionsChang Nie, Guangming Wang, Zhe Liu +1cs.CV2026-09-14
#164End-to-End Cell Detection via Instance-aware Graph ModelingRuochen Liu, Yalin Zheng, Jingxin Liu +5cs.CV2026-09-14
#165Diffusion Trajectory Modeling for Semantic CorrespondenceYusung Choics.CV2026-09-14
#166CapsuleMotion: A Lightweight Real-Time Visual Motion Predictor for Capsule EndoscopyOliver Bause, Julia Werner, Oliver Bringmanncs.CV2026-09-14
#167BSC-Net: A Small-Branch-Sensitive Structural Continuity Network for Coronary Vessel Segmentation and Quantitative Angiographic AnalysisWanxian Li, Jiaqian Qin, Qingyi Xian +4cs.CV2026-09-14
#168MarKey: Marginal Utility Guided Greedy Keyframe Selection for Long Video UnderstandingHongchang Shi, Jinpeng Hu, Ao Wang +4cs.CV2026-09-14
#169ViCo-SAM3: Vision-Conditioned Alignment for Open-Vocabulary Camouflaged Object SegmentationQiangqiang Zhou, Wenjun Tang, Yong Chen +2cs.CV2026-09-14
#170A Conservative OCR-Enabled Workflow for R214 Sodium Screening of South African Packaged FoodsMayimunah Nagayi, Alice Scaria Khan, Tamryn Frank +2cs.CV2026-09-14
#171AnchorGUI: Asymmetric Memory for Dual-Scale Learning in GUI NavigationShengjie Jin, Zelong Sun, Hengbo Xu +2cs.CV2026-09-14
#172BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in BlenderYolo Y. Tang, Daiki Shimada, Jiayue Meng +14cs.CV2026-09-14
#173CatchMonitor: a machine learning system for automated fish discard quantificationGeoff French, Michal Mackiewicz, Mark Fisher +2cs.CV2026-09-14
#174SyntheticDoc: A Large Synthetic Dataset for Document Unwarping and Illumination CorrectionDaniel Woortmann, Tanguy Magne, Olga Sorkine-Hornungcs.CV2026-09-14
#175Assessing nnU-Net Generalization across Brain Tumor Populations in BraTS-GoAT 2026Tristan Kirscher, Vivian Metzger, Philippe Meyer +1cs.CV2026-09-14
#176PIVOT: Physics-Grounded Verification for AI-Generated Audio-Video DetectionBo Zheng, Kangran Zhao, Xiaoyu Zhang +7cs.CV2026-09-14
#177What a gated sensing pipeline never looks at: bandwidth reduction and the misses behind itRaghu Venkat, Tricha Anjalics.CV2026-09-14
#178A Unified Vision-Language Model for PSMA PET/CT Report Generation, Visual Question Answering, and Lesion SegmentationYang Xing, Jiong Wu, Savas Ozdemir +11cs.CV2026-09-14
#179VideoScout: Learning Agentic Active Exploration with Adaptive Reasoning Pacing for Long Video UnderstandingWeixin Xu, Zhenyu Yang, Bing Wang +2cs.CV2026-09-14
#180ModaLens: Measuring Image Sensitivity in Report-Conditioned Medical VLMsSebastián Andrés Cajas Ordóñez, Maximin Lange, Quang Bui +9cs.CV2026-09-14
#181SAM3D-Part: Interactive Part Selection and Generation from 3D ObjectsJiahao Chang, Dong Du, Wanhu Sun +6cs.CV2026-09-14
#182Human-Grounded Calibration for Long-Text Image-Text Congruence in Vision-Language ModelsAlessandro Gambetti, Qiwei Hancs.CV2026-09-14
#183MedDiME: Efficient Latent Diffusion with Adaptive Masking for Medical Counterfactual GenerationYan Zeng, Changlu Guo, Anders Nymark Christensen +2cs.CV2026-09-14
#184From Model Patterns to Abstract Semantics in Compositional Zero-Shot LearningWeize Li, Zhicheng Zhao, Fei Sucs.CV2026-09-14
