mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 13 Apr 2026

556 papers

  1. MindGames Arena Generalization Track: In2AI Solution with Delayed Per-Step Reward AttributionLLM agents and tool use → Reinforcement learning for LLM agents
  2. ClinQueryAgent: A Conversational Agent for Population Health ManagementLLM agents and tool use → Medical and scientific domain agents
  3. Sparse Autoencoder Decomposition of Clinical Sequence Model Representations: Feature Complexity, Task Specialisation, and Mortality PredictionMechanistic interpretability → Interpreting biomedical and science models
  4. RCSB PDB AI Help Desk: retrieval-augmented generation for protein structure deposition supportRetrieval-augmented generation → Medical and biomedical RAG
  5. Accelerating Reinforcement Learning for Wind Farm Control via Expert DemonstrationsDeep reinforcement learning methods → RL for energy, networks and operations
  6. SpikeMLLM: Spike-based Multimodal Large Language Models via Modality-Specific Temporal Scales and Temporal CompressionMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  7. LayerCache: Exploiting Layer-wise Velocity Heterogeneity for Efficient Flow Matching InferenceDiffusion models → Diffusion foundations and sampling
  8. DexWorldModel: Causal Latent World Modeling towards Automated Learning of Embodied TasksWorld models → Embodied and robot world models
  9. DSS: Dynamic Semantic Steering for Robust Concept Erasure in Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  10. Graph Propagated Projection Unlearning: A Unified Framework for Vision and Audio Discriminative ModelsLLM safety and security → Machine unlearning
  11. AgentForge: Execution-Grounded Multi-Agent LLM Framework for Autonomous Software EngineeringLLM agents and tool use → Software engineering coding agents
  12. LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM SafetyLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  13. From Plan to Action: How Well Do Agents Follow the Plan?LLM agents and tool use → General LLM agent frameworks and benchmarks
  14. Retrieval-Augmented Generation Must Move Beyond Factual Grounding to Represent Diverse OpinionsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  15. Towards Platonic Representation for Table Reasoning: A Foundation for Permutation-Invariant RetrievalLLM reasoning → Knowledge- and tool-augmented reasoning
  16. Aethon: A Reference-Based Replication Primitive for Constant-Time Instantiation of Stateful AI AgentsLLM agents and tool use → Software engineering coding agents
  17. Beyond Perception Errors: Semantic Fixation in Large Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  18. The A-R Behavioral Space: Execution-Level Profiling of Tool-Using Language Model Agents in Organizational DeploymentLLM agents and tool use → General LLM agent frameworks and benchmarks
  19. HTDC: Hesitation-Triggered Differential Calibration for Mitigating Hallucination in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  20. Spatial Atlas: Compute-Grounded Reasoning for Spatial-Aware Research Agent BenchmarksLLM reasoning → Spatial and embodied reasoning +1
  21. Think Before You Code: Dual Reasoning for the NLSafety-Utility Trade-Off in LLM Code GenerationLLM reasoning → Reasoning for agents, planning and code +1
  22. Robust Optimization for Mitigating Reward Hacking with Correlated ProxiesLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification +1
  23. Narrative over Numbers: The Identifiable Victim Effect and its Amplification Under Alignment and Reasoning in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  24. Mathematics Teachers Interactions with a Multi-Agent System for Personalized Problem GenerationLLM agents and tool use → Educational agents and math problem solving
  25. LLM-Redactor: An Empirical Evaluation of Eight Techniques for Privacy-Preserving LLM RequestsLLM agents and tool use → Agent threats, guardrails and governance
  26. LoSA: Locality Aware Sparse Attention for Block-Wise Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  27. REGREACT: Self-Correcting Multi-Agent Pipelines for Structured Regulatory Information ExtractionLLM agents and tool use → Web, search, and research agents
  28. Can we Watermark Low-Entropy LLM Outputs?LLM safety and security → Watermarking generated content and models
  29. ORBIT: Guided Agentic Orchestration for Autonomous C-to-Rust TranspilationLLM agents and tool use → Software engineering coding agents
  30. Empirical Evaluation of PDF Parsing and Chunking for Financial Question Answering with RAGRetrieval-augmented generation → Legal and financial RAG
  31. Think Through Uncertainty: Improving Long-Form Generation Factuality via Reasoning CalibrationLLM reasoning → Test-time compute and efficient thinking
  32. VISTA: Validation-Informed Trajectory Adaptation via Self-DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  33. SIR-Bench: Evaluating Investigation Depth in Security Incident Response AgentsLLM agents and tool use → Agent threats, guardrails and governance
  34. When Does Visual Token Pruning Improve Calibration? The Role of Evidence Coverage in MLLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  35. Memory as Metabolism: A Design for Companion Knowledge SystemsRetrieval-augmented generation → Agentic RAG, agents and memory
