PaperScope
LIVE · 2026-09-03 05:40 UTC

New Papers · 2026-08-26 372 submissions

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

#TitleAuthorsCatDate
1Cross-simulator transfer with foundation model summaries: Towards robust SKA-era reionization inferenceYannic Pietschke, Caroline Heneka, Ayodele Ore +1astro-ph.CO2026-08-26
2Finding and using interpretable latents in a neutrino foundation model with sparse autoencodersRaphaël Bonnet-Guerrini, Johann Ioannou-Nikolaides, Inar Timiryasov +1astro-ph.HE2026-08-26
3A Hierarchical Synergistic Deep Learning Framework Integrating Composition, Structure, and Ionic Transport for Solid-State Electrolyte DiscoveryHongwei Du, Dingyang Lv, Baole Wei +5cond-mat.mtrl-sci2026-08-26
#4Hierarchical MoE for Multi-Modal ILD DiagnosisAlec K. Peltekian, Gorkem Durak, Halil Ertugrul Aktas +9cs.AI2026-08-26
#5PhaseShift: Topology-Aware Data Harmonization and Model Consolidation Across Signalized IntersectionsYash Ranjan, Artur Kumik, Rahul Sengupta +2cs.AI2026-08-26
#6BixBench3: Benchmarking AI agents on research-study-scale computational biology tasksZane Koch, Asmamaw T. Wassie, Javier Valdes-Aleman +5cs.AI2026-08-26
#7FinRiskAtlas: Decision-Aligned Evaluation of Large Language Models for Financial Risk ReviewSuyang Zhong, Jingzhe Zhu, Qi Xu +5cs.AI2026-08-26
#8Learning What to Share and What to Personalize: Hierarchical Strategy Co-Evolution for Agent MemoryYupeng Han, Shuochen Liu, Kai Zhang +3cs.AI2026-08-26
#9Where vs What: Decomposing Structural and Content Failures in LLM-Generated Structured OutputsYiwei Zhang, Chengke Wu, Li Wang +1cs.AI2026-08-26
#10Can your AI agent be cheaper? Investigating the effects of task specifications on token spend in agentic coding tasksJakub Smékalcs.AI2026-08-26
#11Paint What You See: Benchmarking Dexterous Visual Tool Use in Multimodal AgentsShudong Liu, Dongyang Chen, Enci Zhang +3cs.AI2026-08-26
#12Distance Is Not Enough: Forget-Retain Alignment Gap Predicts LLM Relearning RobustnessYi Chen, Hanna Hsieh, Shuhong Liu +4cs.AI2026-08-26
#13Training Alignment Auditors via Reinforcement LearningPaul Rosu, Rowan Wangcs.AI2026-08-26
#14PonsRAG: A Pons-Inspired RAG Bridging Cognitive Islands for Coordinated Long Narrative ReasoningRongchen Zhao, Yu Chen, Juyuan Wang +4cs.AI2026-08-26
#15CaSKG: Counterfactual-Causal Skill Graphs for Scalable Agent Skill RetrievalZhiyuan Li, Linyuan Gao, Xuechun Ding +3cs.AI2026-08-26
#16Agentic Game Development as a Verifiable Trajectory Data Engine for Scaling World ModelsPengfei Zhou, Hexin Wang, Zhengfeiyang Zhang +5cs.AI2026-08-26
#17Using profiles of cognitive capability to assess AI suitability for workplace tasksJonathan Prunty, Marko Tešić, Patrick Quinn +2cs.AI2026-08-26
#18Narcissus: Program Synthesis Using Context-Aware LLM ApproximationsTilman Hinnerichs, Sebastijan Dumancic, Neil Yorke-Smithcs.AI2026-08-26
#19Same Model, Different Harness: Different Coding-Agent ResultsSydney Lewiscs.AI2026-08-26
#20ToST: A Tree-of-Thought Socratic Teaching Framework for Multi-Path Guidance and Parallel ThinkingFeng Ling, Heng Yucs.AI2026-08-26
#21LocalLSTC: A Long Short-Term Control Architecture for Locally Deployed GUI AgentsWeiming Li, Helen Paik, Yulei Suics.AI2026-08-26
#22Choose Your Game Wisely: Measuring Game-Theoretic Structures in Real-World Vehicle InteractionsYueyuan Li, Rongcheng Nie, Weijie Xi +4cs.AI2026-08-26
#23Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent SystemsZhongwen Luan, Xiaoyu Zhang, Ming Hu +3cs.AI2026-08-26
#24Formal, Executable and Explainable Runtime Monitoring of Spoken Air Traffic Control Operational ProceduresRoberto Luvini, Giacomo Longo, Alessandro Armando +1cs.AI2026-08-26
#25Agent Mesh: Reliability Primitives for Non-Idempotent Agent Delegation - Identity Adequacy and Evidence AdequacyMazhar Shaikh, Anurag Rajkumar Bombarde, Harshal Pathakcs.AI2026-08-26
#26LLM Agents for Time-Series: A SurveyYilong Chen, Xiao Qin, Chenghao Liu +3cs.AI2026-08-26
#27How Robust Are Automated Fact-Checking Systems? A Cross-Benchmark EvaluationAida Usmanova, Zangir Iklassov, Markus Leippold +1cs.AI2026-08-26
#28Candidate supply and answer selection shape the value of LLM judging in multi-agent systemsJia-Hao Ji, Sijie Li, Jiabei Cheng +3cs.AI2026-08-26
#29LivingRAG: Augmenting Graph RAG with ExperienceYuzhuo Cui, Zongye Zhang, Qingjie Liucs.AI2026-08-26
#30Quantitative Analysis of $ω$-Regular Robust MDPsAli Asadi, Krishnendu Chatterjee, Ehsan Kafshdar Goharshady +3cs.AI2026-08-26
#31SciMIF: Understanding Multimodal Instruction Following in Scientific DomainsYe Shen, Yuting Zheng, Dun Pei +4cs.AI2026-08-26
#32Multi-Granularity Context-Enhanced RAG over Multimodal Knowledge GraphsZongyu Wu, Yilong Wang, Xiaochen Wang +5cs.AI2026-08-26
#33ProgRouter: Online Progress-Guided Orchestration for Multi-Agent LLM Workflows under Quality-Cost TradeoffsSongyuan Li, Ahmed M. Abdelmoniem, Shiqiang Wangcs.AI2026-08-26
#34AsymSpec: Context-Asymmetric Speculative Decoding for Agentic LLMsSheng Liang, Yongyue Zhang, Nathanael Brian +4cs.AI2026-08-26
#35Imitation Learning for Connection-Tableau ConstructionFredrik Rømming, Mantas Bakšys, Martin S. Fixman +1cs.AI2026-08-26
#36Trace Integrity for LLM Data Agents: A Vision for Auditable Structured Reasoning in Real-World SystemsSrimonti Dutta, Akshata Kishore Moharircs.AI2026-08-26
#37The Reasoning Tax: Token Economics of LLM Reasoning Across Task Types and Deployment ContextsSachin Gopal Wani, Ajay Dholakia, David Ellisoncs.AI2026-08-26
#38SwarmWorld: Stigmergic technological evolution in societies of language-model agentsSubhadeep Pal, Fiona Y. Wang, Markus J. Buehlercs.AI2026-08-26
#396.5% of the Neuro-Symbolic Literature Can Be Reproduced from Its Published Artifacts, a Six-Stage Audit Framework and First InstantiationBrandon Colelough, Vladimir Martirosyan, Ishan Tamrakar +6cs.AI2026-08-26
#40Planetary Prediction Engine: Autonomous Geospatial Prediction via Intelligent Data Selection and Foundation Model EmbeddingsEvelyn Ma, Rama Kumar Pasumarthi, Kishwar Shafin +25cs.AI2026-08-26
#41SKILL.state: Scalable Long-Horizon Agent SkillsSanket Badhe, Priyanka Tiwari, Jonghyun Chungcs.AI2026-08-26
#42Assessing mentalization in humans and large language modelsAamir Sohail, Xintong Zhong, Arkady Konovalov +2cs.AI2026-08-26
#43Approved Too Late: Verdict Staleness in LLM-Guarded Self-Adaptive SystemsIlai Shraga, Roei Eshel, Lior Gorelikcs.AI2026-08-26
#44FaithSieve: Fine-Grained Evaluation of Math Proofs with Faithful Formal EvidenceZiyu Wang, Qiming Dai, Yishan Wu +1cs.AI2026-08-26
#45ProofEvolve: Neuro-Symbolic Evolution for Formal Automated Theorem ProvingWenqian Ye, Ziwei Guan, Eric Xie +6cs.AI2026-08-26
#46Fine-Tuning of Transformer models with FramesHarshavardhan Adepu, Li Zhang, Sanjiv Kumar +1cs.AI2026-08-26
