PaperScope
LIVE · 2026-09-04 05:40 UTC

New Papers · 2026-09-03 326 submissions

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

#TitleAuthorsCatDate
1Computing stable configurations of confined smectic liquid crystals with a deep variational frameworkYuchen Xie, Baoming Shi, Yucen Han +1cond-mat.soft2026-09-03
2Speculative Macro Commit for Faster Tool-Using AgentsZeyu Liu, Souvik Kundu, Peter A. Beerelcs.AI2026-09-03
3Fresh Memory, Stale Plans: Dependency-Scoped Validation for Distributed LLM-Agent MemoryEvan Chen, Shiqiang Wang, Christopher G. Brintoncs.AI2026-09-03
#4A Prompt-Engineering Approach to Develop Scalable, Flexible, and Real-Time Hybrid Micro-Level Personalization in a General Purpose AI Teaching AssistantSaptarshi Basu, Sandeep Kakar, Ashok Goelcs.AI2026-09-03
#5Caught in the Story: Narrative Captivity in Multi-turn LLMs ConversationYuhe Wu, Guangyu Wang, Yujie Chen +7cs.AI2026-09-03
#6Dude: A Dual-Detection Multi-Agent System for Paper-Code Discrepancy DetectionWeijie Liu, Running Zhao, Wenhao Yuan +4cs.AI2026-09-03
#7DuplexSpeechBench-IFEval: Evaluating Implicit Instruction Following in Full-Duplex Voice AgentsPuneet Mathur, Dinesh Manochacs.AI2026-09-03
#8Do GUI Agents Know When Not to Act? Enabling Conflict-Aware Termination for Multimodal GUI AgentsZhaoyuan Huang, Tianjie Ju, Pengzhou Cheng +7cs.AI2026-09-03
#9Beyond "Made with AI": Visualizing Provenance Density to Mitigate the Transparency PenaltyQing Zhang, Yifei Huang, Juyoung Lee +2cs.AI2026-09-03
#10AutoGraphForge: Towards Automated Graph Theory DiscoveryJán Pastorekcs.AI2026-09-03
#11Making Every Tool Call Count: Necessary Tool-Evidence Path Rewards for Agentic Vision-Language ModelsXingming Long, Yu Liu, Zhiwei Yang +7cs.AI2026-09-03
#12GrowPage: On-Demand KV Budgeting for Efficient LLM Reasoning ServingQiankun Ma, Yanjiang Zhou, Zinan Xiong +5cs.AI2026-09-03
#13PPO-STGNN: A Proximal Policy Optimization Approach with Spatio-Temporal Graph Neural Networks for DAG Task Scheduling in Cloud-Edge-End ComputingYangshuo Qi, Chenwei Wang, Zihan Shen +1cs.AI2026-09-03
#14What Matters for Aggressive Decoding-Time KV Eviction? Temporal Aggregation and Ranking PreservationBo Zeng, Yu Zhao, Yefeng Liu +3cs.AI2026-09-03
#15CulturalMenuBench: Probing the Knowledge-Application Gap in Multimodal Culinary ReasoningBo Zeng, Linfeng Gao, Peiqin Lin +9cs.AI2026-09-03
#16NeoRed: A Knowledge-Logic-Alignment Multimodal Large Language Model for Neonatal Respiratory Disease DiagnosisYinan Liu, Hongtai Xia, Haoran Xu +3cs.AI2026-09-03
#17Feature Reconfiguration With Visual Prior for Medical Lesion SegmentationYinan Liu, Jiankang Hong, Zhen Gao +1cs.AI2026-09-03
#18Dalek: A Constructive Agent MachineWanpeng Xiecs.AI2026-09-03
#19GPS-Bench: A Governance Policy Benchmark for Automating Policy AnalysisLinh Le, Melanie Bui, My Chiffon Nguyen +2cs.AI2026-09-03
#20HalluPeer: A Taxonomy-driven Benchmark for Detecting Hallucinations in Scientific Peer ReviewsTzu-Ling Lin, Dong-Ting Yao, Teng-Fang Hsiao +2cs.AI2026-09-03
#21The Attention Triangle in Audio-Video ModelsSagi Polaczek, Noa Kraicer, Gal Metzer +4cs.AI2026-09-03
#22KC-Bench: A Dynamic Interactive Benchmark for Evaluating Knowledge Conflicts in LLM AgentsYaxing Lyu, Shengjie Zhou, Binbin Toh +2cs.AI2026-09-03
#23A computable representation of the physical laboratory enables verifiable workflowsXiaobo Li, Luyao Ge, Xiaohui Li +8cs.AI2026-09-03
#24Analysis of Prompt Engineering for Drug Toxicity PredictionMia MacGregor, Aakash Welgamage Don, Mark Bartlettcs.AI2026-09-03
#25Synthetic Semantic Supervision for Contrastive Code Representation Learning in Small Transformers: An Empirical StudyKenneth Paulsen, Florian Tambon, Mike Papadakis +1cs.AI2026-09-03
#26Counterfactual Routing Using Integer Programming with Constraint GenerationDaniël Vos, Sterre Lutzcs.AI2026-09-03
#27Artificial Intelligence for Energy Optimization in Data CentersMohammed Basharath Ullah, Summaiya Unnisa Begum, Mohammed Nadeem Ullahcs.AI2026-09-03
#28Proactive Service Agents: A Unified Decision Framework, Methods, and EvaluationYan Tang, Tingyu Cao, Yuanbo Tang +2cs.AI2026-09-03
#29SimSkill: A Lifelong Learning AI Agent for Autonomous Mastery of Traffic SimulationQi Liu, Qinzheng Wang, Yiming Biecs.AI2026-09-03
#30Rethinking World Models for Safety-Critical Embodied SystemsKailang Ma, Heye Huang, Inhi Kim +1cs.AI2026-09-03
#31DNative-Twin: Decision Graphs and Digital Twins for Reconstructable Agentic DecisionsJunjie Pang, Zhenzhen Xie, Haoke Han +3cs.AI2026-09-03
#32Transfiver: Human-AI Co-Inference through a Shared Editable StateMinji Park, Seunghyun Yoon, Hyuk Limcs.AI2026-09-03
#33Govern the Model, Not Only the Data: Storage, Circulation, and Learning in Creative AIPhoenix Perry, George Simms, Elizabeth Wilson +9cs.AI2026-09-03
#34SVG-Score: Human-Aligned Evaluation of Text-to-SVG GenerationMarco Cipriano, Leonardo Zini, Alexandra Schild +5cs.AI2026-09-03
#35CauseCollab: Causal Unified and Modality-Agnostic Network for Heterogeneous Collaborative PerceptionWeize Li, Yang Li, Quan Yuan +3cs.AI2026-09-03
#36Semantic Bayesian World ModelsTommaso Sorucs.AI2026-09-03
#37Adapting to Evolving Requirements: Agentic AI for Retail Supply Chain OperationsLei Zheng, Liping Yang, Zihao Li +3cs.AI2026-09-03
#38Bioinfoysis Technical ReportQingyang Shao, Xin Zhang, Zhouyang Yuan +24cs.AI2026-09-03
#39STAIR (STructure Aware Information Retriever): A novel dataset and LLM based retriever for document structure augmentationVineet Kumar, Meghanadh Pulivarthi, vishwajeet kumar +3cs.AI2026-09-03
#40Xiaomi-TabLDM: A Tabular Foundation Model Technical ReportXiaomi-TabLDM Team, :, Penghui Wang +10cs.AI2026-09-03
#41Inferring Affective Consciousness in an Artificial Agent: A Case StudyMark Solms, St John Grimbly, Bruce Bassett +7cs.AI2026-09-03
#42Lose the Order, Keep the Hierarchy: Deordering HTN PlansTakudzwa Togarepi, Gaspard Quenard, Damien Pellier +1cs.AI2026-09-03