  36. Benchmarking Deflection and Hallucination in Large Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  37. TriFit: Trimodal Fusion with Protein Dynamics for Mutation Fitness PredictionMixture-of-experts → Medical and biomedical MoE
  38. Identity as Attractor: Geometric Evidence for Persistent Agent Architecture in LLM Activation SpaceLLM agents and tool use → General LLM agent frameworks and benchmarks
  39. Sample Complexity of Autoregressive Reasoning: Chain-of-Thought vs. End-to-EndLLM reasoning → Prompting and chain-of-thought reasoning
  40. TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text AlignmentMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  41. Self-Distillation Zero: Self-Revision Turns Binary Rewards into Dense SupervisionKnowledge distillation → On-policy and self-distillation for LLMs
  42. Filtered Reasoning Score: Evaluating Reasoning Quality on a Model's Most-Confident TracesLLM reasoning → Reasoning benchmarks and evaluation
  43. The Long-Horizon Task Mirage? Diagnosing Where and Why Agentic Systems BreakLLM agents and tool use → General LLM agent frameworks and benchmarks
  44. When Drawing Is Not Enough: Exploring Spontaneous Speech with Sketch for Intent Alignment in Multimodal LLMsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  45. AnyPoC: Universal Proof-of-Concept Test Generation for Scalable LLM-Based Bug DetectionLLM agents and tool use → Software engineering coding agents
  46. AutoSurrogate: An LLM-Driven Multi-Agent Framework for Autonomous Construction of Deep Learning Surrogate Models in Subsurface FlowLLM agents and tool use → Web, search, and research agents
  47. GoodPoint: Learning Constructive Scientific Paper Feedback from Author ResponsesLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  48. Self-Monitoring Benefits from Structural Integration: Lessons from Metacognition in Continuous-Time Multi-Timescale AgentsDeep reinforcement learning methods → Deep RL algorithms and representations
  49. MedConcept: Unsupervised Concept Discovery for Interpretability in Medical VLMsMultimodal LLMs / vision-language models → Medical vision-language models
  50. MVAdapt: Zero-Shot Multi-Vehicle Adaptation for End-to-End Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
  51. Solving Physics Olympiad via Reinforcement Learning on Physics SimulatorsLLM reasoning → Spatial and embodied reasoning +1
  52. Disentangled Point Diffusion for Precise Object PlacementOffline RL and imitation learning from data → Robot manipulation imitation learning
  53. A Mechanistic Analysis of Looped Reasoning Language ModelsLLM reasoning → Test-time compute and efficient thinking
  54. ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt InjectionLLM agents and tool use → Agent threats, guardrails and governance +1
  55. LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and GenerationLLM reasoning → Multimodal reasoning +1
  56. ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI AgentsLLM agents and tool use → GUI and mobile agents
  57. General365: Benchmarking General Reasoning in Large Language Models Across Diverse and Challenging TasksLLM reasoning → Mathematical reasoning
  58. λA: A Typed Lambda Calculus for LLM Agent CompositionLLM agents and tool use → Software engineering coding agents
  59. StarVLA-α: Reducing Complexity in Vision-Language-Action SystemsVision-language-action models → Generalist VLA models and benchmarks
  60. Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic TasksLLM reasoning → Reasoning for agents, planning and code +1
  61. Grounded World Model for Semantically Generalizable PlanningWorld models → Embodied and robot world models
  62. LangFlow: Continuous Diffusion Rivals Discrete in Language ModelingDiffusion models → Discrete and text diffusion
  63. Collaborative Multi-Agent Scripts Generation for Enhancing Imperfect-Information Reasoning in Murder Mystery GamesLLM reasoning → Reasoning for agents, planning and code +2
  64. SCORP: Scene-Consistent Multi-agent Diffusion Planning with Stable Online Reinforcement Post-Training for Cooperative DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  65. On the Robustness of Watermarking for Autoregressive Image GenerationLLM safety and security → Watermarking generated content and models
  66. A Mamba-Based Multimodal Network for Multiscale Blast-Induced Rapid Structural Damage AssessmentState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  67. Agentic Driving Coach: Robustness and Determinism of Agentic AI-Powered Human-in-the-Loop Cyber-Physical SystemsEnd-to-end autonomous driving → Large language models for driving +1
  68. LARY: A Latent Action Representation Yielding Benchmark for Generalizable Vision-to-Action AlignmentVision-language-action models → Human-video and latent-action pretraining
  69. EA-Agent: A Structured Multi-Step Reasoning Agent for Entity AlignmentLLM reasoning → Knowledge- and tool-augmented reasoning +1
  70. Dual-Control Frequency-Aware Diffusion Model for Depth-Dependent Optical Microrobot Microscopy Image GenerationDiffusion models → Inverse problems and image restoration
  71. Playing Along: Learning a Double-Agent Defender for Belief Steering via Theory of MindLLM agents and tool use → General LLM agent frameworks and benchmarks