#47Don't Overthink, Don't Underthink: Toward Adaptive Reasoning in Agentic AIMd Jueal Mia, M. Hadi Aminics.AI2026-08-26
#48Syn2Logic: End-to-End Neuromorphic Design AutomationArtur Podobascs.AR2026-08-26
#49Redwood: A Frontier AI Accelerator Designed, Verified, and Deployed from Scratch in 2 Weeks by AIArchitect Labscs.AR2026-08-26
#50Unlocking Multimodal Protein Language Models at Inference TimeYi Zhou, Qipeng Wang, Yunqing Liu +3cs.CE2026-08-26
#51From Memorization to Absorption: Mixed-Policy RL for Continual Knowledge InjectionZhibo Hou, Fan Zhao, Zhiyu An +1cs.CL2026-08-26
#52Groundhog Bit-Flip Attack: Seeding Infinite Generation Loops in Mixture-of-Experts LLMs through Bit FlipsHuakang Lin, Tiancheng Zheng, Mingxuan Sun +4cs.CL2026-08-26
#53Routed Graph Handoff: Adaptive Format Selection for Multi-Agent LLM DelegationPratyay Banerjee, Ankit Chadhacs.CL2026-08-26
#54Provenance Before Prose: Claim-Locked ReportingXiao Fan, Jingyuan Li, Hongbin Guo +2cs.CL2026-08-26
#55GUIDE: Generative Unsupervised Chinese Query Correction via Phonetic and Visual Shared-ID EncodingLei Yang, Binbin Huang, Jiwei Tan +4cs.CL2026-08-26
#56Short Horizons and Sparse Concepts: a Mathematical View of the Readout in the J-lensShi-Qi Yan, Kai-Xuan Ding, Chao-Hong Tan +4cs.CL2026-08-26
#57Leveraging Speech Acts for Low-Data and Cross-Domain Conversation Derailment ForecastingAngela Yifei Yuan, Christine De Kock, Christopher Leckiecs.CL2026-08-26
#58Adaptive Triggering for Bias Correction in LLM ReasoningNayoung Kim, Mickey Mancenido, Huan Liucs.CL2026-08-26
#59OmniPhys: A Unified Multimodal Benchmark for Physics Understanding and Generation from Chinese Educational CorporaHao Chen, Yumin Lin, Nadila Yushanjiang +2cs.CL2026-08-26
#60DCGC: Draft-Conditioned Global Correction for Complex Reasoning with Masked Diffusion ModelsMinhae Oh, Nakyung Lee, Jungwoo Leecs.CL2026-08-26
#61MathAdv: What Theorem Provers Know, Reason, Formalize, and GeneralizeJiaxin Yuan, Connor Martinez Lockhart, Xiaoyu Liu +11cs.CL2026-08-26
#62VietAIDetector: An Open-Source Zero-Shot Detector for Vietnamese AI-Generated TextTrieu Hai Nguyen, Van-Dung Hoangcs.CL2026-08-26
#63ReliableRAG: Combating Misinformation in Retrieval-Augmented Generation via Reliability-Guided Reasoning ChainsJinpu Jiang, Xuan Wu, Wenhao Song +6cs.CL2026-08-26
#64TOPAS: Workflow-Aware Prefix-State Scheduling for Multi-Agent LLM ServingHongqiu Ni, Han Tian, Chi Zhang +2cs.CL2026-08-26
#65ClueWeaver: Reward-Guided Dual-Agent Evidence Reasoning for Compact LLMs on Literary Long NarrativesJihao Zhu, Zhiwei Yang, Wenxiao Zhang +7cs.CL2026-08-26
#66Virgil: Navigating Explainability for Transformer-based Language ModelsMartino Ciaperoni, Sezer Kutluk, Benedetta Muscato +2cs.CL2026-08-26
#67EgoArgus: Benchmarking VLMs as Situational Assistants for Modality-Grounded User SupportsYu-Chien Tang, Yu-Hsiang Liu, An-Zi Yencs.CL2026-08-26
#68Controllable Affective Generation via Latent Vector SteeringXixian Yong, Siyuan Chang, Yingying Zhang +2cs.CL2026-08-26
#69Generative vs. Encoder Large Language Models for ASR Evaluation: A Comparative StudyThibault Bañeras-Roux, Shashi Kumar, Driss Khalil +6cs.CL2026-08-26
#70Cross-Dataset Stability of Expert-Informed Skill Prompting and Fine-Tuning for Chinese Metaphor IdentificationYufeng Wu, Meichun Liucs.CL2026-08-26
#71GRIP: Granular Reward-Guided Parameter Interpolation for Efficient ReasoningLam So, Canhui Wu, Han Lincs.CL2026-08-26
#72JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness EvolutionGuibin Zhang, Leo Lu, Fangzhou Xie +13cs.CL2026-08-26
#73From Specialization to Generalization: Instruction-tuned LLMs for Robust Harmful Content MitigationLukas Edman, Daryna Dementieva, Alexander Frasercs.CL2026-08-26
#74AWM: Answerable Working Memory for Long-Document VQA AgentsDongzhuoran Zhou, Yuqicheng Zhu, Yule Liu +5cs.CL2026-08-26
#75AutoVerifier: Residual-Guided Non-Parametric Optimization for Reference-Based Answer VerificationZebei Zhao, Zhihao Shi, Minqi Shics.CL2026-08-26
#76Unmatched Does Not Mean False: Incomplete Reference Sets Can Reverse Calibration Rankings in Open-Ended Theory-of-Mind TrackingZhexi Feng, Wuxi Chen, Bingrui Zhangcs.CL2026-08-26
#77Reconstructing the Right Episode: Evaluating Interleaved Conversational Memory Beyond Long ContextZhexi Feng, Ruiyi Zhang, Yongbo Yang +1cs.CL2026-08-26
#78Think-Probe-Respond: Improving Large Language Models as Judges of Research Idea NoveltyTim Schopf, Tobias Schreieder, Akiko Aizawacs.CL2026-08-26
#79Overview of SHROOM-Visions 2026: A Shared Task on Hallucination Detection in Large Vision-Language ModelsRaúl Vázquez, Aman Sinha, Chuyuan Li +12cs.CL2026-08-26
#80Learning New Facts with QLoRA: An Acquisition-Retention FrontierEstelle Zheng, Sébastien Warichet, Emmanuel Helbert +1cs.CL2026-08-26
#81When RAG Fails to Equalize: Geo-bias in Factual Question Answering over Public CompaniesAbhinav Havaldar, Enrico Santuscs.CL2026-08-26
#82Beam Search, Self-Consistency, and the Limits of Inference-Time Scaling for Grammar-Constrained Text-to-SQL in Small Language ModelsTy Chermsirivatana, John MacCormickcs.CL2026-08-26
#83MoganBert-TR: A Turkish Encoder Foundation Model Trained from Scratch with a CLM-to-MLM CurriculumFurkan Yilmaz, Habibe Aleyna Tasdemir, Muhammed Faruk Gozaycs.CL2026-08-26
#84Localize-Then-Decide Guarantees for LLM JudgmentsXinyu Li, Yi Zhou, Guanqun Cao +3cs.CL2026-08-26
#85Unfolding Scientific Papers into Multi-Turn Generation Trajectories for Continued Pre-TrainingQiankai Xu, Qiguang Chen, Zixin Su +4cs.CL2026-08-26
#86Skill Issue: Are Skills Language-Invariant in LLMs?Bobby Cheng, Adam Gaber, Zhengyuan Liu +4cs.CL2026-08-26
#87Key Point Analysis Needs Structure Recovery: Task Definition, Dataset Diagnosis, and a Structure-Aware BenchmarkZhiqiang Shi, Oana Cocarascucs.CL2026-08-26
#88Anchoring Bias in LLM-as-a-Judge Systems: Prior Scores Compromise Evaluation IndependenceAnte Kapetanovic, Kemal Altwlkany, Andro Mercep +2cs.CL2026-08-26
#89Loss-Based Active Learning for Neural Abstractive SummarizationMichail Ioannou, Tatiana Passali, George Michalopoulos +1cs.CL2026-08-26
#90From Passive Response to Proactive Correction: Enhancing LLM Robustness Against Input Fact PerturbationsPing Wang, Xiangguo Sun, Bingbing Xu +2cs.CL2026-08-26
#91One Form to Transfer Them All: Pretraining Multilingual Language Models Beyond Native OrthographyMuge Zhang, Aaron Jencks, Krishna Badikela +2cs.CL2026-08-26
#92SAMpLE: A SystemC-AMS Machine LEarning-based Framework for Virtual PrototypingAndrei Mihai Albu, Sara Vincocs.CL2026-08-26
#93Query-Side Attacks on GNN-Based KGQA: Tracing Failures from Entity Linking to Answer GenerationPankaj Kumar, Subhankar Mishracs.CL2026-08-26
#94Unveiling Spectral Mechanisms in Training-Free LLM Text DetectionHaitong Luo, Xuying Meng, Weiyao Zhang +5cs.CL2026-08-26