#185Circuit-MLLM: Topological Logic-Guided Latent-Space Visual Reasoning for Circuit Schematic UnderstandingJinyuan Deng, Yuqi Jiang, Wenjing Huang +3cs.CV2026-09-14
#186Benchmarking Intra-Patient 3D Deformable Multimodal Image RegistrationMatteo Barbieri, Giammarco La Barbera, Juan Pablo De La Plata +3cs.CV2026-09-14
#187Don't Send What You Don't Need: Question-Guided Token Pruning as a Privacy Defense for Vision-Language ModelsMd Khalid Syfullah, Alvi Ataur Khalilcs.CV2026-09-14
#188MambaMPD: A Mamba-Driven Segmentation Framework for Marine Pollution Detection from Remote Sensing ImageryShuaiyu Chen, Wei Han, Peng Ren +2cs.CV2026-09-14
#189V-ICAL Bench: Evaluating Video In-Context Learning for Multimodal Agents in Interactive EnvironmentsZiqian Fan, Shibo Xu, Junjie Li +8cs.CV2026-09-14
#190SURE-Map: Self-Correcting Streaming Geometric Foundation ModelMingkai Liu, Hao Zhao, Xingxing Zuocs.CV2026-09-14
#191VC-Attention: Value Smoothing and Softmax Casting for Low-bit AttentionXingyang Li, Dongyun Zou, Shining Zhang +8cs.CV2026-09-14
#192Integrating Multi-view Multi-light Surface Reconstruction into Cultural Heritage WorkflowsBaptiste Brument, Robin Bruneau, Benjamin Coupry +6cs.CV2026-09-14
#193TRACE: Two-Stage Detector-Response Estimation With Angular Cosine Expansion for Ring Artifact Correction in Photon-Counting CTJigang Duan, Heran Wang, Ligen Shi +3cs.CV2026-09-14
#194LynnReal-Omni: Native multi-modal Video Generation for Agentic Visual WorkflowsXiaofeng Mao, Peijia Lin, Shaohao Rui +3cs.CV2026-09-14
#195Anatomical Grounding and Leakage-Aware Multimodal Contrastive Learning for Alzheimer's Disease Classification from Structural MRIPaul-Gabriel Nicolae, Irina Georgiana Mocanucs.CV2026-09-14
#196TEAR: Table Extraction with Attribute Recommendation from Texts via Large Language ModelsTong Li, Shuye Ding, Jiachuan Wang +4cs.DB2026-09-14
#197Shared KV Caching for Replicated 27B Inference: Correctness Failures and Performance BoundariesFrank Lics.DC2026-09-14
#198Validating Hybrid-State Cache Recovery for GLM-5.3-Flash with vLLM and LMCacheFrank Lics.DC2026-09-14
#199CIDERS: Cloud-Edge LLM Collaborative Learning via Accelerating Personalized Bilevel OptimizationVictor H. Chen, Hairui Yu, Stella K. Chung +1cs.DC2026-09-14
#200Scalability and Performance Evaluation of Federated Learning Frameworks: A Comparative AnalysisBassel Soudan, Sohail Abbas, Ahmed Kubba +2cs.DC2026-09-14
#201Geometric Signatures of Conceptual Reorganization: A Counterfactual Embedding Framework for Detecting Scientific RevolutionsDimitris Ntounis, Ariel Schwartzman, Chris Chafe +1cs.DL2026-09-14
#202Strong and Compact Policies for Submodular Markov Decision Processes via LP-Based Submodular OrienteeringLars Rohwedder, Rico Zenklusencs.DS2026-09-14
#203Thin-shell stability of Gaussian cooling: logconcave sampling with sesteric complexity from a cold startYunbum Kook, Santosh S. Vempalacs.DS2026-09-14
#204A Game-Theoretic Framework for Incentive-Compatible AI training Under Renewable-Energy ConstraintsKonstantinos Varsos, Ramin Khalili, Adamantia Stamou +2cs.ET2026-09-14
#205MedVA: An End-to-End Neuro-Symbolic Agentic System for Medical Volume VisualizationHaill An, Suhyeon Kim, Minjun Kang +4cs.GR2026-09-14
