mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 25 Feb 2026

407 papers

  1. LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature ReviewLLM agents and tool use → Software engineering coding agents
  2. OOWM: Structuring Embodied Reasoning and Planning via Object-Oriented Programmatic World ModelingWorld models → World models for language agents +1
  3. Help Without Being Asked: A Deployed Proactive Agent System for On-Call Support with Continuous Self-ImprovementLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  4. FinReasoning: A Hierarchical Benchmark for Reliable Financial Research ReportingLLM reasoning → Reasoning for agents, planning and code
  5. GeoChallenge: A Multi-Answer Multiple-Choice Benchmark for Geometric Reasoning with DiagramsLLM reasoning → Spatial and embodied reasoning
  6. Enhancing Legal LLMs through Metadata-Enriched RAG Pipelines and Direct Preference OptimizationRetrieval-augmented generation → Legal and financial RAG +1
  7. DuCCAE: A Hybrid Engine for Immersive Conversation via Collaboration, Augmentation, and EvolutionLLM agents and tool use → General LLM agent frameworks and benchmarks
  8. An Agentic System for Schema Aware NL2SQL GenerationLLM agents and tool use → Web, search, and research agents
  9. Multi-hop Reasoning and Retrieval in Embedding Space: Leveraging Large Language Models with KnowledgeLLM reasoning → Knowledge- and tool-augmented reasoning
  10. Beyond Attention: True Adaptive World Models via Spherical Kernel OperatorWorld models → Latent predictive world models
  11. Explain in Your Own Words: Improving Reasoning via Token-Selective Dual Knowledge DistillationLLM reasoning → Prompting and chain-of-thought reasoning +1
  12. How Transformers Reject Wrong Answers: Rotational Dynamics of Factual Constraint ProcessingMechanistic interpretability → Probing deception, bias and beliefs
  13. Your Code Agent Can Grow Alongside You with Structured MemoryLLM agents and tool use → Software engineering coding agents
  14. Speculative Decoding Scaling Laws (SDSL): Throughput Optimization Made SimpleEfficient LLM inference and serving → Speculative decoding
  15. Adaptive Multi-Objective Tiered Storage Configuration for KV Cache in LLM ServiceEfficient LLM inference and serving → KV cache optimization
  16. HEARTS: Benchmarking LLM Reasoning on Health Time SeriesLLM reasoning → Clinical and biomedical applications
  17. HELIOS: Harmonizing Early Fusion, Late Fusion, and LLM Reasoning for Multi-Granular Table-Text RetrievalLLM reasoning → Knowledge- and tool-augmented reasoning
  18. FlowPortrait: Reinforcement Learning for Audio-Driven Portrait Video GenerationDeep reinforcement learning methods → RL training of language and agent models
  19. EfficientPosterGen: Semantic-aware Efficient Poster Generation via Token Compression and Accurate Violation DetectionEfficient LLM inference and serving → Visual token pruning in multimodal models
  20. Dr. Seg: Revisiting GRPO Training for Visual Large Language Models through Perception-Oriented DesignLLM reasoning → Multimodal reasoning
  21. Attention to Neural Plagiarism: Diffusion Models Can Plagiarize Your Copyrighted Images!Diffusion models → Robustness, privacy and adversarial aspects +1
  22. Physics-Consistent Diffusion for Efficient Fluid Super-Resolution via Multiscale Residual CorrectionDiffusion models → Flow matching, time series and science
  23. Leveraging large multimodal models for audio-video deepfake detection: a pilot studyMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  24. Flow Matching is Adaptive to Manifold StructuresDiffusion models → Flow matching, time series and science
  25. VeRO: A Harness for Agents to Optimize AgentsLLM agents and tool use → Software engineering coding agents
  26. When to Act, Ask, or Learn: Uncertainty-Aware Policy SteeringDiffusion models → Diffusion and flow policies for robotics
  27. Beyond Dominant Patches: Spatial Credit Redistribution For Grounded Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  28. ConstraintBench: Benchmarking LLM Constraint Reasoning on Direct OptimizationLLM reasoning → Test-time compute and efficient thinking
  29. MammoWise: Multi-Model Local RAG Pipeline for Mammography Report GenerationRetrieval-augmented generation → Medical and biomedical RAG
  30. Exploring Multimodal LMMs for Online Episodic Memory Question Answering on the EdgeMultimodal LLMs / vision-language models → Video understanding with MLLMs
  31. CWM: Contrastive World Models for Action Feasibility Learning in Embodied Agent PipelinesWorld models → Embodied and robot world models +1
  32. Silent Egress: When Implicit Prompt Injection Makes LLM Agents Leak Without a TraceLLM agents and tool use → Agent threats, guardrails and governance +1
  33. A Framework for Assessing AI Agent Decisions and Outcomes in AutoML PipelinesLLM agents and tool use → General LLM agent frameworks and benchmarks
  34. Calibrated Test-Time Guidance for Bayesian InferenceDiffusion models → Inverse problems and image restoration
  35. Adversarial Hubness Detector: Detecting Hubness Poisoning in Retrieval-Augmented Generation SystemsRetrieval-augmented generation → Privacy and security of RAG
  36. SimpleOCR: Rendering Visualized Questions to Teach MLLMs to ReadMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  37. ArchAgent: Agentic AI-driven Computer Architecture DiscoveryLLM agents and tool use → Software engineering coding agents
  38. Absorbing Discrete Diffusion for Speech EnhancementDiffusion models → Audio, speech and music
  39. Epistemic Filtering and Collective Hallucination: A Jury Theorem for Confidence-Calibrated AgentsLLM agents and tool use → Social simulation and multi-agent debate
  40. Towards Autonomous Memory AgentsLLM agents and tool use → Agent memory systems