  72. Why Do Large Language Models Generate Harmful Content?LLM safety and security → Safety alignment, refusal and guardrails
  73. Towards Autonomous Mechanistic Reasoning in Virtual CellsLLM reasoning → Clinical and biomedical applications
  74. RPA-Check: A Multi-Stage Automated Framework for Evaluating Dynamic LLM-based Role-Playing AgentsLLM agents and tool use → Social simulation and multi-agent debate
  75. CArtBench: Evaluating Vision-Language Models on Chinese Art Understanding, Interpretation, and AuthenticityMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  76. Back to Basics: Let Conversational Agents Remember with Just Retrieval and GenerationDeep reinforcement learning methods → RL training of language and agent models
  77. POINTS-Long: Adaptive Dual-Mode Visual Reasoning in MLLMsLLM reasoning → Multimodal reasoning +1
  78. RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test TimeLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  79. Context Kubernetes: Declarative Orchestration of Enterprise Knowledge for Agentic AI SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  80. Self-Evolving LLM Memory Extraction Across Heterogeneous TasksSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  81. Geoparsing: Diagram Parsing for Plane and Solid Geometry with a Unified Formal LanguageLLM reasoning → Spatial and embodied reasoning +1
  82. MLLM-as-a-Judge Exhibits Model Preference BiasMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  83. A Triadic Suffix Tokenization Scheme for Numerical ReasoningLLM reasoning → Mathematical reasoning
  84. Finetune Like You Pretrain: Boosting Zero-shot Adversarial Robustness in Vision-language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  85. DA-PTQ: Drift-Aware Post-Training Quantization for Efficient Vision-Language-Action ModelsVision-language-action models → Efficient VLA inference and adaptation
  86. UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM AgentsLLM agents and tool use → Tool learning and function calling
  87. FM-Agent: Scaling Formal Methods to Large Systems via LLM-Based Hoare-Style ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  88. Relax: An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at ScaleDeep reinforcement learning methods → RL training of language and agent models
  89. Eliciting Medical Reasoning with Knowledge-enhanced Data Synthesis: A Semi-Supervised Reinforcement Learning ApproachLLM reasoning → Clinical and biomedical applications +1
  90. RLSpoofer: A Lightweight Evaluator for LLM Watermark Spoofing ResilienceLLM safety and security → Watermarking generated content and models
  91. Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic MemoryLLM agents and tool use → Agent memory systems
  92. A collaborative agent with two lightweight synergistic models for autonomous crystal materials researchLLM agents and tool use → Medical and scientific domain agents
  93. Problem Reductions at Scale: Agentic Integration of Computationally Hard ProblemsLLM agents and tool use → Software engineering coding agents
  94. Beyond Attention Scores: SVD-Based Vision Token Pruning for Efficient Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  95. Continuous Adversarial Flow ModelsDiffusion models → Flow matching, time series and science
  96. From Translation to Superset: Benchmark-Driven Evolution of a Production AI Agent from Rust to PythonLLM agents and tool use → Software engineering coding agents
  97. The Price of Ignorance: Information-Free Quotation for Data Retention in Machine UnlearningLLM safety and security → Machine unlearning
  98. METER: Evaluating Multi-Level Contextual Causal Reasoning in Large Language ModelsLLM reasoning → Causal reasoning in LLMs
  99. Attention-Weighted Value Projection for KV-Cache CompressionEfficient LLM inference and serving → KV cache optimization
  100. Revisiting Compositionality in Dual-Encoder Vision-Language Models: The Role of InferenceMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
All 556
  1. Anthropogenic Regional Adaptation in Multimodal Vision-Language ModelMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  2. CAGenMol: Condition-Aware Diffusion Language Model for Goal-Directed Molecular GenerationDiffusion models → Flow matching, time series and science
  3. OOM-RL: Out-of-Money Reinforcement Learning Market-Driven Alignment for LLM-Based Multi-Agent SystemsLLM agents and tool use → Financial trading and forecasting agents +1
  4. Learning How Much to Think: Difficulty-Aware Dynamic MoEs for Graph Node ClassificationMixture-of-experts → MoE for time series and graphs
  5. Degradation-Aware and Structure-Preserving Diffusion for Real-World Image Super-ResolutionDiffusion models → Inverse problems and image restoration
  6. From Attribution to Action: A Human-Centered Application of Activation SteeringMechanistic interpretability → Activation steering methods
  7. Three Roles, One Model: Role Orchestration at Inference Time to Close the Performance Gap Between Small and Large AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  8. To Learn or Not to Learn: A Litmus Test for Using Reinforcement Learning in ControlDeep reinforcement learning methods → Deep RL algorithms and representations
  9. Escaping the Context Bottleneck: Active Context Curation for LLM Agents via Reinforcement LearningLLM agents and tool use → Agent memory systems