#95Lost but not erased: Finding traces of a forgotten language in neural speech modelsPeter Plantinga, Charlotte Moore, Peter W. Donhauser +2cs.CL2026-08-26
#96When Personality Meets Quantization: A Layer-wise MBTI Analysis of Quantized LLMsYao Fu, Lijia Huang, Xiaomin Li +3cs.CL2026-08-26
#97Distinct dynamics of conceptual and referential disruptions in human reading and large language model processingRui He, Nihal Altay, Wolfram Hinzencs.CL2026-08-26
#98VISA: Agentic Self-Evolving Data Synthesis for Multimodal Instruction FollowingMin Zeng, Guanxin Tan, Libin Cen +5cs.CL2026-08-26
#99Beyond Local Surprise: Grounded Dialogue as Selective Belief Revision under Referential UncertaintyZiming Liu, Bhanu Chaitanya Jasti, Ziyang Xu +3cs.CL2026-08-26
#100Fine-Tuning Whisper for Automatic Speech Recognition in Baniwa: A Preliminary StudyLeonardo Duart, Tiago Fonseca, Thiago Chacóncs.CL2026-08-26
#101Prefix Sliding for efficient test-time scalingNiklas Muennighoff, Zhengyang Wang, Zeyi Chen +15cs.CL2026-08-26
#102On Scope Classification and Current Knowledge-Editing Benchmarks: A Negative Result, with INLAY as a Gradient-Free Case StudyAditya Pratap Singhcs.CL2026-08-26
#103MemToC: Benchmarking Memory-Tool Conflict Resolution in Large Language ModelsArseniy Varlamov, Rishat Zinnatullin, Elisei Rykov +2cs.CL2026-08-26
#104When Is Noise Response Universal? Tokenization as the Hidden Variable in Language ModelsYefan Tao, Gerald Friedland, Luyang Kongcs.CL2026-08-26
#105How Unlikely Is "Unlikely"? Assessing Verbal Probability Perception Across Large Language ModelsChristos Petridis, Konstantinos Pelechrinis, Zoran Obradoviccs.CL2026-08-26
#106Neuro-symbolic PRM: Enhancing Scientific Reasoning via Structured Traces and Symbolic VerificationYuxin Zi, Cong Xu, Suparna Bhattacharya +2cs.CL2026-08-26
#107MoganColBERT-TR: A Late-Interaction Multi-Vector Retrieval Model for TurkishFurkan Yilmaz, Habibe Aleyna Tasdemir, Muhammed Faruk Gozaycs.CL2026-08-26
#108Cross-lingual Representation Learning via Centroid Intervention FusionWei Sun, Marie-Francine Moenscs.CL2026-08-26
#109Knowledge-Verified Emergent Deception in LLM Agents Under Conflicting IncentivesZheyuan Liu, Weiliang Zhao, Xiangchi Yuan +3cs.CL2026-08-26
#110Survival-Guided Length Control for Efficient Diffusion Language ModelsIvan Kobyzev, Abbas Ghaddar, Yufei Cuics.CL2026-08-26
#111Why RAGs Hallucinate: Penalty-Aware Evaluation of Retrieval-Augmented Generation Systems with Knowledge-Gap CanariesAlden Do Rosario, Hussein Younes, Felipe Pirescs.CL2026-08-26
#112Co-Evolving Structured Knowledge and Reasoning in Language ModelsRyan Thomas Noonan, Linxi Zhao, Menghan Xu +6cs.CL2026-08-26
#113LowRankArena: A Standardized Evaluation Platform for SVD-Based LLM CompressionZishan Shao, Lixun Zhang, Kangning Cui +10cs.CL2026-08-26
#114Case2Flow: Bridging Patient Cases and Guideline Flowcharts through Multimodal RetrievalJiale Wei, Yufan Chen, Alexander Jaus +5cs.CL2026-08-26
#115AfriSwitch: A Benchmark for In-the-Wild African Code-Switched Speech RecognitionGabrial Zencha Ashungafac, Busayo Awobade, Tobi Olatunjics.CL2026-08-26
#116Vowel Signs Are Not Letters: A Pre-tokenization Ceiling on Multilingual Tokenizer FertilitySajal Regmi, Siddhartha Pudasaini, Chetan Phakami Puncs.CL2026-08-26
#117Compositional Generalization via Structural Identification in a Category-Theoretic FrameworkAkihiro Maeda, Thomas Seiller, Yohei Osekics.CL2026-08-26
#118LLMscope: Extracting LLM Assets from Edge AI Chips via Optical ProbingDev Mehta, Lily Dukette, William Folan +4cs.CR2026-08-26
#119MACGen: Toward Functionally Correct and Secure Code Generation via Multi-Agent CollaborationMiseon Yu, Jaehoon Choi, Younghan Lee +1cs.CR2026-08-26
#120MMJailBench: A Factorized Benchmark for Disentangling Multimodal Jailbreak VulnerabilitiesTianshi Wang, Jingsong Wang, Yafei Huang +3cs.CR2026-08-26
#121AI Slop and Hallucinations in Vulnerability Assessment: A Survey on Reasoning Failures and Trustworthy MitigationJunchen Ding, Jialiang Dong, Yichen Zhu +5cs.CR2026-08-26
#122Pointing the Way, Hiding the Destination: Practical Private Dense Retrieval at ScalePeichun Hua, Danyang Chen, Junan Zhang +5cs.CR2026-08-26
#123MeMark: Membrane-Space Watermarking for Spiking Neural NetworksRoberto Riaño, Gorka Abad, Stjepan Picek +1cs.CR2026-08-26
#124EVOMAL: Self-Poisoning in Self-Evolving Coding AgentsXiaodong Wu, Yu Shi, Qi Li +5cs.CR2026-08-26
#125Can Tainted Pixels Expose Deepfake Videos?Juan Hu, Shaojing Fan, Sanjay Saha +2cs.CR2026-08-26
#126A Self-Evolving Multi-Agent Framework Defense against LLM Jailbreak AttacksTongyan Hu, Bryan Hooics.CR2026-08-26
#127How Do LLM Agents Actually Get the Flag? Trace-Level Provenance for Agentic Offensive Security EvaluationKimberly Milner, Minghao Shao, Nanda Rani +8cs.CR2026-08-26
#128What Do Medical Vision-Language Models Learn in Radiology? Transfer, Alignment, and Source-Proxy Leakage Under Distribution ShiftAyoub Louaye Bouaziz, Lokmane Chebouba, Yassine Himeurcs.CV2026-08-26
#129Evaluating Constrained Iterative Refinement for Scalable Vector Graphics Generation with Off-the-Shelf VLMsMatthew Perlman, James Beetham, Niels Da Vitoria Lobo +2cs.CV2026-08-26
#130OpenCVL: An Open, Diverse, and Large-Scale Dataset for Fine-Grained Cross-View LocalizationZimin Xia, Mubariz Zaffar, Junsheng Fu +2cs.CV2026-08-26
#131PointRL: Learning Point-Level Vision-Language Grounding from Verifiable Annotation EvidenceJingyang Su, Pu Cao, Xiuze Jin +3cs.CV2026-08-26
#132WAVE: Reversing the Guidance Hierarchy for Coarse-to-Fine Guided Depth Super-ResolutionTayyab Nasir, Daochang Liu, Ajmal Miancs.CV2026-08-26
#133MulVec: Fine-Grained Role-Aware Matching for Training-Free Zero-Shot Composed Image RetrievalZihao Zhang, Dayan Wu, Xinze Liu +6cs.CV2026-08-26
#134V-Link: Recovering Lost Visual Representations in Action DiT for Vision-Language-Action ModelsYehao Lu, Jiarui Yang, Yuning Su +10cs.CV2026-08-26
#135Not All Attention Heads Contribute to Critical Visual Token Selection: Head-Aware Pruning Matters MoreChaofang Ma, Lin Jiang, Carol Jingyi Li +4cs.CV2026-08-26
#136GraftSR: Grafting Authentic Textures for Real-World Image Super-Resolution via Identical-Instance GuidanceQifan Yu, Haoran Bai, Zongyao He +4cs.CV2026-08-26
#137CoRE: Weakly Supervised Coarse-to-Fine Risk Evidence Learning in Driving VideosKaiser Hamid, Can Cui, Nade Liangcs.CV2026-08-26
#138Where to Look Matters: On-Policy Self-Distillation for Long-Video UnderstandingKaishen Wang, Dongdi Zhao, Yijun Liang +4cs.CV2026-08-26
#139FlashNormal: Detailed Surface Normal Estimation from Flash and No-Flash ImagesRuiyang Chen, Feiran Li, Heng Guo +1cs.CV2026-08-26
#140RSFusionDet: Underwater RGB-Sonar Multimodal Object DetectionZhuoyan Liu, Yihan Wang, Bo Wang +2cs.CV2026-08-26
#141Capacity Overflow: A Blind Spot for Backdoor Attacks in Vision MoEXiaocheng Zou, Tiancheng Zheng, Xiaolin Xu +1cs.CV2026-08-26