  41. Contextual Memory Virtualisation: DAG-Based State Management and Structurally Lossless Trimming for LLM AgentsLLM reasoning → Reasoning for agents, planning and code +1
  42. E3VA: Enhancing Emotional Expressiveness in Virtual Conversational AgentsLLM agents and tool use → Social simulation and multi-agent debate
  43. Decoder-based Sense Knowledge DistillationKnowledge distillation → Knowledge distillation for LLMs
  44. Structure and Redundancy in Large Language Models: A Spectral Study via Random Matrix TheoryKnowledge distillation → General knowledge distillation methods
  45. Training Agents to Self-Report MisbehaviorLLM agents and tool use → Agent threats, guardrails and governance
  46. Agent Behavioral Contracts: Formal Specification and Runtime Enforcement for Reliable Autonomous AI AgentsLLM agents and tool use → Agent threats, guardrails and governance
  47. Learning Rewards, Not Labels: Adversarial Inverse Reinforcement Learning for Machinery Fault DetectionOffline RL and imitation learning from data → Inverse reinforcement learning +1
  48. UpSkill: Mutual Information Skill Learning for Structured Response Diversity in LLMsLLM reasoning → Reinforcement learning for reasoning
  49. BrepCoder: A Unified Multimodal Large Language Model for Multi-task B-rep ReasoningLLM reasoning → Spatial and embodied reasoning +1
  50. FIRE: A Comprehensive Benchmark for Financial Intelligence and Reasoning EvaluationLLM reasoning → Reasoning for agents, planning and code
  51. Entropy-Controlled Flow MatchingDiffusion models → Flow matching, time series and science
  52. Code World Models for Parameter Control in Evolutionary AlgorithmsWorld models → World models for language agents
  53. Poisoned AcousticsLLM safety and security → Backdoor and data poisoning attacks
  54. Solaris: Building a Multiplayer Video World Model in MinecraftWorld models → Video-generation world models and simulators
  55. Improving Parametric Knowledge Access in Reasoning Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  56. GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RLLLM agents and tool use → GUI and mobile agents
  57. Provable Last-Iterate Convergence for Multi-Objective Safe LLM Alignment via Optimistic Primal-DualLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  58. NoLan: Mitigating Object Hallucinations in Large Vision-Language Models via Dynamic Suppression of Language PriorsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  59. MedTri: A Platform for Structured Medical Report Normalization to Enhance Vision-Language PretrainingMultimodal LLMs / vision-language models → Medical vision-language models
  60. WeaveTime: Stream from Earlier Frames into Emergent Memory in VideoLLMsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  61. SWE-Prot'eg'e: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering AgentsLLM agents and tool use → Software engineering coding agents
  62. Probing the Geometry of Diffusion Models with the String MethodDiffusion models → Flow matching, time series and science
  63. Brain3D: Brain Report Automation via Inflated Vision Transformers in 3DMultimodal LLMs / vision-language models → Medical vision-language models
  64. Understanding Artificial Theory of Mind: Perturbed Tasks and Reasoning in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  65. Language Models Exhibit Inconsistent Biases Towards Algorithmic Agents and Human ExpertsLLM agents and tool use → Social simulation and multi-agent debate
  66. Learning Quantum Data Distribution via Chaotic Quantum Diffusion ModelDiffusion models → Diffusion foundations and sampling
  67. NESTOR: A Nested MOE-based Neural Operator for Large-Scale PDE Pre-TrainingMixture-of-experts → MoE theory and gating functions
  68. RobustVisRAG: Causality-Aware Vision-Based Retrieval-Augmented Generation under Visual DegradationsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
  69. World Guidance: World Modeling in Condition Space for Action GenerationWorld models → Embodied and robot world models +1
  70. PanoEnv: Exploring 3D Spatial Intelligence in Panoramic Environments with Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  71. When LoRA Betrays: Backdooring Text-to-Image Models by Masquerading as Benign AdaptersDiffusion models → Robustness, privacy and adversarial aspects +1
  72. MindDriver: Introducing Progressive Multimodal Reasoning for Autonomous DrivingLLM reasoning → Chain-of-thought reasoning for driving +2
  73. RADAR: Reasoning as Discrimination with Aligned Representations for LLM-based Knowledge Graph ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  74. MEDSYN: Benchmarking Multi-EviDence SYNthesis in Complex Clinical Cases for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  75. ExpLang: Improved Exploration and Exploitation in LLM Reasoning with On-Policy Thinking Language SelectionLLM reasoning → Reinforcement learning for reasoning
  76. DynamicGTR: Leveraging Graph Topology Representation Preferences to Boost VLM Capabilities on Graph QAsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  77. ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence on Mobile DevicesLLM agents and tool use → GUI and mobile agents
  78. FewMMBench: A Benchmark for Multimodal Few-Shot LearningMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  79. LightSim: A Lightweight Cell Transmission Model Simulator for Traffic Signal Control ResearchDeep reinforcement learning methods → RL for autonomous driving and traffic
  80. A Multi-Turn Framework for Evaluating AI Misuse in Fraud and Cybercrime ScenariosLLM safety and security → Prompt injection and agent security
  81. Self-Curriculum Model-based Reinforcement Learning for Shape Control of Deformable Linear ObjectsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  82. Prompt Architecture Determines Reasoning Quality: A Variable Isolation Study on the Car Wash ProblemLLM reasoning → Prompting and chain-of-thought reasoning
