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

New Papers · 2026-08-23 203 submissions

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

#TitleAuthorsCatDate
1Dataset Complexity Shapes Finite-Distance Loss Geometry in Neural NetworksJaeyong Bae, Hawoong Jeongcond-mat.dis-nn2026-08-23
2Evaluation of Small Vision-Language Models on Qualitative Mechanical ProblemsHenry Fordjour Ansah, Shreya Banerjee, Pranish Ghimirecs.AI2026-08-23
3A survey detection channel overrides the pixels in an astronomical foundation model, and biases tomographic mean redshiftsIhor Kendiukhovcs.AI2026-08-23
#4AUDITA: certified auditing and causal attribution of adverse outcomes in autonomous multi-agent systemsZhixu Du, Yiran Chencs.AI2026-08-23
#5Aggregation-Aware Synthetic Text Generation Against Authorship Re-IdentificationQian Ma, Anna Squicciarini, Sarah Rajtmajercs.AI2026-08-23
#6MCP-Universe RL: A Framework for Training MCP Tool-Use Agents via Reinforcement LearningZiyang Luo, Yan Yang, Xiangru Jian +5cs.AI2026-08-23
#7Role-Specialized Mixture-of-Agents with Open-Weight LLMs for Clinical PredictionJun Hou, Yi Fang, Xuan Wangcs.AI2026-08-23
#8Is Your Neighborhood Safe? Place-based Stigma in Large Language Models' Urban Safety JudgmentsHuy Nguyen, Yue Lincs.AI2026-08-23
#9Disagree to Explore, Agree to Commit: Routing-Guided Test-Time Scaling for Software AgentsKang Chen, Junjie Nian, Yixin Cao +1cs.AI2026-08-23
#10Query-Driven Multimodal Information Extraction from Long DocumentsYikai Gao, Ding Xia, Xi Yangcs.AI2026-08-23
#11Beyond What Meets the Eye: Unveiling Situational Illusions for Multimodal Large Language ModelsZhiming Yang, Zhuoxi Xiong, Donglin Zhou +3cs.AI2026-08-23
#12Read Less, Solve More: Token-Efficient Sparse Reading for AI AgentsZedong Liu, Jiaan Wu, Xinyang Ma +5cs.AI2026-08-23
#13Clarify User Expertise: Towards Proactive Conversational Agents Tailoring Responses to User ProficiencyZhihong Cao, Chen Huangcs.AI2026-08-23
#14Invocation-Level Reliability of Tool-Using AgentsAfiya Noorain, Subhranshu Mohanty, Amritesh Banerjee +1cs.AI2026-08-23
#15HERO: Human-profile Enhanced Retrieval Optimization Framework for Long-term Agent MemoryYuanhua Lin, Yile Li, Zhiyuan Zhao +2cs.AI2026-08-23
#16Where Cognition Lives: Dissecting Emergent from Computed Function in a Minimal Complete Cognitive ArchitectureFrancisco M. Arrabal-Campos, Francisco G. Montoya, Alfredo Alcayde +1cs.AI2026-08-23
#17Addressing the Selection Problem in Explainable AIClaire Vlases, Katelyn Morrisoncs.AI2026-08-23
#18Analyzing and Mitigating Cross-Lingual Degradation in Multilingual Medical VQAJingbo Wang, Sendong Zhao, Haochun Wang +2cs.AI2026-08-23
#19WAM-OPD: On-Policy Distillation for World Action ModelsLiuhaichen Yang, Zhuang Jiang, Chenchao Sheng +1cs.AI2026-08-23
#20Predicting Consequences and Reinforcing Navigation Policies with Latent World ModelsZengmao Wang, Wei Gao, Shuhan Shencs.AI2026-08-23
#21TRACE: Transition-Aware Residual Control for Multi-Objective Materials DiscoveryKang Zhou, Yujia Tong, Yong Tao +1cs.AI2026-08-23
#22LLMs for Survey Text Analysis - A Performance Comparison Between Humans and GPT-5 on Inductive Content AnalysisLeonardo Bergmann, Renata Gheorghiu, Ana Gvritishvili +3cs.AI2026-08-23
#23Where World Models Break: Natural-Input Failure DiscoveryZhanpeng Shi, Zi Liang, Rong Feng +3cs.AI2026-08-23
#24Function-Level Execution Feedback for Code Preference OptimizationIdris Nechnech, Sehwan Kim, Jimin Seo +4cs.AI2026-08-23
#25Think with Structured Grounding: Perceptual Reinforcement Learning for Chart and Visual-Tabular UnderstandingChangjiang Jiang, Qiannian Zhao, Lei Xin +3cs.AI2026-08-23
#26When Persona Simulations Are Informative: Graph-Structured Signals for Pluralistic Opinion SensingTaehyeon An, Jaehyeong Park, Donghyuk Shincs.AI2026-08-23