  10. Think Before you Write: QA-Guided Reasoning for Character Descriptions in BooksLLM reasoning → Reasoning benchmarks and evaluation
  11. Hardening x402: PII-Safe Agentic Payments via Pre-Execution Metadata FilteringLLM agents and tool use → Agent threats, guardrails and governance
  12. Bridging What the Model Thinks and How It Speaks: Expressive Speech Generation via Self-Aware Intent-Realization AlignmentLLM reasoning → Audio-language model reasoning
  13. Beyond RAG for Cyber Threat Intelligence: A Systematic Evaluation of Graph-Based and Agentic RetrievalLLM agents and tool use → Agent threats, guardrails and governance
  14. Retrieval as Generation: A Unified Framework with Self-Triggered Information PlanningRetrieval-augmented generation → RAG pipeline design and evaluation
  15. One Scale at a Time: Scale-Autoregressive Modeling for Fluid Flow DistributionsDiffusion models → Flow matching, time series and science
  16. Lost in Adaptation: Layer-Selective Recovery of Temporal Reasoning in Video-Language ModelsLLM reasoning → Multimodal reasoning
  17. ComSim: Building Scalable Real-World Robot Data Generation via Compositional SimulationWorld models → Embodied and robot world models
  18. From Agent Loops to Structured Graphs:A Scheduler-Theoretic Framework for LLM Agent ExecutionLLM agents and tool use → Software engineering coding agents
  19. What Do Vision-Language Models Encode for Personalized Image Aesthetics Assessment?Multimodal LLMs / vision-language models → Image editing and quality assessment
  20. Learning from Contrasts: Synthesizing Reasoning Paths from Diverse Search TrajectoriesLLM reasoning → Test-time compute and efficient thinking
  21. The Missing Knowledge Layer in Cognitive Architectures for AI AgentsLLM agents and tool use → Agent memory systems
  22. WM-DAgger: Enabling Efficient Data Aggregation for Imitation Learning with World ModelsWorld models → Embodied and robot world models +1
  23. Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at ScaleDiffusion models → 3D, point cloud and scene generation
  24. CLASP: Closed-loop Asynchronous Spatial Perception for Open-vocabulary Desktop Object GraspingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  25. Learning Discrete Diffusion of Graphs via Free-Energy Gradient FlowsDiffusion models → Diffusion foundations and sampling
  26. The Salami Slicing Threat: Exploiting Cumulative Risks in LLM SystemsLLM safety and security → Jailbreaking
  27. PaperScope: A Multi-Modal Multi-Document Benchmark for Agentic Deep Research Across Massive Scientific PapersMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
  28. BankerToolBench: Evaluating AI Agents in End-to-End Investment Banking WorkflowsLLM agents and tool use → Financial trading and forecasting agents
  29. 3D-Anchored Lookahead Planning for Persistent Robotic Scene Memory via World-Model-Based MCTSWorld models → Embodied and robot world models
  30. Enhancing Multimodal Large Language Models for Ancient Chinese Character Evolution Analysis via Glyph-Driven Fine-TuningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  31. Polyglot Teachers: Evaluating Language Models for Multilingual Synthetic Data GenerationSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  32. Transactional Attention: Semantic Sponsorship for KV-Cache RetentionEfficient LLM inference and serving → KV cache optimization
  33. THEIA: Learning Complete Kleene Three-Valued Logic in a Pure-Neural Modular ArchitectureMechanistic interpretability → Steering and interpreting LLM reasoning
  34. Multimodal Large Language Model-Enabled Video Translation: A Role-Oriented SurveyLLM reasoning → Audio-language model reasoning +1
  35. Evaluating LLM Agents on Automated Software Analysis TasksLLM agents and tool use → Software engineering coding agents
  36. Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference OptimizationLLM agents and tool use → GUI and mobile agents +1
  37. Dialectic-Med: Mitigating Diagnostic Hallucinations via Counterfactual Adversarial Multi-Agent DebateMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  38. Script-a-Video: Deep Structured Audio-visual Captions via Factorized Streams and Relational GroundingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  39. Decoupled Similarity for Task-Aware Token Pruning in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  40. Sign Language Recognition in the Age of LLMsLLM reasoning → Multimodal reasoning +1
  41. HiEdit: Lifelong Model Editing with Hierarchical Reinforcement LearningDeep reinforcement learning methods → RL with diffusion and flow models
  42. Exploring Knowledge Conflicts for Faithful LLM Reasoning: Benchmark and MethodLLM reasoning → Reasoning benchmarks and evaluation +1
  43. Designing Adaptive Digital Nudging Systems with LLM-Driven ReasoningLLM reasoning → Reasoning for agents, planning and code
  44. CocoaBench: Evaluating Unified Digital Agents in the WildLLM agents and tool use → General LLM agent frameworks and benchmarks
  45. MedP-CLIP: Medical CLIP with Region-Aware Prompt IntegrationMultimodal LLMs / vision-language models → Medical vision-language models
  46. TRACE: An Experiential Framework for Coherent Multi-hop Knowledge Graph Question AnsweringLLM reasoning → Knowledge- and tool-augmented reasoning
