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

New Papers · 2026-09-12 194 submissions

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

#TitleAuthorsCatDate
1Identity Is More Than Recall: A Benchmark for Persistent Identity in Deployed AI AgentsZhenyu Zhao, Roy Zhaocs.AI2026-09-12
2Solar IntelligenceJyotsna Singhcs.AI2026-09-12
3Safety as a Constraint: Fine-Tuning a LLM Recommender to Explain ItselfJiashu He, Emma Yanyang Kong, JJ Tan +1cs.AI2026-09-12
#4FedV-KGQA in Practice: Design Lessons and an Interactive PrototypeMd Saikat Islam Khan Bappy, Oshani Seneviratnecs.AI2026-09-12
#5Cost Characterization of Vertically Partitioned Federated Knowledge GraphsMd Saikat Islam Khan Bappy, Oshani Seneviratnecs.AI2026-09-12
#6GeoSkill:Experience-Driven Hierarchical Skill Learning with Collaborative Revision forGeospatialAgentsHan Luo, Xian Xu, Yinhe Liu +1cs.AI2026-09-12
#7Enhancing Event Candidate Acquisition for Event LinkingZiyang Zhang, Yinan Liu, Boyi Xue +3cs.AI2026-09-12
#8Recoverability as a System Primitive for Long-Horizon AI AgentsZhihui Zhang, Wei Liucs.AI2026-09-12
#9Windowed A-K-MDPXiangwen Yang, Frankie Cho, Iadine Chadescs.AI2026-09-12
#10Drift-Constrained Optimization: Only Direction Matters in Fine-Tuning Instruct ModelsFei Yuan, Changjiang Gao, Yilei Tu +3cs.AI2026-09-12
#11Degraded but Not Entirely Ineffective: PE-Based Deformable Graph Neural NetworksJinhua Wu, Xinliang Zhangcs.AI2026-09-12
#12JaxAHT: A JAX-Based Library for Ad Hoc TeamworkCaroline Wang, Rolando Fernandez, Zelal Su Mustafaoglu +9cs.AI2026-09-12
#13MANAS-2: Constrained Reconstruction for EEG Foundation ModelsArvasu Kulkarni, Aditya Ray Mishra, Mahir Jain +4cs.AI2026-09-12
#14IBBench-Light: A Paired Evaluation of Task-Conditioned Responses to External DirectivesKainan Zhou, Gangzhen Qian, Zhaoyi Li +1cs.AI2026-09-12
#15Trustworthy Agentic AI: A Comprehensive Cybersecurity and Systems Survey on Threat Landscapes, Defense Architectures, and Open ChallengesSeyedakbar Mostafavics.AI2026-09-12
#16How Many Thoughts Can a Vector Hold? The Capacity of Reasoning by SuperpositionHongyu Gu, Chang Liu, Jingwen Fucs.AI2026-09-12
#17Positioning manuscripts in the scientific landscape with agentic AIJiawen Chen, Zichen Zhang, Bingxuan Li +7cs.AI2026-09-12
#18Homeostatic Continual LearningYue Jincs.AI2026-09-12
#19Surprising Effectiveness of Self-Demonstrations in Enhancing Schema-Ontology Mapping with LLMsSiddhesh Thombre, Manasi Patwardhan, Sunita Sarawagics.AI2026-09-12
#20Partition Scores Are Not System Scores: Deployment-Fidelity Gaps in Decomposed Algorithm SelectionJiachen Zhang, Yu Tang, Li Zhucs.AI2026-09-12
#21Do Not Restart: Residual Completion for Stateful Agent HandoffsRunzhi Deng, Yiming Zhong, Fang Zhao +1cs.AI2026-09-12
#22LLM-Enhanced Multi-Agent Reinforcement Learning for Unified Electric Vehicles-Charging Station-Grid Optimization in Public Charging SystemsYang Zhang, Lindong Xie, Chongyu Wang +3cs.AI2026-09-12
#23Bypass Observation: A Conceptual Design of a Non-Intrusive Layer-Wise Semantic Extraction ArchitectureHaibin Tong, Jiang Yucs.AI2026-09-12
#24ViperQ: Order Flow Pattern Recognition via Auction Market Theory for Reinforcement Learning TradingAsser Moustafa, Rares-Mihail Neagu, Jugal Kalitacs.AI2026-09-12
#25UniCAR-RL: Seeing Better before Thinking Deeper in Visual MathematicsYuzhe Li, Hao Yan, Hao Wang +6cs.AI2026-09-12
#26ClinAgent: A ReAct-Based Agent for Conversational Access to Clinical Trial InformationAntonino Vaccarella, Riccardo Cantini, Domenico Talia +4cs.AI2026-09-12