#206ESG: Generating Physically Consistent Dynamic 3D Scenes from Text DescriptionsXintong Fang, Zhiyuan Fang, Rengan Xie +6cs.GR2026-09-14
#207Kaininja: Extending Native 3D Generators to the Part LevelRuihan Yu, Lian Fu, Muyao Niu +9cs.GR2026-09-14
#208TopoRig: Topology-Agnostic Facial Rigging via Multi-Source SupervisionAndrew Fleet, Soroush Mehraban, Vida Adeli +2cs.GR2026-09-14
#209Delegating Authorization to Misaligned Agents: Coalitional Alignment and Safe ControlNatalie Collina, Surbhi Goel, Aaron Roth +1cs.GT2026-09-14
#210PeerPen: AI-Assisted Writing for Online Mental Health Peer SupportJiwon Kim, Sherry Gong, Maya Ajit +5cs.HC2026-09-14
#211Personalizing Personal Health Interfaces: Co-Design with Generative AIKarthik S. Bhat, Vidhi Shah, Vedika Agnihotri +2cs.HC2026-09-14
#212Spook the Machine: Gamified Exploration of Human Imagination of Machine FearLevin Brinkmann, Hiromu Yakura, Sonia Nicoletti +9cs.HC2026-09-14
#213Beyond AI Literacy: A Structured Review and Exploratory Meta-Analysis of Measures for Competent Generative-AI UseDaniele Veri'cs.HC2026-09-14
#214Can a Neural Encoding Model Replicate an fMRI Visualization Study?Erfan Nasirzadeh Orang, Zack Whilecs.HC2026-09-14
#215More Than Just Access: Generative AI as Communication Intermediary for Blind and Low-Vision UsersProtik Dey, Mohd Saifuzzaman, Taslima Aktercs.HC2026-09-14
#216Generate to Explore, Select to Exploit: Aligning LLM-based Headline Generation with Personalized RecommendationYi Chen, Rufeng Cheng, Qiang Xie +1cs.IR2026-09-14
#217Clean Scores, Buried Evidence, and Confident Wrong: A Receipt-Based Audit of Frontier Agentic QALuis M. Sánchezcs.IR2026-09-14
#218Self-Evolving Memory for Generative RecommendationXinyu Lin, Zhuosong Jiang, Zixiao Suo +12cs.IR2026-09-14
#219IROH: Insightful Ranking Of Humor using Multi-Stage Hybrid Retrieval with Rationale-Distilled LLM Judges for JOKER 2026 Track Task 1 EnglishAna-Maria Luisa Mocanu, Sebastian Mocanu, Ciprian-Octavian Truică +1cs.IR2026-09-14
#220Zero-SNR Analyticity of the Scalar MMSE Is Equivalent to GaussianityYixing Zhangcs.IT2026-09-14
#221Semantic Fibers and Cross-Gram Interference: A Calculus of Safety Drift in Overcomplete RepresentationsMohammed Ahnouch, Lotfi Elaachackcs.LG2026-09-14
#222Interpolation Is Not Invariance: Pair Count Is Not Coverage in Transformation AuditsMohammed Ahnouch, Lotfi Elaachakcs.LG2026-09-14
#223AgentKV: Phase-Aware KV Eviction for Agentic LLMsTaowen Tony Liu, Jeffrey T. H. Wong, Can Xiao +3cs.LG2026-09-14
#224SeqMaestro: From nucleotide sequences to biological hypotheses through interpretable machine learningEvgeny S. Saveliev, Krzysztof Kacprzyk, Charlotte Capitanchik +7cs.LG2026-09-14
#225Cross-Block Conditioning in Deep Boltzmann Machines for Statistical Data FusionJunichiro Niimics.LG2026-09-14
#226Cloud Workflow Scheduling Based on Graph Attention-Driven Hierarchical Reinforcement LearningZongjin Li, Shaohan Feng, Chunxi Yang +1cs.LG2026-09-14
#227High-Probability Nash Regret for Decentralized Learning in Markov $α$-Potential Games: Episodic and Fully Online Asynchronous Algorithms with Applications to Markov Congestion GamesS. Rasoul Etesamics.LG2026-09-14