#27Small Reasoning Models are Instruction Followers in Function CallingYalda Taheri, Mohammad Hassan Heydari, Erfan Naaman +1cs.AI2026-08-23
#28When Does AI for PDEs Yield Scientific Evidence?Wenshuo Wangcs.AI2026-08-23
#29ClawProBench: Trace-Aware Evaluation of AI Agents with Runtime Coverage and Frozen Workplace-Style HoldoutsYuanHang Xiaocs.AI2026-08-23
#30HANSARD: A Reference Architecture for Forensic Readiness, Runtime Witnessing, and Graded Attribution in Autonomous Multi-Agent AI SystemsChristos Sardianos, Iliana Pla, Vasilis Efthymiou +4cs.AI2026-08-23
#31CONTRAMEM: Learning Self-Evolving Procedural Memory from Contrasting Multi-Model TrajectoriesZheyuan Deng, Binghang Lu, Hanqi Feng +10cs.AI2026-08-23
#32STAGE: Stateful Translation to Agentic Graph Execution with Policy-Scoped Context and Deterministic ControlMengxi Luo, Changjia Chen, An Cao +2cs.AI2026-08-23
#33Scaling Curriculum Learning For Autonomous DrivingCevahir Koprulu, David Paz, Feng Tao +4cs.AI2026-08-23
#34ExecRubrics: Executable Tool-Augmented Rubrics for Verifiable and Efficient Long-Form EvaluationKaustubh D. Dhole, Charles L. A. Clarke, Eugene Y. Agichteincs.AI2026-08-23
#35CausalCache: Conditional High-Fidelity Restoration for Long-Horizon GUI AgentsJiaxuan Luo, Zhanfeng Liao, Jiayao Teng +1cs.AI2026-08-23
#36Auditing the Synthetic Memoir: Measuring Scene-Level Confabulation in LLM-Generated Autobiography Against the Documented Record of the Life It DescribesHeather Renzecs.AI2026-08-23
#37Weakly supervised concept Bottleneck Learning for Robust Two stage Object centric visual reasoningSparsh Tiwari, Gesina Schwalbe, Bettina Finzelcs.AI2026-08-23
#38Coalition-Aware Skill Reliability for Self-Evolving AgentsQiyan Zhao, Xiaofeng Zhang, Bo Liu +11cs.AI2026-08-23
#39DeepSAGE: Stage-Aware Reinforcement Learning for Structured CBT Counseling DialogueQi Zhang, Heajun An, Prakriti Dumaru +4cs.AI2026-08-23
#40CAI-DLLM: Convergence Aware Inference for Diffusion Language ModelsFarhana Amin, Sabiha Afroz, Dimitrios S. Nikolopouloscs.AI2026-08-23
#41Precision-Aware Variable Bit Processing Elements for Hardware-Efficient Systolic Array DesignsDantu Nandini Devi, Madhav Raocs.AR2026-08-23
#42The Collaboration Tax: How Much LLM Multi-Agent Systems Pay to CoordinateWeixiang Sun, Zehong Wang, Hong Huang +2cs.CL2026-08-23
#43How Agents Represent Humans: Human-Directed Stereotypes in an Open Agent Social NetworkHuangchen Xu, Yuan Wu, Yi Changcs.CL2026-08-23
#44Dual-Layer Agentic Memory with Fast Write Routing and Slow ConsolidationWenzhi Li, Dong Nie, Rui Lan +7cs.CL2026-08-23
#45Grounded Normative Rule Generation with Structured SearchFanqi Kong, Huaxiao Yin, Ruijie Zhang +5cs.CL2026-08-23
#46Whitewashing Hate, Smearing Harmless Content: Annotator-Style Rebuttal Attacks on LLM-Based ModerationJunyu Lu, Kaiyuan Liu, Jingyi Kang +7cs.CL2026-08-23
#47Improving Few-Step Language Flows with Untied Self-ConditioningBocheng Li, Linli Xucs.CL2026-08-23
#48Nürnberg NLP @ GermEval Shared Task 2026: Harmful Content Detection in German Social Media through Error-Independent LLM VotersPhilipp Steigerwald, Eric Rudolph, Jens Albrechtcs.CL2026-08-23
#49From Triage to Discharge: A Survey of NLP Tasks, Methods, and Open Challenges in the Emergency DepartmentDipankar Srirag, Aditya Joshi, Salil Kanhere +1cs.CL2026-08-23
#50Length-Adaptive Decoding for Masked Diffusion Machine TranslationYan Zhan, Mengkai Hou, Wanting Zhang +1cs.CL2026-08-23
#51LLM Evaluation on Unseen Questions: Contextual Multidimensional IRT ModelErgan Shang, Weijing Tang, Yinqiu Hecs.CL2026-08-23
#52Text-Anchored Semantic Perturbations for Transferable Jailbreak Attacks on Multimodal Large Language ModelsWenyun Li, Guiping Cao, Xiangyuan Lan +1cs.CL2026-08-23