#27Map Users and Mapmakers: The Scope of Cognitive Attribution from Acquired RepresentationsYiling Wucs.AI2026-09-12
#28LoRA Fine-Tuned Models for Control Systems Course Q\&A: A Multidimensional Evaluation of Model Scale and Rank EffectsShaowen Lu, Chengxu Liu, Ping Zhou +1cs.AI2026-09-12
#29SAILOR: Solver-Assisted Interactive LLM-based Optimization RecoveryShaghayegh Sadeghi, Stephen L. Smith, David C. Del Rey Fern'andezcs.AI2026-09-12
#30Synthetic Data in Marketing Research: How to Evaluate and When to TrustOded Netzer, Rajan Sambandamcs.AI2026-09-12
#31Convergent Emergence of In-Context Learning Across ModalitiesNathan Breslow, Seungwook Han, Daniel Hyunsoo Lee +3cs.AI2026-09-12
#32Schizophrenia Detection from EEG Signals: A Transformer Framework with Spectrogram RepresentationAbtin Shafiei, Mohsen Hooshmand, Majid Ramezanics.AI2026-09-12
#33VeriDx: Earning the Right to Diagnose with Disease-Centric VerificationZhong Cao, Shuying Chencs.AI2026-09-12
#34Semantic Knowledge Technologies: what the Semantic Web lost sight of, and what it never hadAchille Zappacs.AI2026-09-12
#35NeuroFlex: Lossless Element-Level ANN-SNN Co-Execution for Efficient Sparse InferenceVarun Manjunath, Pranav Ramesh, Gopalakrishnan Srinivasancs.AR2026-09-12
#36Gap Entropy and Almost Instance-Wise Optimal Best-Arm IdentificationJiarui Yao, Jiaxi Zhao, Xiangxin Zhoucs.CC2026-09-12
#37The University of Melbourne WMT 2026 CreoleMT Submission: A Domain-Balanced Approach to Low-Resource Pacific Creole Machine TranslationRaphaël Merx, Nick Thieberger, Ekaterina Vylomovacs.CL2026-09-12
#38LayerRoute: Adaptive Layer-Skipping with LoRA-Preserved Quality for Efficient LLM InferencePrateek Kumar Sikdarcs.CL2026-09-12
#39Not all Negation Cues are Equal: Affixal Negations Yield Better Negation UnderstandingTian Tan, Eduardo Blancocs.CL2026-09-12
#40When Edit Localization Amplifies Relative Selection Bias: Gradient Geometry, Target Mismatch, and Importance WeightingShengwei Zhang, Haoda Dai, Yifei Li +1cs.CL2026-09-12
#41Scaling Hindi Quantum Natural Language Processing through Automatic Pregroup SupertaggingGautami Sanjay Naik, Krishna Bhatia, Mithun Paul Saint-Germain +1cs.CL2026-09-12
#42PolicyMem: Geometric Policy Memory for LLM GovernanceYuanchen Bei, Zhengzhang Chen, Yanjun Zhao +3cs.CL2026-09-12
#43ForeSight: Enhancing Risk Monitoring via Early Safety Signal DistillationHanling Wang, Chenlong Wei, Ling Xu +6cs.CL2026-09-12
#44Inside VLM Chart Reading: Tracing Value Reading from Vertical Bar Charts Across Space and DepthTianhao Niu, Qingfu Zhu, Wanxiang Checs.CL2026-09-12
#45HyperProve: Answer-Guided Hypergraph Expansion for Multi-Hop Question AnsweringAn Nguyen Phu, Dung Nguyen Quang, Luu Hieu An +3cs.CL2026-09-12
#46SyRHM: Symbolic-Language-Enhanced Reasoning with Associative Retrieval for Zero-shot Harmful Meme DetectionHanling Wang, Chenlong Wei, Yingjuan Li +4cs.CL2026-09-12
#47Understanding the Limits of Agentic ICD CodingChong Yock Eng, Yushi Cao, Yiming Chen +2cs.CL2026-09-12
#48DARE: Dialectical Agentic Reasoning for Structured Knowledge Fact CheckingYifei Li, Xiaohan Zheng, Wentao Qian +1cs.CL2026-09-12
#49When Consistency Does Not Mean Reliability: Evaluating Local LLM Judges Against Human RatingsAakash Kumar Tiwarics.CL2026-09-12
#50Sweet Talkers: How Query Formulation Shapes Sycophancy in Romantic Relationship AdviceHelena Choi, Edric Castel Hao, Karl Bautista +3cs.CL2026-09-12