  47. MathAgent: Adversarial Evolution of Constraint Graphs for Mathematical Reasoning Data SynthesisLLM reasoning → Mathematical reasoning
  48. Probabilistic Prediction of Neural Dynamics via Autoregressive Flow MatchingDiffusion models → Flow matching, time series and science
  49. Do Thought Streams Matter? Evaluating Reasoning in Gemini Vision-Language Models for Video Scene UnderstandingLLM reasoning → Multimodal reasoning +1
  50. Precision Synthesis of Multi-Tracer PET via VLM-Modulated Rectified Flow for Stratifying Mild Cognitive ImpairmentDiffusion models → Medical imaging and segmentation
  51. EmbodiedGovBench: A Benchmark for Governance, Recovery, and Upgrade Safety in Embodied Agent SystemsLLM agents and tool use → Agent threats, guardrails and governance
  52. A Simulation-Based Method for Testing Collaborative Learning Scaffolds Using LLM-Based Multi-Agent SystemsLLM agents and tool use → Educational agents and math problem solving
  53. Environmental Footprint of GenAI Research: Insights from the Moshi Foundation ModelMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  54. Hyper-FEOD: Sparse Hypergraph-Enhanced Frame-Event Object Detection with Fine-Grained MoEMixture-of-experts → Vision mixture-of-experts
  55. From Answers to Arguments: Toward Trustworthy Clinical Diagnostic Reasoning with Toulmin-Guided Curriculum Goal-Conditioned LearningLLM reasoning → Clinical and biomedical applications
  56. BoxTuning: Directly Injecting the Object Box for Multimodal Model Fine-TuningMultimodal LLMs / vision-language models → Video understanding with MLLMs
  57. AIM: Intent-Aware Unified world action Modeling with Spatial Value MapsWorld models → Embodied and robot world models
  58. How Robust Are Large Language Models for Clinical Numeracy? An Empirical Study on Numerical Reasoning Abilities in Clinical ContextsLLM reasoning → Clinical and biomedical applications
  59. Semantic-Geometric Dual Compression: Training-Free Visual Token Reduction for Ultra-High-Resolution Remote Sensing UnderstandingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  60. BITS Pilani at SemEval-2026 Task 9: Structured Supervised Fine-Tuning with DPO Refinement for Polarization DetectionLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  61. DDO-RM: Distribution-Level Policy Improvement after Reward LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  62. Quantum-Gated Task-interaction Knowledge Distillation for Pre-trained Model-based Class-Incremental LearningKnowledge distillation → Graph neural network distillation
  63. Frugal Knowledge Graph Construction with Local LLMs: A Zero-Shot Pipeline, Self-Consistency and Wisdom of Artificial CrowdsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  64. OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic VideoMultimodal LLMs / vision-language models → Video understanding with MLLMs
  65. Bottleneck Tokens for Unified Multimodal RetrievalMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  66. Structured State-Space Regularization for Generation-Friendly Image TokenizationState-space sequence models (S4, Mamba) → Vision Mamba backbones
  67. Guardrails Beat Guidance: A Large-Scale Study of Rules, Skills, and Persistent Configuration for Coding AgentsLLM agents and tool use → Software engineering coding agents +1
  68. RefGlitch-Bench: A Benchmark for Reference-based Gameplay Glitch Detection with Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  69. AI Integrity: A New Paradigm for Verifiable AI GovernanceLLM reasoning → Reasoning benchmarks and evaluation
  70. Pando: Do Interpretability Methods Work When Models Won't Explain Themselves?Mechanistic interpretability → Knowledge and representations inside LLMs
  71. Where Hindsight Credit Can Reside: A Signed-Capacity View of Token Updates in RLVRLLM reasoning → Reinforcement learning for reasoning
  72. LaDA-Band: Language Diffusion Models for Vocal-to-Accompaniment GenerationDiffusion models → Audio, speech and music
  73. Sema Code: Decoupling AI Coding Agents into Programmable, Embeddable InfrastructureLLM reasoning → Reasoning for agents, planning and code +1
  74. From Topology to Trajectory: LLM-Driven World Models For Supply Chain ResilienceWorld models → World models for language agents
  75. RTMC: Step-Level Credit Assignment via Rollout TreesLLM reasoning → Reinforcement learning for reasoning +1
  76. Introspective Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  77. Test-time Scaling over Perception: Resolving the Grounding Paradox in Thinking with ImagesLLM reasoning → Multimodal reasoning +1
  78. Diffusion-CAM: Faithful Visual Explanations for dMLLMsMultimodal LLMs / vision-language models → Image editing and quality assessment
  79. Sanity Checks for Agentic Data ScienceLLM agents and tool use → Web, search, and research agents
  80. TraversalBench: Challenging Paths to Follow for Vision Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  81. ArtiCAD: Articulated CAD Assembly Design via Multi-Agent Code GenerationLLM agents and tool use → Multimodal and embodied agents
  82. MAFIG: Multi-agent Driven Formal Instruction Generation FrameworkLLM agents and tool use → Software engineering coding agents
  83. Back to the Barn with LLAMAs: Evolving Pretrained LLM Backbones in Finetuning Vision Language ModelsLLM reasoning → Multimodal reasoning +1