  83. Where Agent Frameworks Fall Short: Examining Functional Challenges and Usability ConcernsLLM agents and tool use → Software engineering coding agents
  84. Excitation: Momentum For ExpertsMixture-of-experts → Expert routing strategies
  85. D-COT: Disciplined Chain-of-Thought Learning for Efficient Reasoning in Small Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  86. XStreamVGGT: Extremely Memory-Efficient Streaming Vision Geometry Grounded Transformer with KV Cache CompressionEfficient LLM inference and serving → Token pruning and merging for ViTs
  87. Beyond Static Artifacts: A Forensic Benchmark for Video Deepfake Reasoning in Vision Language ModelsLLM reasoning → Multimodal reasoning +1
  88. Easy to Learn, Yet Hard to Forget: Towards Robust Unlearning Under BiasLLM safety and security → Machine unlearning
  89. Generalisation of RLHF under Reward Shift and Clipped KL RegularisationLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  90. Accelerating Diffusion via Hybrid Data-Pipeline Parallelism Based on Conditional Guidance SchedulingDiffusion models → Diffusion foundations and sampling
  91. Offline Reasoning for Efficient Recommendation: LLM-Empowered Persona-Profiled Item IndexingLLM reasoning → LLM reasoning for recommendation
  92. Enhancing Multi-Modal LLMs Reasoning via Difficulty-Aware Group NormalizationLLM reasoning → Multimodal reasoning +1
  93. Joint-Aligned Latent Action: Towards Scalable VLA Pretraining in the WildVision-language-action models → Human-video and latent-action pretraining
  94. Explore-on-Graph: Incentivizing Autonomous Exploration of Large Language Models on Knowledge Graphs with Path-refined Reward ModelingLLM reasoning → Knowledge- and tool-augmented reasoning +1
  95. Evaluating the relationship between regularity and learnability in recursive numeral systems using Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  96. SurGo-R1: Benchmarking and Modeling Contextual Reasoning for Operative Zone in Surgical VideoLLM reasoning → Clinical and biomedical applications
  97. Dynamic Multimodal Activation Steering for Hallucination Mitigation in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  98. E-comIQ-ZH: A Human-Aligned Dataset and Benchmark for Fine-Grained Evaluation of E-commerce Posters with Chain-of-ThoughtLLM reasoning → Multimodal reasoning
  99. TiMi: Empower Time Series Transformers with Multimodal Mixture of ExpertsMixture-of-experts → MoE for time series and graphs
  100. Primary-Fine Decoupling for Action Generation in Robotic ImitationOffline RL and imitation learning from data → Robot manipulation imitation learning
All 407
  1. AkiraRust: Re-thinking LLM-aided Rust Repair Using a Feedback-guided Thinking SwitchLLM reasoning → Reasoning for agents, planning and code
  2. Hierarchical LLM-Based Multi-Agent Framework with Prompt Optimization for Multi-Robot Task PlanningLLM agents and tool use → General LLM agent frameworks and benchmarks
  3. DWA-KD: Dual-Space Weighting and Time-Warped Alignment for Cross-Tokenizer Knowledge DistillationKnowledge distillation → Knowledge distillation for LLMs
  4. CCCaption: Dual-Reward Reinforcement Learning for Complete and Correct Image CaptioningDeep reinforcement learning methods → RL training of language and agent models
  5. Score-Based Conditional Flow Models for MIMO Receiver Design with Superimposed PilotsDiffusion models → Diffusion for compression and wireless
  6. PPCR-IM: A System for Multi-layer DAG-based Public Policy Consequence Reasoning and Social Indicator MappingLLM reasoning → Causal reasoning in LLMs
  7. Scalable Multilingual Multimodal Machine Translation with Speech-Text FusionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  8. AgentLTV: An Agent-Based Unified Search-and-Evolution Framework for Automated Lifetime Value PredictionLLM agents and tool use → Web, search, and research agents
  9. Self-Correcting VLA: Online Action Refinement via Sparse World ImaginationVision-language-action models → Reinforcement learning and post-training
  10. RuCL: Stratified Rubric-Based Curriculum Learning for Multimodal Large Language Model ReasoningLLM reasoning → Reinforcement learning for reasoning +1
  11. Multi-Layer Scheduling for MoE-Based LLM ReasoningMixture-of-experts → Efficient MoE training and inference systems +1
  12. When More Is Less: A Systematic Analysis of Spatial and Commonsense Information for Visual Spatial ReasoningLLM reasoning → Spatial and embodied reasoning +1
  13. Structurally Aligned Subtask-Level Memory for Software Engineering AgentsLLM agents and tool use → Software engineering coding agents
  14. NGDB-Zoo: Towards Efficient and Scalable Neural Graph Databases TrainingLLM reasoning → Knowledge- and tool-augmented reasoning
  15. A Hidden Semantic Bottleneck in Conditional Embeddings of Diffusion TransformersDiffusion models → Diffusion foundations and sampling
  16. Breaking Semantic-Aware Watermarks via LLM-Guided Coherence-Preserving Semantic InjectionDiffusion models → Robustness, privacy and adversarial aspects +1
  17. CADC: Content Adaptive Diffusion-Based Generative Image CompressionDiffusion models → Diffusion for compression and wireless
  18. Duel-Evolve: Reward-Free Test-Time Scaling via LLM Self-PreferencesLLM reasoning → Test-time compute and efficient thinking +1
  19. Learning End-to-End Control for Omnidirectional Aerial Motion on Overactuated Tilt-rotor QuadrotorsDeep reinforcement learning methods → RL for robot navigation and UAV control
  20. Revisiting RAG Retrievers: An Information Theoretic BenchmarkRetrieval-augmented generation → RAG pipeline design and evaluation
  21. DualPath: Breaking the Storage Bandwidth Bottleneck in Agentic LLM InferenceEfficient LLM inference and serving → Serving systems and request scheduling