#51Measuring the Cost of Variety Conflation in Multilingual MT Evaluation: Adding Mozambican Xichangana, Nyanja and Sena to FLORES+Felermino D. M. A. Ali, Delfina Lázaro Mateus, Manuel Valente Manguecs.CL2026-09-12
#52ShopEase: A Generative AI-Based Multi-Agent Framework for Intelligent Enterprise Customer Support Using Hybrid Retrieval-Augmented GenerationAakash Kumar Tiwari, Somesh Kumarcs.CL2026-09-12
#53Bangla Sentence Function Classification: Corpus Development, Model Benchmarking, and InterpretabilitySwapnil Kundu Argha, Abdullah Al Shafi, Rowzatul Zannat +4cs.CL2026-09-12
#54SHIFT-M3: Pre-fusion Alignment-based Consistency Screening for Multimodal ECG Record IntegrityMd Ashik Khan, Md Nahid Siddiquecs.CL2026-09-12
#55Phorecaster365: A Human-Supervised Reference Architecture for Hybrid Pharmaceutical Sales Forecasting and Planning Decision SupportHouman Kazemzadeh, Kamyar Naderics.CL2026-09-12
#56North Small Translate: Advanced Cost-Effective Translation (Cohere CAT+)Tom Kocmi, Alexandre Bérard, Phil Blunsom +20cs.CL2026-09-12
#57Inter-Rater Reliability of LLM and Rule-Based Annotation for Inferential Narrative Features: Three Studies on a Turkish CorpusLevent Bulutcs.CL2026-09-12
#58CRITICS - Critical Science Without Borders: Language Models to Promote Critical Thinking in Science EducationRodrigo Agerri, Itziar Aldabe, Elena Cabrio +10cs.CL2026-09-12
#59Thought without systematicity? Evaluating reasoning models on rule induction tasksSimon Schug, Brenden M. Lakecs.CL2026-09-12
#60Mizan: A National Benchmark for Evaluating Large Language Models on Iraqi Arabic and the Iraqi Civic ContextNawar S. Alseelawi, Mustafa S. Aljumailycs.CL2026-09-12
#61Unlocking the Unsolvable: Teacher-Guided Curriculum for Data-Efficient RLVRYukang Zhu, Zhen Hancs.CL2026-09-12
#62Measuring the Creativity of Frontier LLMs in Automated ResearchYiheng Zhao, Mengzhuo Chen, Chengming Hu +2cs.CL2026-09-12
#63GraMRAG: Orchestrating Multi-Agent Multi-Step Reasoning via Graph Memory with Reinforcement LearningZhongyu Wangcs.CL2026-09-12
#64One Size Does Not Fit All: Setting Inference Depth from the Questions a Deployment Actually AsksJerry Kaplancs.CL2026-09-12
#65When Tools Get in the Way: The Effect of Unnecessary Tool Availability on LLM AnsweringSaanvi Paturi, Arsen Kenzhebayev, Arham Sethi +3cs.CL2026-09-12
#66Towards Evolving Context Parameterization for Large Language ModelsXiaobing Shi, Zherui Li, Yiming Jiang +2cs.CL2026-09-12
#67A Multi-Stage Agentic Framework for Effective Counter-Narrative Generation and RefinementCarmel Kronfeld, Sharva Gogawale, Tetsuro Kobayashi +1cs.CL2026-09-12
#68EI-DDLGN: Efficient Encrypted Inference with Deep Differentiable Logic Gate Networks under TFHEMahmoud Y. M. Yassin, Mahmoud AbdelHafeez Sayed, Mostafa Tahacs.CR2026-09-12
#69Exploring Automated Vulnerability Identification in JavaScript Code Using Large Language ModelsManit Kaushik, Ishir Bhardwaj, Pranav Gupta +2cs.CR2026-09-12
#70When Malicious Instructions Persist: Persistent Memory Poisoning Attack on Harness-Based AgentsShuhuai Huang, Jingfeng Zhang, Hong Jiacs.CR2026-09-12
#71Confuse the Model, Control the Flow: Understanding and Mitigating Privacy Leakage from LLM Agents with Information Flow ControlMinsun Shim, Ramisha Raida Karim, Ruthwik Jakkula +4cs.CR2026-09-12
#72AGENTQ: Quantization-Conditioned Backdoor Attacks on LLM AgentsXiaoqun Liu, Qiben Yancs.CR2026-09-12
#73From Advertised Improvements to Measured Capabilities: Evaluating ChatGPT Images 2.5 on Forgery TasksAnkit Raj, Yuxin Zhang, Kidus Zewde +7cs.CV2026-09-12