#142Efficient Training with Foresight: Multi-Token Auxiliary Supervision for Autoregressive Image GenerationGuo Niu, Xiongfei Yao, Teng Wang +1cs.CV2026-08-26
#143PIVOT: A Multi-Trajectory Dataset and Testbed for Pose, Intrinsics, and Novel Viewpoint Evaluation in Real-World 3D ReconstructionMary Raymondcs.CV2026-08-26
#144AdaptiveEmbed: Sample-Adaptive Multi-Vector Representation for Multimodal RetrievalXinze Liu, Lei Yang, Dayan Wu +7cs.CV2026-08-26
#145Bootstrapping a 4D LiDAR Annotation Tool from Video Foundation ModelsJihun Kim, Hyun-Kurl Jang, Hyemin Yang +3cs.CV2026-08-26
#146Saliency-Depth Conditioning for Zero-Shot Segmentation of Communication-Tower Components in Cluttered UAV ImageryAli Lesani, Chul Min Yeum, Su-Min Kangcs.CV2026-08-26
#147Multi-Sensor Mapping of Vulnerable Urban Settlements Using SAR, Multispectral, and Hyperspectral Imagery: A Case Study in Córdoba, ArgentinaLuigi Russo, Anabella Ferral, Silvia Liberata Ullo +1cs.CV2026-08-26
#148VGA-BenchV2: An Expanded Unified Benchmark and Multi-Model Framework for Evaluating Video Aesthetics and Generation QualityLongteng Jiang, DanDan Zheng, Qianqian Qiao +7cs.CV2026-08-26
#149CARD: Calibration via Agreement in Reverse Diffusion for Out-of-Domain MRI SegmentationJiaheng Dai, Weidong Guo, Qingbiao Li +4cs.CV2026-08-26
#150Automatic weld seam segmentation for industrial quality control: a comparison of RGB and polarimetric imaging with CNN and transformer architecturesSimone Garbin, Leonardo Venturoso, Marco Todescatocs.CV2026-08-26
#151PAGS: Autofocusing Photoacoustic Tomography via Speed-of-Sound-Adaptive Gaussian SplattingJiarui Ge, Jintao Ma, Bangxu Fan +4cs.CV2026-08-26
#1524DStreamCtrl: Interactive Video Generation with Online 4D ControlShiqian Li, Chenguo Lin, Zhiguang Liu +4cs.CV2026-08-26
#153DeCO: Discriminative Evidence Composition for Fine-Grained Dataset DistillationChuixuan Fan, Guang Li, Shijie Wang +5cs.CV2026-08-26
#154Gaussian Splatting Underwater: A Controlled Cross-Regime StudyOlaya Álvarez-Tuñón, Stella Graßhofcs.CV2026-08-26
#155Semi-Supervised Adaptation of Vision-Language Models for Image ClassificationMohamed L. Mekhalfi, Mohamad M. Al Rahhal, Yakoub Bazi +4cs.CV2026-08-26
#156SMART: MLLM-guided Temporal Alignment for Unifying Sign Language Recognition and SpottingEunjee Choi, JungHoon Sung, Seongwhan Cho +2cs.CV2026-08-26
#157Pose-Anchored Optical Flow for Low-Latency Human Action Anticipation in Human-Robot TeamingLewis de Zoete Grundy, Chris McCarthy, Christopher Flukecs.CV2026-08-26
#158OpenVeinNet: Robust Open-Set Finger Vein Verification with Dynamic Snake Convolution and Graph LearningSushrut Patwardhan, Raghavendra Ramachandracs.CV2026-08-26
#159Surgical Video Generation From Diffusion to World Models: A SurveyFuxiang Huang, Chenxu Zhang, Liang Han +1cs.CV2026-08-26
#160Asymmetric Cross-Modal Fine-Grained Visual Categorization: ACF-Net and the BirdPro BenchmarkBohan Deng, Shuo Ye, Zitong Yucs.CV2026-08-26
#161Video-IFBench: Evaluating Instruction Following of Multimodal LLMs in Video Understanding ScenariosHongbo Liu, Peixian Chen, Sihan Liu +12cs.CV2026-08-26
#162CropCop: An Auditable 120-Class Plant-Health Model from Benchmark Reconstruction to a Quantised Runtime ArtifactRana Muhammad Ahmed, Sabahat Abbascs.CV2026-08-26
#163AdaVDR: Adaptive Tool Use and Reflection for Video Deep ResearchXintong Zhang, Xiaomeng Fan, Shilin Yan +7cs.CV2026-08-26
#164CrossMambaTuning: Synergistic Spatial and Cross-Layer Adaptation for Machine Vision CompressionHaobo Xiong, Shaobo Liu, Kai Liu +1cs.CV2026-08-26
#165MLLMCLIP: Feature-Level Distillation of MLLM for Robust Vision-Language RepresentationsJongsuk Kim, Qiyu Wu, Zhuoyuan Mao +3cs.CV2026-08-26
#166V-Rubrics: Visual Faithfulness via Rubric-Based Reinforcement LearningShulin Tian, Minglun Li, Yuhao Dong +6cs.CV2026-08-26
#167Distributed Semantic Segmentation With Improved Rate-Distortion Trade-OffDanish Nazir, Timo Bartels, Thorsten Bagdonat +1cs.CV2026-08-26
#168A Dual-Transformer for Multi-Camera View RecommendationJosep Cabacas-Maso, Carles Ventura, Ismael Benito-Altamiranocs.CV2026-08-26
#169When Should a Network Emit Geometry, and When Should It Detect It? Readout, Reconciliation, and Representation in Floorplan VectorizationHe Zhangcs.CV2026-08-26
#170On the Separation of Human and AI-Generated Images in CLIP Embedding SpaceAndrea Aspertics.CV2026-08-26
#171Plans You Can Check: Verifier-Grounded Learning of an Open-Weight Planner for Executable Video-EditingHaoyu Wang, Cheng Feng, Liuyang Bian +5cs.CV2026-08-26
#172SeVeR: Selective Visual Exposure and Retrieval for 3D Medical Image Question AnsweringYaojun Hu, Danyang Tu, Yang Liu +8cs.CV2026-08-26
#173MAMA-FLUX.2: Image-to-Image Synthesis of Post-Contrast Breast DCE-MRI for the MAMA-SYNTH ChallengeKamil Kwarciak, Marek Wodzinskics.CV2026-08-26
#174Diffusion Transformers for Roof Graph Synthesis and ReconstructionDaniel Panangian, Ksenia Bittnercs.CV2026-08-26
#175Towards Purified Multi-Label Test-Time Adaptation of Vision-Language ModelsYiwen Liang, Hui Chen, Yizhe Xiong +7cs.CV2026-08-26
#176Deep Learning Segmentation of Diffusion-Weighted MRI Acute Ischaemic Stroke: A Pragmatic Evaluation Across Three DatasetsAtle Bjørnerud, Till Schellhorn, Thor H. Skattør +4cs.CV2026-08-26
#177Data Diversity, Not Frequency Invariance: A Controlled and Self-Audited Study of Compression-Robust Deepfake DetectionAbbas Aliyev, Samir Rustamovcs.CV2026-08-26
#178CloSeR: Unified Relational Distillation from Closed-Set Teachers for Category DiscoveryYuanpei Liu, Zhenqi He, Jialu Tang +1cs.CV2026-08-26
#179Unsupervised Anatomical Feature Learning via Diffusion Models: Enhanced Medical Image Segmentation with Denoising Diffusion Probabilistic ModelsAkshat G, Divyansh Gupta, Shaleen Bhatnagar +2cs.CV2026-08-26
#180Skeleton-based Zero-Shot Spatio-Temporal Action Localization via Weakly-Supervised PretrainingKoshiro Nagano, Fumiaki Sato, Ryo Hachiuma +2cs.CV2026-08-26
#181Difficulty-Aware Sample Allocation for Adaptive Data Augmentation in Semantic SegmentationOlasimbo Ayodeji Arigbabu, Abimbola Ismail Arigbabucs.CV2026-08-26
#182LongVU-TTT: Causal Test-Time Training for Visual Resampling in Long Video UnderstandingMahmoud Ahmed, Sameh Abdulah, Olatunji Ruwase +3cs.CV2026-08-26
#183MIMONet: Multi-scale Input and Multi-scale Output Network for Salient Object DetectionZhaojian Yao, Wei Gao, Tiesong Zhao +2cs.CV2026-08-26
#184InteractGesture: Progressive Chunk Guidance for Continuous Streaming Co-Speech Gesture ControlEkkasit Pinyoanuntapong, Ajinkya Deogade, Paul Streli +5cs.CV2026-08-26
#185Moving Beyond More Views: Redundancy-Aware Ego-Exo Fusion for Proficiency EstimationXu Dong, Wanqing Li, Anthony Adeyemi-Ejeye +1cs.CV2026-08-26