  22. Mamba Meets Scheduling: Learning to Solve Flexible Job Shop Scheduling with Efficient Sequence ModelingState-space sequence models (S4, Mamba) → Core SSM architectures for language
  23. ARLArena: A Unified Framework for Stable Agentic Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents
  24. Reasoning-Driven Design of Single Atom Catalysts via a Multi-Agent Large Language Model FrameworkLLM agents and tool use → Medical and scientific domain agents
  25. Which Tool Response Should I Trust? Tool-Expertise-Aware Chest X-ray Agent with Multimodal Agentic LearningLLM agents and tool use → Medical and scientific domain agents
  26. Training Generalizable Collaborative Agents via Strategic Risk AversionLLM agents and tool use → Reinforcement learning for LLM agents
  27. See It, Say It, Sorted: An Iterative Training-Free Framework for Visually-Grounded Multimodal Reasoning in LVLMsLLM reasoning → Multimodal reasoning +1
  28. Beyond Refusal: Probing the Limits of Agentic Self-Correction for Semantic Sensitive InformationLLM agents and tool use → Agent threats, guardrails and governance +1
  29. Both Ends Count! Just How Good are LLM Agents at "Text-to-Big SQL"?LLM agents and tool use → Web, search, and research agents
  30. Pancake: Hierarchical Memory System for Multi-Agent LLM ServingLLM agents and tool use → Agent memory systems
  31. The Design Space of Tri-Modal Masked Diffusion ModelsDiffusion models → Discrete and text diffusion
  32. D-Flow SGLD: Source-Space Posterior Sampling for Scientific Inverse Problems with Flow MatchingDiffusion models → Flow matching, time series and science
  33. Geometric Priors for Generalizable World Models via Vector Symbolic ArchitectureWorld models → Latent predictive world models
  34. Factorizing formal contexts from closures of necessity operators
  35. Avenir-UX: Automated UX Evaluation via Simulated Human Web Interaction with GUI Grounding
  36. ShobdoSetu: A Data-Centric Framework for Bengali Long-Form Speech Recognition and Speaker Diarization
  37. LARFT: Closing the Cognition-Action Gap for Length Instruction Following in Large Language Models
  38. A comprehensive study of LLM-based argument classification: from Llama through DeepSeek to GPT-5.2
  39. Can Structural Cues Save LLMs? Evaluating Language Models in Massive Document Streams
  40. Spelling Correction in Healthcare Query-Answer Systems: Methods, Retrieval Impact, and Empirical Evaluation
  41. BenchBrowser: Retrieving Evidence for Evaluating Benchmark Validity
  42. DECODE: Dual-Enhanced Conditioned Diffusion for EEG Forecasting
  43. Tokenization vs. Augmentation: A Systematic Study of Writer Variance in IMU-Based Online Handwriting Recognition
  44. Neural-Symbolic Logic Query Answering in Non-Euclidean Space
  45. Knowledge, Rules and Their Embeddings: Two Paths towards Neuro-Symbolic JEPA
  46. Federated Personal Knowledge Graph Completion with Lightweight Large Language Models for Personalized Recommendations
  47. Evaluation of Audio Language Models for Fairness, Safety, and Security
  48. Deep Convolutional Architectures for EEG Classification: A Comparative Study with Temporal Augmentation and Confidence-Based Voting
  49. Architectural Design and Performance Analysis of FPGA based AI Accelerators: A Comprehensive Review
  50. RECAP: Local Hebbian Prototype Learning as a Self-Organizing Readout for Reservoir Dynamics
  51. OnDA: On-device Channel Pruning for Efficient Personalized Keyword Spotting
  52. DINOv3 Meets YOLO26 for Weed Detection in Vegetable Crops
  53. FujiView: Multimodal Late-Fusion for Predicting Scenic Visibility
  54. BiCLIP: Bidirectional and Consistent Language-Image Processing for Robust Medical Image Segmentation
  55. Pulse-Driven Neural Architecture: Learnable Oscillatory Dynamics for Robust Continuous-Time Sequence Processing
  56. Multiview Progress Prediction of Robot Activities
  57. Cross-Task Benchmarking of CNN Architectures
  58. Explainability-Aware Evaluation of Transfer Learning Models for IoT DDoS Detection Under Resource Constraints
  59. Importance of Prompt Optimisation for Error Detection in Medical Notes Using Language Models
  60. Sydney Telling Fables on AI and Humans: A Corpus Tracing Memetic Transfer of Persona between LLMs
  61. Efficient Continual Learning in Language Models via Thalamically Routed Cortical Columns
  62. Mind the Gap in Cultural Alignment: Task-Aware Culture Management for Large Language Models
  63. Beyond performance-wise Contribution Evaluation in Federated Learning
  64. Automating the Detection of Requirement Dependencies Using Large Language Models
  65. Identifying Crucial Attention Heads for Multilingual Language Models: Retrieval and Retrieval-Transition Heads
  66. A Fusion of context-aware based BanglaBERT and Two-Layer Stacked LSTM Framework for Multi-Label Cyberbullying Detection
  67. ECHO: Encoding Communities via High-order Operators
  68. How Do Latent Reasoning Methods Perform Under Weak and Strong Supervision?
  69. From Bias to Balance: Fairness-Aware Paper Recommendation for Equitable Peer Review
  70. veScale-FSDP: Flexible and High-Performance FSDP at Scale
  71. GetBatch: Distributed Multi-Object Retrieval for ML Data Loading
  72. LoBoost: Fast Model-Native Local Conformal Prediction for Gradient-Boosted Trees
  73. mmWave Radar Aware Dual-Conditioned GAN for Speech Reconstruction of Signals With Low SNR
  74. TopoEdit: Fast Post-Optimization Editing of Topology Optimized Structures
  75. Causality neq Invariance: Function and Concept Vectors in LLMs
  76. Revisiting Chebyshev Polynomial and Anisotropic RBF Models for Tabular Regression
  77. CLIP Is Shortsighted: Paying Attention Beyond the First Sentence
  78. A Learning-Based Hybrid Decision Framework for Matching Systems with User Departure Detection
  79. Exploring Human Behavior During Abstract Rule Inference and Problem Solving with the Cognitive Abstraction and Reasoning Corpus