#43Value-Preserving Architectures for Agentic AI SystemsAlessandro Pesare, Tommaso Dolci, Katja Hose +1cs.AI2026-09-03
#44Speak for Me: Giving LLMs the Situational Awareness to Participate in a MeetingMuneeb Khan, Frederic Kirstein, Terry Ruas +1cs.AI2026-09-03
#45Towards Numerical TOHTN Planning with SMT-based HTN-SAT EncodingGaspard Quenard, Takudzwa Togarepi, Damien Pellier +1cs.AI2026-09-03
#46More Criticism Does Not Make a Better Review: EquiReview-RZexing Zhang, Jichao Li, Tianyang Lei +2cs.AI2026-09-03
#47FiMI Banking: A Sovereign Model for Indian Retail BankingNPCI AI Research Team, Aman Kumar, Asit Desai +15cs.AI2026-09-03
#48Interface-Induced Trajectory CensoringWenbo Wangcs.AI2026-09-03
#49Common-Witness Certificates and Sharp Feature Bounds for Counterfactual Image AuditingUsef Faghihi, Amir Sakics.AI2026-09-03
#50The Dually Flat Geometry of Planning as InferenceNikola Milosevic, Asaki Kataoka, Nicolas Hinrichs +2cs.AI2026-09-03
#51LLM4CKD: Large Language Models for Early Stage Chronic Kidney Disease ScreeningMuhammad Ashad Kabir, Sirajam Muniracs.AI2026-09-03
#52InSituMeasure: Probing Situated Measurement Grounding in Industrial Scenes with Multimodal Large Language ModelsChao Shen, Xinyuan Li, Yunfan Zhou +4cs.AI2026-09-03
#53FLY-EVAL++: An Evidence-Driven Evaluation Protocol for Safety-Constrained Flight Prediction with Large Language ModelsYalun Wu, Junfeng Fang, Jiawei Wang +6cs.AI2026-09-03
#54Instruction Duplication as an Inference-Time Control PrimitiveVictor Lavrenkocs.AI2026-09-03
#55IRWOZ 2.0: A Large Language Model-driven Dialogue Dataset for Industrial Robot ConversationsChen Li, Dimitrios Chrysostomoucs.AI2026-09-03
#56Spurious Advantage Hidden in GRPOJiamian Wang, Samyadeep Basu, Koustava Goswami +2cs.AI2026-09-03
#57DRACO: Fine-Grained Credit Assignment with Dynamic Rubrics for Long-Horizon Agent TrainingShubham Gandhi, Saurabh Goyal, Kiran Kate +1cs.AI2026-09-03
#58Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLMSergii Kozyrev, Davyd Maiborodacs.AI2026-09-03
#59Epistemic Warrant for LLM Recommendations: Characterizing the Basis for Reliance When Ground Truth Is UnavailableShai Vardi, João Sedoccs.AI2026-09-03
#60Environment Evolution for Terminal AgentsZhiyuan Fan, Tinghao Yu, Yuanjun Cai +9cs.AI2026-09-03
#61The Natural Language Interaction Protocol and Standard for AI AgentsLuyi Xing, Rasit Onur Topaloglu, Ranjan Sinha +9cs.AI2026-09-03
#62Efficient Test-Time Adaptation through Human-AI InteractionZora Zhiruo Wang, Apurva Gandhi, Rulin Shao +22cs.AI2026-09-03
#63Terminal-Universe: Turning Agent Trajectories into Scalable Terminal EnvironmentsJie Wu, Zhenru Zhang, Beichen Zhang +11cs.AI2026-09-03
#64From Deceptive Outputs to Deceptive Mechanisms: A Causal Framework for Language-Model Deception ResearchYakov Pyotr Shkolnikovcs.AI2026-09-03
#65A Case Study on Emergent Cheating and Whistleblowing in Autonomous Research SwarmsDavide Paglieri, Logan Cross, Tim Genewein +3cs.AI2026-09-03
#66Rethinking On-Policy Distillation of Large Language Models II: One Training ExampleZixuan Fu, Bingxiang He, Yuxin Zuo +10cs.AI2026-09-03
#67A Computationally Feasible Framework for Causal Probabilistic ExplanationRafal Urbaniak, Sam Witty, Daniel Waxman +7cs.AI2026-09-03
#68Clean Engineering, Unstable Measurement: A Preregistered Reliability Failure of Black-Box LLM Observers on Shared EndpointsHaoyaun Zhu, Jie Zhangcs.AI2026-09-03
#69LevelSyn: Physical-Aware Logic Synthesis via Level-Asynchronous Graph Neural NetworksJingyi Zhou, Zhengyuan Shi, Ziyang Zheng +1cs.AR2026-09-03
#70The Head Complexity of Boolean Functions in Single-Layer AttentionRajmohan Rajaraman, Ravi Sundaram, Amanuel Tesfayecs.CC2026-09-03
#71What Do CAE Simulation Agents Really Need Beyond a Generic Harness?Jiasheng Shi, Tianhan Zhangcs.CE2026-09-03
#72Differentiable Hybrid Modelling for Learning and Optimising Chemical Transport Processes from Experimental DataArthur Jessop, Mohammed Alsubeihi, Ben Moseley +1cs.CE2026-09-03
#73Influence of Extruded Filament Shape on Buildability in 3D Concrete Printing: A Geometry-Informed Deep Learning-FEM ApproachGiacomo Rizzieri, Saif-Ur-Rehman, Jörg F. Unger +1cs.CE2026-09-03
#74SGD-KV: Summarization Guided KV Cache CompressionZeyu Liu, Woomin Song, Xuandi Fu +5cs.CL2026-09-03
#75What Else Needs Fixing? Exploring Cost-Effective Test-Time Compute for Revision Propagation in Artifacts Generated Through ConversationDaisuke Kikutacs.CL2026-09-03
#76Contextual Tamil Spelling and Grammar Correction Using Progressively Fine-Tuned Sequence-to-Sequence TransformersKarthikeyan A, Jaya Nirmala S, Sangeetha Sivanesan +4cs.CL2026-09-03
#77PACE: Towards Surfacing Hidden Conflicts in User RequestsYoojin Kim, Jihyoung Jang, Hyounghun Kimcs.CL2026-09-03
#78Decoupling Turn-Taking from Semantics: A Decoupled Data Approach for Finite-State-Machine-Based Full-Duplex DialogueYihang Li, Chenhui Chucs.CL2026-09-03
#79How Perturbations Propagate: A Multi-Level Analysis of Robustness in Large Language ModelsDun Li Chan, Emily Liu, Niyathi Allu +1cs.CL2026-09-03
#80Less Is Moral: A CHARMing Framework for Moral Foundations Detection in Endorsement BehaviourHuixiang Fu, Marian-Andrei Rizoiucs.CL2026-09-03
#81FPCO-Dialog: A Multi-Turn False-Premise Benchmark for Correction and Cooperation in Vision-Language ModelsJiayuan Ma, Yuqi Lu, Weiyang Guo +5cs.CL2026-09-03
#82Accountable AI with Grounded, Faithful, Consistent, Actionable Rationales: A Case Study in Clinical Trial Matching with VERDICTZikai Zhou, Yufei Jin, Yilin Xu +3cs.CL2026-09-03
#83FrameBench:A Language Understanding Benchmark Based on Frame SemanticsChihiro Yano, Ryohei Sasanocs.CL2026-09-03
#84Chiaroscuro for Emotions: A Contrastive Emotion Benchmark Grounded in Appraisal TheoryDivyesh Bommana, Mohammad Saim, Tianyu Jiangcs.CL2026-09-03