#186TDFNet: Tri-projection Deformable Fusion Network for Panoramic Salient Object DetectionQiangqiang Zhou, Jiacong Yu, Jiawei Xu +3cs.CV2026-08-26
#187Label-Free Foundational Model Selection for Medical Image Classification under Distribution Shift via Pseudo Label DiscrepancyJuan Iñaki Larrea, Lucas Mansilla, Enzo Ferrantecs.CV2026-08-26
#188Steer the Sampling, Not the Kernel Grid: Geometry-Guided Sampling Operator for Volumetric SegmentationSizhe Wang, Himashi Peiris, Zhaolin Chencs.CV2026-08-26
#189FLM: Frequency-Aware Language Models for Generative Image CompressionJiarun Chen, Kejun Wu, Li Li +3cs.CV2026-08-26
#190FlowMoDL: Model-Based Deep Learning with Conjugate-Gradient Data Consistency for Highly Accelerated 4D Flow MRI ReconstructionTristan Gottwald, Michelle Bruch, Mubashir-Ul Hassan +6cs.CV2026-08-26
#191Socialized Detector Learning: Trajectory-Guided and Reciprocal Distillation for Heterogeneous Object DetectorsWeihao Li, Yunqi Zhu, Zhihe Fan +5cs.CV2026-08-26
#192THA-Flow Generative Model: Prosthesis Geometry Prediction from Preoperative CTYiping Wang, Jie Li, Jingyu Shen +1cs.CV2026-08-26
#193DEFUSE: Generalizable Backdoor Defense for Self-Supervised Encoders with Generative PriorsTuo Chen, Jie Gui, Minjing Dong +4cs.CV2026-08-26
#194Precipitation Downscaling Using Foundation Model-Conditioned DiffusionVictor Nascimento Ribeiro, Jorge Guevara, Jorge Sebastian Moraga +7cs.CV2026-08-26
#195Learning Late, Guiding Early: Timestep-Decoupled Semantic Guidance for Fair Face GenerationSubir Kumar Parida, Rajbabu Velmurugan, Ketan Kotwal +2cs.CV2026-08-26
#196Projection-Aware End-to-End Learned Video Compression for 360-Degree VideoNiloofar Maanics.CV2026-08-26
#197LUTSeg: A Longitudinal Multi-Expert Dataset for Ulcer Tissue SegmentationKaren Sanchez, Carlos Hinojosa, Albert A. Ávila +5cs.CV2026-08-26
#198Embedding NDRE Trajectories into Contrastive Learning for Label-Free, Physiology-Aware Crop-Stress Staging and DSS OutputsShafqaat Ahmadcs.CV2026-08-26
#199Visual General Intelligence: A White PaperHirokatsu Kataoka, Yoshihiro Fukuhara, Yonglong Tian +18cs.CV2026-08-26
#200Code World Model: Coding Agent as World BrainYiwen Chen, Guosheng Lin, Chi Zhangcs.CV2026-08-26
#201When Composition Doesn't Add Up: Humans Identifying Defects in AI-Generated ImagesRuoqi Hu, Chulin Zhao, Jiashuo Chang +2cs.CV2026-08-26
#202TAU-Agent: An Agentic Retrieval-Augmented Framework for Traffic Anomaly UnderstandingYuqiang Lin, Yan Shi, Sam Lockyer +5cs.CV2026-08-26
#203Auditable CT Phenotyping Through Report-derived Radiological ObservationsRiga Wu, Walter Witschey, Yicheng Li +9cs.CV2026-08-26
#2044DGS-WAM: Bridging Past and Future with an Object-Centric World Action Model based on 4D Gaussian SplattingYueen Ma, Zenglin Xu, Irwin Kingcs.CV2026-08-26
#205Less Contouring, More Accuracy: Lesion-Guided ROI Deep Learning for Ovarian Ultrasound ClassificationMehran Ahmad, Ali Abbasian Ardakani, Afshin Mohammadi +3cs.CV2026-08-26
#206PANDA - Prototype-Anchored Alignment for Partially Unpaired Multimodal Learning, with Applications to Alzheimers MRI and TCGA PathologySheethal Bhat, Mahfuzur Rahman Chowdhury, Paula Andrea Perez-Toro +4cs.CV2026-08-26
#207FRAME: separating sampling variation from representational cause in medical imaging fairnessMahshad Lotfinia, Daniel Truhn, Andreas Maier +1cs.CV2026-08-26
#208Uncertainty-Guided Latent Diffusion Models for Faithful Super ResolutionRen Wang, Yung-Yu Chuangcs.CV2026-08-26
#209UltraPIPS: Improving model perception in B-mode ultrasound with foundation modelsTal Grutman, Tali Ilovitshcs.CV2026-08-26
#210StreamPI: Streaming Multimodal Temporal Modeling for Vision-Language-Action ModelsZhe Liu, Jinghua Hou, Yuxiang Lu +7cs.CV2026-08-26
#211Procedura: Agentic 3D Modeling with Procedural ControlYoutian Lin, Yikang Yang, Zhanpeng Hu +5cs.CV2026-08-26
#212MyoMechanix: Biomechanically-Grounded Compositional Skilled Activity Understanding and CoachingHao Yin, Paritosh Parmar, Lijun Gu +6cs.CV2026-08-26
#213A Visual Dependence-Aware Framework for Multimodal Unsupervised Continual Post-TrainingKaichen Li, Zhilin Zhu, Jianhao Huang +7cs.CV2026-08-26
#214RefVideo-6M: A Reliable Reference-Based Dataset for Instructional Video EditingBojia Zi, Xiaoyan Yang, Yu Zhou +7cs.CV2026-08-26
#215VBVR-Pro: A Scalable and Verifiable Suite for Native Visual ReasoningJunxiang Xu, Ruisi Wang, Fanyi Pu +49cs.CV2026-08-26
#216Modality Maturity Index: A benchmark for assessing multimodal capabilities of omni modelsRohit Patel, Dieuwke Hupkes, Sloan Stradercs.CV2026-08-26
#217Finding the Right Evidence: Factor-Guided Coarse-to-Fine Reasoning for Long VideosBaixuan Xu, Yinyui Xu, Tianshi Zheng +9cs.CV2026-08-26
#218A Unified Framework for the Mechanics of Information in Convolutional Neural Network Image SpaceAryan Shukla, Matthew Toewscs.CV2026-08-26
#219VIPER: An Expert-Curated Benchmark for Vision-Language Models in Veterinary PathologyLuca L. Weishaupt, Simone de Brot, Javier Asin +9cs.CV2026-08-26
#220Defending Wearable VLMs Against Private Attribute InferenceZhimin Li, Pan Wang, Jingxian Chen +4cs.CV2026-08-26
#221Mapping Woody Vegetation from Multi-Source Imagery and Prediction Fusion for Enhanced Data Efficiency and AccuracyKal Backman, Jared Wood, Adam Roffcs.CV2026-08-26
#222GGSS: Geodesic-Gated Spherical Steering for Inference-Time Debiasing of Generative Vision-Language ModelsYiqun Sun, Junyu Chen, Pengfei Wei +1cs.CY2026-08-26
#223PolyMemDB: A Polyglot Database System for AI Memory ManagementYu Wang, Jiaheng Lucs.DB2026-08-26
#224MetaSieve: Faster Relational Deep Learning through SQL-Based Metapath SelectionFahim Shahriar Khan, Ashraf Aboulnagacs.DB2026-08-26
#225Scalable Multi-GPU Simulation of 3D Multicellular Growth with RNN-Based Workload BalancingMatvey Moisseyev, Huijing Du, Dandan Zheng +2cs.DC2026-08-26
#226Multi-Dataset Inverse Problem Solving with Distributed Generative AIDaniel Lersch, Steven Goldenberg, Johann Rudi +5cs.DC2026-08-26
#227Simultaneous Envy and Equitability GuaranteesHadi Hosseini, Shraddha Pathak, Lirong Xia +1cs.GT2026-08-26
#228Q&A or Document-Based? The Effects of Interface Type on How Screen Reader Users Access Interconnected DocumentsColleen F. Cipriano, Yichun Zhao, Miguel A. Nacenta +2cs.HC2026-08-26
#229Are Concept Bottleneck Models Effective as Decision-Support Systems?Alessandro Bogani, Nicola Debole, Emanuele Marconato +3cs.HC2026-08-26
#230Large Language Model Few-Shot Prompting with Dilemma Training Outperforms Human Surrogates in Predicting Patient PreferencesNatasha Ureyang, Sebastian Porsdam Mann, Yuxin Liu +9cs.HC2026-08-26
#231Do Vision-Language Models Agree on the Affective Qualities of Shape? A Cross-Model Audit for Generative Design InterfacesLuca Bux, Thiago Rios, Ingo Scholtes +1cs.HC2026-08-26
#232The "Curse of Knowledge" in LLM Query Simulation: Concept Provenance for Tracing Answer-Side IntrusionChenglong Ma, Xinye Wanyan, Danula Hettiachchi +2cs.IR2026-08-26