  80. MolFM-Lite: Multi-Modal Molecular Property Prediction with Conformer Ensemble Attention and Cross-Modal Fusion
  81. SAFARI: A Community-Engaged Approach and Dataset of Stereotype Resources in the Sub-Saharan African Context
  82. Vibe Researching as Wolf Coming: Can AI Agents with Skills Replace or Augment Social Scientists?
  83. Predicting Multi-Drug Resistance in Bacterial Isolates Through Performance Comparison and LIME-based Interpretation of Classification Models
  84. Vision Transformers Need More Than Registers
  85. Detecting Hate and Inflammatory Content in Bengali Memes: A New Multimodal Dataset and Co-Attention Framework
  86. Disentangling Shared and Target-Enriched Topics via Background-Contrastive Non-negative Matrix Factorization
  87. Enhancing Renal Tumor Malignancy Prediction: Deep Learning with Automatic 3D CT Organ Focused Attention
  88. AeroDGS: Physically Consistent Dynamic Gaussian Splatting for Single-Sequence Aerial 4D Reconstruction
  89. Sampling from Constrained Gibbs Measures: with Applications to High-Dimensional Bayesian Inference
  90. EyeLayer: Integrating Human Attention Patterns into LLM-Based Code Summarization
  91. Learning geometry-dependent lead-field operators for forward ECG modeling
  92. Optimizing Neural Network Architecture for Medical Image Segmentation Using Monte Carlo Tree Search
  93. Scaling In, Not Up? Testing Thick Citation Context Analysis with GPT-5 and Fragile Prompts
  94. GRAU: Generic Reconfigurable Activation Unit Design for Neural Network Hardware Accelerators
  95. Enabling clinical use of foundation models for computational pathology
  96. A 1/R Law for Kurtosis Contrast in Balanced Mixtures
  97. Testable Learning of General Halfspaces under Massart Noise
  98. Decoding the Hook: A Multimodal LLM Framework for Analyzing the Hooking Period of Video Ads
  99. AviaSafe: A Physics-Informed Data-Driven Model for Aviation Safety-Critical Cloud Forecasts
  100. When Should a Model Change Its Mind? An Energy-Based Theory and Regularizer for Concept Drift in Electrocardiogram (ECG) Signals
  101. Topology enables learning-based hydrodynamic prediction of the global river system
  102. Manifold of Failure: Behavioral Attraction Basins in Language Models
  103. What Topological and Geometric Structure Do Biological Foundation Models Learn? Evidence from 141 Hypotheses
  104. Reliable XAI Explanations in Sudden Cardiac Death Prediction for Chagas Cardiomyopathy
  105. Multi-Level Causal Embeddings
  106. OmniZip: Learning a Unified and Lightweight Lossless Compressor for Multi-Modal Data
  107. Early Risk Stratification of Dosing Errors in Clinical Trials Using Machine Learning
  108. Differentially Private Truncation of Unbounded Data via Public Second Moments
  109. Integrating Machine Learning Ensembles and Large Language Models for Heart Disease Prediction Using Voting Fusion
  110. Learning to reconstruct from saturated data: audio declipping and high-dynamic range imaging
  111. RETLLM: Training and Data-Free MLLMs for Multimodal Information Retrieval
  112. X-REFINE: XAI-based RElevance input-Filtering and archItecture fiNe-tuning for channel Estimation
  113. Deep Accurate Solver for the Geodesic Problem
  114. Positional-aware Spatio-Temporal Network for Large-Scale Traffic Prediction
  115. Support Tokens, Stability Margins, and a New Foundation for Robust LLMs
  116. Prior Knowledge-enhanced Spatio-temporal Epidemic Forecasting
  117. CQSA: Byzantine-robust Clustered Quantum Secure Aggregation in Federated Learning
  118. AutoQRA: Joint Optimization of Mixed-Precision Quantization and Low-rank Adapters for Efficient LLM Fine-Tuning
  119. Data-Driven Supervision of a Thermal-Hydraulic Process Towards a Physics-Based Digital Twin
  120. WaveSSM: Multiscale State-Space Models for Non-stationary Signal Attention
  121. CryoNet.Refine: A One-step Diffusion Model for Rapid Refinement of Structural Models with Cryo-EM Density Map Restraints
  122. Sustainable LLM Inference using Context-Aware Model Switching
  123. Orthogonal Weight Modification Enhances Learning Scalability and Convergence Efficiency without Gradient Backpropagation
  124. Neu-PiG: Neural Preconditioned Grids for Fast Dynamic Surface Reconstruction on Long Sequences
  125. WHOLE: World-Grounded Hand-Object Lifted from Egocentric Videos
  126. Recovered in Translation: Efficient Pipeline for Automated Translation of Benchmarks and Datasets
  127. SumTablets: A Transliteration Dataset of Sumerian Tablets
  128. Off-The-Shelf Image-to-Image Models Are All You Need To Defeat Image Protection Schemes
  129. Surrogate models for Rock-Fluid Interaction: A Grid-Size-Invariant Approach
  130. LiCQA : A Lightweight Complex Question Answering System
  131. Discovering Subgroups with Exceptional Survival Characteristics
  132. Mixed Magnification Aggregation for Generalizable Region-Level Representations in Computational Pathology
  133. DySCO: Dynamic Attention-Scaling Decoding for Long-Context Language Models
  134. CASR: A Robust Cyclic Framework for Arbitrary Large-Scale Super-Resolution with Distribution Alignment and Self-Similarity Awareness
  135. Dynamic Personality Adaptation in Large Language Models via State Machines
  136. CoLoGen: Progressive Learning of Concept-Localization Duality for Unified Image Generation