#74YOLO12-MambaScan: An Efficient Object Detector with High-Frequency Enhancement and State-Space ModelingHao Wangcs.CV2026-09-12
#75Multimodal Foundation Models Adaptation based on Domain-Aware Relaxed Orthogonal Subspace for Remote SensingHan Luo, Ruoyu Yang, Yinhe Liu +1cs.CV2026-09-12
#76MARC: Morphology-Aware Regression of Consensus for Cell Segmentation in Subcellular Spatial TranscriptomicsXinyu Shu, Andrew Zhang, Jean Yang +1cs.CV2026-09-12
#77MomentBA: Second-order Spatial Moments for Anisotropic Correspondence Uncertainty in Differentiable Bundle AdjustmentYuqing Wang, Xiaoji Niu, Yan Wang +3cs.CV2026-09-12
#78Rank-Consistent Set Reasoning for Co-Salient Object DetectionYuan Xiang, Matteo Rossi, Yingzhou Chencs.CV2026-09-12
#79FFVO: A Feedforward Pose Decoder for Long-Horizon Visual OdometryMeng-Li Shih, Shih-Yang Su, Yuliang Zou +7cs.CV2026-09-12
#80Hyper-LLaVA: Hyperbolic Uncertainty-aware Modality-Balanced Routing for Multimodal Continual Instruction TuningKunlun Xu, Yanqin Zhang, Wenwen Qiang +1cs.CV2026-09-12
#81Development of Low-Cost Real-Time Driver Drowsiness Detection System using Eye Centre Tracking and Dynamic ThresholdingFuzail Khan, Sandeep Sharma, M. R. Arulalancs.CV2026-09-12
#82GEAR: From Dynamic Encoding to Dynamic Activation in Social Trajectory PredictionJiaheng Chen, Jiaxing Li, Leixia Wang +2cs.CV2026-09-12
#83Restore What Matters: Lessons from Joint Restoration and RecognitionLanqing Guo, Xijun Wang, Minchul Kim +7cs.CV2026-09-12
#84StepPrune: Adaptive Sequential Visual Token Selection across Multimodal Large Language ModelsHansen Zhang, Landi He, Mingde Yao +1cs.CV2026-09-12
#85Realtime-Venus: A full-duplex interaction system with asynchronous delegationRuixiang Zhao, Hualei Wang, Renhe Sun +24cs.CV2026-09-12
#86Beyond OCR Accuracy: Text-Centric VQA Under Image Degradation with Modular and End-to-EndRitali Vatsi, Rachapudi Jagadeesh, Shruti Singh Baghel +3cs.CV2026-09-12
#87Semantic Privacy Protection with Utility Preservation for 3D Point CloudsJinchang zhang, Jiakai Lin, David Crandall +1cs.CV2026-09-12
#88DiVA: Enabling Interactive Digital Life Simulation via Video ModelsCheng Chen, Hao Ouyang, Qiuyu Wang +11cs.CV2026-09-12
#89TotalSynth: Robust Whole-Body Synthetic CT from MRI and CBCTValentin Boussot, Cedric Hemon, Anais Barateau +3cs.CV2026-09-12
#90Event-Level Emotion Recognition in the Wild Using Deep Facial Expression AnalysisAleksandr Semerikov, Pakizar Shamoics.CV2026-09-12
#91Physically Typed and Geometry-Aware Representations for Earth Foundation ModelsRajiv Ranjancs.CV2026-09-12
#92SkyAnchor: Updating Metric-scale Aerial 3D Gaussian Scenes from Unposed Ground-View SequencesZhuoxiao Li, Xinyi Liu, Taoyu Wu +8cs.CV2026-09-12
#93BLInD: Learning Driver Intent as a Distribution over Future Ego TrajectoriesFlavian Pegado, Ronit Hire, Shreyas Rajesh +1cs.CV2026-09-12
#94SGWIB:Sliced Gromov-Wasserstein Information Bottleneck for Video Highlight DetectionHanjuan Huang, Yung-Chieh Yeh, Hsing-Kuo Paocs.CV2026-09-12
#95Zero-Shot Cross-Material Ptychographic Phase Reconstruction Using Deep LearningWen-Chun Lin, Yu-Chee Tseng, Jen-Jee Chen +1cs.CV2026-09-12
#96Mind2Cloud: EEG-to-Point Cloud Generation with Two-Granularity Diffusion DecodingYongyi Lu, Xiongfeng Huang, Zhijing Yangcs.CV2026-09-12
#97CirrGuide: A Deep Cascaded Framework for Liver Cirrhosis Segmentation and Severity Classification from T2-Weighted MRIMuntaqim Ahmed Raju, Ruizhe Macs.CV2026-09-12