#233CRAMER: Control via Request-Aware Masking for Editing RecommendersZhiyuan Julian Su, Naihe Feng, Zhen Luther Qin +1cs.IR2026-08-26
#234When Stale Constraints Go Unchecked: Budgeted Verification Failures in Inherited Agent MemoryKazuki Nakayashikics.IR2026-08-26
#235Data Citation for Large Language Models: A ChallengeGianmaria Silvellocs.IR2026-08-26
#236PlanSightRAG: A Visual-First Multimodal RAG for Automating Question Answering and Compliance Checking for Civil Standard PlansNabaraj Subedi, Shuvo Dip Datta, Ahmed Abdelaty +1cs.IR2026-08-26
#237Assessing the Downstream Utility of Evidence-Aware Retrieval in RAGUtshab Kumar Ghosh, Debayan Mukhopadhyay, Shubham Chatterjeecs.IR2026-08-26
#238Conditional Total Correlation and the Serial Depth of Adaptive Parallel SamplingChuling Wen, Weijie Liang, Jian Lucs.IT2026-08-26
#239ShuttleArena: Interpretable Self-Play in Physics-Based BadmintonPeize Dingcs.LG2026-08-26
#240Neural-Bayesian Structure Learning for Discrete Choice ModelingHyunsoo Yun, Eun Hak Lee, Jiaru Zhang +2cs.LG2026-08-26
#241Mitigating LLM sycophancy with RL-based fine-tuning: Bayesian Truth Serum approachSerhii Mytsyk, Yiming Zhang, Vikram Krishnamurthycs.LG2026-08-26
#242SHSP: Structure-Aware Hierarchical Solution Prediction for Mixed-Integer Linear ProgrammingZherong Zhang, Guanlin Li, Chengrui Gao +5cs.LG2026-08-26
#243InsightSR: Refining Symbolic Regression Search Spaces via Parallel Semantic and Structural LLM GuidanceYating Ling, Wenjing Cun, Zhitang Chencs.LG2026-08-26
#244Prefix-Denoising Consistency: Test-Time Verification for Diffusion Language ModelsYuki Ichihara, Naoto Iwase, Mohammad Atif Quamar +1cs.LG2026-08-26
#245Activation-Space Order-Swap Geometry: A Site-Asymmetry AuditAnqi Peter Lics.LG2026-08-26
#246Two Dimensions Govern Agnostic Multiclass Transductive LearningPahan Dewasurendracs.LG2026-08-26
#247Neither Precision Nor Architecture Alone: Controlled Tests of Failure Remedies for Physics-Informed Neural NetworksJinyuan Zhang, Peng He, He Hu +2cs.LG2026-08-26
#248Beyond Pairwise Feedback: Listwise Vision-Language Supervision for Preference-Based Reward LearningSrivalli Katkuri, Maxwell Kawada, Juan Wachscs.LG2026-08-26
#249Escaping Low-Dimensional Overlap: Multi-Task Model Merging via High-Dimensional Sparse DisentanglementYihang Zhang, Shengke Sun, Junjie Wen +1cs.LG2026-08-26
#250PaSta: Noisy Node Classification with Partial Label LearningYujing Liu, Yixin Liu, Yu Zheng +3cs.LG2026-08-26
#251Refusal geometry reflects refusal training: diverse refusal prefixes can raise stable rank and weaken refusal vector ablation attacksAndrey Labunetscs.LG2026-08-26
#252Joint Initialization of Flux Networks and Effective Multiplication Factor for Physics-Informed Neural Networks Solving Neutron Diffusion ProblemsQin Hang, Yangdi Yi, Jiayi Li +2cs.LG2026-08-26
#253Resolving Multi-Modal Regression by Difference-Quotient-Based Clustering:Fast Coarse Conditional-Label AssignmentHuang Weiquancs.LG2026-08-26
#254A Storage-Retrieval Gap in Parametric Knowledge Graph MemoryMartino M. L. Pulici, Cuong Xuan Chu, Evgeny Kharlamov +1cs.LG2026-08-26
#255FedQoS: Federated QoS-Risk Learning for Heterogeneous Indoor-Outdoor Access SelectionNguyen Van Thieu, Ti Ti Nguyen, Ons Aouedi +3cs.LG2026-08-26
#256Resilient Decentralized Wireless Federated Learning via Gradient Tracking with AdamWNguyen Van Thieu, Ti Ti Nguyen, Ons Aouedi +2cs.LG2026-08-26
#257Reflection Steering: Disentangling Reflection from Reasoning in Activation Space for Token-Efficient InferenceJiarui Hu, Zhiyuan Wen, Xiaoyun Liu +2cs.LG2026-08-26
#258Interpreting Protein Language Model Embeddings via Orthogonal Projection for Protein Fitness PredictionPaulo Yanez Sarmiento, Pia Francesca Rissom, Manuel Pfeuffer +6cs.LG2026-08-26
#259Beyond Optimal Rates in Stochastic Optimization: Trajectory-Adaptive Stopping RulesLiviu Aolaritei, Lucas Lévy, Francis Bach +1cs.LG2026-08-26
#260Physics-Informed Foresight Pruning for Sparse PINN Solvers of Nonlinear PDEsAhmad Ishaque Karimi, Uvini Balasuriya Mudiyanselage, Kookjin Leecs.LG2026-08-26
#261Beyond Scaling: Self-Evolving LLM Agents for Hardware Kernel Optimization via an Experience-Driven Workflow and Experience Graph MemorySiyuan Chen, Runlin Hou, Shenxiu Wu +7cs.LG2026-08-26
#262Individual Fairness in Hierarchical ClusteringBinita Maity, Shrutimoy Dascs.LG2026-08-26
#263M-Fibration Theory with Applications to Neural Network CompressionPaolo Boldics.LG2026-08-26
#264Frequency-aware forecasting for short-term typhoon gust predictionXuefei Wang, Tingyi Liu, Heng Zhang +2cs.LG2026-08-26
#265DCEO: Direct Causal Effect Optimization for Long-Term User Value Modeling in E-commerce SearchJunzhao Zhang, Tao Zhang, Liren Yu +4cs.LG2026-08-26
#266A Token-Level Analysis of Sampled-Token Reverse-KL On-Policy DistillationBing Shao, Jiazheng Zhang, Long Ma +11cs.LG2026-08-26
#267LDAC-Net: A Learnable Multi-Lag Differencing Attention-Convolution Network for Drift-Robust Recognition with Low-Cost MOX Gas SensorsXin Zhang, Liangxiu Han, Yue Shi +1cs.LG2026-08-26
#268Adversarial Training of Linear Models under Stealthy AttacksLovisa Eriksson, Dave Zachariah, André M. H. Teixeiracs.LG2026-08-26
#269Modeling spatio-temporal locality in multi-step forecasting of geo-referenced time seriesAnnunziata D'Aversa, Gianvito Pio, Michelangelo Cecics.LG2026-08-26
#270Tropospheric temperature and humidity profile retrieval from Meteosat Flexible Combined Imager based on deep learningAlejandro Salgueiro, Johannes Rausch, Julie Thérèse Villinger +1cs.LG2026-08-26
#271Fairness-Aware Test-Time Prompt TuningYoann Launay, Parameswaran Kamalaruban, Tom Kempton +2cs.LG2026-08-26
#272It's a matter of timescale: non-linear utility in successor features and multi-objective planning and learningLiam P. H. Mertens, Lucas N. Alegre, Florent Delgrange +3cs.LG2026-08-26
#273Are LLM-Enhanced GNNs Privacy-Safe?Longzhu He, Zelang Wen, Chaozhuo Li +1cs.LG2026-08-26
#274NeuronFuzz: Safety Neuron Guided Fuzzing for LLM Safety EvaluationZhiyuan Xu, Muhammad Firhard Roslan, Joseph Gardiner +2cs.LG2026-08-26
#275Why Does Graph Learning Fail to Fully Benefit from a Text Teacher?Fumiaki Kimino, Ryoma Satocs.LG2026-08-26
#276A Constitutive Markov Physics-Informed Neural Operator (MPNO) for Autoregressive Stability in Transient DynamicsWenpu Du, Peng Zhou, Yunlong Xia +5cs.LG2026-08-26
#277Comparing Corrupted Constrained Learning ProblemsLaura Iacovissi, Rabanus Derr, Robert C. Williamsoncs.LG2026-08-26
#278TailSFT: Filtered Fine-Tuning Improves Post-Training PerformanceSadhika Malladi, Samy Jelassi, Dylan Foster +2cs.LG2026-08-26
#279Learning from waste: Machine Learning for health risk prediction and computer vision-based sorting in GhanaHilda Adwubi Osei, Catherine Tenewaa Osei, Desdemona Yaa Asobayirecs.LG2026-08-26