  84. Energy-oriented Diffusion Bridge for Image Restoration with Foundational Diffusion ModelsDiffusion models → Inverse problems and image restoration
  85. ATANT v1.1: Positioning Continuity Evaluation Against Memory, Long-Context, and Agentic-Memory BenchmarksLLM agents and tool use → Agent memory systems
  86. Tracking High-order Evolutions via Cascading Low-rank FittingDiffusion models → Diffusion foundations and sampling
  87. Robust Adversarial Policy Optimization Under Dynamics UncertaintyDeep reinforcement learning methods → Adversarial robustness and RL in finance
  88. CFMS: A Coarse-to-Fine Multimodal Synthesis Framework for Enhanced Tabular ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  89. MMR-AD: A Large-Scale Multimodal Dataset for Benchmarking General Anomaly Detection with Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  90. YIELD: A Large-Scale Dataset and Evaluation Framework for Information Elicitation AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  91. You Only Judge Once: Multi-response Reward Modeling in a Single Forward PassLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  92. ScoRe-Flow: Complete Distributional Control via Score-Based Reinforcement Learning for Flow MatchingDiffusion models → Diffusion and flow policies for robotics +2
  93. FineEdit: Fine-Grained Image Edit with Bounding Box GuidanceDiffusion models → Image generation, text-to-image and editing
  94. Diffusion Reinforcement Learning Based Online 3D Bin Packing Spatial Strategy OptimizationDeep reinforcement learning methods → RL for robot navigation and UAV control
  95. Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal ModelsLLM reasoning → Multimodal reasoning
  96. AgentWebBench: Benchmarking Multi-Agent Coordination in Agentic WebLLM agents and tool use → Web, search, and research agents
  97. Ro-SLM: Onboard Small Language Models for Robot Task Planning and Operation Code GenerationLLM reasoning → Spatial and embodied reasoning
  98. Mem2Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience DistillationLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  99. HTAA: Enhancing LLM Planning via Hybrid Toolset Agentization & AdaptationLLM agents and tool use → Tool learning and function calling
  100. RouterWise: Joint Resource Allocation and Routing for Latency-Aware Multi-Model LLM ServingEfficient LLM inference and serving → Serving systems and request scheduling
  101. CASK: Core-Aware Selective KV Compression for Reasoning TracesLLM reasoning → Test-time compute and efficient thinking +1
  102. ZoomR: Memory Efficient Reasoning through Multi-Granularity Key Value RetrievalLLM reasoning → Test-time compute and efficient thinking +1
  103. Beyond A Fixed Seal: Adaptive Stealing Watermark in Large Language ModelsLLM safety and security → Watermarking generated content and models
  104. OccuBench: Evaluating AI Agents on Real-World Professional Tasks via Language Environment SimulationLLM agents and tool use → General LLM agent frameworks and benchmarks
  105. LRD-Net: A Lightweight Real-Centered Detection Network for Cross-Domain Face Forgery DetectionDiffusion models → Image generation, text-to-image and editing
  106. AEyeDE: An Attention-Based Attribution Framework for AI-Generated Text Detection
  107. SortingHat: Redefining Operating Systems Education with a Tailored Digital Teaching Assistant
  108. Toward Robust In-Context Learning: Leveraging Out-of-distribution Proxies for Target Inaccessible Demonstration Retrieval
  109. A phenomenon of AI-conformity: how algorithms change human moral decision-making
  110. DraDDP: A Multimodal Multi-Party Dialogue Discourse Parsing Dataset
  111. A Survey of Text and Speech Resources for Hausa and Fongbe: Availability, Quality, and Gaps for NLP Development
  112. DualView: Adaptive Local-Global Fusion for Multi-Hop Document Reranking
  113. MCQ Difficulty Prediction via Modeling Learner Heterogeneity Using Data-Driven Cognitive Profiling
  114. Linguistic Uncertainty and Reply Engagement on X: A Cross-Domain Replication of the Uncertainty-Reply Asymmetry
  115. When AI Tells You What You Want to Hear: Sycophantic Behavior of Large Language Models in Dementia Care Settings
  116. Homoglyph-based Adversarial Perturbation of Introductory Computer Science Theory Problems
  117. A Hormone-inspired Emotion Layer for Transformer language models (HELT)
  118. MorphOPC: Advancing Mask Optimization with Multi-scale Hierarchical Morphological Learning
  119. Confronting Label Indeterminacy in Automated Bail Decisions
  120. FlatASCEND: Autoregressive Clinical Sequence Generation with Continuous Time Prediction and Association-Based Pharmacological Testing
  121. Toward Human-AI Complementarity Across Diverse Tasks
  122. Beyond Sequential Prediction: Learning Financial Market Dynamics in Volatile and Non-Stationary Environments through Sentiment-Conditioned Generative Modelling
  123. Hierarchical RL-MPC Control for Dynamic Wake Steering in Wind Farms
  124. Load constrained wind farm flow control through multi-objective multi-agent reinforcement learning
  125. From Equations to Algorithms and Data: Transforming Microwave Engineering and Education with Machine Learning
  126. HHL with a Coherent Fourier Oracle: A Proof-of-Concept Quantum Architecture for Joint Melody-Harmony Generation