#98Quantum-Gated LiteSSD: A Parameter-Efficient Lightweight Hybrid Quantum-Classical Framework for Forward-Looking Sonar Object DetectionNiloy Kumar Mondal, Poulomi Sarker Pujacs.CV2026-09-12
#99LPA-CWM: A Learned Physical Adjudicator for Motion Reasoning with Counterfactual World ModelsKunwei Wu, Xiang Liu, Guocai Yao +5cs.CV2026-09-12
#100Adapting Open-Weight MLLMs to Generate Point Prompts for Electron Microscopy SegmentationSamia Mohinta, Albert Cardonacs.CV2026-09-12
#101Bridging the Synthetic-to-Real Gap for Few-Shot Cryo-ET ClassificationSiddhant Bharadwaj, Ashish Vashist, Rashi Singh +5cs.CV2026-09-12
#102RA-CoA: Training-free Fashion Image Captioning via Retrieval-Augmented Chain-of-AttributesAbhirama Subramanyam Penamakuri, Shreya Shukla, Anand Mishracs.CV2026-09-12
#103A Voxel-Spacing-Aware Extension of PyRadiomics for Anisotropic Texture AnalysisDavid Corral Fontecha, Juan Miranda Bautista, Pablo Menendez Fernández-Miranda +3cs.CV2026-09-12
#104Accelerating HKTex without Mesh Eigensystems: Local Unfolding and Randomized Thermal FeaturesZhewen He, Junyi Hu, Yi Fangcs.CV2026-09-12
#105Parameter-Efficient Fine-Tuning of Foundation Models for Liver Tumor Segmentation in CTRamtin Mojtahedi, Mohammad Hamghalam, Jacob J. Peoples +2cs.CV2026-09-12
#106Talking to Me or Someone Else? Rethinking Talk-to-Me Detection in Egocentric VideosFeiyu Du, Xi He, Jia Li +2cs.CV2026-09-12
#107SignMimic: Robust High-Quality Sign Language Motion Generation via Human-Shape-Oblivious Pose Transfer GuidanceZhewen He, Junyi Yu, Haomian Huang +2cs.CV2026-09-12
#1083D Gait-Based Autism Classification Using Attention-Enhanced Deep Learning with Cross-Fold Statistical Stability AnalysisMd Nadim Mahamood, Md Arif Shahriar, Md Parvej Sikder +4cs.CV2026-09-12
#109Bi-Level Routing and Sparse Spatial Attention based Multi-View BEV 3D Object Detection for Autonomous DrivingJing Zhang, Jiaqi Liu, Zibo Wangcs.CV2026-09-12
#110MorphoStyle: Motion Style Transfer with Morphology ControlXin Feng, Eleonora D'Arnese, Mohan Sridharancs.CV2026-09-12
#111Real-World Deployment and Performance Characterisation of Fog-Based Deep Learning for Cold-Chain Temperature Prediction over LoRaWANJeremiah Taguta, Jean Frederic Isingizwe Nturambirwe, Clement Nthambazale Nyirendacs.DC2026-09-12
#112Prefix Sharing Is a Sorting ProblemRong Hecs.DS2026-09-12
#113FaithfulBench: Does AI Counsel Uphold or Undermine the User's Professed Faith?M Waleed Kadous, Benjamin Olsen, Walter Scheirer +3cs.HC2026-09-12
#114Oops, Not Now: PEARL, a RAG-Based Support Agent for Gameplay and What Players Want from AI HelpJiahong Li, Sai Siddartha Maram, Atieh Kashani +6cs.HC2026-09-12
#115Odds-Shift Slippage in One-vs-Rest Rankers: Diagnosing and Repairing Reweighting-Induced Top-K ErrorsAkifumi Gotocs.IR2026-09-12
#116TF-IDF and BM25 Are Exact KL DivergencesIvan Silajevcs.IR2026-09-12
#117An Efficient and Modular Framework for Targeted Harm Mitigation in LLMSRoberto Campbell, Momin Abbass, Muneeza Azmat +5cs.LG2026-09-12
#118FlowTSFM: Turning Encoder Depth into Quantile TransportBahaeddine Abdessalem, Shifeng Xie, Zehao Xiao +6cs.LG2026-09-12
#119When Compliance Data Masquerades as Evaluation: Measurement Validity for Deployed AI SystemsHung-Yu Lin, Xingran Huang, Qiming Guo +1cs.LG2026-09-12
#120Curvature-Independent Regret Bounds for Distributed Online Optimization on Hadamard ManifoldsZhanyuan Cai, Emre Sahinoglu, Shahin Shahrampourcs.LG2026-09-12
#121Online Bayesian Node Classification on Inductive Graphs under Distribution ShiftJinwen Xu, Gonzalo Mateos Buckstein, Qin Lucs.LG2026-09-12