#228HiGFRL: Hierarchical Graph Fusion-Driven Reinforcement Learning for Dependency-Aware Task Scheduling in Heterogeneous CloudTiangang Li, Shi Ying, Xiangbo Tiancs.LG2026-09-14
#229Learning to Solve Stochastic Controls with Unknown Drifts and Running Rewards: Theory, Algorithms and ConvergenceJin Ma, Gaozhan Wang, Jianfeng Zhang +1cs.LG2026-09-14
#230LiftGCN: Efficient Energy-Preserving Graph Learning via Joukowski Spectral Lifting for Finite Element Stress PredictionChen Zeng, Qiao Wangcs.LG2026-09-14
#231HGTO: A Unified Graph-Based Physics-Informed Formulation for Structural Topology OptimizationKangzheng Liu, Uday Kumar Punna, Leixin Macs.LG2026-09-14
#232Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor AttacksAashiq Muhamed, Mona T. Diab, Virginia Smith +2cs.LG2026-09-14
#233MoARa: Module-Aware Rank Allocation and Structure-Preserving Decomposition for Low-Rank LLM Pre-trainingKeunyoung Kim, Nojun Kwakcs.LG2026-09-14
#234Structured Features Overfit Where Random Features GrokChon-Fai Kam, Miloud Bessafi, Frederic Cadetcs.LG2026-09-14
#235Ensemble Complexity in Photovoltaic ForecastingSun Ze, Zhou Liguo, Xu Yuqing +2cs.LG2026-09-14
#236Not All Prompts Are Equal: Exploration-Guided Prompt Scaffolding for Multimodal Reinforcement Post-TrainingYuanhao Yue, Qianli Ma, Chengyu Wang +3cs.LG2026-09-14
#237What Does an LLM Learn from Reinforcement Learning? A Mechanistic Interpretability Perspective with Fixed-SAE TrackLingheng Du, Yiming Tang, Xufeng Duan +1cs.LG2026-09-14
#238Sensory Precision Inference for Multimodal Arbitration under UncertaintyTin Mišić, Takato Horiics.LG2026-09-14
#239Branched Optimal Transport AmortizationSemyon Semenov, Viktor Kovalchuk, Meir Roketlishvili +4cs.LG2026-09-14
#240Ensemble-Conditioned Molecular DesignRoss Irwin, Alessandro Tibo, Jon Paul Janet +1cs.LG2026-09-14
#241$\mathbb{SL}(n)$ Representation Learning: An Intrinsic Mixed-Curvature Space with Higher Curvature Capacities and Deeper Order-Aware CompositionXingrun Li, Yusuke Mukuta, Xin Yang +2cs.LG2026-09-14
#242Beyond Numerical Time Series: A Unified Benchmark for Multimodal Forecasting with Heterogeneous ContextPeng Chen, Zhihao Zhuang, Hongzhou Chen +6cs.LG2026-09-14
#243Refinement-based Flow Policy OptimizationBumgeun Park, Hyukjun Yang, Donghwan Leecs.LG2026-09-14
#244Omni-Streaming ThinkingEnjun Du, Siyi Liu, Ziyu Zheng +4cs.LG2026-09-14
#245Multi-source Transfer Learning of Time Series with a Shapelet-based Distance MeasureJiseok Lee, Brian Kenji Iwanacs.LG2026-09-14
#246Nearly Minimax-Optimal Regret for Linear Contextual Bandits with Arbitrary Adaptive Action SetsTianyuan Jincs.LG2026-09-14
#247Temporal Self-Distillation: Faster Inference in Discrete Diffusion Language ModelsShijian Xu, Andrea Miele, Metod Jazbec +3cs.LG2026-09-14
#248Rethinking Correctness for Uncertainty Estimation in Clinical Prediction with Vision-Language ModelsMingcheng Zhu, Jinning Liang, Tingting Zhucs.LG2026-09-14
#249Convergence rates for generative drifting flows: fixed-scale obstructions and multihead accelerationArthur Stéphanovitch, Eddie Aamarics.LG2026-09-14
#250ProtoGuide: Prototype-Driven Guidance for Class-Conditional Graph GenerationSalvatore Romano, Marco Grassia, Pietro Liò +1cs.LG2026-09-14
