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

New Papers · 2026-09-07 371 submissions

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

#TitleAuthorsCatDate
1AstroSpecLM: A Spectrum-Language Model for Evidence-Grounded Astronomical Spectral AnalysisJinghang Shi, Yanxia Zhang, Ali Luo +2astro-ph.IM2026-09-07
2Neural Posterior Estimation for Tomographic Weak Lensing Mass MappingTim White, Shreyas Chandrashekaran, Camille Avestruz +2astro-ph.IM2026-09-07
3Graph neural networks and the energetic cavity method for combinatorial optimizationJoe Bacchus George, George T. Cantwellcond-mat.dis-nn2026-09-07
#4Human-agent discovery of reconfigurable in-plane ferroelectric superdomain controlYu Liu, Boris Slautin, Ching-Che Lin +3cond-mat.mtrl-sci2026-09-07
#5Microcanonical Hamiltonian Monte Carlo and the Helmholtz TheoremHeinrich von Campe, Bjoern Malte Schaefercond-mat.stat-mech2026-09-07
#6A visual large language foundational model for medical image recognition using clinician-oriented social mediaLingxuan Hou, Yuhua Xie, Yue Hu +14cs.AI2026-09-07
#7When and Why LLM Causal Priors Help: Closed-Loop Prior Selection for Amortized Causal InferenceHaohao Zhoucs.AI2026-09-07
#8iBrain: A Unified Foundation Model Reading the Brain from Surface to SpikesYing Chen, Tiou Wang, Zhifeng Yuecs.AI2026-09-07
#9SSP-DMGTimeNet: Physics-Constrained Learning for Spatiotemporal Trajectory Prediction of Vehicle PlatoonsYuhang Wang, Kailang Ma, Zirui Li +4cs.AI2026-09-07
#10RedKnot-MLA: Multi-Head Offline-Online Reuse for DeepSeek-V4 Long-Context ServingYang Liu, Zhaokai Luo, Huayi Jin +10cs.AI2026-09-07
#11Beyond One-Shot Expansion: Contrastive Evidence Exploration for Multi-Hop RetrievalJungMin Yun, YoungBin Kimcs.AI2026-09-07
#12VST: Verifiable Structured Transport for Auditable Agent-to-Agent Alpha DiscoveryYuqi Li, Siyuan Liu, Bingjun Liucs.AI2026-09-07
#13A Hierarchical Consistency Framework for Auditing Retrieval-Augmented Generation SystemsRamon Gonzalez, Antonio Diazcs.AI2026-09-07
#14Risk Is Not Review Value: Wrong-Answer Exposure Under Bounded Review BudgetsSangJin Park, Myungsub Choi, Jineok Kim +1cs.AI2026-09-07
#15Beyond Sparse Rewards: A New Benchmark and Structure-Aware Graph Alignment for Micro-Drama UnderstandingYixin Qin, Shi-Zhe Chen, Zhiqi Yu +4cs.AI2026-09-07
#16EEG-Driven Decoding Framework for Passenger Hazard Perception in Highly Automated VehiclesYingkai Yang, Ashton Yu Xuan Tan, Bowen Li +10cs.AI2026-09-07
#17Encoded Early, Used Late: Where Transformers Begin to Act on an Inferred Partner's ExpertiseMika Okamoto, Gabriele Sartics.AI2026-09-07
#18An Auditable Symbolic-RAG-Generative AI Architecture for Goal-Oriented Conversation OrchestrationRamon Gonzalez, Antonio Diazcs.AI2026-09-07
#19PhysMAS: Physics-Grounded Multi-Agent Synthesis of Compositional 4D GaussiansJiang Qin, Chunji Lv, Yangguang Wei +6cs.AI2026-09-07
#20EmoMed: An Emotionally-Aware Agent for Multimodal Medical Support with Real-Time Information RetrievalIvan Nasonov, Nikita Glazkov, Ivan Makovetskiy +4cs.AI2026-09-07
#21Agentic Algorithm Engineering: Improving Shared-Memory Exact Minimum CutsDavid A. Bader, Adil Chhabra, Ernestine Großmann +3cs.AI2026-09-07
#22Unraveling the Real Working Mechanism and Inherent Flaws of GAE: A Method for Interpreting Transformer Processes from an Economic PerspectiveYongjin Cui, Xiaohui Fancs.AI2026-09-07
#23Distance-Aware Attention and Wall-Distance Expert Routing for Transformer-Based 3D Flow PredictionSanghyeon Kim, Sunwoong Yang, Namwoo Kangcs.AI2026-09-07
#24Elastic Horizon: Discovering the Effective Interaction Frontier in Agentic Reinforcement LearningGangyi Zhang, Junjie Meng, Letian Zhang +6cs.AI2026-09-07
#25SkillAlign: Aligning Skill Interfaces for LLM-based AgentsShuo Ren, Xiaomian Kang, Jiajun Zhangcs.AI2026-09-07
#26World Models Under Asynchronous Sensor ObservationsAkash Anand, Abhay Anand, Yash Vishecs.AI2026-09-07
#27Weakly supervised neural network: segmentation of complex structures in X-ray microCTDaniele Rusconi, Michela Ascolese, Stephanie Fest-Santini +2cs.AI2026-09-07
#28DGCPath: Distribution-Aware Generative Contrastive Framework for Self-supervised Path Representation Learning -- Extended VersionSean Bin Yang, Hao Miao, Zongyi Xu +5cs.AI2026-09-07
#29AAS-RAIL: Improving Information Extraction for Asset Administration Shells through Retrieval-Augmented In-Context LearningJanek Groß, Jens Heidrichcs.AI2026-09-07
#30Human-like moral judgments conceal divergent motive attributions in large language modelsXiaoyan Wu, Jean-Claude Drehercs.AI2026-09-07
#31RAFM-SER++: A Lightweight Multimodal Emotion Recognition Framework for Real-Time Behavioral Monitoring in Surveillance SystemsNgo Truong Dinh, Tung-Lam Bui, Chi-Trung Duong +3cs.AI2026-09-07
#32CIT-CAD: Constraint Intent Tree-based CAD Code Generation and VerificationYali Du, Hui Sun, San-Zhuo Xi +1cs.AI2026-09-07
#33The Internal Anatomy of Strategic Choice in Large Language ModelsVinícius Ferraz, Leon Houf, Enrico Ferreacs.AI2026-09-07
#34Modus Tollens and Counterfactuals and Counterfactual Reasoning Based on Three Types of NegationZhenghua Pancs.AI2026-09-07
#35Quantile-Led Feature Extraction for Multi-Horizon Predictive Maintenance in Industrial Manufacturing SystemsDavid J Poland, Daniele Ravi, Na Heliancs.AI2026-09-07
#36Scoring Without the Engine: Validating a Deterministic, Manipulation-Resistant Content Score for Generative Engines, End to EndElisha Bajemon, Andre-Louis Rochetcs.AI2026-09-07
#37From Simulated Citizens to Simulated Deliberation: Challenges in Representation and InteractionChaemin Jang, Junsik Min, Jaewoo Choi +9cs.AI2026-09-07
#38A Tool-Augmented, GPT-4 Chatbot for Real-Time Repository Data AnalysisMuhammad Jawad Chowdhury, Md. Sakib Khancs.AI2026-09-07
#39FinCUABuild: Can Agents Build Reliable Benchmarks for Dynamic Financial Computer Use?Jingpu Yang, Fengxian Ji, Jinri Guo +7cs.AI2026-09-07
#40AgentIdeaBench: Benchmarking Scientific Ideation in the Agent EraYunxiang Mo, Tianshi Zheng, Yisen Gao +7cs.AI2026-09-07
#41Norms at a Price: Why RL-Based Alignment Can Promise Conditional Compliance at BestKevin Baum, Rūta Binkytė, Felix Jahncs.AI2026-09-07
#42Aegix Pulse: A Traceable Three-Stage Architecture for Personalized Content Generation and Context-Preserving RevisionHongnan Zhao, Shiyu Chen, Zhihao Chencs.AI2026-09-07
#43APPSim-Bench: Bridging Real-world Apps and Reproducible Evaluation for Mobile GUI AgentsJintian Feng, Long Chen, Xiao Yu +7cs.AI2026-09-07
#44The Emerging AI Paper-Review Arms Race: Adversarial Co-Evolution in Scholarly PublishingChenguang Wang, Ming Li, Adebayo Braimah +6cs.AI2026-09-07
#45A radiographic world model for clinical reasoning and evidence generationSuyang Xi, Songtao Hu, Shansong Wang +8cs.AI2026-09-07