#280Drift-Aware Multimodal User Representation Learning via Multi-Scale Temporal Modeling and Sparse Mixture-of-ExpertsZiqing Qian, Haohang Chen, Shengqi Dang +4cs.LG2026-08-26
#281EXAONE Tabular 1.0 : Technical ReportMoonjung Eo, Min-Kook Suh, Hye-Seung Cho +4cs.LG2026-08-26
#282Cooperative Multi-Agent Reinforcement Learning for Adaptive Aggregation in Semi-Supervised Federated Learning with non-IID DataRene Glitza, Luca Becker, Rainer Martincs.LG2026-08-26
#283Geometry-Constrained Kolmogorov-Arnold Networks: Learning Edge Geometry via Banach DualityK S Sesh Kumarcs.LG2026-08-26
#284Canalization Before Generalization: Grokking as a Dynamical ProbeYiming Lincs.LG2026-08-26
#285Learning Continuous Regional Temperature Fields with Lead-Time and Resolution QueriesChunlei Shi, Jiong Wang, Yi-Lin Wei +4cs.LG2026-08-26
#286VINCENT: Validated Interaction Network for Cross-drug Explanation of TherapeuticsFan-Sheng Chuang, Xuchen Li, Yujing Bian +1cs.LG2026-08-26
#287CEDAR: Controlled and Event-Driven Demand Forecasting via Residual DecompositionJunjie Meng, Ranxu Zhang, Zi-an Zhang +6cs.LG2026-08-26
#288How Edge of Stability Hinders SCAFFOLD in Federated OptimizationAnant Khandelwal, Michael Crawshaw, Mingrui Liucs.LG2026-08-26
#289A General-Purpose Molecular Foundation Model Transfers Across Diverse Olfactory TasksYikun Han, Yi Wang, Neil Mankodi +2cs.LG2026-08-26
#290Towards A Unified Information Bottleneck Framework for Time Series ExplanationsXu Zheng, Zichuan Liu, Zhuomin Chen +7cs.LG2026-08-26
#291Forecasting Multiple Observables with SCROLL: Score-Trained Uncertainty for Stochastic DynamicsPavel Prochazkacs.LG2026-08-26
#292Quantum-Inspired Modeling of Driving BehaviorMohammad Elayan, Omid Armantalab, Wissam Kontarcs.LG2026-08-26
#293One Symptom, Three Levers: A Critical Review of On-Policy Self-DistillationJustin Robert, Raheel Qadercs.LG2026-08-26
#294When Pruning Meets Interpretability: Preserving Sparse Autoencoder Robustness in LLMsSuchit Gupte, Xueru Zhang, Mohammad Mahdi Khalilics.LG2026-08-26
#295Spectral Allocation: Why Muon Outperforms Adam, and How to Improve MuonXiaodong Wu, Wenyi Yu, Chao Zhang +1cs.LG2026-08-26
#296DualOPSD: Adaptive Privileged Teachers for On-Policy Self-DistillationYutong Chen, Guangfu Guo, Zhichao Xu +1cs.LG2026-08-26
#297Robust CurveMoE: Multi-Norm Adversarial Defense for Mixture-of-Experts Models via Mode ConnectivityXu Zhang, Ren Wangcs.LG2026-08-26
#298How Much Rank Does LoRA Need? Rank-Error Bounds for Transformer AttentionGerard Conangla Planescs.LG2026-08-26
#299Group-Shared Low-Rank Approximation for Mobile-Efficient Pointwise Convolutions in Large-Kernel CNNsHao Luo, Yiting Yang, Wenyi Zhao +10cs.LG2026-08-26
#300Pruning Binarized Neural Networks: A Dedicated Framework and Globally Weighted AlgorithmsRoan Rubiales, Jean Pierre Davidcs.LG2026-08-26
#301ICON Decomposition: Auditing Deep Neural Networks with Multivariate Variance-based Concept-level ExplanationsRoshan Prakash Rane, Marco Simnacher, Manuel Pfeuffer +7cs.LG2026-08-26
#302TraceML: An Empirical Analysis of Human-Agent Planning in Machine Learning DevelopmentJiarui Yan, Weiwei Sun, Sijie Li +2cs.LG2026-08-26
#303Agentic Autoresearch for Cell-Edge Power Control: Radically Redefining the Researcher's RoleAhmad Khan, Akram Bin Sediq, Sara Azadegi Naeini +1cs.LG2026-08-26
#304Muon with Finite Newton-Schulz: The Smoothing Benefit in Nonsmooth Nonconvex OptimizationMingyi Li, Taira Tsuchiyacs.LG2026-08-26
#305Algebraic Multigrid Acceleration for Efficient Label SpreadingAntonia van Betteray, Jonathan Klees, Miriam Schäfers +1cs.LG2026-08-26
#306Privacy Without Regret: Differentially Private Inference-Time AlignmentIshi Jain, Nandini Bhattad, Sayak Ray Chowdhurycs.LG2026-08-26
#307Beyond Capability Benchmarks: Learning Operational Fingerprints of LLM Cloud Services from Production Incident MetadataMeiwei Zhang, Eduardo Miranda, Bruce Baynes +4cs.LG2026-08-26
#308CG4AI: A Column Generation Framework for Training AI Models Under ConstraintsYoucef Magnouche, Abderrahmane Driouch, Sébastien Martin +1cs.LG2026-08-26
#309The Latent Diagnostic Taxonomy: A Framework for Constructing Classifiers and Diagnosing Their Decisions, Applied to Prompt Injection DetectionJaturong Kongmanee, Smile Thanapattheerakulcs.LG2026-08-26
#310FedCMAPSS: A Benchmark for Federated Learning in Remaining Useful Life EstimationAmelia Sorrenti, Matteo Pennisi, Concetto Spampinato +1cs.LG2026-08-26
#311NeoTriFuse: Reliability-Aware Multimodal Fusion under Missingness Heterogeneity for Neonatal Mortality Risk PredictionJiyuan Tian, Qincheng Shen, Ye Lin +2cs.LG2026-08-26
#312Subgraph Filtering for Fair Graph Neural NetworksHaohui Lu, jiyuan Tian, Fangyu Zhou +1cs.LG2026-08-26
#313Toward Equitable Low-Carbon Mobility: Fairness-Aware Demand Prediction for Expanding Bike-Sharing SystemsMan Luo, Yixuan Zhaocs.LG2026-08-26
#314Distributed Training using an Intelligent NetworkNihar Shah, Ben Bliercs.LG2026-08-26
#315Diff Mining: Logit Differences Reveal Finetuning ObjectivesGreg Kocher, Robert West, Clément Dumas +1cs.LG2026-08-26
#316Active Curriculum Refinement for Reinforcement LearningZhenya Liu, Yuxin Chencs.LG2026-08-26
#317BVR Sim: An Open and High-Throughput Environment for Heterogeneous Air-Combat Reinforcement LearningHaocheng Sun, Mulai Tancs.MA2026-08-26
#318ES-AHD: An Evolution Strategy Framework for Automatic Heuristic DesignYutao Lai, Kezhao Lai, Hai-Lin Liu +2cs.NE2026-08-26
#319Homo-RAG: Homology-Guided Retrieval-Augmented Generation for Cross-Species Gene Function PredictionAzrin Sultanacs.NE2026-08-26
#320AERIS: Offline Policy Improvement for Multi-UAV Integrated Sensing and CommunicationZiyuan Wang, Yifan Sui, Wei Wei +5cs.NI2026-08-26
#321Generative Action-Chunk Sampling for Adaptive Stiffness Control in Physical Human-Robot CollaborationAoi Otake, Ferdinand Hartmann, Ko Igari +1cs.RO2026-08-26
#322A Tendon-Driven Five-Fingered Hand with Distributed Tactile Perception for Dexterous ManipulationHuayang Chen, Longhui Qincs.RO2026-08-26
#323ConfAL-WM: Confidence-Guided Active Learning for Action-Conditioned World ModelsXiang Liu, Sen Cui, Changshui Zhangcs.RO2026-08-26
#324Leveraging Inter-object Affordances for Efficient Planning in Contact-rich TasksPouya P. Niaz, Justus Piater, Alejandro Agostinics.RO2026-08-26
#325LM-X: Explainable Action Modeling with Progress, Event, and Uncertainty Prediction for Generalist Robot ManipulationJin Lou, Zhiyuan Jing, Andong Chen +20cs.RO2026-08-26
#326TacForcing: Streaming Action Generation with Execution-Time Tactile FeedbackJianbo Zhou, Boyuan Zhao, Yuzheng Zhang +8cs.RO2026-08-26
#327A Statistical Audit of Physical AI Benchmark RedundancyZaruhi Navasardyan, Hrant Davtyancs.RO2026-08-26
#328$R^3$: Training Robots to Reason in Natural Language via Reinforcement LearningLehong Wu, Yuxiao Qu, Zheyuan Hu +4cs.RO2026-08-26