#85TabScope: Question-Adaptive Scope Selection for Table Question AnsweringYuxiang Wang, Junhao Gan, Jianzhong Qics.CL2026-09-03
#86To What Extent Do Large Language Models Understand Bangla Idioms?Mousumi Akter, Md. Faiyaz Abdullah Sayeedi, Nurul Labib Sayeedi +1cs.CL2026-09-03
#87Lngram v2: Latent N-Gram Memory with Interpretable Discrete RepresentationsYunao Zheng, Bin Wen, Xiaojie Wangcs.CL2026-09-03
#88Random Attention: Rethinking KV Cache Eviction for Efficient ReasoningHeng Wang, Jielin Qiu, Wenting Zhao +7cs.CL2026-09-03
#89Decoupled Analysis-Judging: An Automated Creativity Evaluator Using LLMs in Complex Multi-step Creativity TasksXiangyu Wang, Jin Wu, Xiaoyu Li +2cs.CL2026-09-03
#90When Retrieval Helps: Selective Retrieval for Single-Turn Mental-Health QAHyunseo Oh, Chong-Kwon Kim, Yoonhyuk Choics.CL2026-09-03
#91When Users Don't Ask: Benchmarking Context-Driven Memory Retrieval in Conversational AgentsWen-Yu Chang, Yun-Nung Chencs.CL2026-09-03
#92Pattern Over-Generalization of Knowledge Graph EmbeddingJunsik Kim, Kangil Kimcs.CL2026-09-03
#93Building and Evaluating Fixed-Voice Thai TTS from Synthetic SpeechKunat Pipatanakul, Potsawee Manakul, Warit Sirichotedumrong +3cs.CL2026-09-03
#94Lost in Reordering: Structural Sensitivity of Multilingual LLMs under Semantics-Preserving PerturbationsKarthika Nhayakkat, Rajat Verma, Maharaj Brahma +4cs.CL2026-09-03
#95Language, Language Models, and What We're Talking AboutMalvina Nissimcs.CL2026-09-03
#96How Far Can Synthetic Data Take Thai OCR?Kunat Pipatanakulcs.CL2026-09-03
#97KhatianDoc: A Human-Verified Benchmark Diagnosing Multimodal LLM Failure on Bengali Legal Land RecordsTasmiad Hasan, Arafat Zaman Ratul, Sarker Sadman Saalim +3cs.CL2026-09-03
#98Remember and Reweight: Enhancing Multi-Agent Debate with Experience Memory and Confidence EstimationXuanfa Jin, Zhijian Ma, Yongcheng Zeng +3cs.CL2026-09-03
#99</think> Doesn't Stop Reasoning: Analysis of Spurious CoT TerminationSeunghee Koh, Sungjae Choi, Minchan Kwon +2cs.CL2026-09-03
#100The Impact of Synthetic Data Augmentation on Discourse-Pragmatic Function ClassificationSara Sorahi, Kevin Tang, Reza Kazemiancs.CL2026-09-03
#101Enhancing Financial Question Answering: A Novel Benchmark Dataset of Banks' financial statementsArianna Miola, Bruno Spaccavento, Lorenzo Silotto +2cs.CL2026-09-03
#102A Circuit for Plural Reference: How LLMs Represent and Retrieve Singular and Plural EntitiesAnh Danh, Rick Nouwen, Massimo Poesiocs.CL2026-09-03
#103Opening mind by opening architecture: analysis strategiesFrancesco Vitucci, Giuseppe Silvi, Daniele Giuseppe Annese +2cs.CL2026-09-03
#104Beyond BLEU: A Case for Redefining Sign Language Translation BenchmarksOline Ranum, Edward Fish, Simon Hadfield +1cs.CL2026-09-03
#105Typological Feature Prediction with Large Language Models: An In-Context Learning ApproachQianwen Wang, York Hay Ng, Aditya Khan +1cs.CL2026-09-03
#106IndicSafeEval: Safety Robustness of Large Language Models under Multilingual Persuasive Jailbreak AttacksSaikat Mondal, Mamta, Deeksha Varshney +2cs.CL2026-09-03
#107Evaluating Criterion-Conditioned Behaviour of Large Language Models in Content ModerationDanting Zhang, Bei Peng, Robert Loftincs.CL2026-09-03
#108Beyond Shallow Alignment: How Post-Training Methods Determine Refusal Circuits And Steering RobustnessHoang Cuong Nguyen, Mark Dras, Usman Naseemcs.CL2026-09-03
#109CROCODIL: Cross-Model Code Editing with LLMsLinghan Zhong, Aditya Thimmaiah, Jayanth Srinivasa +2cs.CL2026-09-03
#110RuleMem: Active Rule Memory for Long-Term Conversational AgentsXingyuan Zeng, Zuohan Wu, Quanming Yao +5cs.CL2026-09-03
#111Fixed Suffix Dependency Ratio: Quantifying the Dual-Track Mechanism of Gender Assignment in Latvian LoanwordsYelingyun Zhang, Atis Kapenieks, Marina Platonovacs.CL2026-09-03
#112Beyond Majority Vote: Multi-Perspective Adjudication for Medical Hallucination DetectionJoe Cecil, Marjorie Freedmancs.CL2026-09-03
#113Two-Stage Reinforcement Learning for Sound and Adversarial Test Generation in Code LLMsJiacheng Xu, Wentao Zhang, Zhiyi Lyu +4cs.CL2026-09-03
#114Investigating the Ability of Large Language Models to Analyze Recipes for DiabetesRevathy Venkataramanan, Aditya Luthra, Venkatesan Nadimuthu +1cs.CL2026-09-03
#115Alignment-Free Text-Audiobox for Voice Dubbing and Full-Duplex Dialogue SynthesisSanyuan Chen, Min-Jae Hwang, Sho Inoue +12cs.CL2026-09-03
#116Representational alignment yields generalizable safety in language modelsLingyu Li, Yan Teng, Yingchun Wang +1cs.CL2026-09-03
#117Translation as a Decision Space: A Multi-Agent Perspective on Low-Resource Dialect GenerationHasan Alkhder, Mohammad Abboush, Igor Tchappi +2cs.CL2026-09-03
#118Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVRBoyan Li, Bingsen Chen, Chenghao Yang +3cs.CL2026-09-03
#119Last Translation BenchmarkVilém Zouhar, Niyati Bafna, Mukund Choudhary +241cs.CL2026-09-03
#120Knowledge Acquisition During Pre-training? Large Language Models Learn Better With Auxiliary ViewsJoseph Lee, Yidi Huang, Dokyoon Kim +2cs.CL2026-09-03
#121Legibility is Not Interpretability: Comparing Judged and Actual Importance in Chain-Of-Thought ReasoningKevin Du, Alexander Hoyle, Laura Ruis +1cs.CL2026-09-03
#122ESPO: Error-Structured Prompt Optimization via Diagnose, Diversify, and StabilizeLihao Liu, Peng Tang, Kunwar Yashraj Singh +1cs.CL2026-09-03
#123Compile by Training: Turning Natural-Language Specifications into Local Neural FunctionsYuntian Deng, Pengyu Nie, Stuart Shiebercs.CL2026-09-03
#124Spruce: Scalable Private Outsourced Retrieval Using Compact EmbeddingsPeichun Hua, Yunming Xiaocs.CR2026-09-03
#125Privacy, Robustness, and Fairness Trade-offs in Federated Intrusion Detection: Geometric Indistinguishability at the Aggregation InterfaceAdrita Rahman Tory, ABM Shawkat Ali, Md Abu Layek +1cs.CR2026-09-03