  137. Enhancing Framingham Cardiovascular Risk Score Transparency through Logic-Based XAI
  138. When AI Writes, Whose Voice Remains? Quantifying Cultural Marker Erasure Across World English Varieties in Large Language Models
  139. Lumosaic: Hyperspectral Video via Active Illumination and Coded-Exposure Pixels
  140. SigmaQuant: Hardware-Aware Heterogeneous Quantization Method for Edge DNN Inference
  141. Sample Complexity Bounds for Robust Mean Estimation with Mean-Shift Contamination
  142. IndicIFEval: A Benchmark for Verifiable Instruction-Following Evaluation in 14 Indic Languages
  143. GeoDiv: Framework For Measuring Geographical Diversity In Text-To-Image Models
  144. Slice and Explain: Logic-Based Explanations for Neural Networks through Domain Slicing
  145. Don't stop me now: How Validation Criteria Affect Checkpoint Selection and Early Stopping
  146. On Imbalanced Regression with Hoeffding Trees
  147. WeatherCity: Urban Scene Reconstruction with Controllable Multi-Weather Transformation
  148. Petri Net Relaxation for Infeasibility Explanation and Sequential Task Planning
  149. Overview of the CXR-LT 2026 Challenge: Multi-Center Long-Tailed and Zero Shot Chest X-ray Classification
  150. Learning to Drive is a Free Gift: Large-Scale Label-Free Autonomy Pretraining from Unposed In-The-Wild Videos
  151. Confidence-Driven Multi-Scale Model Selection for Cost-Efficient Inference
  152. MBD-ML: Many-body dispersion from machine learning for molecules and materials
  153. Coarsening Bias from Variable Discretization in Causal Functionals
  154. AdaSpot: Spend Resolution Where It Matters for Precise Event Spotting
  155. Semantic Partial Grounding via LLMs
  156. DualWeaver: Synergistic Feature Weaving Surrogates for Multivariate Forecasting with Univariate Time Series Foundation Models
  157. FlowCorrect: Efficient Interactive Correction of Generative Flow Policies for Robotic Manipulation
  158. Physics-Informed Machine Learning for Vessel Shaft Power and Fuel Consumption Prediction: Interpretable KAN-based Approach
  159. AutoSew: A Geometric Approach to Stitching Prediction with Graph Neural Networks
  160. SPGen: Stochastic scanpath generation for paintings using unsupervised domain adaptation
  161. DLT-Corpus: A Large-Scale Text Collection for the Distributed Ledger Technology Domain
  162. TG-ASR: Translation-Guided Learning with Parallel Gated Cross Attention for Low-Resource Automatic Speech Recognition
  163. RT-RMOT: A Dataset and Framework for RGB-Thermal Referring Multi-Object Tracking
  164. RGB-Event HyperGraph Prompt for Kilometer Marker Recognition based on Pre-trained Foundation Models
  165. Disease Progression and Subtype Modeling for Combined Discrete and Continuous Input Data
  166. Function-Space Empirical Bayes Regularisation with Student's t Priors
  167. A Diversity Diet for a Healthier Model: A Case Study of French ModernBERT
  168. Neural solver for Wasserstein Geodesics and optimal transport dynamics
  169. Enhancing LLM-Based Test Generation by Eliminating Covered Code
  170. Outpatient Appointment Scheduling Optimization with a Genetic Algorithm Approach
  171. Solving stiff dark matter equations via Jacobian Normalization with Physics-Informed Neural Networks
  172. PatchDenoiser: Parameter-efficient multi-scale patch learning and fusion denoiser for Low-dose CT imaging
  173. CxMP: A Linguistic Minimal-Pair Benchmark for Evaluating Constructional Understanding in Language Models
  174. Dream-SLAM: Dreaming the Unseen for Active SLAM in Dynamic Environments
  175. Compact Circulant Layers with Spectral Priors
  176. Global-Aware Edge Prioritization for Pose Graph Initialization
  177. Robustness in sparse artificial neural networks trained with adaptive topology
  178. Estimation and Optimization of Ship Fuel Consumption in Maritime: Review, Challenges and Future Directions
  179. Learning to Collaborate via Structures: Cluster-Guided Item Alignment for Federated Recommendation
  180. Global-Local Dual Perception for MLLMs in High-Resolution Text-Rich Image Translation
  181. Bayesian Generative Adversarial Networks via Gaussian Approximation for Tabular Data Synthesis
  182. Algorithmic Blindness in Large Language Models: A Calibration Study of Performance Prediction
  183. Learning to Fuse and Reconstruct Multi-View Graphs for Diabetic Retinopathy Grading
  184. Mobile-Ready Automated Triage of Diabetic Retinopathy Using Digital Fundus Images
  185. Directed Ordinal Diffusion Regularization for Progression-Aware Diabetic Retinopathy Grading
  186. Hidden Topics: Measuring Sensitive AI Beliefs with List Experiments
  187. A Framework for Cross-Domain Generalization in Coronary Artery Calcium Scoring Across Gated and Non-Gated Computed Tomography
  188. Small Wins Big: Comparing Large Language Models and Domain Fine-Tuned Models for Sarcasm Detection in Code-Mixed Hinglish Text
  189. Geometry-as-context: Modulating Explicit 3D in Scene-consistent Video Generation to Geometry Context
  190. Learning Unknown Interdependencies for Decentralized Root Cause Analysis in Nonlinear Dynamical Systems
  191. Bridging Through Absence: How Comeback Researchers Bridge Knowledge Gaps Through Structural Re-emergence
  192. Learning in the Null Space: Small Singular Values for Continual Learning