#46The Profit Alignment Problem: How Profit Mandates Induce Alignment Failures in LLMsEric Socs.AI2026-09-07
#47When Intelligence Becomes Agency: A Theory of Governed, Proactive Agency for Symbiotic AI SystemsJoão Dias Ferreiracs.AI2026-09-07
#48xDailyBench: Benchmarking LLMs on Professional Consultation for Real-Life ProblemsYongchang Peng, Qingshui Gu, Liya Zhu +31cs.AI2026-09-07
#49What Does an LLM-Agent Leaderboard Rank Actually Compare?Wei-Jung Huangcs.AI2026-09-07
#50Understanding the Impact of Model Pruning on Long-Tail Forgetting and Explanation Reliability in Medical ImagingNazish Khalid, Tausifa Jan Saleem, Amal Saqib +2cs.AI2026-09-07
#51Do Large Language Models Know What They Don't Know II? A Fully Behavioral, Non-Cognitive Measure of Epistemic HonestyAli Şenol, H. Russell Bernard, Huan Liucs.AI2026-09-07
#52Explainable Temporal Attention-based Defect Detection For Fillet Joints in Real-Time Gas Metal Arc Welding Based on Multi-modal DataMobina Mobaraki, Mahyar Asadi, Klaske Van Heusden +1cs.AI2026-09-07
#53Quantization Amplifies Determinism, Not Bias: Scale-Dependent Behavioral Effects of Serving-Time Weight CompressionDachi Kurtskhaliacs.AI2026-09-07
#54PRIMUS: Identity, Governance, and Verification for Multi-Agent FederationsSasank Annapureddy, Anjaneya Prasad Thamatanics.AI2026-09-07
#55FrogNano: Training a 4B Coding Agent via Online Task SynthesisMinseon Kim, Zhengyan Shi, Emiliano Penaloza +14cs.AI2026-09-07
#56Beliefs and Behavior in Language ModelsAlex Smolin, Bryan Wildercs.AI2026-09-07
#57CausalVerify: An Execution-Grounded Benchmark for LLM Causal Inference WorkflowsYonghong Zhang, Ricardo Correia, Isabel M. Parra +1cs.AI2026-09-07
#58Support Topology and Gradient Mixing in Sinkhorn LayersDylan Fordecs.AI2026-09-07
#59From Event Logs to Governed Action: A BlueSky Agenda for Agentic Process MiningYiyuan Yang, Zheshun Wu, Yong Chu +3cs.AI2026-09-07
#60When Can LLM Digital Twins Reduce Human Measurement? From Behavioral Fidelity to Statistical SubstitutabilitySteven Wang, Kyle Hunt, Shaojie Tang +1cs.AI2026-09-07
#61Mini-Batch Risk-Averse Deep Q-Learning: A Robot Navigation Case StudyAayush Patel, Andrzej Ruszczyńskics.AI2026-09-07
#62Sparks of In Silico Cognitive Science: Theories from Simulated Data Can Generalize to HumansAkshay K. Jagadish, Younes Strittmatter, Nori Jacoby +4cs.AI2026-09-07
#63From Version Conflicts to Decision Conflicts: Selective Revalidation for Long-Running AI AgentsYongjian Lyu, Yang Ren, Ruofei Lai +1cs.AI2026-09-07
#64A Layered Analysis of Disagreement And Answer Quality in Multi-Agent LLM DebateChen Qiancs.AI2026-09-07
#65Eliciting Self-Verification in Multimodal Reasoning Agents with Reinforcement LearningVishwas Sathish, Viresh Ranjan, Xinliang Zhu +2cs.AI2026-09-07
#66Your Agent Says Yes: Interpreting Adversarial Market Behavior Beyond Individual TransactionsZelin Li, Yiyun Su, Matt White +3cs.CE2026-09-07
#67A Sub-4 Approximation for Fair $k$-MeansKangke Cheng, Guanlin Mo, Shihong Song +1cs.CG2026-09-07
#68Towards Bridging the Gap Between Offline and Iterative Alignment via Preference DistillationWenbo Zhang, Wenzhuo Zhou, Hengrui Cai +1cs.CL2026-09-07
#69Dynamic-Programming-Guided Hierarchical BPE and Empirical Analysis of Vocabulary PruningKenny Shaocs.CL2026-09-07
#70TurEngMix: A Text Corpus and Benchmark for Turkish-English Code-Mixed Language Identification and Named Entity RecognitionIlayda Dogan, Phuong-Anh Nguyen-Le, Julia Mendelsohncs.CL2026-09-07
#71CantoneseLLM v2: Reasoning in a Low-Resource LanguageTsz Chung Cheng, Chung Shing Cheng, Chaak Ming Lau +1cs.CL2026-09-07
#72Train Overcomplete, Deploy Compact: Scaling Recovery Capacity for Structured LLM PruningSeungmin Oh, Donggeon Lee, Jongbin Ryucs.CL2026-09-07
#73Aha-Flow Distillation: Flow Markers Matter in LLM ReasoningXiaodong Wang, Peixi Pengcs.CL2026-09-07
#74A Hyperbolicity Atlas of Large Language Model Hidden StatesZhichao Yang, Yuanze Hu, Gen Li +7cs.CL2026-09-07
#75Where to Look and What to Use: Retrieve-Localize-Generate for Long-Term Conversational Memory Question AnsweringYifan Wang, Xinkui Lin, Yongxiu Xu +9cs.CL2026-09-07
#76Revisiting Complete Reasoning Traces for Post-TrainingJaehui Hwang, Sangdoo Yun, Byeongho Heo +1cs.CL2026-09-07
#77The Illusion of Debiasing: Persona Steering Redistributes Rather Than Reduces Bias in LLMsZiyue Feng, Hongbo Fang, James A. Evanscs.CL2026-09-07
#78PTCG: Persona-guided Tree-based Counterargument GenerationEunbeen Son, Yohan Jo, Joonsuk Park +1cs.CL2026-09-07
#79Line-Coupled Language ModelShiyuan Li, Shaorong Zhang, Zhaorui Yang +3cs.CL2026-09-07
#80Retrieval-Augmented Multi-Prompt Ensemble for Minor-Grain Breeding Information ExtractionHang Zhao, Jiahao Wangcs.CL2026-09-07
#81Vishing-Tactics-Bench: Forecasting Exploitation Trajectories in Voice Phishing CallsJeongmin Lee, Dongmyung Sul, Seung Yun +1cs.CL2026-09-07
#82FreqBLiMP: Frequency-Controlled Minimal Pairs Reveal Robustness and Fragility of LLMs Under Lexical RarityTyrone White, Yuki Arasecs.CL2026-09-07
#83In-Place Instruction Following in Diffusion Language ModelsZheng Nie, Zherui Li, Jiaming Zhang +3cs.CL2026-09-07
#84CircuitLens: Reasoning Circuits as Data Selection Signals for Reinforcement Learning with Verifiable RewardsZhuofan Chen, Ziqian Jiao, Yikai Cui +3cs.CL2026-09-07
#85SIFTING: A Novel LLM-Based Framework for Structured and Transparent Information Extraction from Clinical Free-Text Reports, with Application to Tumor Staging in Lung CancerMirco Hess, Gerben van Veenendaal, Joris Wakkie +5cs.CL2026-09-07
#86CEDAR: Error-Bounded Residual Routing for Efficient Long-Context AttentionSiyu Li, Dong Wang, Jie Zhou +3cs.CL2026-09-07
#87Separating Stream Stability from Long-Term Recall in Language ModelsPeipei Cao, Xin Zhang, Jie Tang +3cs.CL2026-09-07
#88Probing the Structure and Dynamics of LLM Value Expression through Value ConflictsKaicheng Zhang, Jingyi Xiao, Renjun Hu +3cs.CL2026-09-07
#89Marginal Fidelity Does Not Establish User Simulation in Demographic Synthetic Survey Panels: Response Contracts, Support Collapse and Conditioning FailureAlexander Doudkincs.CL2026-09-07
#90RouteRelay: Event-Triggered Cross-Layer Route Reuse for Efficient Dynamic Sparse AttentionBin Li, Sisi Liu, Chenyang Hu +3cs.CL2026-09-07
#91SPARROW: Scalable Taxonomy Induction via Structure-Preserving Partitioning and Constraint-Guided MergingYirui Zhang, Yixuan Tang, Yandong Sun +2cs.CL2026-09-07
#92LANTERN: Language Model Assessment on Noisy and Transformed Tasks for Understanding Error and Robustness NuancesVamsi Krishna Kodavali, Rituraj Singhcs.CL2026-09-07
#93Content-Based Addressing for Long ContextMahesh Godavartics.CL2026-09-07
#94BlueprintAgent: Constraint-Triggered Targeted Revisits for Simulation-Ready Generation from Scanned Structural BlueprintsZhouyuan Xu, Chen Yang, Linhao Wang +2cs.CL2026-09-07