#251Bandits with Probing: Optimal Regret and the Limits of Winner FeedbackYongjie Guancs.LG2026-09-14
#252BioDCASE: Active Learning for BioacousticsBen McEwen, Rupa Kurinchi-Vendhan, Shiqi Zhang +3cs.LG2026-09-14
#253Learning CNF Formulas from Uniform Random Solutions: Near-Tight Sample Complexity for Valiant's AlgorithmWeiming Feng, Yixiao Yu, Yiyao Zhangcs.LG2026-09-14
#254Draining Fictitious Knots: Restoring Distance-Awareness Guarantees for High-Dimensional Spline NetworksMasoud Ataei, Mohammad Javad Khojasteh, Vikas Dhimancs.LG2026-09-14
#255Impute-EM: Native Mixed-State Diffusion Models for Heterogeneous Data ImputationSergei Kholkin, Kirill Sokolov, Dmitry Baranchuk +2cs.LG2026-09-14
#256Admissable: Training Reinforcement Learning Agents against Adversarial MissingnessPaul Stahlhofen, Luca Hermes, Tim Kochs +2cs.LG2026-09-14
#257When Correlations Mislead: Confounder-Aware Multi-View Urban Region Representation LearningSean Bin Yang, Ying Sun, Zongyi Xu +6cs.LG2026-09-14
#258The Universe of Universes: Benefit Yield Functions, Implosion Thresholds, and Infrastructure-Aware Optimization in Multi-LLM SystemsDanielle Franklin, Vasu Raj Jaincs.LG2026-09-14
#259Robust and Efficient Communication for Multi-Agent LearningRafael Pina, Varuna De Silva, Corentin Artaudcs.LG2026-09-14
#260Representing Clinical Conditions on Vital Signs from Healthy Individuals using Latent ModelingRafael Pina, Varuna De Silva, Mindula Illeperumacs.LG2026-09-14
#261CodeTS: Verifiable Text-to-Time Series Generation via Executable CodeXudong Yuan, Shunyu Liu, Tongya Zheng +3cs.LG2026-09-14
#262Single-condition neural solvers encode transferable response spaces for parametric differential equationsWenbo Cao, Weiwei Zhangcs.LG2026-09-14
#263On the role of the tokenizer in ECG transformer modelsJiawei Li, Fabio Bonassi, Johan Sundström +2cs.LG2026-09-14
#264GSLAD: Prototype-Regularized Graph Structure Learning for Multivariate Time Series Anomaly DetectionZepeng Zhang, Fuad Khuri, Keivan Faghih Niresi +1cs.LG2026-09-14
#265Data-driven Prediction of Satellite-observed Avalanche Activity from Snowpack SimulationsJakob Grahn, Filippo Maria Bianchi, Bert Kruyt +1cs.LG2026-09-14
#266Rotation-Based Subspace Tracking for Robust Kernel PCA on Streaming DataKris Lokere, John Fossacecacs.LG2026-09-14
#267Same path, different: a mechanistic comparison of looped and stacked transformer encoders on 12-lead ECGPawel Olszowiec, Michal Byra, Grzegorz Gruszczynski +2cs.LG2026-09-14
#268End-to-End Verifiable and Robust Federated LearningDoryan Lesaignoux, Enrique Mármol Campos, Gabriele Spini +2cs.LG2026-09-14
#269Beyond Noise: Understanding and Overcoming Temperature Effects in Analog DNN InferenceNiklas Summ, Xiao Wang, Hendrik Borras +2cs.LG2026-09-14
#270The Misery of Mechanistic Interpretability: A Formal PerspectiveTobias Ladner, Matthias Althoffcs.LG2026-09-14
#271Specifying Reward Functions for RL Without Environment SamplingStephane Hatgis-Kessell, W. Bradley Knox, Emma Brunskillcs.LG2026-09-14
#272The Token Before the Value Is the Key: How Hybrid Architectures Organize Induction CircuitsKe Cheng, Xin Xu, Yixiao Chen +6cs.LG2026-09-14