  193. Scan Clusters, Not Pixels: A Cluster-Centric Paradigm for Efficient Ultra-high-definition Image Restoration
  194. Protein Graph Neural Networks for Heterogeneous Cryo-EM Reconstruction
  195. The Error of Deep Operator Networks Is the Sum of Its Parts: Branch-Trunk and Mode Error Decompositions
  196. TIRAuxCloud: A Thermal Infrared Dataset for Day and Night Cloud Detection
  197. UNet-Based Keypoint Regression for 3D Cone Localization in Autonomous Racing
  198. EndoDDC: Learning Sparse to Dense Reconstruction for Endoscopic Robotic Navigation via Diffusion Depth Completion
  199. 2-Step Agent: A Framework for the Interaction of a Decision Maker with AI Decision Support
  200. How to Take a Memorable Picture? Empowering Users with Actionable Feedback
  201. GFPL: Generative Federated Prototype Learning for Resource-Constrained and Data-Imbalanced Vision Task
  202. Personalized Graph-Empowered Large Language Model for Proactive Information Access
  203. Distill and Align Decomposition for Enhanced Claim Verification
  204. Understanding Annotation Error Propagation and Learning an Adaptive Policy for Expert Intervention in Barrett's Video Segmentation
  205. Meta-FC: Meta-Learning with Feature Consistency for Robust and Generalizable Watermarking
  206. Scalable Kernel-Based Distances for Statistical Inference and Integration
  207. xai-cola: A Python library for sparsifying counterfactual explanations
  208. JSAM: Privacy Straggler-Resilient Joint Client Selection and Incentive Mechanism Design in Differentially Private Federated Learning
  209. Resilient Federated Chain: Transforming Blockchain Consensus into an Active Defense Layer for Federated Learning
  210. UniVBench: Towards Unified Evaluation for Video Foundation Models
  211. StoryMovie: A Dataset for Semantic Alignment of Visual Stories with Movie Scripts and Subtitles
  212. DocDjinn: Controllable Synthetic Document Generation with VLMs and Handwriting Diffusion
  213. Joint Shadow Generation and Relighting via Light-Geometry Interaction Maps
  214. SemVideo: Reconstructs What You Watch from Brain Activity via Hierarchical Semantic Guidance
  215. SkyReels-V4: Multi-modal Video-Audio Generation, Inpainting and Editing model
  216. GeoMotion: Rethinking Motion Segmentation via Latent 4D Geometry
  217. An Evaluation of Context Length Extrapolation in Long Code via Positional Embeddings and Efficient Attention
  218. Neural Learning of Fast Matrix Multiplication Algorithms: A StrassenNet Approach
  219. Efficient Scaling of LLM Training with Flexible Context Parallelism
  220. Therapist-Robot-Patient Physical Interaction is Worth a Thousand Words: Enabling Intuitive Therapist Guidance via Remote Haptic Control
  221. From Statics to Dynamics: Physics-Aware Image Editing with Latent Transition Priors
  222. UniWhisper: Efficient Continual Multi-task Training for Robust Universal Audio Representation
  223. RAMSeS: Robust and Adaptive Model Selection for Time-Series Anomaly Detection Algorithms
  224. Improving Implicit Discourse Relation Recognition with Natural Language Explanations from LLMs
  225. SAPNet++: Evolving Point-Prompted Instance Segmentation with Semantic and Spatial Awareness
  226. Survey on Neural Routing Solvers
  227. Learning from Yesterday's Error: An Efficient Online Learning Method for Traffic Demand Prediction
  228. LiREC-Net: A Target-Free and Learning-Based Network for LiDAR, RGB, and Event Calibration
  229. From Words to Amino Acids: Does the Curse of Depth Persist?
  230. RABot: Reinforcement-Guided Graph Augmentation for Imbalanced and Noisy Social Bot Detection
  231. fEDM+: A Risk-Based Fuzzy Ethical Decision Making Framework with Principle-Level Explainability and Pluralistic Validation
  232. The ASIR Courage Model: A Phase-Dynamic Framework for Truth Transitions in Human and AI Systems
  233. Robust Long-Form Bangla Speech Processing: Automatic Speech Recognition and Speaker Diarization
  234. Structure-to-Image: Zero-Shot Depth Estimation in Colonoscopy via High-Fidelity Sim-to-Real Adaptation
  235. SigVLP: Sigmoid Volume-Language Pre-Training for Self-Supervised CT-Volume Adaptive Representation Learning
  236. Private and Robust Contribution Evaluation in Federated Learning
  237. C2TC: A Training-Free Framework for Efficient Tabular Data Condensation
  238. TranX-Adapter: Bridging Artifacts and Semantics within MLLMs for Robust AI-generated Image Detection
  239. Two-Stage Active Distribution Network Voltage Control via LLM-RL Collaboration: A Hybrid Knowledge-Data-Driven Approach
  240. Innovative Tooth Segmentation Using Hierarchical Features and Bidirectional Sequence Modeling
  241. Assessing airborne laser scanning and aerial photogrammetry for deep learning-based stand delineation
  242. Learning spatially adaptive sparsity level maps for arbitrary convolutional dictionaries
  243. Brain Tumor Segmentation with Special Emphasis on the Non-Enhancing Brain Tumor Compartment
  244. Learning Complex Physical Regimes via Coverage-oriented Uncertainty Quantification: An application to the Critical Heat Flux
  245. SF3D-RGB: Scene Flow Estimation from Monocular Camera and Sparse LiDAR
  246. Hierarchical Lead Critic based Multi-Agent Reinforcement Learning
  247. Trie-Aware Transformers for Generative Recommendation
  248. Error-awareness Accelerates Active Automata Learning