#53Semantics or Structure? Auditing Text Sensitivity in Multimodal Time-Series ForecastingKarthik Sridhar, Atharva Gupta, Nishant Pradhan +3cs.CL2026-08-23
#54Noise Floor Audit for Agent BenchmarksYihang Chen, Pin Qian, Su Wang +4cs.CL2026-08-23
#55Mechanistic Interpretability of Chain-of-Thought Reasoning via Sequential Activation PatchingMurat Dura, Serkan Öztürk, Selma Tekircs.CL2026-08-23
#56Register Shifts Break LLM Safety: A Bengali Benchmark with Culturally Grounded HarmsNaymul Islam, Nusrat Jahan Lia, Shubhashis Roy Dipta +2cs.CL2026-08-23
#57When Not to Imitate: Boundary-Aware Skill Memory for Reliable Tool-Use LLM AgentsZihan Lin, Zhenyu Chen, Jiawen Wei +6cs.CL2026-08-23
#58Context-Aware Cluster Decoding: Semantic Anchor-Driven Coherence in dMLLMsYikai Zhao, Qiyan Zhao, Jiaquan Zhang +3cs.CL2026-08-23
#59Can Large Language Models "Hyper-Thread"?Fei Dingcs.CL2026-08-23
#60ProBel: Propaganda Detection with Techniques, Spans, and ExplanationsMohamed Bayan Kmainasi, Ali Ezzat Shahroor, Elisa Sartori +2cs.CL2026-08-23
#61SchemaGUI: A Schema-Driven Benchmark for Controllable GUI Generation EvaluationJiarui Dong, Yin Cai, Zhouhong Gu +7cs.CL2026-08-23
#62Don' t Box Me In: Dynamic Cultural Adaptation and Cognitive Tracking for Social UnderstandingChongyuan Dai, Yaling Shen, Shengeng Tang +2cs.CL2026-08-23
#63Rank Reversal in Multilingual LLM Judges: A Label-Free Double-Centering CalibratorAlhasan Mahmood, Samir Abdaljalil, Hasan Kurbancs.CL2026-08-23
#64Aligned Alone, Misaligned Together: Forecasting Adversarial Capture in LLM Agent PopulationsIsotta Magistrali, Chen Shanics.CL2026-08-23
#65Figurative Justice: Detecting metaphors in Hindi judgements with qualitative assessment and transformersBhumika Bhattacharyya, Shouvik Kumar Guha, Indranil Duttacs.CL2026-08-23
#66From Exposure to Expectation: Frequency, Surprisal, and Language Across Development in SpanishFrancisco Portillo Lópezcs.CL2026-08-23
#67XHotpotQA: A Benchmark for Cross-Lingual Knowledge Composition in Multi-Hop Question AnsweringIman Barati, Arash Ghafouri, Behrouz Minaei-Bidgolics.CL2026-08-23
#68GTA-RAG: Graph-Trajectory-Augmented Reinforcement Learning for Multi-Turn Retrieval-Augmented ReasoningJun Chen, Yongchao Liu, Pengyu Qiu +6cs.CL2026-08-23
#69Claim-Level Confidence Calibration for Reliable Decision Making with Large Language ModelsToghrul Abbasli, Kentaroh Toyoda, Yuan Wang +1cs.CL2026-08-23
#70Who Pays More for Safety? Measuring the Disparate Cost of Safety Alignment across LanguagesChanwoong Yoon, Jungsoo Park, Alan Rittercs.CL2026-08-23
#71Kernel Token Contradiction: a Fast and Principled Approach for LLM Claim Uncertainty QuantificationJérémie Dentan, Alexi Canesse, Mahammed El Sharkawy +1cs.CL2026-08-23
#72From Diagnosis to Redesign: Using Quantitative Ethnography to Improve Multi-Agent LLM ReasoningVedant Khatri, Anthony Cusimano, Zachari Swiecki +3cs.CL2026-08-23
#73Hybrid Panels: Toward Human-AI Collaboration in Survey ResearchJulia Romberg, Tobias Gummer, Gabriella Lapesa +2cs.CL2026-08-23
#74Teaching LLMs How ICU Physicians Approach Clinical Reasoning Through OMOP-Aligned Retrieval Improves Reasoning Across Clinical DomainsMiguel Contreras, Scott Siegel, Subhash Nerella +30cs.CL2026-08-23
#75GeoRisk-RAG: A Hierarchy-Aware Risk Framework for Improving RAG Reliability through Selective AnsweringMeenu Ravi, Shailik Sarkar, Lulwah AlKulaib +2cs.CL2026-08-23
#76Iteration Without Elaboration: A Simple ReAct Architecture Suffices for Text-to-SQL GenerationJian Lu, Haiwei Yu, Raymond M Xiong +2cs.CL2026-08-23
#77KONTOGRAPH: Verified Point-in-Time Feature Consistency and Amortised Explanation for Real-Time Anti-Money Laundering under a 200 ms Decision BudgetAhmed Abolfadlcs.CR2026-08-23