#126Rent-a-RAG: Embedding-Space Watermarks for Auditing Third-Party RAGAlexandr Goultiaev Tolstokorov, Kyriakos Mouratidis, Javad Dogani +1cs.CR2026-09-03
#127Flip, Don't Shuffle: Watermarking LLMs at the Speed of InferenceSimone Ceppi, Ignacio Sanchezcs.CR2026-09-03
#128A Blind Trust, the Bloody Thrust: When Attacker-Controlled Hook Updates Steer AI Agent Harnesses towards Malicious BehaviorsPengxun Li, Litian Zhang, Jianwei Hou +4cs.CR2026-09-03
#129PatchBench: Evaluating AI Agents for Vulnerability PatchingChihao Shen, Jiacheng Li, Aastha Mahajan +3cs.CR2026-09-03
#130A Non-Formulable Theorem: A Fundamental Limit of Finite Syntactic Systems and Its Consequences for Security and AIFabio F. G. Buonocs.CR2026-09-03
#131SENTINEL-RL: Offloading Topological Reasoning from LLM Agents in the Security Operations CenterUday Vallabhaneni, Cassie L. Cagwin, David J. Wildcs.CR2026-09-03
#132Counting Animals in Camera-Traps Image Sequences without Count Labels: Winning Solution to the iWildCam 2021 ChallengeFagner Cunha, Juan G. Colonna, Eulanda M. dos Santoscs.CV2026-09-03
#133An Ensemble-Based Self-Taught Learning Approach for Parking Space Classification Under Limited DataLucas de Oliveira Cunha, Joelton Deonei Gotz, Paulo Lisboa de Almeida +1cs.CV2026-09-03
#134MedQA-MM: Shortcuts Behind Medical Visual ReasoningBenlu Wang, Yifan Zhang, Jiaqing Yu +7cs.CV2026-09-03
#135Tensor-based Brain Surface Modeling and AnalysisMoo K. Chung, Keith J. Worsley, Steve Robbins +1cs.CV2026-09-03
#136Laplacian Frequency Hierarchies for Efficient 3D Gaussian Splatting TrainingYixiong Yang, Sisheng Zhang, Qingsong Yan +2cs.CV2026-09-03
#137PointGT: Simultaneous Geometry and Texture Editing for Point-Based RepresentationsYanshu Zhang, George Shramko, Pratul P. Srinivasan +1cs.CV2026-09-03
#138P-CORE: Self-Supervised Surface Consistency for Point-Based Neural EditingYanshu Zhang, Shichong Peng, Mehran Aghabozorgi +2cs.CV2026-09-03
#139When Depth Hurts: Reliability-Aware Geometry Distillation for Depth-Free RGB-D Salient Object DetectionXuehao Wang, Jiaxin Hua, Runmei Li +4cs.CV2026-09-03
#140FoRIS: Progressive Foreground Refinement for Training-Free In-Context SegmentationMing Hu, Jianfu Yin, Mingyu Dou +5cs.CV2026-09-03
#141Exploring the Potential of Contrastive Language-Image Pre-training for Multi-Source Remote Sensing DataXiangyang Miao, Kelu Yao, Yekai Huang +7cs.CV2026-09-03
#142Neural-Collapse-guided Task-Free Continual Anomaly DetectionXiaotong Kong, Chaoyang Song, Ziai Zhou +3cs.CV2026-09-03
#143Mudragen: Geometrically Supervised Generation of Interacting Two-Hand Mudras for Preserving Indian Classical Dance HeritageJagadish Kashinath Kamble, Jayanta Mukhopadhyay, Debaditya Roy +1cs.CV2026-09-03
#144When Do Frozen VLMs Respond to Image-Free Object-Token Edits? An Answer-Key-Free Protocol and What It RevealsWonbin Son, Gyumun Choi, Junil Seo +3cs.CV2026-09-03
#145OCR-EDR: Rendering-Aware Diagnosis and Repair for Closed-Loop OCR ImprovementLinnan Zhao, Kang Liu, Hao Yu +3cs.CV2026-09-03
#146Preserving Knowledge across Space and Time for Continual Video Deepfake DetectionTaehoon Kim, Jongwook Choi, Heejae Jo +2cs.CV2026-09-03
#147STARS-GS: Structure-Aware Regularized Gaussian Splatting for Large-Scale Aerial Surface ReconstructionBocheng Li, Wenjuan Zhang, Jie Pan. Dongxu Han +3cs.CV2026-09-03
#148Preprocessing Failure and Adversarial Detection in Depthwise-Separable Edge Vision SystemsJannatul Masruk Mukta, Rifa Sanjida, Adrita Rahman Tory +2cs.CV2026-09-03
#149BMCTrack-d: Pig re-identification and tracking via back marks in challenging camera settingsDavid Brunner, Maciej Oczak, Marie Bordes +3cs.CV2026-09-03
#150SafeRestore: Detector-Relative Risk Certificates for Selective Industrial Image RestorationShaoliang Yang, Jun Wangcs.CV2026-09-03
#151Tree species mapping in Denmark: A comparison of spectral-temporal features with geospatial foundation model embeddingsAlkiviadis Koukos, Spyros Kondylatos, Thomas Nord-Larsen +3cs.CV2026-09-03
#152Residual Optimal Transport-Based Experts Collaboration Towards Modality-Aware Infrared-Visible Object DetectionYue Zhao, Hua Yu, Yukun Zhao +6cs.CV2026-09-03
#153Neural Video Compression Based on Deformable Temporal Alignment and Difference-aware FusionChuyue Shan, Songlin Sun, Wang Chenwei +1cs.CV2026-09-03
#154TruncGradGS: Improved 3D Gaussian Splatting via Truncated Gradient UpdatesTheo Morales, Nhat-Quynh Le-Pham, Robin Atkins +1cs.CV2026-09-03
#155SafeRI: Recognition and Intervention for Token-Level Safety Intervention in Large Vision Language ModelsCaoyuan Ma, Tian Gu, Wenpu Liu +11cs.CV2026-09-03
#156WIDE: Wildcard Inference with Dynamic Expansion for Cross-Modal Generative RetrievalTeng Guo, Xin Wang, Jiayou Xu +3cs.CV2026-09-03
#157Building Pretraining Data for World Models: An Unreal Engine-Based Pipeline for Action-Conditioned Video GenerationHaoyu Wang, Songchun Zhang, Haoran Li +3cs.CV2026-09-03
#158FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlowByeongjun Park, Byung-Hoon Kim, Hyungjin Chungcs.CV2026-09-03
#159Occlusion-Robust Multimodal Emotion Recognition in VR via Fusion of Facial Images and EMGBirgit Nierula, Karam Tomotaki-Dawoud, Mert Akguel +5cs.CV2026-09-03
#160Drive-HWM: Hierarchical World Models for Dynamic-Latent Guided Autonomous DrivingZhaoxin Fan, Tianbao Zhang, Wenjun Wu +5cs.CV2026-09-03
#161Text2Thermal: Physics-Aware Thermal Image Synthesis from Textual PriorsTayeba Qazi, Brejesh Lall, Prerana Mukherjeecs.CV2026-09-03
#162SV-WAM: An Efficient Surround-View World-Action Model for End-to-End Autonomous DrivingJinyang Wang, Shiwei Li, Junjian Wang +12cs.CV2026-09-03
#163Auditing Patient Privacy in Medical Generative Models: Scalable Memorization Detection with DeepSSIM++Antonio Scardace, Francesco Guarnera, Sebastiano Battiato +1cs.CV2026-09-03
#164EraseSAE: Surgical Concept Erasure in Text-to-Video Diffusion Models via Sparse AutoencodersXinghao Wang, Dong Li, Wei Yu +5cs.CV2026-09-03