#122Leakage-Safe and Scheduler-Aware Machine Learning for Grid Job Runtime PredictionAshfaq Ali Shafin, Khandaker Mamun Ahmedcs.LG2026-09-12
#123Certifying Model Upgrades with Slice-Wise Non-Regression and Incumbent FallbackShengwei Zhang, Tao Wu, Fei Qiancs.LG2026-09-12
#124A Variational Optimal Transport Operator on Incompressible FlowJinjin He, Shenyifan Lu, Sinan Wang +3cs.LG2026-09-12
#125JumpStart Your Policy Learning with Lessons from 160,000 Training RunsNabil Omi, Eric Bae, Chung Yik Edward Yeung +2cs.LG2026-09-12
#126HarnessBandit: Joint Learnability-Transferability Scheduling for Multi-Harness Agentic Reinforcement LearningHongliang Wei, Xiaobing Tu, Yinggui Wang +6cs.LG2026-09-12
#127Training Specialist Models without Reasoning Trajectories for Domain Expert DistillationYilei Tu, Zihao Li, Shaoxiong Ji +2cs.LG2026-09-12
#128Does Reasoning Improve Psychological Depth in Large Language Models? It Depends on Who's JudgingRuichen Zheng, Yihe Wang, Fabrice Y Harel-Canada +4cs.LG2026-09-12
#129PPDL: A Real-world Industrial User Retention Ratio Forecasting Framework Integrating Physical Priors with Deep LearningZibo Zhao, Zhengxiong Guan, Chaoli Zhang +4cs.LG2026-09-12
#130Benchmarking Optimizers to Solve Inverse Problems with Differentiable Physics SimulatorsXiang Chen, Huanhuan Xiacs.LG2026-09-12
#131Graph Neural Networks for Influence Maximization in Social Networks: An Unsupervised Minimum Dominating Set ApproachErfan Ahmadi, Mina Shirazi, Behnam Bahrakcs.LG2026-09-12
#132Accuracy Is Not Service: A Decision-Aware Benchmark for Intermittent-Demand ForecastingJoo Ern Chin, Shih-Fen Cheng, Aldy Gunawancs.LG2026-09-12
#133Pre-training with Graph TransformersJiaming Wang, Thomas Laurent, Xavier Bressoncs.LG2026-09-12
#134Affinity-Aware Sharding for Delayed Tensor ParallelismEloi de Reynalcs.LG2026-09-12
#135ReH-FUSE: Reliability-Aware Hierarchical Fusion of Experts for Multimodal Emotion Recognition in ConversationGuan-Hua Wen, Hou-Chiang Tseng, Kuan-Yu Chencs.LG2026-09-12
#136An Uncertainty-Aware Hybrid Mathematical-Machine-Learning Model for Smart Irrigation Decision SupportAndrea Scariolocs.LG2026-09-12
#137The Filter Metric is Safety-Critical: Phantom Advantages in Group-Relative RL under Shaped RewardsJuntao Yucs.LG2026-09-12
#138A Multi-Resolution Multi-Domain Pre-Training Framework for Universal Traffic ForecastingZhouyang Liu, Jindong Han, Hao Wang +4cs.LG2026-09-12
#139Lie to me: Detecting Managerial Evasiveness in Earnings Calls via Conversational Audio EncodersHuizhong Chen, Huan Zhangcs.LG2026-09-12
#140Machine Learning under Imperfect Data: Challenges and MethodsMasoumeh Zareapoorcs.LG2026-09-12
#141Learning Through Energy Refinement and Manifold Projection: A Cooperative EBM-AE FrameworkRyad Zemourics.LG2026-09-12
#142Machine Learning in Fish FarmingFearghal O'Donncha, Nikos Papandroulakis, Jennie Korus +10cs.LG2026-09-12
#143Finite-Time Node Separation in Recurrent Graph Neural Networks with Persistent Gaussian PerturbationsMostafa Haghir Chehreghanics.LG2026-09-12
#144Minibatch persistency, eight years later: what batch reuse costs in steps and joules, and what it saves in dataMatteo Fischettics.LG2026-09-12
#145Exploring napping paradigm for Recurrent Spiking Neural NetworksAndreas Massey, Stefano Nichele, Aliaksandr Hubincs.LG2026-09-12
#146Optimal Transport for Efficient, Unsupervised Anomaly Detection on Industrial DataAbigail Langbridge, Fearghal O'Donncha, James T Rayfield +1cs.LG2026-09-12