#78Neighbor-embedded Graph Neural Network-based Crowd Delivery Traffic Management in Smart CityKishu Gupta, Deepika Saxena, Ashutosh Kumar Singh +1cs.CR2026-08-23
#79When Does Visual Generation Help Visual Understanding in Unified Multimodal Models?Yubo Zhu, Zhehan Kan, Jingyi Yang +6cs.CV2026-08-23
#80VERDICT: Agreement Beats Pixel-Space Verification in Real-Document OCSRYani Guan, Dengpan Dong, Shuang Luo +6cs.CV2026-08-23
#81SAM3Dual: A 3rd Place Solution to the MOSEv2 Track, 8th LSVOS ChallengeJeongRae Kim, Chaehyun Kim, Changwon Limcs.CV2026-08-23
#82UR$^{2}$-MLLM: Uncertainty-aware Revisit Reasoning in Multimodal Large Language Models for Radiology Report GenerationYucheng Chen, Yang Yu, Jiazhou Zhou +5cs.CV2026-08-23
#83Hyper^2: Unleashing Hyperbolic Geometry's Full Potential via Dual-Space ConsistencyGuantian Zheng, Haiyang Xu, Tianyu Gaocs.CV2026-08-23
#84Training-Free VLM Personalization via Calibrated Residual DecodingJiaao Yu, Yujian Ma, Xianming Hu +2cs.CV2026-08-23
#85GAN-Diff : Coupling Pretrained WGAN-GP Features with Conditional Diffusion U-NetsSaif Ahmed, Asadullah Hil Galib, S. M. Riaz Rahman Antu +5cs.CV2026-08-23
#86OVIBench: Benchmarking Online Video Question Answering under InterruptionNaiming Liu, Zhiheng Wu, Shuning Wang +3cs.CV2026-08-23
#87DECO: Depth-Guided Co-Visibility Reasoning for Low-Altitude UAV Visual LocalizationYibin Ye, Xichao Teng, Shuo Chen +4cs.CV2026-08-23
#88Targeted Iterative FilteringFreddie Åström, Michael Felsberg, George Baravdish +1cs.CV2026-08-23
#89Self-Calibrating Dense Displacement Fields for Reliable Co-Registration of Large Optical Satellite ImageryShoukun Sun, Zhe Wang, Sanaz Salati +3cs.CV2026-08-23
#90On Tensor-Based PDEs and their Corresponding Variational Formulations with Application to Color Image DenoisingFreddie Åström, George Baravdish, Michael Felsbergcs.CV2026-08-23
#91Adapting Dense Vision-Language Relationships for Multi-label Classification with Partial LabelCheng Chen, Yifan Zhao, Jia Lics.CV2026-08-23
#92On the Choice of Tensor Estimation for Corner Detection, Optical Flow and DenoisingFreddie Åström, Michael Felsbergcs.CV2026-08-23
#93MedReaMM: Evaluating Large Multimodal Models on Expert-Level Clinical Diagnostic SynthesisLai Wei, Yuchao Chen, Zhenbiao Cao +5cs.CV2026-08-23
#94AcroMELD: Recovering Interactive PDF Forms with Structure-Aware Graph Set TransformersSamuel Abramovcs.CV2026-08-23
#95TransHands: Repurposing Human Pose Encoders as Hand Pose EncodersMilo Piccioli, Gianluca Amprimo, Claudia Ferraris +1cs.CV2026-08-23
#96Fast and Compact 3D Gaussian Splatting with Polarized Opacity PriorZi-Ming Wang, Kai-Wen Duan, Kowei Huang +2cs.CV2026-08-23
#97Multimodal examination answer data with expert-designed Outcome-Based Education rubrics for criterion-level assessmentJahangir Alam SM, Md Khalid Syfullah, Saad Ahmed +4cs.CV2026-08-23
#98Pre-Decoding Acoustic Triage for Budgeted Vision-Language Captioning of Untrimmed Egocentric VideoMasoud Jalayer, Changyi Li, Yu Xiaocs.CV2026-08-23
#99When Do VLMs Help Arabic Manuscript OCR? A Cross-Dataset StudyMoshiur Farazi, Firoj Alam, Abderrahmane Maaradji +3cs.CV2026-08-23
#100DiD It in 87 Minutes: A Label-Free Softmax-to-Linear Adaptation of Vision Transformers for Object DetectionHuaiyuan Qin, Gabriel James Goenawan, Zihang Lin +2cs.CV2026-08-23
#101LiST: Local-Simplex Test-Time LoRA FusionYihua Shao, Jia Li, Siyu Chen +12cs.CV2026-08-23
#102The Blending Ratio Is Not Where the Performance Is: Diagnosing Prototype Blending for Few-Shot Adaptation of Vision-Language ModelsLiangzhi Li, Bowen Wang, Yiming Qian +3cs.CV2026-08-23
#103M$^3$ISR: A Multi-Modal Multi-View Benchmark for 3D/4D Gaussian Splatting and Feedforward CompressionXinhui Liu, Lei Liu, Zhenghao Chen +3cs.CV2026-08-23