#95Beyond Fluent Generation: A CPU Reliability Benchmark for MCP-Style Tool Calling in Sub-2B Small Language Models for Edge DeploymentAbrar Shahriar Qurat-Ul-Ain Mastoics.CL2026-09-07
#96Beyond Single-Negative Preference: Multi-Negative DPO for LLM-Centric Historical Entity LinkingTien Nam Nguyen, Emanuela Boros, Ahmed Hamdi +3cs.CL2026-09-07
#97An LLM-Associated Register Shift in Korean Journal Abstracts: A Morphology-Aware Excess-Vocabulary Study, 2018-2026Aron Leecs.CL2026-09-07
#98FramingQA: Does the Question Shape the Answer? Measuring the Compositional Framing EffectHazel H. Kim, Andrew M. Bean, Guilherme Affonso Ferreira de Camargo +10cs.CL2026-09-07
#99MEMO: Multimodal Evidence Memory Organization for Long-Horizon LLM AgentsXian Gao, Jinpeng Wang, Jiacheng Ruan +3cs.CL2026-09-07
#100Where Should Language Sit in a Multimodal Model? Lessons from What Language Does to Human Perception and CognitionPeng Xiecs.CL2026-09-07
#101Qwen-Audio-3.0-ASR Technical ReportChuanmeng Bian, Daren Chen, Peixin Chen +42cs.CL2026-09-07
#102We're Cooked! - Probing LLM Political Alignment Via Conflict-Framed Recipe TranslationSvetlana Gorovaia, Angelica Henestrosa, Ivan P. Yamshchikovcs.CL2026-09-07
#103Validating DBpedia Triple Sets for Natural Language GenerationMark Andrade, Simon Mille, Anya Belz +1cs.CL2026-09-07
#104ObGynLongBench: Revealing the Evidence-to-EHR Gap in Longitudinal EHR Decision-MakingJun Xiang, Zhijie Bao, Rong Hu +3cs.CL2026-09-07
#105The Art of Hierarchical Competing Patterns: Gaussian Process Optimization of HyphenationOndřej Sojka, Petr Sojkacs.CL2026-09-07
#106Syntactic Patterns and Stylistic Functions in Narrative Prose: A Rule-Based and Machine-Learning ApproachStefana Janicijeviccs.CL2026-09-07
#107How AI Models Manage Epistemic Authority: A Taxonomy and Comparative Analysis of Responses to User DisagreementRiyadh Alnasser, Yusuf Mücahit Çetinkaya, Sumin Zhao +1cs.CL2026-09-07
#108Perspectives on Cross-Lingual Consistency in LLMs for Medical QuestionsMinh Duc Bui, Mario Sanz-Guerrero, Abteen Ebrahimi +4cs.CL2026-09-07
#109Fine PT-PT Web: A High-Quality 41 Billion Tokens Data Collection of the European Portuguese WebGonçalo Vinagre, Rui Pedro Guerra, Pedro Gomes +7cs.CL2026-09-07
#110DeepTable: Structural Attention Biases and Tree Path Encoding for Hierarchical Table UnderstandingJyun-Ying Yen, Cheng-Kuan Lin, Yu-Chee Tsengcs.CL2026-09-07
#111Translation Indeterminacy and the Distributional FallacyMichael Carlcs.CL2026-09-07
#112From Echo Chambers to Epistemic Monoculture: Large Language Models Present Temporally Contingent Partisan Alignments as KnowledgeWend K. Tamcs.CL2026-09-07
#113LLM Forensics: Where Do Backdoors Hide? Localizing and Controlling Trigger Mechanisms with Sparse AutoencodersWissam Antoun, Francis Kulumba, Théo Lasnier +2cs.CL2026-09-07
#114Replicating a Disjoint-Set Union Experiment over Various Notions of Micro Units to assess Translation EffortMichael Carlcs.CL2026-09-07
#115Bag of Tricks or Bag of Myths? Reducing Modeling Complexity with Task Knowledge in Explainable Suicide Risk AssessmentShlok Shelat, Shrey Salvi, Souvik Roy +2cs.CL2026-09-07
#116Signed Rescue Routing: Harm-Aware Cascades for Efficient LLM InferenceZheyuan Wang, Siyu Li, Peiqiao Song +3cs.CL2026-09-07
#117LLM Agents as Computational TypologistsChangbing Yang, Christopher Hammerly, Freda Shi +1cs.CL2026-09-07
#118Does Syntax Matter? A Graph-Augmented Variational Topic Model for Computational Social SciencesAlessandro Meneghinics.CL2026-09-07
#119Climate-ModernBERT: Revisiting Corpus Composition for Domain-Adaptive Continued PretrainingYongan Yu, Shantam Raj, Jingwei Ni +3cs.CL2026-09-07
#120You Can't Prefer Emotions You Don't Sample: Intensity Undershoot in DPO-Tuned LLMsHyunwoo Kim, Usama Khalidcs.CL2026-09-07
#121A*-Thought-V2: Efficient Latent Reasoning via Geometric Dynamics of LLMXiaoang Xu, Siyuan Liu, Shuo Wang +13cs.CL2026-09-07
#122LLM Layers Immediately Correct Each OtherArjun Patrawala, Jiahai Feng, Erik Jones +1cs.CL2026-09-07
#123Deadline-Aware Adaptive Prefill Chunking for Efficient Large Language Model ServingSiyu Song, Qi Bai, Jinbo Hao +3cs.CL2026-09-07
#124Rethinking Sign Language Translation: The Impact of Signer Dependence on Model EvaluationKeren Artiaga, Sabyasachi Kamila, Haithem Afli +2cs.CL2026-09-07
#125Reasoning Beyond Transcription: Audio Language Models on Child Stuttering SpeechChibuzor Okocha, Christan Grant, Zoey Liucs.CL2026-09-07
#126MeRoTune: RoPE-Safe Merging with a Tunable DialSalman Farozcs.CL2026-09-07
#127BanglaMemeX: Advancing Cultural Metaphoric Image Interpretation in Bangla with a Multimodal Explainable DatasetMd. Sadman Sakib, Zisan Mahmud, Md. Fahim Arefin +1cs.CL2026-09-07
#128AgentDrift: A Step-Labeled Benchmark of Injection-Hijacked LLM Agent TrajectoriesAsif Pinjari, Mithun Paul Saint-Germaincs.CR2026-09-07
#129CIPHER: Benchmarking Cross-record Inference over Privacy-Hardened Evidence RecordsSuparno Roy Chowdhury, Manan Roy Choudhury, Dhruv Madhwal +1cs.CR2026-09-07
#130AgentLeak: Cloning Stronger LLM Agent Capabilities onto Weaker Agents Beyond Skill StealingXiaoting Lyu, Yuhong Wu, Yufei Han +6cs.CR2026-09-07
#131Towards a Resilience-Theoretic Foundation for Adversarial Robustness in Industrial Control System Anomaly DetectionBranka Stojanović, Andreas Flatscher, Michael Sommacs.CR2026-09-07
#132Staying on the Attack Path: Structured State for Long-Horizon Automated Penetration TestingWeizhe Wang, Yitong Zhang, Yao Zhang +4cs.CR2026-09-07
#133Privacy Leakage from a Thousand Words: Millipixel Location Recovery from Dot MapsYuntao Du, Tanishq Pauskar, Hao Wang +2cs.CR2026-09-07
#134Do AI Coding Assistants Check Before They Install? A Pre-Registered Demand-Side Audit of Trust Signals in the Research Software Supply ChainPengyin Shancs.CR2026-09-07
#135VEX-Bench: Benchmarking LLM Agents for Assessing Exploitability of Software Supply Chain VulnerabilitiesJiahao Shi, Edward Tsien, Yifeng Di +10cs.CR2026-09-07
#136Contextual Observer Grounding: Evaluating Situated Spatial Reasoning in Vision-Language ModelsMimo Shirasaka, Haochen Zhang, Yonatan Biskcs.CV2026-09-07
#137BEFORE THE FLIP: Measuring Hidden Score Shifts In Quantized Vision Language Models Before The Answer Changes for Visual Question AnsweringSourajit Saha, Shubhashis Roy Dipta, Shaswati Saha +2cs.CV2026-09-07
#138Emo-DVS: A Multimodal Benchmark for Privacy-Aware Emotion Recognition with Event CamerasJiaqi Chen, Qinfu Xu, Hao Zhuang +1cs.CV2026-09-07
#139Sub-Pixel Affine Registration of Space Debris Images via the Radon Point Spread FunctionShenshen Luan, Miaomiao Tian, Shuai Jiang +3cs.CV2026-09-07
#140CARDEA: Auditable Reasoning Grounded in Spatial Evidence for End-to-End Coronary Angiography InterpretationJia-Jen Lee, Shih-Yen Hou, Kee Koon Ng +2cs.CV2026-09-07