#273Bayesian Optimisation Using Product-of-Experts Gaussian Process Models with Uncertainty CalibrationYean Hoon Ongcs.LG2026-09-14
#274Multi-View Molecular Representation Learning with Hierarchical Graphs and Contextualized FingerprintsGwang-Hyeon Yun, Jong-Hoon Park, Bing Hu +3cs.LG2026-09-14
#275Where to Compute and How to Interact: Operator-Readable Adaptation with Gauge-Aware TransportZixuan Shen, Quanxu Wan, Bingchuan Wang +2cs.LG2026-09-14
#276FedLTLib: A Comprehensive Benchmark for Federated Long-Tail LearningChangkun Lin, Junxiao Wangcs.LG2026-09-14
#277Principal-timestep Restricted Init via Sparse Matrix-decomposition in Flow-matchingJiayang Gu, Zheng Fang, Lichaun Xiang +3cs.LG2026-09-14
#278Backward SDEs-based Diffusion for Physics-Constrained GenerationZihao Wangcs.LG2026-09-14
#279Knowledge-Enriched Structured EHR Features for 30-Day Hospital Readmission Prediction on MIMIC-IVMohamad Najafi, Hongyun Fu, Mathias Brochhausen +2cs.LG2026-09-14
#280Assembling the CREW: A Collaborative Multi-agent Reinforcement Learning Framework for Automated Related Work GenerationHai-Dang Dang, Bao-Yen Pham, Bao Nguyen +2cs.LG2026-09-14
#281Solving Finite-sum Coupled Compositional Optimization via Multi-block-Single-probe EstimatorWei Jiang, Sifan Yang, Yibo Wang +2cs.LG2026-09-14
#282A Language-Guided Multimodal Foundation Model for Zero-Shot and Multi-Task Brain Signal AnalysisMingzhi Chen, Yiyu Gui, Guibo Luo +1cs.LG2026-09-14
#283Sylvas: Synergistic Learning Value based Device Scheduling in Federated Continual LearningYuxuan Sun, Yuxuan Bai, Tan Chen +2cs.LG2026-09-14
#284Transfer Learning for Socioeconomic Estimation in Forced-Displacement SettingsSteven Ndung'u, Adel Daoud, Ismael Yacoubou Djima +2cs.LG2026-09-14
#285MoveBench: A Benchmark for Global-Scale Wildlife Movement ForecastingJustin Kay, Shir Bar, Ellen O. Aikens +28cs.LG2026-09-14
#286Sharp Rates and a One-Line Correction for Spectral Representation LearningDier Tang, Jing Yee Tan, Guangyue Hancs.LG2026-09-14
#287Per-Matrix Optimality Is Not Enough: Three-Level Optimization for Low-Rank LLM CompressionHuicheng Zhang, Xiyao Feng, Ze-Tong Li +6cs.LG2026-09-14
#288Task-Directed Residual AddUNet:Perfect-Reconstruction Routing for Full-Rate RepresentationsVikram R. Lakkavallics.LG2026-09-14
#289LLM-Based Schema-Aware Split Learning for Privacy-Preserving Mental Distress Prediction Across Heterogeneous SurveysMd Khalid Syfullah, Alvi Ataur Khalilcs.LG2026-09-14
#290Learning Multimodal One-step Flow Policy via Value-weighted Optimal TransportJaehun Shon, Jinha Choi, Jongwook Jeon +1cs.LG2026-09-14
#291Privacy-enhanced federated learning via asynchronous aggregation and local differential perturbationZhen Zhong, Shini Yang, Liesheng Weics.LG2026-09-14
#292Discrete Beckmann Transport Models for One-Step Language Modeling and ReasoningSophia Tang, Shiyi Wangcs.LG2026-09-14
#293Safe Meta-Reinforcement Learning via Information Space ReachabilityZeyang Li, Sunbochen Tang, Navid Azizancs.LG2026-09-14
#294Privacy-Aligned Personalized Federated Learning with Compact Adaptation and Variable-Length Gaussian CommunicationYilin Xu, Chun Hei Michael Shiu, Chih Wei Ling +1cs.LG2026-09-14