  127. Neuromorphic Continual Learning for Sequential Deployment of Nuclear Plant Monitoring Systems
  128. NL2SQLBench: A Modular Benchmarking Framework for LLM-Enabled NL2SQL Solutions
  129. A Lightweight Transformer for Pain Recognition from Brain Activity
  130. An Uncertainty-Aware Loss Function Incorporating Fuzzy Logic: Application to MRI Brain Image Segmentation
  131. Geometry-Aware CLIP Retrieval via Local Cross-Modal Alignment and Steering
  132. Aletheia: Physics-Conditioned Localized Artifact Attention (PhyLAA-X) for End-to-End Generalizable and Robust Deepfake Video Detection
  133. Saccade Attention Networks: Using Transfer Learning of Attention to Reduce Network Sizes
  134. A Survey of Spatial Memory Representations for Efficient Robot Navigation
  135. Machine learning approaches to uncover the neural mechanisms of motivated behaviour: from ADHD to individual differences in effort and reward sensitivity
  136. MEME-Fusion@CHiPSAL 2026: Multimodal Ablation Study of Hate Detection and Sentiment Analysis on Nepali Memes
  137. Generalization Guarantees on Data-Driven Tuning of Gradient Descent with Langevin Updates
  138. Learning Probabilistic Responsibility Allocations for Multi-Agent Interactions
  139. Synthetic Tabular Generators Fail to Preserve Behavioral Fraud Patterns: A Benchmark on Temporal, Velocity, and Multi-Account Signals
  140. Spectral Entropy Collapse as a Phase Transition in Delayed Generalisation: An Interventional and Predictive Framework for Grokkin
  141. ViLL-E: Video LLM Embeddings for Retrieval
  142. XANE(3): An E(3)-Equivariant Graph Neural Network for Accurate Prediction of XANES Spectra from Atomic Structures
  143. Observing the unobserved confounding through its effects: toward randomized trial-like estimates from real-world survival data
  144. Phantom Paradoxes: Language Models Treat Unresolved Circular Truth Dependence as Contradiction
  145. Long-Horizon Plan Execution in Large Tool Spaces through Entropy-Guided Branching
  146. PR-MaGIC: Prompt Refinement Via Mask Decoder Gradient Flow For In-Context Segmentation
  147. SOLARIS: Speculative Offloading of Latent-bAsed Representation for Inference Scaling
  148. LLM-Based Automated Diagnosis Of Integration Test Failures At Google
  149. Parametric Interpolation of Dynamic Mode Decomposition for Predicting Nonlinear Systems
  150. PC-MIL: Decoupling Feature Resolution from Supervision Scale in Whole-Slide Learning
  151. The Effect of Document Selection on Query-focused Text Analysis
  152. Temporal Flattening in LLM-Generated Text: Comparing Human and LLM Writing Trajectories
  153. LLM-HYPER: Generative CTR Modeling for Cold-Start Ad Personalization via LLM-Based Hypernetworks
  154. A Nonparametric Adaptive EWMA Control Chart for Binary Monitoring of Multiple Stream Processes
  155. INST-Align: Implicit Neural Alignment for Spatial Transcriptomics via Canonical Expression Fields
  156. Human-Inspired Context-Selective Multimodal Memory for Social Robots
  157. Robust Reasoning and Learning with Brain-Inspired Representations under Hardware-Induced Nonlinearities
  158. OpenTME: An Open Dataset of AI-powered H&E Tumor Microenvironment Profiles from TCGA
  159. Robust Explanations for User Trust in Enterprise NLP Systems
  160. Privacy-Preserving Structureless Visual Localization via Image Obfuscation
  161. Interpretable DNA Sequence Classification via Dynamic Feature Generation in Decision Trees
  162. Leveraging Weighted Syntactic and Semantic Context Assessment Summary (wSSAS) Towards Text Categorization Using LLMs
  163. On the continuum limit of t-SNE for data visualization
  164. Simpler Logarithmic Approximation Algorithms for the Optimal Decision Tree and Adaptive Set Cover
  165. Curvelet-Based Frequency-Aware Feature Enhancement for Deepfake Detection
  166. WiseOWL: A Methodology for Evaluating Ontological Descriptiveness and Semantic Correctness for Ontology Reuse and Ontology Recommendations
  167. Convolutional Maximum Mean Discrepancy for Inference in Noisy Data
  168. A Framework for Longitudinal Health AI Agents
  169. LLMs Struggle with Abstract Meaning Comprehension More Than Expected
  170. UCS: Estimating Unseen Coverage for Improved In-Context Learning
  171. When to Forget: A Memory Governance Primitive
  172. BayMOTH: Bayesian optiMizatiOn with meTa-lookahead -- a simple approacH
  173. The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results
  174. Loss-Driven Bayesian Active Learning
  175. Offline-Online Reinforcement Learning for Linear Mixture MDPs
  176. Ultra-low-light computer vision using trained photon correlations
  177. ReefMapGS: Enabling Large-Scale Underwater Reconstruction by Closing the Loop Between Multimodal SLAM and Gaussian Splatting
  178. Exploring Concept Subspace for Self-explainable Text-Attributed Graph Learning
  179. A Geometric Algebra-informed NeRF Framework for Generalizable Wireless Channel Prediction
  180. Multi-Head Residual-Gated DeepONet for Coherent Nonlinear Wave Dynamics
  181. Classification of Epileptic iEEG using Topological Machine Learning
  182. INDOTABVQA: A Benchmark for Cross-Lingual Table Understanding in Bahasa Indonesia Documents
  183. Narrative-Driven Paper-to-Slide Generation via ArcDeck