#141PRG-Fusion: Orchestrating Generative Priors with Reconstruction Evidence for Driving View SynthesisSipeng He, Jialei Chen, Zhen Fang +2cs.CV2026-09-07
#142Joint-Conditioned Stereo Surface Reasoning for Interaction Field EstimationYanlin Jin, Yifan Yang, Bowen Yang +1cs.CV2026-09-07
#143MSSP: Multi-Scale Spatially-Constrained Partition for Unsupervised Semantic Segmentation of 3D Point CloudsZhenghao Zhang, Xinjie Wang, Wei Wang +2cs.CV2026-09-07
#144DPSF-Net: A Dual-Prior Spatial-Frequency Network for Real-World Remote Sensing Image DehazingMei Lu, Shangliang Shao, Shanliang Yaocs.CV2026-09-07
#145Re-calibrated Contrastive Loss for Transformation-Aware Prompt Conditioning in Vision-Language ModelsSeungmin Oh, Seunghun Kang, Jongbin Ryucs.CV2026-09-07
#146AnomalyCraft-700K: Component-Level Controllable and Verifiable Synthetic Anomalies for Fine-Grained Video Anomaly UnderstandingYuzhou Long, Haodong Zhang, Yunpeng Yang +2cs.CV2026-09-07
#147AV-SafetyBench: A Safety Benchmark for Text-to-Audio-Video GenerationSuah Choi, Tae-Young Lee, Gyeong-Moon Parkcs.CV2026-09-07
#148CGSM: Concept-Guided Segmentation Model for Precise Pulmonary Lesion DelineationChangheng Lin, Wenjie Zhang, Yushan Lu +3cs.CV2026-09-07
#149GIFT: Goal-Injected Fine-Tuning for Efficient Manipulation Policy AdaptationXiaoyuan Fang, Shuo Feng, Yuxuan Wang +3cs.CV2026-09-07
#150Fine-Grained Visual Preprocessing and Dual-Stream Temporal Modeling for Multimodal Sentiment Analysis on Social MediaSu Li, Yigong Zhang, Lei Xiong +1cs.CV2026-09-07
#151ARNAI: Artifact Removal Network based on Autoencoding and Inpainting for Robust Spinal Image Segmentation and MeasurementSang-Jin Park, Jinyoung Choi, Seokwon Kim +13cs.CV2026-09-07
#152LoGAN: Multilingual Font Localization with Generative AgentsZhuoning Yuan, Ta-Ying Cheng, Benjamin Kleincs.CV2026-09-07
#153FreqDoor: A Hidden Trojan in the Frequency Domain for Backdoor Attacks on Vision-Language ModelsYasir Arafat Prodhan, Sadad Hasan, Mohammed Imamul Hassan Bhuiyancs.CV2026-09-07
#154CNsEMD: An Expert-Annotated Multi-Field-Strength MRI Dataset and a Hyperspherical Manifold Network for Multimodal Cranial Nerve ParcellationLei Xie, Junxiong Huang, Guoqiang Xie +9cs.CV2026-09-07
#155SpatialBlock: Enhancing Spatial Intelligence in LVLMs via Synthetic Block-Stacking ProblemSoohyun Ryu, Sohee Kim, Eunho Yangcs.CV2026-09-07
#156Continuous Token-Level Spatio-Temporal Context Modeling for Visual Object TrackingDing Xia, Meiqin Liu, Jing Zhou +1cs.CV2026-09-07
#157Detect Anything in Graphic Design: Element-Level Rewards for Autoregressive DetectionJiangning Zhu, Bowen Li, Shenyu Qiao +4cs.CV2026-09-07
#158One for All: Generalist Foundation Model for Cross-Sensor Skeleton Representation LearningJeonghyeok Do, Yun Chen, Munchurl Kimcs.CV2026-09-07
#159SupGRPO: Enhancing GRPO with Matching-based Online SFT for Text SpottingXudong Xie, Yuzhe Li, Jing Shi +3cs.CV2026-09-07
#160Single Image to Textured 3D Object Generation in Frequency Domain: From Theory to PipelineQisen Wang, Yifan Zhao, Jia Lics.CV2026-09-07
#161CASCADE: A Spatio-Temporal-Causal Reasoning Representation and Dataset for DrivingJenny Schmalfuss, Despoina Paschalidou, Simon Gerstenecker +2cs.CV2026-09-07
#162Ambient @ EgoProactive 2026 : Proactive Egocentric Assistance with Visually Grounded SupervisionLogesh Kumar Umapathics.CV2026-09-07
#163Discovering Natural Transformation Vulnerabilities in Black-Box Vision ModelsDongsu Song, DaeYun GO, Jay Hoon Jungcs.CV2026-09-07
#164A Two-Stage Framework for Ego-Centric Key Object Identification via Object State PredictionShihong Ling, Yue Wan, Xiaowei Jia +1cs.CV2026-09-07
#165NutriBench-Kitchen: Benchmarking Embodied AI for Nutrition ManagementYulin Wei, Xiangchen Wang, Jianhui Pan +5cs.CV2026-09-07
#166Flow3D-OPD: Multi-Teacher On-Policy Distillation for 3D Geometry Generation with Flow-Matching Diffusion TransformerZhiwei Ning, Zhen Zhou, Puhua Jiang +7cs.CV2026-09-07
#167Ambient @ EgoLongQA 2026: Distilling Long-Video perception into a Sub-2B ModelLogesh Kumar Umapathics.CV2026-09-07
#168Mind the Approximation: Fisher-Weighted SVD Compression for ViTsMoritz Thoma, Maximilian Groezinger, Maximilian Forstenhäusler +7cs.CV2026-09-07
#169Unsupervised Domain Adaptation for Symbol Spotting in Historical Encrypted ManuscriptsGiuseppe De Gregorio, Alicia Fornés, Lei Kang +1cs.CV2026-09-07
#170Weakly-supervised Kidney Tumor Classification from CT Scans with Multi-Instance Learning and Anatomical FilteringJoonas Ariva, Dmytro Fishmancs.CV2026-09-07
#171Deep Learning for Biopsy-Free Subtyping of Basal Cell Carcinoma from Dermatoscopic ImagesAlexandros Papadopoulos, Chrysa Episkopou, Ioannis Sarafis +2cs.CV2026-09-07
#172CHILD: Human-in-the-Loop OOD Detection for Safe Clinical DeploymentJinlun Ye, Kaiyue Lu, Runhe Lai +3cs.CV2026-09-07
#173The Price of Consistency: Exploiting Visual Anchors for Multimodal Jailbreaking in Video GenerationPeng Li, Qianqian Xu, Yangbangyan Jiang +2cs.CV2026-09-07
#174Proximity-CLIP: Text-Guided Semantic Proximity Learning for Zero-Shot Anomaly DetectionManwen Yang, Leqian Ding, Yu Guo +1cs.CV2026-09-07
#175MV-STRIDE: Enabling MLLMs to Master Multi-View Spatial Reasoning via Hierarchical Capability ModelingJin Xu, Xiaojian Huang, Zhuodong Luo +6cs.CV2026-09-07
#176KODAMA: Multimodal Digital Twin Reconstruction for Urban RF Propagation ModellingMaximiliano Wardle, A. Ryo Koblitzcs.CV2026-09-07
#177CRISP: Corneal Confocal Microscopy Real-Time Image Stitching PipelineQincheng Qiao, Puli Zhang, Jian Zhou +1cs.CV2026-09-07
#178From Explicit References to Scene Manifolds: Distributional Fidelity and Realism for Radiance Field Quality AssessmentSaeed Mahmoudpour, Gi-Mun Um, Hyon-Gon Choo +1cs.CV2026-09-07
#179DF26: We Cannot Tell Fake From Real AnymoreSeveryn Shykula, Andrii Yermakov, Ivan Samarskyi +3cs.CV2026-09-07
#180TRAIL: Trajectory-Aware Visual Place Recognition against Unordered DatabasesDominik A. Kloepfer, Patrick Wenzelcs.CV2026-09-07
#181Social Intuition vs. Machine Reasoning: Anticipating Human-Robot Interaction from multiple modalitiesRaphael Lorenzo-Louis, Bertrand Luvison, Serena Ivaldics.CV2026-09-07
#182Federated Binary Gating with Server-Side Vision-Language Inference for Surveillance Anomaly ClassificationCôme-Alexis Puech, Sébastien Thuau, Amira Gran +3cs.CV2026-09-07
#183Multi-label versus multi-class classification of blood cells and their aggregates in microfluidic channelsIgor Zingman, Shada Abuhattum, Sara Kaliman +8cs.CV2026-09-07
#184RelightFormer: Feed-forward Generative Transformer for Multiview Object RelightingHejun Wang, Jinxi Li, Junwei Jiang +4cs.CV2026-09-07
#185Self-Supervised Multi-View 3D Gaze Target Estimation via Probabilistic Ray MarchingKeqi Chen, Vinkle Srivastav, Nicolas Padoycs.CV2026-09-07