#295A Chosen Future Can Still Be Rewritten: Causal Writability in Video ModelsXingyun Wang, Haomin Zheng, Man Yuan +2cs.LG2026-09-14
#296The Router Within: Eliciting Native Skill Routing from a Frozen LLMRuishuo Chen, Xun Wang, Yu Chen +2cs.LG2026-09-14
#297Bellman Policy OptimizationZhuoqing Song, Haotian Xu, Xikun Zhang +1cs.LG2026-09-14
#298Big Brains and Changing Environments: Cause or Consequence?Sian Heesom-Green, Jonathan Shock, Geoff Nitschkecs.NE2026-09-14
#299Event-Native Symbolic-Temporal Spike Encoding Framework for Heterogeneous Cyber StreamsDalton Diez, Peyton Andras, Max Shroyer +1cs.NE2026-09-14
#300Proportional-Fair Resource Allocation and Dual-Threshold Early-Exit Inference for Secure Cooperative Multi-Layer Edge IntelligenceThai T. Vu, John Le, Tu N. Nguyen +3cs.NI2026-09-14
#301Accelerating Transfer-Learning-Based Autotuning with Predictive LLVM IR Performance RankingMd Arafat Hossain, Thomas Randall, Akash Dutta +3cs.PF2026-09-14
#302IMPACT-VLA: Interaction-aware Multimodal Propagation Attribution via Counterfactual Trajectories for Vision-Language-Action PoliciesJinwoong Kim, Sangjin Parkcs.RO2026-09-14
#303Steering Generative Robot Policies with Lexicographic PreferencesYixuan Jia, Jonathan P. Howcs.RO2026-09-14
#304Task-Distribution-Aware Counterweight Synthesis and Constrained Co-Design for Serial ManipulatorsMohammad Abbadics.RO2026-09-14
#305Legislating World-Model-Based Planning with Legal ReasoningDylan Waldner, Yiannis Kantaros, Guido Governatori +2cs.RO2026-09-14
#306Planning in the Backbone: DiffAdapterVLA for Native Continuous Trajectory Generation with Driving VLMsChangxin Lu, Xiaoliang Meng, Yu Wu +5cs.RO2026-09-14
#307Bench2Dex: Benchmarking Visuo-Tactile Bimanual Dexterous Manipulation Across Dexterous HandsZhenjie Yang, Yideng Zhang, Dongjie Zhang +21cs.RO2026-09-14
#308SlipSense: Multimodal Tactile Learning for Low-Latency and Generalized Slip DetectionTong Jian, Aditya Thurvas Senthil Kumar, Xinyi Li +7cs.RO2026-09-14
#309CAL-MOS: Bridging Layers with Adapters for Robust MOS Prediction Across Speech Foundation ModelsAlef Iury Siqueira Ferreira, Pedro Lustosa Rege Botelho, Fernanda Silva +5cs.SD2026-09-14
#310Rethinking Procedural Audio Pre-training: Source Scaling and Objective AdaptationJiajun Peng, Fengrui Liu, Xinyu Liu +1cs.SD2026-09-14
#311Augmenting Large Audio-Language Models with Frame-Level Grounding for Fine-Grained Temporal PerceptionYanfeng Shi, Yan Song, Junhui Li +4cs.SD2026-09-14
#312MAST: Label-Efficient, Robust, and Generalizable Sound Detection for Biodiversity Monitoring via Masked Audio Pretraining and Self-TrainingTianyi Xu, Daniel Pimentel-Alarcón, Zuzana Buřivalová +1cs.SD2026-09-14
#313DepthBenchCAD: When Does Deeper Auditing Yield More Reliable Conclusions?Hongye Yang, Zhihao Xie, Shengjun Xiong +1cs.SE2026-09-14
#314woma: a real-time foundation model and its fine-tuned models for endoscopyThang Tran, Lan Dangcs.SE2026-09-14
#315Failure-Guided Co-Evolution of Prompts and Training DataTianyu Yuan, Zhuzhong Qiancs.SE2026-09-14
#316IWC-Bench: Evaluating Web Application Generation from a Software Testing PerspectiveChenxu Liu, Zilu Zou, Peizhong Gao +9cs.SE2026-09-14