#104HeatTok: Enhancing Remote Sensing Image Understanding via Thermodiffusion-based TokenizationYingying Yan, Jiaqi Tang, Wei Wei +6cs.CV2026-08-23
#105Learning Sample-wise Rank-aware Interpolation Weights for Composed Visual Data RetrievalBoseung Jeong, Taegyu Park, Donghyeon Kwon +2cs.CV2026-08-23
#106Cross-Generation Optimization of YOLOv26, YOLOv11, and YOLOv8 for Fine-Grained Small-Object Detection and Instance Segmentation in Complex OrchardsRanjan Sapkota, Manoj Karkeecs.CV2026-08-23
#107Fusing Perceptual Vision Experts with Multimodal Large Language Models for Explainable Plant Disease Diagnosis: From Benchmark Imagery to Real-World Robotic Field ValidationRanjan Sapkota, Konstantinos I. Roumeliotis, Pengyao Xie +3cs.CV2026-08-23
#108TRACE: Temporal Retrieval with Anchored and Convergent Evidence for Long-Horizon Video UnderstandingPengyiang Liu, Junbo Niu, Xiaoyang Hu +4cs.CV2026-08-23
#109VISTA: Test-Time Compositional Alignment for Visual Autoregressive GenerationHossein Shahabadi, Niki Sepasian, Mahdieh Soleymani Baghshahcs.CV2026-08-23
#110RS$^3$-Prune: Read-Sparse, Store-Sparse Token Pruning for Video Object SegmentationAvilasha Mandal, Sarvesh Shashikumarcs.CV2026-08-23
#111SymmAdapt: Symmetrical Flow Matching for Source-Free Domain Adaptation in Medical Image SegmentationTal Grossman, Noa Cahan, Hayit Greenspancs.CV2026-08-23
#112Understanding Temporal Semantic Stability in Open-Vocabulary UAV Perception through Metric 3D FusionSaurbh Singh Jamwalcs.CV2026-08-23
#113Improving Spatial-Temporal Reasoning in Video-Language Models with Structured Video PromptingSadegh Mohammadiancs.CV2026-08-23
#114A Lightweight Multimodal Vision-Language Framework for Early-Stage Anatomical Green Fruit Classification in Commercial OrchardsRanjan Sapkota, William Bu, Chen Chen +2cs.CV2026-08-23
#115Vision-Language Models for Occupational Physical Exposure Assessment: Estimating External Hand Forces in Manual Material Handling Tasks from RGB VideoMohammad Sadra Rajabi, Aanuoluwapo Ojelade, Sunwook Kim +1cs.CV2026-08-23
#116AI-based worker guidance in assembly and disassembly operations using multimodal ego/exo-centric data capture and structured task knowledgeVivek Chavan, Jörg Krügercs.CV2026-08-23
#117OmniCAD: A Large-Scale Benchmark for 3D Spatial Reasoning in Robotics AssembliesMingjia Wang, Taiting Lu, Ziwei Dong +25cs.CV2026-08-23
#118Multiple View Neural Regression of a Facial Shape ModelXiang Lics.CV2026-08-23
#119Model-Consistent Byzantine-Resilient Decentralized Federated Learning for Collaborative MissionsYue Li, Sudip Bhujel, Cameron Lira +2cs.DC2026-08-23
#120NeuroPrefetcher: Storage-Aware Sparse LLM Inference via Delta PrefetchingNobel Dhar, Md Romyull Islam, Xuechen Zhang +4cs.DC2026-08-23
#121CAIA in Practice: Field Evaluation of an AI-Assisted Support System for Text-Based Online CounsellingPhilipp Steigerwald, Nico Bienlein, Jennifer Burghardt +3cs.HC2026-08-23
#122All four leading LLMs talk more than they listen to personality-verified synthetic help-seekersPablo A. Fonseca, Raquel Rodríguez-Carvajal, Rafael A. Calvocs.HC2026-08-23
#123GRAFT: Graph-Distilled Generative Retrieval for Facet-Aware Scientific Literature ExplorationItalo Luis da Silva, Hanqi Yan, Yujing Wang +3cs.IR2026-08-23
#124Loss Landscape Features That Make Adam Stall: Definitions, Estimators, and the Preconditioned Hessian ViewRodion Podorozhnycs.LG2026-08-23
#125More accurate behavioral predictions with hybrid Bayesian-connectionist modelsBrenden M. Lake, Akshay K. Jagadish, Guangyuan Jiangcs.LG2026-08-23
#126Why Does Robustness Reduce Superposition?Adam Elimadics.LG2026-08-23
#127Unveiling the Depth-Performance Dilemma in Split-Federated Fine-tuning of LLMsHariharan Ramesh, Someshwaran Murugaiyan, Jyotikrishna Dasscs.LG2026-08-23