#186Unified Vision-Centric Pedestrian Crossing Action Prediction via Adaptive Patch Projection and Proactive Spatial RectificationYao Tian, Le Yang, Binglu Wangcs.CV2026-09-07
#187AFID: A Unified Open Framework for Automated Fingermark Identification, Quality Assessment and Feature ExtractionTim Oblak, Rudolf Haraksim, Peter Peercs.CV2026-09-07
#188Parser-Free VLM Verification for Federated Weakly Supervised Video Anomaly DetectionSébastien Thuau, Amira Gran, Siba Haidar +1cs.CV2026-09-07
#189Latent-to-Latent Flow for Volumetric Stochastic SegmentationOmar Todd, Sooha Kim, Raghav Mehta +5cs.CV2026-09-07
#190When Superpixels Fail on Documents: A Study of Segmentation for LIME ExplanationsQuentin Telnoff, Emanuela Boros, Mickaël Coustaty +3cs.CV2026-09-07
#191CrACK: Adversarial Attacks on Cross-Model Consistency in Collaborative Vision Foundation ModelsFeifei Liu, Jintao Cheng, Chi Man Vong +1cs.CV2026-09-07
#192Mitigating Shortcut Learning: Texture-Penalized Prototype NetworksAkshay Anilkumar Girija, Elena Hoemann, Frank Köster +1cs.CV2026-09-07
#193PICANet: Physics-Informed Cascaded Asymmetric Network for Infrared Small Target DetectionJingjing Liu, Yinchao Han, Xianchao Xiu +2cs.CV2026-09-07
#194Topologically Consistent Agricultural Parcel Vectorization with Semantic-Guided Diffusion and Topology-Aware PolygonizationWeiqin Jiao, Xiaolong Zuo, Claudio Persellocs.CV2026-09-07
#195When Semantically Consistent Encoding Meets View-Label Heterogeneity Modeling: A Unified Framework for Incomplete Multi-View Multi-Label LearningChengliang Liu, Bo Li, Bob Zhang +3cs.CV2026-09-07
#196TeMo: Temperature Modulation for Multimodal Contrastive LearningDhimitrios Duka, Bernt Schiele, Hilde Kuehne +1cs.CV2026-09-07
#197Re-engineering SORT-based algorithms for low-cost small object tracking from omnidirectional footageXin Shu, Meegan Gower, Yvonne Buckley +1cs.CV2026-09-07
#198Heat Kernel Textures: the Geodesic Gaussians That Do Not SplatSimone Foti, Caner Korkmaz, Stefanos Zafeiriou +1cs.CV2026-09-07
#199SphereSOD: Geometry-Structure Coupled Learning for 360 Salient Object DetectionJunsong Zhang, Zhijie Shen, Shuai Zheng +4cs.CV2026-09-07
#200Solution for UCF UrbanTwin LUMPI Track: Sim-to-Real Urban LiDAR 3D Object DetectionPu Luo, Cong Xu, Yumei Li +4cs.CV2026-09-07
#201BarkNet-Lite: A Lightweight Texture and Colour Network with the BarkBD Benchmark for Bark-Based Tree Species Recognition in BangladeshAroshi Ali, Saad Ahmed, Md. Khalid Syfullahcs.CV2026-09-07
#202Search-to-World: Evaluation of 3D World Delivery from User Request through Web SearchZixiao Gu, Yabo Chen, Xunzhi Xiang +5cs.CV2026-09-07
#203Solution for UCF UrbanTwin V2X-Real Track: Sim-to-Real Urban LiDAR 3D Object DetectionPu Luo, Cong Xu, Yumei Li +4cs.CV2026-09-07
#204Harnessing CLIP and DINO: An Uncertainty-Aware Cascaded Fusion Network for Generalizable Deepfake Image DetectionXuechao Zou, Yi Zhou, Kai Li +4cs.CV2026-09-07
#205CrowdTraj: A Benchmark for Dense Crowd Trajectory Prediction in Realistic Crowded EnvironmentsAntonius Bima Murti Wijaya, Paul Henderson, Marwa Mahmoudcs.CV2026-09-07
#206Better Call CineCrew: Consistent Ultra-Long Narrative-to-Film GenerationJiaben Chen, Sixun Dong, Qinhong Zhou +4cs.CV2026-09-07
#207Zero-Shot 3D Plant Organ Segmentation with SAM3 and Semantic NeRFsAndreas Gilson, Laura Hennig, Peter Pietrzykcs.CV2026-09-07
#208TV-SGS: Gaussian Splatting with Geometric Information Propagation via Tensor Voting under sparse viewsHarish N Sathishchandra, Philippos Mordohaics.CV2026-09-07
#209TFTrack: A Template-Free Framework for Efficient 3D Point Cloud TrackingZhaofeng Hu, Sifan Zhou, Jiahao Nie +3cs.CV2026-09-07
#210Cross-modal learning for SAR target recognition using optical vision foundation modelsLucas Hirsch, James R. Hopgood, Javid Khan +2cs.CV2026-09-07
#211DroneGround: Open-Vocabulary Drone Payload Characterization Using Synthetic Data and Grounded Vision-Language ModelsAmi Pandat, Rajasekhar Punna, Gopika Vinod +1cs.CV2026-09-07
#212VoT: Vision-of-Thought for Unified Multimodal Representation AlignmentJingxiang Sun, Chao Liao, Zhengxiong Luo +6cs.CV2026-09-07
#213SAFIRE: Safety-Critical Benchmark for Fine-grained Fire and Smoke Understanding in Multimodal LLMsPengfei Li, Naufal Suryanto, Sicheng Zhang +2cs.CV2026-09-07
#214Are Image Generators Zero-Shot Perceivers? A Rigorous EvaluationShangzhe Di, Zhaokai Wang, Weidi Xiecs.CV2026-09-07
#215JEDI: JEPA-to-Edge Distillation for Efficient Cropland Segmentation from Satellite ImageryKishor Kumar Bhaumik, Nicolas Roque dos Santos, Jia Chen +1cs.CV2026-09-07
#216Poisson Image Denoising Using Minimax Concave and Reweighted $\ell_1$ Penalties: Nonblind and Blind ApproachesReza Parvazcs.CV2026-09-07
#217TDDN: Text-aligned Diffused DINO Network for Puzzle UnderstandingHarsha Patnala, Debopriyo Banerjee, Ayush Sunil Munot +1cs.CV2026-09-07
#218Bottom-up Modeling of Repeated Elements via Single Image Analysis-by-SynthesisSyrine Kalleli, Alexei A. Efros, Mathieu Aubrycs.CV2026-09-07
#219ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly UnderstandingChia-Hui Chen, Shih-Ying Yeh, Fu-En Yang +2cs.CV2026-09-07
#220TaskGuard: Task-Conditioned Restoration Utility for Risk-Aware Object DetectionVung Phamcs.CV2026-09-07
#221A Black-Box Adversarial Attack on Human Pose Estimation and Keypoint-Based Action Recognition ModelsKacper Mroczek, Michal Kepskics.CV2026-09-07
#222Flexible Motion Generation from Language and Style ReferencesKai Weixian Lan, Bodie Criswell, Briana Fedkiw +3cs.CV2026-09-07
#223SAFER-Activities: A Dataset for Smart Assessment of Fall Events and Routine ActivitiesDiwas Lamsal, Pramod Wickramatilake, Jednipat Moonrinta +2cs.CV2026-09-07
#224MamMA: A Mamba-Based Pedestrian Trajectory Prediction Algorithm Considering Occupancy Map and Pedestrian Awareness StatesJuncen Long, Xiaofeng Jin, Gianluca Bardaro +2cs.CV2026-09-07
#225A Quantitative Evaluation Framework for Temporal Explainability in Echocardiographic Video SegmentationJiyoo Noh, Jonathan H. Chancs.CV2026-09-07
#226RFS-UNet: Decoder-Conditioned High-Resolution Skip Recalibration for Bone-Selective DRR SynthesisXiaoyang Li, Yixuan Liu, Yuan Chaics.CV2026-09-07
#227Mapping the Emerging Social Science of Large Language ModelsYi Yang, Xiao Jia, Zeyun Dong +2cs.CY2026-09-07
#228An emancipatory vision for designing (generative) AI for learner flourishingLuis P. Prieto, Yannis Dimitriadiscs.CY2026-09-07
#229PLATOS: A Power and Latency-Aware Task-Oriented Scheduling Strategy for Healthcare IoT in Fog ComputingMohammed Alaa Ala'anzy, Zulfiqar Ahmad, Zhanar Mukashcs.DC2026-09-07
#230Scalability Analysis of Distributed Kolmogorov-Arnold Network Training on High-Performance Computing SystemsGuangneng Chen, David Garcia Selfa, Pablo Quesada Barriusocs.DC2026-09-07