#317Eigenvalue-Decomposition Cost Denoising as an Alternative to Predict-then-Optimize for Shortest-Path ProblemsHenry Aldridge-Krawciw, Irene Aldridgeecon.EM2026-09-14
#318Learned Bow Control on a Measured Bowed-String Model: a Revised Minimum-Bow-Force Law, a Recurrent Controller, and the Domain of a Supervision CeilingHomayoon Beigi, Grace Conneelyeess.AS2026-09-14
#319Interpreting hierarchical organisation of speaker embeddingsYanze Xu, Wenwu Wang, Mark D. Plumbleyeess.AS2026-09-14
#320Reducing the Output-Mode Gap in Speech Language Models via Joint-Output On-Policy DistillationDaxin Tan, Dehua Tao, Chengxi Deng +2eess.AS2026-09-14
#321Bridging the Gap in ECG-Based Emotion Recognition: A Unified Evaluation of Deep Learning ModelsTimothy C Sweeney-Fanelli, Ajan Ahmed, Masudul Imtiazeess.SP2026-09-14
#322Transforming harmonic coefficients for 3D splat compressionTam Thuc Do, Philip A. Chou, Gene Cheungeess.SP2026-09-14
#323An explicit solution of the five-expert prediction PDE and the exact optimality set of COMBJeff Calder, Nadejda Drenskamath.AP2026-09-14
#324Linearized PINN with pretrained nonlinear layersWenhao Chen, Alexandre M. Tartakovskymath.AP2026-09-14
#325Math for AI safety: an invitation for mathematiciansLionel Levinemath.HO2026-09-14
#326Improving the Last-Iterate Guarantees of Anytime Algorithms for Stochastic Monotone Variational InequalitiesJun-Hyun Kim, Ahmet Alacaoglumath.OC2026-09-14
#327Projection-Free Multi-level Algorithms for Stochastic Constrained Compositional OptimizationWei Jiang, Sifan Yang, Wenhao Yang +4math.OC2026-09-14
#328Online local learning for generative thermodynamic computingHuilin Wang, Weibing Dengphysics.data-an2026-09-14
#329Physics Informed Neural Network model for the dynamical study of Abdominal Aortic AneurysmAdrián Robles Arques, Martín Ruiz Fernandez, Javier Sanchis +2physics.flu-dyn2026-09-14
#330Proximal-Only Transmission Matrix Recovery of an Arbitrarily Deformed Graded-Index Multimode FiberCole Reynoldsphysics.optics2026-09-14
#331Shapley Value Estimation for Multi-Site Data with Blockwise-Missing FeaturesSiqi Li, Wangxuan Fan, Yiming Li +2stat.ML2026-09-14
#332Steady-State Convergence of Stochastic ApproximationYixuan Zhang, Qiaomin Xiestat.ML2026-09-14
#333Data Attribution at Scale via Influence Matrix EstimationYuxi Chen, Hamza Golubovic, Han Tong +2stat.ML2026-09-14
#334Conformal Individual Treatment Effect Estimation under Networked InterferenceMatteo Zecchin, Osvaldo Simeonestat.ML2026-09-14
#335ReLU Neural Network Approximation to Smooth Functional Operator: Dimensional Decay and Error AnalysisShuhao Jiaostat.ML2026-09-14
#336Graph Matching Relaxations and Amortization for Supervised Graph PredictionFederico Méndez, Paul Krzakala, Gabriel Melo +3stat.ML2026-09-14
#337Predictive Likelihood Ratios for Language Model Watermark DetectionLi Mastat.ML2026-09-14
#338Learning under Target Shift: Optimal Density Ratio Estimation and Importance-Weighted RegressionRen-Rui Liu, Zheng-Chu Guostat.ML2026-09-14
#339Quenched Ensemble SamplingDavid Yallupstat.ML2026-09-14

latest · trends · arXiv announcement batches follow US Eastern weekdays