  249. Space-Time Forecasting of Dynamic Scenes with Motion-aware Gaussian Grouping
  250. Send Less, Perceive More: Masked Quantized Point Cloud Communication for Loss-Tolerant Collaborative Perception
  251. HybridINR-PCGC: Hybrid Lossless Point Cloud Geometry Compression Bridging Pretrained Model and Implicit Neural Representation
  252. Following the Diagnostic Trace: Visual Cognition-guided Cooperative Network for Chest X-Ray Diagnosis
  253. Sparsity Induction for Accurate Post-Training Pruning of Large Language Models
  254. Multimodal Survival Modeling and Fairness-Aware Clinical Machine Learning for 5-Year Breast Cancer Risk Prediction
  255. Mitigating Structural Noise in Low-Resource S2TT: An Optimized Cascaded Nepali-English Pipeline with Punctuation Restoration
  256. Lie Flow: Video Dynamic Fields Modeling and Predicting with Lie Algebra as Geometric Physics Principle
  257. Multi-dimensional Assessment and Explainable Feedback for Counselor Responses to Client Resistance in Text-based Counseling with LLMs
  258. CARE: A Molecular-Guided Foundation Model with Adaptive Region Modeling for Whole Slide Image Analysis
  259. Axial-Centric Cross-Plane Attention for 3D Medical Image Classification
  260. UniHand: A Unified Model for Diverse Controlled 4D Hand Motion Modeling
  261. Tokenizing Semantic Segmentation with Run Length Encoding
  262. Revisiting the Bertrand Paradox via Equilibrium Analysis of No-regret Learners
  263. Virtual Biopsy for Intracranial Tumors Diagnosis on MRI
  264. MixSarc: A Bangla-English Code-Mixed Corpus for Implicit Meaning Identification
  265. Deep Clustering based Boundary-Decoder Net for Inter and Intra Layer Stress Prediction of Heterogeneous Integrated IC Chip
  266. Iterative Closed-Loop Motion Synthesis for Scaling the Capabilities of Humanoid Control
  267. Retrieval Challenges in Low-Resource Public Service Information: A Case Study on Food Pantry Access
  268. SEF-MAP: Subspace-Decomposed Expert Fusion for Robust Multimodal HD Map Prediction
  269. ABM-UDE: Developing Surrogates for Epidemic Agent-Based Models via Scientific Machine Learning
  270. Exploring Human-Machine Coexistence in Symmetrical Reality
  271. MultiAnimate: Pose-Guided Image Animation Made Extensible
  272. Goodness-of-Fit Tests for Latent Class Models with Ordinal Categorical Data
  273. How many asymmetric communities are there in multi-layer directed networks?
  274. Routing by Reaching: Composition of Pre-trained GFlowNets for Multi-Objective Generation
  275. Power and Limitations of Aggregation in Compound AI Systems
  276. Generalizing Visual Geometry Priors to Sparse Gaussian Occupancy Prediction
  277. From Basis to Basis: Gaussian Particle Representation for Interpretable PDE Operators
  278. Extending Sequence Length is Not All You Need: Effective Integration of Multimodal Signals for Gene Expression Prediction
  279. MUON+: Towards More Effective Muon via One Additional Normalization Step for LLM Pre-training
  280. Enhancing Multilingual Embeddings via Multi-Way Parallel Text Alignment
  281. VasGuideNet: Vascular Topology-Guided Couinaud Liver Segmentation with Structural Contrastive Loss
  282. IHF-Harmony: Multi-Modality Magnetic Resonance Images Harmonization using Invertible Hierarchy Flow Model
  283. Pseudo-View Enhancement via Confidence Fusion for Unposed Sparse-View Reconstruction
  284. LiLo-VLA: Compositional Long-Horizon Manipulation via Linked Object-Centric Policies
  285. One Brain, Omni Modalities: Towards Unified Non-Invasive Brain Decoding with Large Language Models
  286. Fair Model-based Clustering
  287. WaterVIB: Learning Minimal Sufficient Watermark Representations via Variational Information Bottleneck
  288. AHAN: Asymmetric Hierarchical Attention Network for Identical Twin Face Verification
  289. A Researcher's Guide to Empirical Risk Minimization
  290. Easy3E: Feed-Forward 3D Asset Editing via Rectified Voxel Flow
  291. Learning Recursive Multi-Scale Representations for Irregular Multivariate Time Series Forecasting
  292. GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning
  293. Evaluating the Usage of African-American Vernacular English in Large Language Models
  294. Unified Unsupervised and Sparsely-Supervised 3D Object Detection by Semantic Pseudo-Labeling and Prototype Learning
  295. Perceptual Quality Optimization of Image Super-Resolution
  296. Global Sequential Testing for Multi-Stream Auditing
  297. Efficient Inference after Directionally Stable Adaptive Experiments
  298. A Knowledge-Driven Approach to Music Segmentation, Music Source Separation and Cinematic Audio Source Separation
  299. Automatic Map Density Selection for Locally-Performant Visual Place Recognition
  300. Unsupervised Discovery of Intermediate Phase Order in the Frustrated J1-J2 Heisenberg Model via Prometheus Framework
  301. Asymptotically Fast Clebsch-Gordan Tensor Products with Vector Spherical Harmonics
  302. iMiGUE-Speech: A Spontaneous Speech Dataset for Affective Analysis
  303. Effects of Training Data Quality on Classifier Performance
  304. VecGlypher: Unified Vector Glyph Generation with Language Models
  305. Revisiting Text Ranking in Deep Research
  306. When Learning Hurts: Fixed-Pole RNN for Real-Time Online Training
  307. Adversarial Robustness of Deep Learning-Based Thyroid Nodule Segmentation in Ultrasound