#231Same Problem, Different Field: Cross-Domain Solution Import via Domain-Stripped Computational FingerprintsEryk Kulikowskics.DL2026-09-07
#232From Citations to Contributions: LLM-Assisted Credit Scoring of Research ArticlesSana Ebrahimi, Suraj Shetiya, Abolfazl Asudehcs.DL2026-09-07
#233Large-Scale User Behavior Analysis in Multimodal AI-Assisted Manual Task ExecutionRafael Ferreira, Diogo Tavares, Diogo Glória-Silva +2cs.HC2026-09-07
#234Quantifying the Engagement Trap: Impact of Short-form Video Recommender Systems on Users with ADHDVedad Misirlic, Gregor Mayr, Elisabeth Lexcs.HC2026-09-07
#235Query-Aware Token Budgeting for Efficient Late-Interaction Visual Document RetrievalPS Rishi, Rajeev Ranjan Dwivedi, Vinod K Kurmics.IR2026-09-07
#236Matryoshka Hash Representations for Model-Aware Compact Semantic RetrievalPeichun Hua, Yunming Xiaocs.IR2026-09-07
#237EigenLI: Spectral Approximations to Late InteractionArchish S, Sabyasachi Basu, Ankit Garg +2cs.IR2026-09-07
#238Open Tabular Insight Extraction: Where Do We Stand, and Where Should We Go?Daniel Gomm, Maarten de Rijke, Madelon Hulseboscs.IR2026-09-07
#239Noēsis: Deterministic-First Retrieval with Two-Tier Context Hydration for Factuality-Critical Queries on Small Local ModelsNicola Cogottics.IR2026-09-07
#240Learning Adaptive SED for heterogeneous load balancingSanne van Kempen, Jaron Sanders, Fiona Sloothaak +1cs.LG2026-09-07
#241Noisy-Space Policy Gradient for Diffusion Policies in Offline Reinforcement LearningMahmoud Selim, Cristina Cipriani, Karl H. Johanssoncs.LG2026-09-07
#242From Synthetic Priors to Model Behavior: Structural Coverage in Tabular Foundation ModelsHe Zhao, Ryan Thompson, Daniel M. Steinberg +3cs.LG2026-09-07
#243Constrained Online Learning with Noisy Constraint ValuesVaneet Aggarwalcs.LG2026-09-07
#244The Geometry of Refusal: Why Post-Hoc Safety Is Fragile and Pretraining-Time Safety PersistsSrikanth Malla, Chiho Choi, Joon Hee Choics.LG2026-09-07
#245PCSDiff: Diffusion-Based Bias Correction and Super Resolution Toward Practical Operational Medium-Term Precipitation ForecastYuze Sun, Shiyi Wang, Jiancheng Pan +7cs.LG2026-09-07
#246Particle Dynamics of Flow Matching and Classifier-Free Guidance from a Stagewise Geometry PerspectiveJian-Feng Cai, Zhengyi Su, Chao Wangcs.LG2026-09-07
#247Steering Interference Reflects the Model's Defaults, Not the Behavior DirectionsSrikanth Malla, Chiho Choi, Joon Hee Choics.LG2026-09-07
#248MOLE: Detecting Insider Threats in AI AgentsAashiq Muhamed, Virginia Smithcs.LG2026-09-07
#249HealthLoopQA: A Context-Aware Question Answering Benchmark for Interpreting Wearable Monitoring Data in Diabetes CareYuchen Niu, Yanan Ma, Srinivasan Nandakumar +7cs.LG2026-09-07
#250AF-Mamba: Efficient Long-Term Signal Modeling for Early Prediction of Atrial Fibrillation OnsetYongbin Lee, Ki H. Choncs.LG2026-09-07
#251Continual Learning Mechanisms Compose for Long-Horizon MemorizationZheyuan Zhang, Alvin Zhang, Daniel Khashabi +1cs.LG2026-09-07
#252NeuCME: Toward Dynamic Multimodal Continual Learning via Neural Combinatorics of Multiple ExpertsKai Guo, Chuanbin Liu, Peng Hu +2cs.LG2026-09-07
#253HyperTransfer: Understanding the Equivalence between Base Optimizer and HyperballJinghui Yuan, Hongtao Zhang, Jade Zou +4cs.LG2026-09-07
#254Efficient Learning and Symmetry Discovery under Exact InvariancesAshkan Soleymani, Behrooz Tahmasebi, Patrick Jaillet +1cs.LG2026-09-07
#255Disentangling Steering VectorsTakeru Hiramatsu, Kyohei Atarashi, Koh Takeuchi +1cs.LG2026-09-07
#256AI and TCAD for Inverse Design and Defect Discovery: From Simple Machine Learning to LLMHiu Yung Wongcs.LG2026-09-07
#257TrojanWorld: Backdooring World-Model Agents via Imagination SteeringWenkai Huang, Siyuan Liang, Gaolei Li +4cs.LG2026-09-07
#258PhysSAE: Mechanistic Interpretability with Sparse AutoencodersNandita N. Patil, Eshwar R. A., Gajanan V. Honnavarcs.LG2026-09-07
#259Trust-But-Verify: Poisoning-Resilient Locally Private Graph Learning ProtocolsLongzhu He, Li Sun, Hao Peng +3cs.LG2026-09-07
#260Conditioned Initialization for AttentionHemanth Saratchandran, Simon Luceycs.LG2026-09-07
#261Temporal Heterogeneous Graph Transformer for Credit Card Fraud DetectionQinwen Yancs.LG2026-09-07
#262Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-TrainingZili Wang, Zhaopeng Qiu, Yuekai Zhang +2cs.LG2026-09-07
#263Fine-grained Distributed Backdoor Attacks in Federated LearningJian Wang, Hong Shen, Wei Ke +1cs.LG2026-09-07
#264Stable-MM-R1: Anchoring Multimodal Reasoning Dynamics via Entropy-Guided StratificationYimeng Ye, Shuang Chen, Wenxuan Huang +8cs.LG2026-09-07
#265The Oversight Gap: What LLM Safety Monitors Miss, and Why It Is Not CapabilityXin Xucs.LG2026-09-07
#266FedRAW: Preserving Rare-Label Influence in Asynchronous Federated LearningPrashant Bajpai, Divya Saxena, Philippe Lalanda +1cs.LG2026-09-07
#267Protocol effects on feature-based hardware-Trojan detection across Trust-Hub familiesHang Xiao, Chuhong Xu, Kainan Zhou +2cs.LG2026-09-07
#268REFINE: Trajectory Representation Learning via Closed-Loop Transcription -- Extended VersionSean Bin Yang, Ying Sun, Jilin Hu +5cs.LG2026-09-07
#269Robust Decentralized Federated Distillation via Multi-Modality Knowledge CollaborationXiao Ma, Hong Shen, Hui Tian +2cs.LG2026-09-07
#270Parallelism Strategy Chaining for Fast Training ConvergenceMinchul Kang, Changyong Shin, Younghun Go +4cs.LG2026-09-07
#271Kolmogorov--Arnold stability for discontinuous functionsSviatoslav V. Dzhenzhercs.LG2026-09-07
#272Dense Structural Compression of Transformers via Gauge-Correct Channel RemovalJed A. Duersch, Naïm Es-Sebbani, Nathanaël Haas +1cs.LG2026-09-07
#273Constitutive State-Space Modeling of Path-Dependent Plasticity: A Resolution-Consistent and Parallelizable Computational FrameworkRui Barreira, Taylan Soydan, Francesco Scipione +2cs.LG2026-09-07
#274PCFlow: Physics-Conditioned Flow Matching for GPR B-Scan Image SynthesisZhijie Shen, Chenchen Fu, Xuanhao Chang +2cs.LG2026-09-07
#275Long-Horizon Language Model Reinforcement Learning via Progressive Point MatchingPreston Fu, Kevin Frans, Oleh Rybkin +2cs.LG2026-09-07
#276Robust Decentralized Personalized Federated Learning via Prediction-Constrained Neighborhood CollaborationXiao Ma, Hong Shen, Hui Tian +2cs.LG2026-09-07
#277Inferring Urban Mobility Interactions from Aggregated DynamicsYi Wang, Jing Li, Jinliang Deng +5cs.LG2026-09-07
#278Think Wider: Mitigating Latent Rank Collapse in Implicit Chain-of-Thought ReasoningYuwen Hao, Menglin Yangcs.LG2026-09-07
#279Impact of canny edge detection preprocessing on performance of machine learning models for Parkinson's disease classificationSameer Bhat, Piotr Szczukocs.LG2026-09-07