#147Hardware-Aware Learned Representation Compression for Distributed In-Sensor VisionChengwei Zhou, Abu Masum, Xuming Chen +7cs.LG2026-09-12
#148Linear Ensemble Sampling with Smaller EnsemblesTaehyun Hwang, Min-hwan Ohcs.LG2026-09-12
#149Tabby: An Open Pretraining Recipe for Time Series Foundation ModelsShifeng Xie, Bahaeddine Abdessalem, Zehao Xiao +9cs.LG2026-09-12
#150Data-Efficient Agentic Graph Domain Adaptation via Reliability-Aware Prototype LearningYingxu Wang, Kunyu Zhang, Siyang Gaocs.LG2026-09-12
#151Stabilizing Performative Feedback Loops with Minimal Model DeploymentsGabriele Farina, Juan Carlos Perdomocs.LG2026-09-12
#152Multi-Modal Tumor Survival Prediction via Graph-Guided Mixture of ExpertsH Mathavan, H Liucs.LG2026-09-12
#153To do($x$) or not to do($x$): Medical Image Counterfactuals for Dataset AugmentationYasin Ibrahim, Robin J. Evans, Konstantinos Kamnitsascs.LG2026-09-12
#154LIMBO: Lifelong Inference-Time Memory and Budget Optimization for LLM AgentsSiddharth Sharma, Nilesh Prasad Pandey, Onat Gungor +1cs.LG2026-09-12
#155T-SMART: Mechanism-Level Attribution for Tool-Augmented Time-Series Question AnsweringIvan Delgado, Himansi Gupta, Bishal Khatri +4cs.LG2026-09-12
#156Signatures of Steerability in Activation Space of Language ModelsPrajjwal Bhattarai, Tuka Alhanaics.LG2026-09-12
#157CyFM: Cylindrical Optimal Transport for Few-Step Complex-Valued Flow MatchingMarcel Musiałek, Iga Wolanin, Damian Ryczko +2cs.LG2026-09-12
#158Inherited Heads: Audio language models track speakers with their text backbone's attention, and an attention-mass ranking retrieves a different setBojro Dascs.LG2026-09-12
#159A Machine Learning Framework for Fault Detection, Isolation, and Severity Prediction of Autonomous VTOL AircraftRipon C. Sarker, Pedram H. Dabaghian, Raman Goyal +1cs.LG2026-09-12
#160ZAPS: Zero-Cost Active Proxy Search for Neural Architecture SearchHassan Touayouch, Rabie Najem, Mohammed Benjellouncs.LG2026-09-12
#161Entropy-Punctured Bloom Filters for Memory-Efficient Machine LearningJohn Cartmell, Mihaela Cardei, Ionut Cardeics.LG2026-09-12
#162Data-free On-policy DistillationGengsheng Li, Mao Zheng, Mingyang Song +7cs.LG2026-09-12
#163Neuron Activation-based Computation of Logical Explanations for Deep Neural NetworksTomáš Kolárik, Faezeh Labbaf, Fabrizio Leopardi +3cs.LO2026-09-12
#164Trustworthy, Explainable, and Sustainable Decentralized Intelligence for 6G NetworksGiovanni Perin, Michele Rossi, Enrique Tomás Martínez Beltrán +13cs.NI2026-09-12
#165HQARRF: Hierarchical Q-learning and Force-aware Routing for Multi-Charger Scheduling in Wireless Rechargeable Sensor NetworksLiang-Ching Tao, Pi-Chung Wangcs.NI2026-09-12
#166Compositional Shift Algebra: Extrapolating Mixed Robot Shifts Without Mixed FinetuningJinting Hang, Zhenhui Caics.RO2026-09-12
#167When Do Learned Priors Help Visual Inertial Estimation? A Controlled Study of Prior Integration, Calibration, Initialization, and Backend ConsistencyJinchang Zhang, Guoyu Lucs.RO2026-09-12
#168LePlanner: An Iterative Amortized Controller For World ModelsSaksham Bansal, Om Naphade, Chayan Aggarwal +1cs.RO2026-09-12
#169ReWeight: Leveraging Human Data for VLA Post-Training via Demonstration Retrieval and Sample WeightingChenwei Wang, Dianye Huang, Match W. L. Ko +2cs.RO2026-09-12
#170Rethinking the Implications of Human Feedback for Preference Learning in Human-Robot CollaborationQiping Zhang, Kate Candon, Debasmita Ghose +1cs.RO2026-09-12
#171What Makes an Efficient VLA? Navigating Action-Head Design, Scaling, and LatencyLuoyang Sun, Guoyang Xia, Fengfa Li +9cs.RO2026-09-12