#165Stabilizing Camera-Controlled Novel View Synthesis at Inference TimePrajwal Singh, Arjun Badola, Seema Kumari +2cs.CV2026-09-03
#166Tree-Structured Vector Quantization For Efficient And Progressive Image CompressionXinkun Wang, Tianyi Xu, Qingyu Luo +4cs.CV2026-09-03
#167PL-SCEA: Reconfiguring Pretrained Attention for Few-Shot Industrial Anomaly DetectionXiaoyu Yang, Qixing Wu, Huixian Zhao +1cs.CV2026-09-03
#168Rethinking 3D Noise: Learning 3D-Aware Video Priors via Optimization-Free Morphological PerturbationsOnat Şahin, Mohammad Altillawi, George Eskandar +2cs.CV2026-09-03
#169Cross-Dataset Transfer and Reliability of Explainable Artificial Intelligence for RhythmFormer Remote PhotoplethysmographyLouis Chen, Torbjörn E. M. Nordlingcs.CV2026-09-03
#170ARCOS: Zero-shot Boundary Localization for Corneal Layer Segmentation Across Optical Coherence Tomography DevicesNuno Vivas Brás, Benjamin Memmi, Maëlle Bouhassane +4cs.CV2026-09-03
#171Do Video Generators Track the World Across Segments? A Benchmark and Method for World-State Reasoning in Video ContinuationYingmao Miao, Pengfei Zhang, Chaoran Xu +5cs.CV2026-09-03
#172CoFiE: Coarse-to-Fine Evidence Selection for Efficient Streaming Video UnderstandingJing Jiang, Yiran Ling, Ruonan Li +2cs.CV2026-09-03
#173Understanding Autonomous Driving Datasets by Describing Differences between Image Subsets in Natural LanguageJulian Truetsch, Felix Hauser, Christoph Stiller +1cs.CV2026-09-03
#174DropClick: Semi-Automated One-Click Segmentation for Agricultural Robotic DataPatrick Zimmer, Michael Halstead, Chris McCoolcs.CV2026-09-03
#175ToPO: Token-Conditioned Preference Routing for Attention-Based Latent Diffusion ModelsJuntao Xu, Shihong Li, Hoi Fan Au +1cs.CV2026-09-03
#176Semantic-Aware Subgraph State Space Model for WSI Classification in HistopathologyFeixing Chen, Hao Lu, Lin Luo +1cs.CV2026-09-03
#177MetaStructAtlas: A Grounded 3D Vision-Language Dataset and Benchmark for Functional and Structural Reasoning in Whole-Body PET/CTChenguang Zheng, Le Xue, Yichi Zhang +8cs.CV2026-09-03
#178Observation-Conditioned Latent Energy Priors for Sparse Implicit Neural Shape CompletionPaul Büschl, Ezequiel de la Rosa, Julia Wolleb +3cs.CV2026-09-03
#179SignSeek: Learning Transferable Representations for Sign Dictionary RetrievalSobhan Asasi, Ozge Mercanoglu Sincan, Richard Bowdencs.CV2026-09-03
#180Unfold The World: Factorize 4D Properties in Reinforcing Spatial ReasoningYijun Yang, Shenghe Zheng, Wenbo Li +8cs.CV2026-09-03
#181Fill My Mirror: Geometry-Constrained Mirror InpaintingOfek Basson, Shimon Vainer, Yacov Hel-Or +1cs.CV2026-09-03
#182KnowVis: Knowledge-Centric Visual Summarization for Video LecturesYi Xu, Yifan Hou, Xiaoyu Zhangcs.CV2026-09-03
#183ENEAS: Embedding-guided Neural Ensemble for Adaptive SegmentationJavier del Pino, Salvador Rodríguez, Alejandro Garabito +2cs.CV2026-09-03
#184RealCADBench: Benchmarking Parametric CAD Modeling from Industrial Design IntentsJoyIndustrial VisCAD Team, Linxin Cai, Qiuhe Hong +10cs.CV2026-09-03
#185A Reverse Sign Language Dictionary: Open-Vocabulary Sign Recognition from Continuous Signing via Video Captioning and Description RetrievalSantiago Poveda-Gutiérrez, Hideki Nakayama, Mayumi Bonocs.CV2026-09-03
#186LLaDA-Image: Building Strong Image Generators with Fully Open Training RecipesChuyan Chen, Haoxing Chen, Kun Chen +27cs.CV2026-09-03
#187Urban Boundaries, Social Barriers: A Benchmark and Vision-Centric Framework for Mapping Gated Communities and Equity ImplicationsMinwei Zhao, Weiming Zhang, Jiawang Du +4cs.CV2026-09-03
#188VisCAD: A Foundation Model Suite with Multimodal Industrial CAD IntelligenceJoyIndustrial VisCAD Team, Linxin Cai, Qiuhe Hong +10cs.CV2026-09-03
#189SPARK: Input-Conditioned Sparse Activation Modulation for Frozen DiT-based Super-ResolutionFederico Putamorsi, Leonardo Zini, Marcella Cornia +1cs.CV2026-09-03
#190Select, Compress, Reinvest: A Controlled Study of Visual-Token Allocation in Long-Video MLLMsPrakhar Khatrics.CV2026-09-03
#191VI3: Grounding Pretrained 3D Foundation Models with Inertial CuesErnesto Lozano, Alberto Jaenal, Javier Civeracs.CV2026-09-03
#192The impact of phase information for few-shot fine-grained image classificationRuiling Liu, Linyue Zhang, Wenyi Zeng +5cs.CV2026-09-03
#193GraFT: A Training-Free Framework for Spatial Reasoning in Multimodal Large Language Models via 3D Scene GraphsJunqing Du, Fernando Ropero, Erkin Turkoz +2cs.CV2026-09-03
#194Concept of a Sensor Test Environment for Dusty Agricultural ConditionsPeter Buckel, Johannes Hermann, Jonas Wollmann +2cs.CV2026-09-03
#195OctWorld: Long-Range World-Consistent Video Generation with Octree-Based 3D MappingZelong Lv, Sicheng Xu, Jianfeng Xiang +5cs.CV2026-09-03
#196Sparse auto-regressive modeling for scene generation from multi-view imagesThomas Lucas, Maxime Pietrantoni, Philippe Weinzaepfel +4cs.CV2026-09-03
#197WorldReward: Reward Modeling for Camera-Conditioned World ModelsYibin Wang, Zehan Wang, Junshu Tang +13cs.CV2026-09-03
#198RARF: Region-Aware Rectified Flows for 3D Brain MRI InpaintingTomas Guija-Valiente, Blanca Rodriguez-Gonzalez, Norberto Malpica +1cs.CV2026-09-03
#199Sharpening the Ensemble: An SSIM-Aligned Residual Refiner for Brain-MRI Inpainting Post-ProcessingKubilay Kağan Kömürcü, İlkay Öksüzcs.CV2026-09-03
#200IchthyoNoma: Nomenclature and Context Sensitivity of Zero-Shot Biological Vision--Language Models for Bangladeshi Freshwater Fish RecognitionNazim-E-Alam, Tarek Rahman, Md Kishor Morolcs.CV2026-09-03
#201Catalogue Photography as a Cold Start: Toward Deployable Carbide Burr RecognitionAbilash Philip Madavath, Chandra Yuvesh Aubeeluck, Augustin Raju +3cs.CV2026-09-03
#202The Blind Spot in 2D Infants' Pose Estimation:Robust Learning from Noisy AnnotationsEmanuele Cardinale, Marco Proietti, Alessandro Cacciatore +3cs.CV2026-09-03