#280Revisiting Thinning Methods for Kernel Learning ProblemsBlanca Cano-Camarero, Yago R. Aguado-Carrillo-de-Albornoz, Ángela Fernández-Pascual +1cs.LG2026-09-07
#281TabBench-Bio: A Living Benchmark for Machine Learning on High-Dimensional Biomedical TablesJules Kreuer, Sofiane Ouaari, Julia Hellmig +2cs.LG2026-09-07
#282TASTE: Throughput-Aware Batch Size Tuning for On-Device Edge LearningAvik Bhatnagar, Federico Nicolas Peccia, Oliver Bringmanncs.LG2026-09-07
#283Temporal-Causal Inference for Reinforcement Learning via Automata LearningJan Corazza, Daniil Kaminskyi, Simon Lutz +4cs.LG2026-09-07
#284Improving Multivariate Time Series Classification with Class-Wise Training and Model AggregationMouhamadou Mansour Lo, Gildas Morvan, Mathieu Rossi +2cs.LG2026-09-07
#285Statistical versus machine learning-based spatial interpolation of post-processed ensemble weather forecastsMária Lakatoscs.LG2026-09-07
#286CoRL: Co-Evolutionary Reinforcement Learning for Adaptive Indirect Prompt-Injection Attacks and DefensesBoyang Zhang, Qingxin Xiao, Lingwei Dang +1cs.LG2026-09-07
#287No-Regret Mixing of LRU and LFU with Optimal Switching CostYounes Ben Mazziane, Xinying Zoucs.LG2026-09-07
#288Efficient Exploration Is EnoughMikel Malagón, Jon Vadillo, Josu Ceberio +2cs.LG2026-09-07
#289I Don't Miss You, but I Do: Self-Explanation Faithfulness of Modality Missingness in Vision-Language ModelsAydin Javadov, Daniel Schoess, Florian von Wangenheimcs.LG2026-09-07
#290Beyond the Matrix Sign: Quadratic Spectral DescentQiaozhe Zhang, Jun Sun, Yingzhuang Liucs.LG2026-09-07
#291CLUES-WEASEL: No additional clues required to choose your time series clustering algorithmJohann Faouzics.LG2026-09-07
#292Translation of Black-Box Clinical Prediction Models into Standalone Transparent Nomograms: Temporal External Validation in Heart TransplantationHenry Pigot, Paulo J. G. Lisboa, Sandra Ortega-Martorell +3cs.LG2026-09-07
#293Forecasting the Winner of a Live Tennis MatchCharles Xie, Aneesh Muppidics.LG2026-09-07
#294Online Surrogate Repair: Decoupling High-Fidelity Feedback from Search Length in Closed-Loop DiscoveryXiaotang Feng, Philip Torr, Bruno Andreiscs.LG2026-09-07
#295Accuracy is Not Enough: A Divergence-Based Approach to Evaluate Fidelity Loss in Quantized LLMsShahzeb Qamar, Lorenz Sparrenberg, Christian Bauckhage +5cs.LG2026-09-07
#296MpSub: A Momentum $p$-Dimensional Subspace Trust-Region Method for Derivative-Free Fine-Tuning of Large Language ModelsYuyang Wang, Haoyu Yao, Pengcheng Xiecs.LG2026-09-07
#297On the Recall Scaling Laws in Mamba: A Theoretical and Mechanistic Study via HashingYuval Koren, Assaf Ben-Kish, Raja Giryes +2cs.LG2026-09-07
#298Emergent Charging Coordination in Electric Delivery FleetsJavier Vales-Alonso, Juan J. Alcarazcs.LG2026-09-07
#299ParetoTransport: Generative Optimization by Mass Transport Toward The Pareto FrontStephanie Holly, Sepp Hochreiter, Werner Zellingercs.LG2026-09-07
#300Attributing Cohen's d: Training Data Attribution for Disease-Related Effects in Normative Age BiomarkersJakob Snel, Marc-Andre Schulzcs.LG2026-09-07
#301Guiding Worker Self-Selection in Crowdsourcing Contests: An LLM-Augmented Algorithmic ApproachNguyen Thach, Hau Chan, David Parkes +1cs.LG2026-09-07
#302Local gradient neural operatorBaiming Zhang, Jinsong Tang, Ying Xu +2cs.LG2026-09-07
#303A Theoretical Analysis of Generalization Dynamics in Neural Networks under Gradient Descent with Weight DecayYuqing Wang, Ioannis G. Kevrekidis, Mikhail Belkincs.LG2026-09-07
#304Decomposition-Guided Diffusion Language Models for Inertial Confinement Fusion PredictionXiang Zhang, Varchas Gopalaswamy, Rahman Ejaz +2cs.LG2026-09-07
#305Latent-MoE: Domain-Aware Mixture-of-Experts for PDEs with Multi-Regime PhysicsHanwen Wang, Paris Perdikariscs.LG2026-09-07
#306Kalman Delta Networks: Uncertainty-aware Associative MemoryNgoc Bui, Tinglin Huang, Rex Yingcs.LG2026-09-07
#307Foundation Models for Generalizable Semantic and Goal-Oriented CommunicationBoliang Liu, Wint Yi Poe, Riccardo Trivisonno +1cs.LG2026-09-07
#308InfluenceField: A Differentiable Field with Interventionally Identifiable Causal Structure for Multimodal World ModelingZihao Yang, Zijia Wang, Zhiqiu Huangcs.LG2026-09-07
#309The Accuracy Paradox: Empirical Diagnostic of Default Decision Thresholds in Multi-Label Enzyme Commission Prediction [With Code]Bilal Ahmad, Rajed Mehmoodcs.LG2026-09-07
#310AVCG: A Generalized Variational Framework for Counterfactual Generation under Hypothesis DistributionsJamie Duell, Alejandro Jimenez Rodriguez, Mahault Albarracincs.LG2026-09-07
#311Prevalence calibration as shortcut mitigationMohamed Amine Kina, Eike Petersencs.LG2026-09-07
#312Structured Extrema Errors in Classical Surrogates for Viscous Burgers: A Physics-Consistent InterpretationYoussef Oubarics.LG2026-09-07
#313Streaming Hierarchical Inference with Tabular Foundation ModelsVitor Crista, Afonso Lourenço, Diogo Martinho +1cs.LG2026-09-07
#314$α$-Graph: Attention-Infused Normalizing Flow Approach to Tractable Graph ModelingThanh-Dat Truong, Sarah Alharbi, Susan Gauch +3cs.LG2026-09-07
#315MetaKV: Adaptive KV Cache Compression for Constrained LLM InferenceMichael Wang, Keith Li, Roozbeh Bostandoostcs.LG2026-09-07
#316Heat Field Signatures: From Point Clouds to Smooth GeometryYuanqing Wang, Yapeng Tian, Baris Coskunuzercs.LG2026-09-07
#317Semi-Supervised Learning under Spatially Biased SamplingBright Wiredu Nuakoh, Francky Fouedjio, Stephen Bradshaw +4cs.LG2026-09-07
#318Solving the Elastic Wave Equation with Physics-Informed Neural Networks: A Robust and Critical AssessmentDavide Staub, Ben Moseleycs.LG2026-09-07
#319Automated Chest CT Protocol Selection via Large Language Model Derived Text Embeddings from Imaging Request TextZahra Hosseini, Mahan Pouromidi, Farzad Khalvati +1cs.LG2026-09-07
#320HyCO: A Hybrid Neural Solver for Combinatorial OptimizationYuheng Li, Di Yang, Haipeng Chen +1cs.LG2026-09-07
#321Sharp Structure-Agnostic Minimax Risk for Partial Linear ModelsHaichen Hu, David Simchi-Levics.LG2026-09-07
#322Two-Scale Localized PCA-Net: Coarse-Global and Local-Residual Representations for Artifact-Reduced PDE Operator LearningMrigank Dhingra, Jordan Stout, Omer Sancs.LG2026-09-07
#323Monadic Second-Order Logic in HOL: Deep and Shallow with Automated Faithfulness (Extended Preprint)Christoph Benzmueller, Daniel Kirchnercs.LO2026-09-07
#324The OCUDU dApp Platform: An Open Runtime and E3 Interface for Real-Time AI-RANTimothy O'Shea, Matthew Pennybacker, Andriy Kharchenkocs.NI2026-09-07
#325Distributed Dexterous Manipulation with Spatially Conditioned Multi-Agent TransformersSarvesh Patilcs.RO2026-09-07
#326Mind the Phase: Effective Rank and Representation Health in Legged LocomotionFelipe Tommaselli, Thiago H. Segreto, Juliano D. Negri +2cs.RO2026-09-07