#172When Faster VLA Deployment Changes Closed-Loop Behavior: Task Success-Latency Analysis of SmolVLA Across PyTorch and ONNX VariantsRafiqul Islamcs.RO2026-09-12
#173UniqueShip: Mitigating Data Leakage in Acoustic Ship Classification Benchmark DatasetsConnor Hashemi, Trevor Stout, Anthony Hoogs +1cs.SD2026-09-12
#174CRAF: Cross-View Residual-Aware Fusion for Deepfake Speech DetectionMinh-Xuan Phan, Khalid Zaman, Candy Olivia Mawalim +1cs.SD2026-09-12
#175DiTAR+: Dual Optimization for Robust Autoregressive Diffusion Speech SynthesisZiyu Zhang, Tianlun Zuo, Hanzhao Li +2cs.SD2026-09-12
#176A New Transformer-Based Approach for Audio-Based Kinship Verification and a New Uncontrolled Mandarin Kinship Speech DatasetQiyang Sun, Langqing Zhang, Yupei Li +1cs.SD2026-09-12
#177TyPatch: Transforming Patches into Typestate Rules for Kernel Bug DetectionRuoyu Wang, Tuo Li, Jia Lics.SE2026-09-12
#178Introspective Uncertainty Estimation for LLM-Based Code GenerationThomas Klassertcs.SE2026-09-12
#179Not All Duplicates Are Coordination: Generic vs. Non-Generic Duplicate Campaigns in Information OperationsAshfaq Ali Shafin, Khandaker Mamun Ahmedcs.SI2026-09-12
#180From Network Inequality to Network Fairness: A Perspective on Responsible Decision-MakingLisette Espín-Noboa, Tina Eliassi-Rad, Pak-Hang Wong +5cs.SI2026-09-12
#181SONAR: A Structure-Consistent Neural Operator for Null-Space-Aware Sparse View CT ReconstructionSong Ni, Haijun Yu, Haodong Li +4eess.IV2026-09-12
#182Deformable 2D Gaussian Splatting for Efficient 4K Video CompressionChenhao Zhang, Fengqing Zhueess.IV2026-09-12
#183Diffusion-Based Multiple-Shooting Indirect Optimal Control for Fuel-Optimal Spacecraft Trajectory GenerationSaeid Tafazzol, Ehsan Taheri, Ryne Beesoneess.SY2026-09-12
#184Real-Time Synthesis of Robust Controlled Invariant Sets for Monotone SystemsYasin Sonmez, Mahmoud Khaled, Majid Zamani +1eess.SY2026-09-12
#185On the Equivalence of Stochastic Control and Path Space Formulations for Schrödinger Bridges over Compact Connected Lie GroupsHamza Mahmood, Georgiy A. Bondar, Abhishek Halder +1math.OC2026-09-12
#186Generation of Custom Solvers in Rust for Convex OptimizationHao Zhu, Joschka Boedeckermath.OC2026-09-12
#187CyclOT: Learning Quadratic Optimal Transport Maps via Synchronized Forward-Backward InterpolantsShizhou Xu, Jiachen Liu, Shih-Hsin Wang +4math.OC2026-09-12
#188Equilibrium bias and convergence in augmented primal--dual dynamics with sampled constraintsKang Liu, Mengxiao Chen, Siqi Xiong +1math.OC2026-09-12
#189Riemannian ascent--descent for nonconvex nonconcave minimax landscapes: convergence to basin saddle points and applications to distributionally robust optimizationRishabh Dixit, Pranav Upadrashta, Alex Cloningermath.OC2026-09-12
#190URCHIN: A Horizontal Spiking Language Model for Data-Constrained PretrainingPo-Han Chiangq-bio.NC2026-09-12
#191Conditional Quantum Flow Matching for Data-Scarce Physiological Signal AugmentationChi-Sheng Chen, Samuel Yen-Chi Chenquant-ph2026-09-12
#192Resolution-Independent Analysis of Encoder--Decoder Operator Learning via Limiting KernelsLei Shi, Jia-Qi Yang, Ding-Xuan Zhoustat.ML2026-09-12
#193Just add noise: Debiasing tree-based variable importance in mixed dataJiahe Li, Omar Melikechistat.ML2026-09-12
#194Exact Finite Attention Responses From RoPE DerivativesJulie Huang, Maggie Chlon, Gregory Gutin +1stat.ML2026-09-12

latest · trends · arXiv announcement batches follow US Eastern weekdays