#203Stable and Scalable Bundle Adjustment of Holistic 3D StructuresShaohui Liu, Rémi Pautrat, Daniel Barath +3cs.CV2026-09-03
#204DSAQuant: Denoising-Stage-Aligned Quantization-Aware Training for Video GenerationShuaiting Li, Zelin Gao, Haibin Shen +3cs.CV2026-09-03
#205Editable Visual DesignJunyan Ye, Wei Liu, Dongzhi Jiang +9cs.CV2026-09-03
#206Continuous Actions from Discrete Minds: Latent-Aligned Planning for End-to-End Autonomous DrivingRuoyu Yao, Yusen Xie, Qingzhao Liu +5cs.CV2026-09-03
#207TAP-Path: Task-Adaptive Structural and Token Pruning for Efficient and Trustworthy Pathology Foundation ModelsMehedi Hasan, Ashfak Yeafi, Md Khairul Islamcs.CV2026-09-03
#208CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker DistillationTingyu Song, Mingxin Li, Yanzhao Zhang +5cs.CV2026-09-03
#209Efficient Semantic Understanding from Digital FoveationCaterina Caccavella, Vittorio Fra, Andreas Ziegler +2cs.CV2026-09-03
#210The Shape of Time: Video-Token Contrast for Temporal Understanding in VideoLMsYumeng Shi, Quanyu Long, Yin Wu +1cs.CV2026-09-03
#211BooM-VVT: Boosting Mask-Free Video Virtual Try-On with Image-Level Pseudo DataWei Zhang, Xin Li, Peishu Shi +4cs.CV2026-09-03
#212Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video UnderstandingHongyu Qu, Guangming Yao, Ling Xing +7cs.CV2026-09-03
#213Persistent Identity Preservation in Generative Image Models: A Benchmark and Evaluation SystemMengwei Ren, Xuaner Zhang, Zhihao Xiacs.CV2026-09-03
#214Zero-Shot Novel Depth Synthesis Using 3D Foundation Models Scene RepresentationsDenis M. Akola, David F. Fouheycs.CV2026-09-03
#215Seeing Before Synthesizing: VLM-Guided Transition Event Discovery for Weakly-Supervised Dense Video CaptioningYe-Chan Kim, Seunghee Choi, SeungJu Cha +4cs.CV2026-09-03
#216One Editor, Many Edits: A Unified Training-Free Framework for Diverse Video EditingAdheesh Sunil Juvekar, Onkar Kishor Susladkar, Kiet A. Nguyen +6cs.CV2026-09-03
#217Puffin-World: Scaling a Unified Multimodal Model with Native 3D World StatesKang Liao, Yihang Luo, Xiao-Ming Wu +7cs.CV2026-09-03
#218Principia: Relational Physics Tests for Video ModelsVarun Varma Thozhiyoor, Shivam Tripathi, Venkatesh Babu Radhakrishnan +1cs.CV2026-09-03
#219Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D ReconstructionChin-Yang Lin, Yang-Che Sun, Cheng Sun +5cs.CV2026-09-03
#220TokenMatch: 3D Mesh Correspondence Transformer with Curvature-Guided TokenisationAdeela Islam, Zorah Lähner, Vittorio Murino +1cs.CV2026-09-03
#221Temporal Self-Distillation: Learning Visual State Tracking in Videos Without SupervisionShravan Venkatraman, Wenshuai Zhao, Mohammad Hassan Vali +1cs.CV2026-09-03
#222Para-Pipe: Exploiting Hierarchical Operator Parallelism of ML Computational Graphs on SoCsYujie Zhang, Huiying Lan, Ehsan Aghapour +5cs.DC2026-09-03
#223Relative Prime Factorization and Finite-State Presentations under Fixed Finite-Monoid ObservationTakayuki Kuriyamacs.FL2026-09-03
#224EF1-Constrained Nash Social Welfare with Identical Additive Valuations: Complexity, Guarantees, and ExperimentsZih-Sian Yang, Yi-Hao Chen, Yu-Te Kuan +3cs.GT2026-09-03
#225GazeFS: Target-Centered Gaze-Trajectory Forecasting and Stabilization from Gaze-Head HistoryYaozheng Xia, Zaiping Zhu, Bo Pang +4cs.HC2026-09-03
#226Plan Pointers and Record-Directive Form in Budgeted Verification of Inherited Agent MemoryKazuki Nakayashikics.IR2026-09-03
#227EPIC: Explicit Posterior Item Conditioning for Semantic ID Diffusion RecommendationTuan-Binh Tran, Thanh Tam Nguyen, Quoc Viet Hung Nguyen +3cs.IR2026-09-03
#228Comparing Retrieval Methods for Academic Advisor Discovery: A Six-Method Study of 768 CS Faculty Profiles Across 9 US UniversitiesBiraj Subedics.IR2026-09-03
#229The Dice Roll Method: A Standardized Protocol for Repeated-Query Auditing of Large Language Model Brand RecommendationsDmitrij Żatuchincs.IR2026-09-03
#230Language-encoded network topology enables large language models to reason about complex networksUcchwas Talukder Utsha, Sakib Mostafa, James Zou +1cs.LG2026-09-03
#231The 2026 PNPL Competition: Word Classification and Efficient Cross-Subject Generalisation in LibriBrain100Francesco Mantegna, Gereon Elvers, Dulhan Jayalath +18cs.LG2026-09-03
#232B2B Customer Conversion Prediction: A Document Representation, Graph Theory, and CatBoost Driven MethodologyTianqi Wang, Sheikh Shams Azam, Wan Eih Huang +3cs.LG2026-09-03
#233FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning ExperienceZixun Huang, Kishan Panaganti, Haitao Mi +1cs.LG2026-09-03
#234Selective Hypergraph Refinement for Frozen Graph ClusteringZimo Sics.LG2026-09-03
#235Latent Energy Action Planning with World ModelsPhu Pham, Aniket Beracs.LG2026-09-03
#236Geometry-Aware Graph Construction via Adaptive Spectral Bandwidth ControlEcem Bozkurt, Antonio Ortegacs.LG2026-09-03
#237Risk and Anomaly Identification for Distribution Network Optimal Operation Based on Reinforcement Learning and Uncertainty QuantificationZiqi Zhangcs.LG2026-09-03
#238DE-Venus: A Data-Efficient RLVR Framework for Large Language ModelsShenzhi Yang, Guangcheng Zhu, Kai Tang +11cs.LG2026-09-03
#239A Large Open Multi-Energy Corpus of Soil Compaction Tests, with Machine-Learning BaselinesSompote Youwai, Chana Phutthananon, Warat Kongkitkulcs.LG2026-09-03
#240Gradients Know What Outcomes Don't: Unlocking Reinforcement Learning for LLM Reasoning with Gradient-Aligned RewardsLeqi Zheng, Jinbo Su, Fang Niu +8cs.LG2026-09-03
#241From Zero to Hero: An Open LLM Ecosystem for ArmenianErik Arakelyan, Khatun Avetisyan, Meri Davtyan +5cs.LG2026-09-03
#242Time Without Timesteps: Simulating Coupled Dynamical Systems via Self-ConsistencyLiyu Zerihun, Mark Shinyoung Leecs.LG2026-09-03
#243SimpleDesign: A Joint Model for Protein Sequence and Structure CodesignJiarui Lu, Yuyang Wang, Yizhe Zhang +4cs.LG2026-09-03