#329Gating Before Commitment: Anticipating Intent Divergence to Prevent Post-Interaction Decision Failures in Autonomous DrivingCong Xu, Ravi Sankarcs.RO2026-08-26
#330Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task GeneralizationJiaming Zhou, Qihang Zhang, Gangwei Xu +9cs.RO2026-08-26
#331Constraint-Aware Physics-Informed Neural Networks for Static Shape Estimation of Co-Manipulative Continuum RobotsRana Danesh, Pari Qarehdaghi, Farrokh Janabi-Sharifics.RO2026-08-26
#332A Training-Free Proactive Defense Against Partial Speech Manipulation via Self-Embedding SteganographyYigitcan Özer, Zhe Zhang, Wanying Ge +2cs.SD2026-08-26
#333Combining Self-Embedding Audio Watermarking with Ultra-Low-Bitrate Neural CodecsYigitcan Özer, Xin Wang, Zhe Zhang +1cs.SD2026-08-26
#334Attention-Guided Reliability Scaling for Contrastive Decoding in Robust Audio-Visual Speech RecognitionYoungChae Kim, Da-Hee Yang, Joon-Hyuk Changcs.SD2026-08-26
#335Dissonance Spectrum explicitly models perceptual frequency interactions for better music understandingTianle Wang, Xinyi Tong, Liangke Zhao +7cs.SD2026-08-26
#336StreamAV-Bench: A Comprehensive Benchmark for Streaming Audio-Video GenerationKaiqi Liu, Haoxuan Zeng, Jingqi Liu +7cs.SD2026-08-26
#337Decay-Region Group Delay as a Forensic Cue for AI-Generated Impulsive SoundsJaeHyeong Chang, Chengzhe Sun, Siwei Lyucs.SD2026-08-26
#338SpeechGym: An Audio-Native Gym for Training Voice Agents via Reinforcement LearningJiajun Fan, Jingyuan Li, Prashanth Gurunath Shivakumar +6cs.SD2026-08-26
#339A Few Pages of Markdown: Committed AI Configuration and Lower Quality Cost after Coding-Agent AdoptionYegor Denisov-Blanch, Shyam Agarwal, Pavel Azaletskiy +5cs.SE2026-08-26
#340Fairness Invariants: A Relational Approach to Explaining and Mitigating Fairness BugsRanit Debnath Akash, Ashish Kumar, Gang Tan +1cs.SE2026-08-26
#341RotDroid: Cross-Orientation State Equivalence Testing for Detecting GUI Rotation Bugs in Android AppsMengdi Qin, Bo Jiangcs.SE2026-08-26
#342A Hybrid Usability Approach for Rating Evaluation of M-Commerce ApplicationsAhmad Ibtisam, Bilal Khan, Arshad Alics.SE2026-08-26
#343From General Agents to RCA Experts: A Self-Evolving Harness for Root Cause AnalysisHaiyu Huang, Jiewei Lyu, Zhihan Jiang +5cs.SE2026-08-26
#344Why ML-based cough models do not generalize: a systematic cross-dataset evaluation for tuberculosis screeningWensi Zhang, Tomas Teijeiro, Jérôme Thevenot +1eess.AS2026-08-26
#345VoiceMem: Streaming Dual-Brain Memory for Real-Time InteractionZhifei Xie, Jiaqi Lang, Ze An +7eess.AS2026-08-26
#346Token-Oriented Semantic Communication with Pretrained Vision TransformersJiwoong Im, Minwoo Kim, Jaeho Lee +2eess.SP2026-08-26
#347CardioFusion-AI: Robust ECG--PPG Fusion for Multimodal Physiological Monitoring Under Signal DegradationNavaneetha Krishnan Kamalakannan, Janakiraman Kamalakannaneess.SP2026-08-26
#348Goodput Maximization for Large Language Model Edge Inference: A Two-Phase Maskable PPO ApproachXiaojing Chen, Qi Zhang, Wei Ni +2eess.SY2026-08-26
#349Classical and Hybrid Quantum Machine Learning for Trigger-Like Event Selection on CMS Open Data: An Eight-Qubit, PCA-Constrained BenchmarkTariq Mahmood, Muhammad Awais Rafique, Talab Hussain +3hep-ph2026-08-26
#350Data-driven Effective Modeling of Stochastic Chemical Reaction NetworksYuan Chen, Weize Mao, Dongbin Xiumath.NA2026-08-26
#351Adaptive Hybrid Subspace Levenberg Marquardt Algorithm with Adequacy Monitor for Large Scale Least Squares ProblemsM. Duc Hoang, Timothy J. Lewismath.NA2026-08-26
#352A Multi-View Coupled Tensor Decomposition for Lightweight Online Adaptive Traffic PredictionQuan Yu, Jie Ni, Yu-Hong Dai +1math.OC2026-08-26
#353The Value of Human ExpertiseBradley Sturtmath.OC2026-08-26
#354Missing the Butterfly and Predicting the Past: Features or Bugs of Accurate AI Weather Models?Pedram Hassanzadeh, Weidong Li, Y. Qiang Sun +4physics.ao-ph2026-08-26
#355Energy Yield and Lifetime Climate Classification via Machine Learning for Optimizing Photovoltaic Module Design and MaterialsYouri Blom, Sofia Dutto, Alexandru Costache +7physics.comp-ph2026-08-26
#356Continually learning neural-operator surrogate for three-dimensional airborne electromagnetic Bayesian inversionJaehong Chung, Andrew Lockwood, Jef Caersphysics.geo-ph2026-08-26
#357Towards a universal meta-optics solver via large language modelsHuanshu Zhang, Lei Kang, Yuyan Chen +3physics.optics2026-08-26
#358Real-time virtual circuits for plasma shape control via neural network emulators: integration and testing in the MAST-U PCSMatthew J. Marshall, Edward Jones, Graham J. McArdle +10physics.plasm-ph2026-08-26
#359Prompt Sensitivity of Generative Agents: Evidence from an Epidemic ModelRoss Williams, Niyousha Hosseinichimehphysics.soc-ph2026-08-26
#360District-Level Food Environment Indicators and Social Vulnerability in São PauloPedro Lemes Sixel Lobo, Eric Tokuda, Kuruvilla Joseph Abraham +4physics.soc-ph2026-08-26
#361A meta-algorithm for ab initio reconstruction of complex mixtures in cryo-EMAlkin Kaz, Arda Kaz, Ellen D. Zhongq-bio.BM2026-08-26
#362Propensity Straight-Through Gradients for Discrete Stochastic SystemsJose M. G. Vilar, Leonor Saizq-bio.QM2026-08-26
#363Interpreting Latent Protein Language Model Features with Geometric AnnotationsSiddharth Setlur, Djordje Mihajlovic, Darrick Leeq-bio.QM2026-08-26
#364A causal graph-informed temporal convolution architecture for interpretable retail electricity price forecastingYufan Ji, Abdollah Shafieezadeh, Noah Dormadystat.AP2026-08-26
#365SAUSS: Stochastic Approximation with Unbiased Simulated Scores for Limited Dependent Variable ModelsSokbae Lee, Yuan Liao, Myung Hwan Seo +1stat.ME2026-08-26
#366Functional linear regression from sparse to dense designs: a pooling-ridge method and minimax optimalityShunxing Yan, Fang Yaostat.ME2026-08-26
#367Controlling for Omitted Variable Bias in Deep Neural NetworksManuel Pfeuffer, Roshan Prakash Rane, Kerstin Ritter +1stat.ME2026-08-26
#368Adaptive Regularization for Random Features: A Neighboring Early-Stopping Rule with Oracle-Rate GuaranteesCaixing Wang, Zhibo Chen, Yue Wangstat.ML2026-08-26
#369TRACE: Retrospective Streaming Generation of Physical Fields under Sparse Structured SensingXinyu Zhang, Lihao Chen, Panqi Chen +4stat.ML2026-08-26
#370Fast rates in Bayesian online learning with approximate posteriorsIlsang Ohnstat.ML2026-08-26
#371Multi-output Gaussian process prediction of physical fields under linear equality constraintsMahamat Hamdan Nassouradine, Clément Gauchy, Pierre-Emmanuel Angeli +1stat.ML2026-08-26
#372Efficient Estimation of High Information Projections using Nearest NeighboursDavid P. Hofmeyrstat.ML2026-08-26

latest · arXiv announcement batches follow US Eastern weekdays