#327MEMOBench: A Process Level Memory Benchmark for Robotic ManipulationHaiyang Sun, Haoxiao Wang, Junming Chen +6cs.RO2026-09-07
#328Large Discrete Policy: Advancing Explicit Behavior Modeling with Stochastic Iterative ScoringZhenxin Li, Nadine Chang, Xinglong Sun +8cs.RO2026-09-07
#329From LLM-Generated Specifications to Learned Quadruped LocomotionMerve Atasever, Keyan Azbijari, Cagan Bakirci +5cs.RO2026-09-07
#330Beyond Task Success: Stage-Wise Reliability of World Model Planning under Sensing DegradationGeonmyeong Lee, Byoung-Tak Zhangcs.RO2026-09-07
#331LightSplat: Real-Time High-Fidelity 3D Gaussian SLAM with Loop ClosureJunze Bao, Ye Gao, Yiming Huang +5cs.RO2026-09-07
#332PV-WM: A Heterogeneous Micro-Macro World Model for Articulated Pedestrian-Vehicle Co-RolloutHaozhuang Chi, Jingsong Liang, Ziying Song +4cs.RO2026-09-07
#333D3ARC: Time-Critical Distributed Disaster Detection for Asynchronous Cooperative Multi-Robot SystemsNikolaos Koursioumpas, Lina Magoula, Nancy Alonistioti +1cs.RO2026-09-07
#334Measuring Language Transfer in Robot Policies: Adding Greek to a Cosmos3 Vision-Language-Action PolicyAyoub Kirouane, Georgios Giaples, Christos Petrocheiloscs.RO2026-09-07
#335CosmoH2G: A Hand-to-Gripper Transfer Dataset and Baseline Method for Object Manipulation with Complex Spatial MovementsHongxiang Zhao, Mutian Xu, Zeyu Jin +3cs.RO2026-09-07
#336Generation of Vectorized Maps Beyond Vehicle ViewClara Gomez, Alberto Jaenal, Antonio Artuñedo +2cs.RO2026-09-07
#337Zero-Shot Sim-to-Real Contact-Rich Assembly via Proprioception-Anchored Cross-Modal PretrainingYuhan Wang, Yurou Chen, Hongye Jiang +1cs.RO2026-09-07
#338Scene Graph-Driven Haptic Feedback for Safety Enhancement in Robotic Ophthalmic Surgery via Physically Simulated iOCTDanial Arbabi, Korab Hoxha, Angelo Henriques +2cs.RO2026-09-07
#339Frequency Estimation Based on SNR-adaptive Frequency Estimator Under Wide SNR RangeHee-Yang Jung, Dong-Hee Paek, Woo-Jin Jung +1cs.SD2026-09-07
#340Comparing Self-Supervised and Domain-Invariant Features for Cross-Domain Voice Phishing DetectionJeongmin Lee, Seung Yun, Minkyu Lee +3cs.SD2026-09-07
#341KABURI-TTS: Phoneme-Keyed Activity-conditioned Bi-channel Utterance Rendering for InteractionRyuichiro Higashinaka, Shinnosuke Takamichi, Tetsuji Ogawacs.SD2026-09-07
#342Iterative Audio Separation with Mixture Consistency via MIMO Model ExtensionYukara Ikemiya, WeiHsiang Liao, Yuki Mitsufujics.SD2026-09-07
#343TAD: Token-Adaptive Contrastive Decoding with Confidence-Guided Gating for Hallucination Mitigation in Large Audio-Language ModelsHeyu Chang, Nianwen Si, Hao Zhang +2cs.SD2026-09-07
#344Clean Accuracy Does Not Guarantee Provenance Robustness: A Prospective Codec-Stress Evaluation of Audio AttributionGang Shics.SD2026-09-07
#345LatentMD: Benchmarking Markdown Boundary Failures in LLM-Generated TextSungjune Lee, Myungjoo Kangcs.SE2026-09-07
#346Recompilation Is Not Enough: Test-Guided Decompiled-C RepairYuhan Huang, Puzhuo Liu, Jianlei Chics.SE2026-09-07
#347Quality Metrics for LLM-Generated Asset Administration Shells: A Perturbation-Based Evaluation ApproachJanek Groß, Elena Zentgraf, Jens Heidrichcs.SE2026-09-07
#348CodeTD: Topology of Attention Detects Hallucinations in Code LLMsDaria Voronkova, Ilya Trofimov, Anton Dmitriev +3cs.SE2026-09-07
#349LLMs for Social Network Modeling: From Network Generation to Dynamic ProcessesShikha Mallick, Alex Thomo, Akrati Saxenacs.SI2026-09-07
#350AstraMoE-SR: Trajectory-Guided Diffusion for Blind Satellite Jitter Deblurring and Super-ResolutionYi-Chung Lai, Chin-Tien Wu, Yu-Chih Cheneess.IV2026-09-07
#351Spatial Feature-wise Linear Modulation (SpFiLM) for Contrast Agent-Aware Brain ParcellationPushpendra Singh, Joshua R. Astley, Roman Rodionov +3eess.IV2026-09-07
#352Masking Radar Cognition under Adversarial Surveillance: A Distributional Privacy FrameworkSreedevi K, Nandhini K, Anup Aprem +1eess.SP2026-09-07
#353Sub-6 GHz Over-the-Air AMC via Curriculum Fine-Tuned CNN-TransformersNurettin Safak, Muhammet Sefa Demirel, Alperen Marasli +3eess.SP2026-09-07
#354Pre-Whitening and BCJR Posterior Distillation for Bi-LSTM Detection in Faster-than-Nyquist SignalingNurettin Safak, Osman Tokluoglu, Enver Cavuseess.SP2026-09-07
#355Decentralized Safe Multi-Agent Reinforcement Learning via Predictive ShieldingYacine El Yamani, Hanna Krasowski, Elena Vanneauxeess.SY2026-09-07
#356A Systematic Analysis of Automatic Differentiation versus Discretization-based Constraints for Physics-Informed PDE SolversXing Guo, Hongwei Tang, Zewei Meng +3math.NA2026-09-07
#357Input-to-State Stability Framework for Fully Distributed Primal-Dual Dynamics for Quadratic GNEPs Without Multiplier ConsensusShao-An Yinmath.OC2026-09-07
#358Mathematical Programming in Machine Learning and Artificial Intelligence: A Unified Taxonomy of Models and ApplicationsChaosheng Dongmath.OC2026-09-07
#359Accelerated High-Accuracy Sampling from a Warm Start via the Proximal Bouncy Particle SamplerFan Chen, Sinho Chewi, Jianfeng Lu +1math.ST2026-09-07
#360Smoothed Picard Hamiltonian Monte CarloFan Chen, Sinho Chewi, Jianfeng Lu +1math.ST2026-09-07
#361Tensor network representations of discrete maximum entropy distributions via mean polytopesAlex Goessmann, Martin Eigelmath.ST2026-09-07
#362SeisBench DAS: A machine learning framework for Distributed Acoustic SensingJannes Münchmeyer, Han Xiao, Frederik Tilmannphysics.geo-ph2026-09-07
#363Human mutation field reveals an equilibrium-like structure with irreversible circulationIsabella Caranzano, Daniel Maria Busiello, Stefano Priorelli +2q-bio.GN2026-09-07
#364MI-PEFT: Mixture-of-Experts Integrated Parameter-Efficient Fine-Tuning Protein Language Models Improves Acidophilic Proteins ClassificationHonghan Shenq-bio.QM2026-09-07
#365Riemannian Optimization for Multi-Player Quantum Games on Product Unitary ManifoldsAlireza Habibi, Setareh Maghsudiquant-ph2026-09-07
#366Topology Obstructs Pure Foundation Neural Quantum StatesTimothy Heightman, Elena Orlova, Philip Mantrov +1quant-ph2026-09-07
#367Thermodynamic Cyclic Processes with Markov Samplers in Bayesian InferenceHeinrich von Campe, Bjoern Malte Schaeferstat.CO2026-09-07
#368Bayesian Matrix-Valued Graphs for Context-Dependent Multivariate RelationshipsPapri Deystat.ME2026-09-07
#369Distributed Lag Neural Additive ModelsCalle Helmersson, Shivang Pandey, Leonardo Olivetti +1stat.ML2026-09-07
#370SGD in Multiclass Logistic Regression: Sequential Learning and Scaling LawsKonstantinos Christopher Tsiolis, Denny Wu, Christos Thrampoulidis +1stat.ML2026-09-07
#371The Role of Uncertainty in Assessing the Fairness of Machine Learning ModelsFrancesca Panero, Ernst C. Wit, Marco Scutaristat.ML2026-09-07

latest · trends · arXiv announcement batches follow US Eastern weekdays