#244RecurTrace: Adaptive Latent Reasoning with Loop-Time MemoryYuxiang Wang, Kunyu Feng, Yingda Shen +3cs.LG2026-09-03
#245TIGPO: Temporal Instance-Graph Policy Optimization for Long-Horizon LLM AgentsJinwei Gancs.LG2026-09-03
#246Inferred Generative-Process Diversity Predicts Correlated Failure Across Language ModelsRoss Tieman, Evan Markoucs.LG2026-09-03
#247TraveL: Transformer-based Multi-view Path Distributional Representation LearningFang He, Tao-yang Fu, Wang-chien Leecs.LG2026-09-03
#248It's the Problem, Not the Path: Budget and Difficulty Confounds in LLM Reasoning TrajectoriesYigit Utku Bulutcs.LG2026-09-03
#249Guide, Not Bind: Why Defeasible Priors Fail in Augmented Lagrangian Causal DiscoverySairam Sundararaman, Sara Girdhar, Manit Narasimha Murthy +2cs.LG2026-09-03
#250Beyond Straightness: Non-Crossing Flow Matching via Quantile AlignTree CouplingJunyi Lin, Mengyu Li, Jingxuan Hu +2cs.LG2026-09-03
#251A Two-Stage Forecasting System for CPU Workload Prediction in Private CloudsAshir Javeed, Anton Borg, Håkan Grahn +3cs.LG2026-09-03
#252Mind the Gap: Robustness Risks in PII Detection SystemsAdeel Zafar, Slawomir Nowaczykcs.LG2026-09-03
#253Spectral characteristics of autoencoder parameters as a vector representation of dataMaria Nikitina, Anton Bishuk, Oleg Bakhteevcs.LG2026-09-03
#254Restricted Eigenvalues Beyond Gaussian Width: Threshold Occupancy under Heavy TailsShi Fu, Huibo Xu, Qixin Zhang +1cs.LG2026-09-03
#255An Adversarial Zero-Shot Learning Approach for Anomaly Detection in Multivariate IoT Traffic DataMahshid Rezakhani, Tolunay Seyfi, Fatemeh Afghahcs.LG2026-09-03
#256LongCounsel-8: A Benchmark Suite for Longitudinal Depression Tracking from Multi-Session Counseling DialoguesJiayi Li, Zhaomin Wu, Bingsheng Hecs.LG2026-09-03
#257LeanGRPO: Eliminating Redundant Recomputation in Diffusion RLSijie Wang, Zhiqiang Tan, Xinrui Yang +1cs.LG2026-09-03
#258Coupled Scaling: A Representational Accessibility Framework for Neural Scaling LawsJie Wangcs.LG2026-09-03
#259WeatherNext 3: Increasing resolution and performance of global weather models with raw observationsStephan Rasp, Boris Babenko, Dominic Masters +22cs.LG2026-09-03
#260Neural-Network Maxent: a general extension with learned nonlinearity, applied to time-series for Desert Locust distribution modellingAlessandro Grassi, Edoardo Kimani Bellotto, Wassim El Azami +2cs.LG2026-09-03
#261On the Interaction Between Model Compression and Test-Time AdaptationFrancesco Corti, Dong Wang, Young D. Kwon +2cs.LG2026-09-03
#262Local Updates, Global Learning (LUGL): Playing Games with non-incremental LearnersDavid Milec, Spyridon Samothrakis, Michael Fairbank +1cs.LG2026-09-03
#263Extracting Forgotten Prompts from Targeted Unlearned ModelsAu Ashley Hoi-Ting, Meghdad Kurmanji, William F. Shen +2cs.LG2026-09-03
#264Out-of-Distribution Generalisation with Sequence Models in Offline Multi-Agent Reinforcement LearningOussama Hidaoui, Omer Ebead, Ulrich Armel Mbou Sob +14cs.LG2026-09-03
#265Resolution-Aware Experimental Design under Partial IdentifiabilitySofianos Panagiotis Fotiascs.LG2026-09-03
#266Federated Causal Discovery via Regression-Directed CumulantsPablo Torrijos, Fabio Stella, José A. Gámez +1cs.LG2026-09-03
#267Projected Riemannian Gradient Descent for the Bures-Wasserstein Barycenter: Dimension-Independent Linear Convergence at Unit Step SizeA. Afhamcs.LG2026-09-03
#268From Nowcasting to Forecasting: Adapting a Reanalysis-TrainedMikko Partio, Leila Hieta, Ossi Lainecs.LG2026-09-03
#269OBER+: Continuity-Aware Reporting and Traceable Continuous Improvement in Outcome-Based EducationElakkiya Rajasekarcs.LG2026-09-03
#270Landmark-Based Discrimination of Injury-Associated Athlete-Sessions from Minute-Resolution Multimodal Football Monitoring DataEvangelos Chatzidimitriou, Konstantinos Tserpescs.LG2026-09-03
#271From Ordered Bernoulli Levels to Critical-Line Geometry: Integer Quantization, Bernoulli Residual Phase, and Prime-Power SpectraY. Kenan Yılmazcs.LG2026-09-03
#272Free Pause TokensJohn Langford, Nathan Godey, Giovanni Monea +5cs.LG2026-09-03
#273A Peer-Relative Representation Learning Framework for Energy Inefficiency Identification in Mobile Network SitesEliud Nyakweba Koto, Jaco du Toit, Adham Stoltz +1cs.LG2026-09-03
#274Witnesses Explain AnomaliesLamine Diopcs.LG2026-09-03
#275Multi-step Proximal Policy Improvement in Offline Reinforcement LearningSoohyun Choi, Seonvin Cho, Songnam Hongcs.LG2026-09-03
#276Pushing the (Decision) Boundaries: Dynamically Calibrating Differentially Private Noise to Explainability in Federated LearningMichael Khavkin, Kichang Lee, Jaeho Jin +2cs.LG2026-09-03
#277High-Dimensional Learning Dynamics of Attention-Indexed ModelsYizhou Xu, Margarita Sagitova, Lenka Zdeborová +1cs.LG2026-09-03
#278Differentiable Interval Bottlenecks for Interpretable Anomaly Detection in Numerical DataLamine Diop, Marc Plantevitcs.LG2026-09-03
#279Beyond Endpoint Scores: Time- and Capacity-Conditioned Evaluation of Continual Knowledge UpdatingHeejin Choics.LG2026-09-03
#280RATL: Learning from Retrieved Residuals for Robust Multivariate Time-Series ForecastingYuchen He, Yueyang Cang, Zhiyuan Ning +2cs.LG2026-09-03
#281Headroom-Drift Replay: A Primitive for Principled Replay Control in GRPOHyun Bin Park, Du-Seong Changcs.LG2026-09-03
#282VestigeKV: The NoPE-MLA KV Cache Carries Its Own Eviction Signal in a Vestigial BranchWenJie Fancs.LG2026-09-03
#283OSR: Output Space Redistribution for Adaptive Label Removal in Classification ModelsMinyi Peng, Darian Gunamardi, Ivan Tjuawinata +2cs.LG2026-09-03
#284RobustSeiz: An Open-Source Framework for Benchmarking the Robustness of EEG Seizure Detection ModelsMohammad Mohammadi, Alireza Zareics.LG2026-09-03
#285Unlocking Lossless Speedups in LLMs via Discrete DiffusionSubham Sekhar Sahoo, Lingjie Chen, Khiem Pham +14cs.LG2026-09-03