#128On the Capability Separation Between World-Model Policy Learning and Imitated World-Action ModelsYang Yucs.LG2026-08-23
#129Joint Causal Structure and Cluster Discovery Using Variational InferenceAvni Rajpal, Anubhav Kumar, Rishabh Karnad +2cs.LG2026-08-23
#130Counterfactual Evaluation of Temporal Observation ProtocolsXizhe Zhangcs.LG2026-08-23
#131FreKoo++: Learning Continuous Spectral Dynamics for Temporal Domain GeneralizationEn Yu, Xiaoyu Yang, Wei Duan +2cs.LG2026-08-23
#132Risk-Sensitive Reinforcement Learning with Smoothed Quantile ObjectivesMohammad Alipour-Vaezi, Huaiyang Zhong, Sajad Khodadadiancs.LG2026-08-23
#133When Test-Time Adaptation Helps, Harms, or Becomes Inactive: A Condition-Level Study on CIFAR-10-CSreeja Guha Majumdar, Aratrika Sahacs.LG2026-08-23
#134A Query-Time Framework for Transient 2D Pore-Scale Flow Prediction and Generative DesignYiming Wang, Jiale Zhu, Zhichen Ye +4cs.LG2026-08-23
#135Toward a First-Principles Update Geometry for the Language-Model HeadAditya Somasundaramcs.LG2026-08-23
#136DAW: Dynamics-Aware Weighting for Deep Learning Forecasts of Chaotic SystemsZhou Fang, Gianmarco Mengaldocs.LG2026-08-23
#137StocBench: A Benchmark for Generative Modeling of Stochastic DynamicsSebastian Pfister, Benjamin Holzschuh, Nils Thuereycs.LG2026-08-23
#138Does a Modern-Handwriting Warm-Up Help Historical Arabic OCR? A Reproducible, Compute-Matched Evaluation on Muharaf and KHATTSumaih Almarshad, Maram Alamri, Dona Aloraini +4cs.LG2026-08-23
#139Beyond Dense Adam States: Adaptive Log-Space Quantization for Memory-Efficient OptimizersYan Wangcs.LG2026-08-23
#140Gaussian process learning with flow map refinement for parameter estimation in dynamical systemsYue Hao, Dongwei Yecs.LG2026-08-23
#141SANE: State Anomaly Neutralization for Stable Extreme-Context Delta-Rule ModelsQingwen Lin, Boyan Xu, Xiao Liu +2cs.LG2026-08-23
#142Tracing the Unlabeled Storm: Cross-Variable Transfer in a Lagrangian Atmospheric JEPA FrameworkK M Anirudh, S Sandeep, Hariprasad Kodamanacs.LG2026-08-23
#143Self-Supervised Graph Representation Learning for In-The-Wild Wearable and Smartphone based Emotion RecognitionIoannis N. Ziogas, Leontios J. Hadjileontiadis, Ahsan H. Khandoker +1cs.LG2026-08-23
#144Dual-Scale State-Space Modeling with Speaker-Wise Dynamic CRF for Speech Emotion Recognition in ConversationGuan-Hua Wen, Kuan-Yu Chen, Hou-Chiang Tsengcs.LG2026-08-23
#145Geometric Structures on Graphs: a Holonomy-Based Discretization of CurvatureHao Li, Yuhan Peng, Junwen Dongcs.LG2026-08-23
#146KPI-Conditioned Generative Design of Automotive Hood Inner Panels: A Two-Stage Retrieval-Generation Pipeline with Surrogate-Based Performance EstimationSudeep Chavarecs.LG2026-08-23
#147MASH-Bench: Diagnosing Cross-Source Failure in Mass-Shooting Risk ClassificationNeha Sharma, Ritesh Sharmacs.LG2026-08-23
#148Functional compatibility as a determinant of persistent neural learningHossein Javidniacs.LG2026-08-23
#149The Variance of Thought: Policy Variance, Critical Forks, and Local Credit AssignmentYingru Lics.LG2026-08-23
#150Quantum-Inspired Hybrid Neural Networks for Neural Decoding: A Controlled Ablation Study of Learnable Quantum Sidecar IntegrationDiana Legziel Levy, Menachem Finkelstein, Peter Chin +2cs.LG2026-08-23
#151From Symmetry to Invariance: Learning Galois Equivalent Representations in Finite FieldsZheng Zhang, Na Zhangcs.LG2026-08-23
#152From Detrimental to Beneficial: Dynamic Influence-based Valuation and EditingAdrian Nyakairu, Hongfu Liucs.LG2026-08-23
#153Stress Testing Unlearning AlgorithmsNoam Diamant, Neta Glazer, Ethan Fetayacs.LG2026-08-23
#154BLADE: Bilevel Low-rank Augmented-Lagrangian Erasure for LLM UnlearningMd Toufikuzzaman, Ahmad Mousavi, Dongwon Leecs.LG2026-08-23