#286A location-invariant estimator of extremal quantile treatment effects for heavy-tailed distributionsXin Yu, Shuwei Huang, Jicheng Liu +4cs.LG2026-09-03
#287Subspace Inference Enables Efficient Active Reward Learning from PreferencesYutai Zhou, Erdem Bıyıkcs.LG2026-09-03
#288Conditioning Degenerate Diffusion ModelsUğur Aydın, Tamer Başarcs.LG2026-09-03
#289Hardware-Aware FP4 FlashAttention-4Robert Hucs.LG2026-09-03
#290Constant regret in general games via higher-order optimismOmar Abbadi, Rida Laraki, Panayotis Mertikopouloscs.LG2026-09-03
#291Prospective Coding Improves Learning in Deep Continuous-Time Recurrent NetworksShivang Rawat, Mirko Morello, Flaviano Morone +1cs.LG2026-09-03
#292A Low-Cost, Open Platform for End-to-End Autonomous Driving on a Miniature Ackermann VehicleGustavo Claudio Karl Couto, Eric Aislan Antonelo, Gabriel George Zipperercs.LG2026-09-03
#293Robust PAC Learning of Concurrent Stochastic GamesAngel Y. He, David Parkercs.LG2026-09-03
#294The Civilization Framework: Sovereign-Anchored Communication Between Personal Multi-Agent SystemsGuangjun Liucs.MA2026-09-03
#295Efficient Constant Optimization for Symbolic Regression with GPU-Accelerated Tree-Based Genetic ProgrammingHao Mao, Xu Tony Liu, Shuai Lu +3cs.NE2026-09-03
#296Genetic Algorithms for Tractable Bayesian Network Fusion via Pre-Fusion Edge PruningPablo Torrijos, José A. Gámez, José M. Puerta +1cs.NE2026-09-03
#297From Prior-Guided Heuristics to Deployable Agents: Accelerating Demonstration-Driven Reinforcement Learning for Deadline-Constrained Network ControlVincenzo Norman Vitale, Mohammad Solki, Antonia Maria Tulino +2cs.NI2026-09-03
#298Air-Ground Collaborative Vision-and-Language Navigation via Shared Bird's-Eye MapsShuning Zhang, Liang Li, Yunheng Wang +3cs.RO2026-09-03
#299BRIDGE: An Open-Source Humanoid Platform via Morphology-Control Co-Design for Physical AIJianren Wang, Letian Qian, Zikai Wang +4cs.RO2026-09-03
#300Toward Physically Grounded JEPA World Models for Goal-Conditioned Robotic PlanningMuyuan Liu, Yue Huang, Zheng Liang +1cs.RO2026-09-03
#301FailBench: How Reliable are VLMs at Judging Robot Task Success?Zaruhi Navasardyan, Tatul Danielyan, Hrant Davtyancs.RO2026-09-03
#302FWBC-VLA: Force-Aware Whole-Body Compensation for Contact-Rich Loco-ManipulationYutian Zhang, Siyuan Ma, Liwen Yang +6cs.RO2026-09-03
#303Adaptive Vision-Language Grasping via Composable Foundation Priors and Generalizable Grasp SynthesisSixu Yan, Shikang Wang, Binhua Huang +11cs.RO2026-09-03
#304Beyond .WAV: Design and Software Verification of VocalCap, a Traceable Browser-Based Audio Capture System for Vocal Biomarker ResearchAugusto Camargocs.SD2026-09-03
#305StrixAE: An Intelligent Agent for Audio Enhancement under Complex Distortion Coupling in Real-World ScenariosChenglin Wu, Junjie Wu, Jinhang Chen +5cs.SD2026-09-03
#306Test-time adaptation for speech enhancement with an autoregressive speech priorSofiene Kammoun, Simon Leglaive, Xavier Alameda-Pineda +1cs.SD2026-09-03
#307Masked Autoregressive Speech Enhancement with Continuous Neural Audio Codec RepresentationsYoto Fujita, Simon Leglaive, Laurent Girincs.SD2026-09-03
#308The Psychological Costs of Artificial Intelligence Adoption in Software EngineeringAdam Alami, Elda Paja, Abhishek Tiwarics.SE2026-09-03
#309Can LLMs Extract Architectural Design Decisions from Source Code Commits? - A Preliminary Exploratory StudyAmey Karan, Rudra Dhar, Mohamed Soliman +1cs.SE2026-09-03
#310When Models Edit Too Much: On the Fidelity of Minimal Code EditsTongyao Zhu, Wei Hern Lim, Min-Yen Kancs.SE2026-09-03
#311SWE-Gate: Passing Functional Tests Is Not Enough for Software Engineering AgentsXin He, Yanlin Wang, Mingwei Liu +3cs.SE2026-09-03
#312When Vision Meets Graphs: A Survey on Graph Reasoning and LearningXinjian Zhao, Wei Pang, Zhixuan Yu +8cs.SI2026-09-03
#313ToolDF: Tool-Integrated Reasoning for Mixed-Authenticity Audio Deepfake DetectionTaewoo Kim, Young Han Lee, Nam In Park +1eess.AS2026-09-03
#314Cooperative Multi-Task Semantic Communication for Joint Classification and Regression TasksAhmad Halimi Razlighi, Mohammad Siddiqur Rahman, Maximilian H. V. Tillmann +2eess.SP2026-09-03
#315Introducing SINFONIA: Symplectic, slimplectic and Magnusian (Neural) Flows for Orbital Numerical Integration and AccelerationLidia J. Gomes Da Silvagr-qc2026-09-03
#316Grassmann--Plücker Parametrization of Convolutional Filter Subspaces: Regularity and Closed EmbeddingsHongyu Yuan, Huaiqing Zuomath.AG2026-09-03
#317SurgeGen: A Hybrid Generative Diffusion Framework for Storm Surge Scenario SynthesisShunan Zheng, John J. Hasenbeinmath.DS2026-09-03
#318Learning Informative Prior with Infinite-Dimensional Continuous Normalizing Flow for Bayesian Inverse ProblemYang Zhao, Junxiong Jia, Tao Zhoumath.NA2026-09-03
#319Spectral Convergence of Random Feature Method in Multiple DimensionsPingbing Ming, Hao Yumath.NA2026-09-03
#320Residual neural networks overcome the curse of dimensionality for semilinear heat equationsIlkhom Mukhammadiev, Diyora Salimovamath.NA2026-09-03
#321Correlated initialization of deep residual networksFelix Benning, Ivan Nourdin, Giovanni Peccatimath.PR2026-09-03
#322What is Smoothness?Zachary P Bradshawmath.RT2026-09-03
#323Symmetries and Causality: Causal Effect Identification Beyond IID DataMartin Rabel, Jakob Rungemath.ST2026-09-03
#324Parameterised graph theory for tensor networks: entanglement rerouting, structural simplification, and agnostic tomographyMatthias C. Caro, Natalie McHugh, Sergii Strelchukquant-ph2026-09-03
#325ALRA: Adaptive Local Relational Alignment for Logit-Based Pre-training Distillation of Autoregressive Language ModelsQuang Hoang Trung, Quang Huu Hieu, Nguyen Van Hoang Phuc +1stat.ML2026-09-03
#326Towards a Statistical Understanding of Mixture-of-ExpertsSiyuan He, Bokai Yang, Jie Hu +2stat.ML2026-09-03

latest · trends · arXiv announcement batches follow US Eastern weekdays