#155Clinical Graph-JEPA: Predictive Patient-State Knowledge Graphs for Cognitive Decision SupportKushagra Yadav, Nalin Prabhath, Amit Lamba +3cs.LG2026-08-23
#156GCA: Global Centroid Alignment in Federated LearningJong-Ik Park, Harry Jiang, Logan Blakely +3cs.LG2026-08-23
#157Tabular foundation models for non-tabular tasksGoran Nakerst, John Brennan, Wouter Beugeling +1cs.LG2026-08-23
#158Adversarial Agents on Topology Optimization: Understanding the Fragility and Robustness of Deep Learning-based and Physics-Based Design Models under Adversarial PerturbationHoang Anh Nguyen, Yuan Hong, Hongyi Xucs.LG2026-08-23
#159Mitigating Explanation Leakage in Financial Fraud Detection SystemsMuhammad Waleed Gul, Elaheh Homayounvalacs.LG2026-08-23
#160What AstroPT knows about galaxies, and what that can teach us about LLMsUniverseTBD, :, Kshitij Duraphe +3cs.LG2026-08-23
#161KMGen: A Skill-based Approach for Synthetic Individual Patient Data GenerationJalen Jiang, Chufan Gao, Ethan Rasmussen +2cs.LG2026-08-23
#162Learning Generalizable Behaviors for Terminal AgentsYihang Yao, Bo Pang, Xuan Phi Nguyen +3cs.LG2026-08-23
#163Q-Learning with Stable Infinite-Dimensional Linear Function ApproximationShengbo Wangcs.LG2026-08-23
#164Mol-JEPA: A multimodal Joint Embedding Predictive Architecture for MoleculesFlorian Rottach, Sebastian Schieferdecker, William Rudman +2cs.LG2026-08-23
#165GreenLeaf Law Embed Tiny: A Compact Embedding Model for Legal Domain RetrievalSurya Sakacs.LG2026-08-23
#166ReART: Reference-Guided Retrieval and Refinement for Emotion-Aware Art GenerationQianqian Tang, Jiayi Gao, Ting Lei +1cs.MM2026-08-23
#167Motion-Aware Reasoning from Speech to Mask Tracks: Runner-up Solution for the MeViS-Audio Track of the 8th LSVOS Challenge 2026Jinxing Zhou, Suiyi Zhao, Yanghao Zhou +1cs.MM2026-08-23
#168Advanced LLM-Enhanced Intent-Based 5G Network Management using Dynamic Semantic RoutesThomas Benton Townsend, Dimitrios Michael Maniascs.NI2026-08-23
#169Meta-Ctrl: Guaranteed Plan Generation by Decoupling Syntactic and Semantic ConstraintsGwen Yidou-Weng, Edward Sun, Tianyi Ma +5cs.RO2026-08-23
#170BehaviorWorldGen: Closing the Loop between Action Models and World Simulators via Controllable Behavior-Aware Structured World GenerationJiaqi Wang, Zhuo Zhang, Haining Guan +15cs.RO2026-08-23
#171The Potential of Haptic Foundation ModelsJianquan Wang, Haiwei Dong, Abdulmotaleb El Saddikcs.RO2026-08-23
#172TONAV: Task-Oriented Navigation and Action-Velocity Chunk Learning for Articulated Object Quadrupedal Mobile ManipulationHaoran Lin, Mingyu Yang, Pengfei Qi +6cs.RO2026-08-23
#173The Imitator Game: Benchmarking Robot Imitative Ability Beyond Action PredictionXunzhe Zhou, Yiyang Cai, Fengyi Wang +9cs.RO2026-08-23
#174Macro-Operator Generation and Predicate Selection for TAMP Operator LearningCan Emir Bora, Emre Ugurcs.RO2026-08-23
#175MotionDLO: Hybrid Event- and Frame-Based Tracking of Deformable Linear ObjectsAnnalena Hartmann, Priyamvada Ajithkumar, Patrick Bründl +1cs.RO2026-08-23
#176Robust Bimanual Vision-Language-Action Models via Embarrassingly Simple Modality MaskingDongzhou Cheng, Ziang Li, Yixiao Zhou +6cs.RO2026-08-23
#177EMPIRE: Explicit Manipulation Planning as a Learnable Intermediate Representation for Egocentric Hand-Motion ForecastingWen Wang, Ruibing Hou, Hong Chang +2cs.RO2026-08-23
#178Physical Agentic AI: An Architecture for Orchestrating a Robot Crew with LLMsXinyuan Liu, Eren Sadikoglu, Riana Chatterjee +1cs.RO2026-08-23
#179AudioNoisePrints: Model-free audio watermarking using spatial correlation in flow matching TTSTimothy Tin-Long, Jian Zhu, Aidan Pine +1cs.SD2026-08-23
#180MRMAD: A Multi-Round Multi-Audio Benchmark for Evaluating Acoustic Degradation Perception in Large Audio-Language ModelsYize Li, Ningyuan Yang, Sile Yin +6cs.SD2026-08-23
#181Multi-Task Learning for Non-Canonical Phoneme Recognition via Articulatory Feature DecompositionSophia Riaz, Haoze Zheng, Amos Roche +5cs.SD2026-08-23
#182Cross-Subject Generalization in Decoding Perceived Speech from Non-Invasive Brain RecordingsAoke Zhang, Bo Wang, Xihong Wu +2cs.SD2026-08-23
#183Learning from the Test: Self-Referential Differential Testing for Deep RL AgentsJunda He, Jieke Shi, Zhou Yang +2cs.SE2026-08-23
#184ToolRobustBench: Stage-Wise Perturbation Evaluation and Failure Diagnosis for Tool-Calling AgentsYiShan Zheng, Yuan Wu, Yi Changcs.SE2026-08-23
#185Do Not Copy/Paste: Soft Barriers for Copying in AI-Assisted ProgrammingIyiola E. Olatunji, Alberick Euraste Djire, Jacques Klein +1cs.SE2026-08-23
#186Evaluating Inference-Time Defenses Against Package Hallucination in LLM-Generated CodeAlberick Euraste Djire, Iyiola E. Olatunji, Melissa Tessa +3cs.SE2026-08-23
#187Mitigating Speaker Leakage in Cascaded Multi-talker ASR with Diarization-based Transcript CorrectionHermann Yepdjio Nkouanga, Minwei Luo, Maggie Wigness +1eess.AS2026-08-23
#188Modality Contribution Score - A Per-Patient Framework for Quantifying the Relative Diagnostic Contribution of Structural MRI and Amyloid PET in Alzheimer's DiseaseDawa Chyophel Lepcha, Aaliya Ali, Sophie A. Martin +3eess.IV2026-08-23
#189CiUNet: A Hybrid Swin-CNN UNet for Medical Image SegmentationBin Dong, Jinghong Cheneess.IV2026-08-23
#190GET: Generative Embedding Translation for Medical Image SegmentationMd Maklachur Rahman, Md Hasan Al Banna, Saraf Anjum +2eess.IV2026-08-23
#191Lightweight Multi-scale Hierarchical Anomaly Detection and Localization for Geospatial Big Data Applications at the EdgeThomas Benton Townsend, Joshua Bean, Benjamin K Tkach +2eess.SP2026-08-23
#192Sharp Barron Regularity Results for Coulombic Many-Electron Wave FunctionsPingbing Ming, Hao Yumath.AP2026-08-23
#193Two-level domain-decomposition AdaGrad method for scalable training of graph neural networksLaurynas Varnas, Julien Herrmann, Alexander Heinlein +2math.NA2026-08-23
#194The spatial anatomy of urban wildfire vulnerability: a spatially validated GeoAI framework reveals the roles of building density and vegetation moisture in structure loss during the 2025 Palisades FireParastoo Farajpoor, Mohammadreza Narimaniphysics.geo-ph2026-08-23
#195Interpretable statistical feature engineering for early disruption prediction in the short pulse ADITYA tokamakJyoti Agarwal, Kavit Patel, Bhaskar Chaudhury +3physics.plasm-ph2026-08-23
#196Arbitrage-Aware Multi-Step Forecasting of Implied Volatility Surfaces: Modelling Surface Trajectories Using Latent DiffusionDominik Manuel Buchegger, Lukas Gononq-fin.MF2026-08-23
#197Spending Scarce Confirmatory PET Measurements: Target-Aligned Validation in A4/LEARNEliuvish Han Cuistat.AP2026-08-23
#198Efficient Regression Models for Scan StatisticsGazi Abdur Rakib, Tristan Ashton, Ryan A. Loomis +4stat.ME2026-08-23
#199Token-Level Likelihood-Array Regression for Membership Inference and AI-Generated Text DetectionJiajun Sun, Zhanrui Caistat.ML2026-08-23
#200Recovering Weighted Tangent Geometry from a Single-Scale Score FieldZiqi Zhao, Qingjian Nistat.ML2026-08-23
#201Replicable Conformal PredictionMarios Papamichalis, Regina Ruane, Theofanis Papamichalisstat.ML2026-08-23
#202Sparse Additive Off-Policy Evaluation for Reinforcement Learning with Potentially Limited Number of TrajectoriesTuoyi Zhao, Chengchun Shi, Zhengling Qi +1stat.ML2026-08-23
#203Scale-invariant Optimal Sampling for Rare-events Data with Sparse ModelsJing Wang, HaiYing Wang, Qiang Zhang +1stat.ML2026-08-23

latest · arXiv announcement batches follow US Eastern weekdays