  184. The Linear Centroids Hypothesis: Features as Directions Learned by Local Experts
  185. Fall Risk and Gait Analysis in Community-Dwelling Older Adults using World-Spaced 3D Human Mesh Recovery
  186. Agentic LLM Reasoning in a Self-Driving Laboratory for Air-Sensitive Lithium Halide Spinel Conductors
  187. Active Imitation Learning for Thermal- and Kernel-Aware LFM Inference on 3D S-NUCA Many-Cores
  188. ResBM: Residual Bottleneck Models for Low-Bandwidth Pipeline Parallelism
  189. A unified data format for managing diabetes time-series data: DIAbetes eXchange (DIAX)
  190. ProbeLogits: Kernel-Level LLM Inference Primitives for AI-Native Operating Systems
  191. EigenCoin: sassanid coins classification based on Bhattacharyya distance
  192. Fast and principled equation discovery from chaos to climate
  193. INTARG: Informed Real-Time Adversarial Attack Generation for Time-Series Regression
  194. A Workflow to Efficiently Generate Dense Tissue Ground Truth Masks for Digital Breast Tomosynthesis
  195. Spectral Structure in Finite Free Information Inequalities and p-Stam Phase Transitions
  196. Can AI Detect Life? Lessons from Artificial Life
  197. V-Nutri: Dish-Level Nutrition Estimation from Egocentric Cooking Videos
  198. How Transformers Learn to Plan via Multi-Token Prediction
  199. Thermodynamic Liquid Manifold Networks: Physics-Bounded Deep Learning for Solar Forecasting in Autonomous Off-Grid Microgrids
  200. Subcritical Signal Propagation at Initialization in Normalization-Free Transformers
  201. Disposition Distillation at Small Scale: A Three-Arc Negative Result
  202. Obtaining Partition Crossover masks using Statistical Linkage Learning for solving noised optimization problems with hidden variable dependency structure
  203. Limitations of Sequence-Based Protein Representations for Parkinson's Disease Classification: A Leakage-Free Benchmark
  204. Who Handles Orientation? Investigating Invariance in Feature Matching
  205. Pair2Scene: Learning Local Object Relations for Procedural Scene Generation
  206. Physics-Informed State Space Models for Reliable Solar Irradiance Forecasting in Off-Grid Systems
  207. Detecting Safety Violations Across Many Agent Traces
  208. OmniShow: Unifying Multimodal Conditions for Human-Object Interaction Video Generation
  209. Saar-Voice: A Multi-Speaker Saarbr"ucken Dialect Speech Corpus
  210. Psychological Concept Neurons: Can Neural Control Bias Probing and Shift Generation in LLMs?
  211. CLSGen: A Dual-Head Fine-Tuning Framework for Joint Probabilistic Classification and Verbalized Explanation
  212. Budget-Aware Uncertainty for Radiotherapy Segmentation QA Using nnU-Net
  213. SyncFix: Fixing 3D Reconstructions via Multi-View Synchronization
  214. C-ReD: A Comprehensive Chinese Benchmark for AI-Generated Text Detection Derived from Real-World Prompts
  215. LottieGPT: Tokenizing Vector Animation for Autoregressive Generation
  216. HDR Video Generation via Latent Alignment with Logarithmic Encoding
  217. GenTac: Generative Modeling and Forecasting of Soccer Tactics
  218. Efficient KernelSHAP Explanations for Patch-based 3D Medical Image Segmentation
  219. Autonomous Diffractometry Enabled by Visual Reinforcement Learning
  220. MosaicMRI: A Diverse Dataset and Benchmark for Raw Musculoskeletal MRI
  221. Retrieval Is Not Enough: Why Organizational AI Needs Epistemic Infrastructure
  222. HistLens: Mapping Idea Change across Concepts and Corpora
  223. Inferring Change Points in Regression via Sample Weighting
  224. KL Divergence Between Gaussians: A Step-by-Step Derivation for the Variational Autoencoder Objective
  225. Discourse Diversity in Multi-Turn Empathic Dialogue
  226. Learning Long-term Motion Embeddings for Efficient Kinematics Generation
  227. Endogenous Information in Routing Games: Memory-Constrained Equilibria, Recall Braess Paradoxes, and Memory Design
  228. Nested Atoms Model with Application to Clustering Big Population-Scale Single-Cell Data
  229. Multimodal Ambivalence/Hesitancy Recognition in Videos for Personalized Digital Health Interventions
  230. Universality of first-order methods on random and deterministic matrices
  231. The Devil is in the Details -- From OCR for Old Church Slavonic to Purely Visual Stemma Reconstruction
  232. Evaluating Cooperation in LLM Social Groups through Elected Leadership
  233. SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context
  234. BEM: Training-Free Background Embedding Memory for False-Positive Suppression in Real-Time Fixed-Background Camera
  235. Seeing Through the Tool: A Controlled Benchmark for Occlusion Robustness in Foundation Segmentation Models
  236. Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction
  237. Fairness is Not Flat: Geometric Phase Transitions Against Shortcut Learning
  238. DreamKG: A KG-Augmented Conversational System for People Experiencing Homelessness
  239. Legal2LogicICL: Improving Generalization in Transforming Legal Cases to Logical Formulas via Diverse Few-Shot Learning
  240. Please Make it Sound like Human: Encoder-Decoder vs. Decoder-Only Transformers for AI-to-Human Text Style Transfer
  241. Unfolding 3D Gaussian Splatting via Iterative Gaussian Synopsis
  242. Towards Brain MRI Foundation Models for the Clinic: Findings from the FOMO25 Challenge
  243. AffordSim: A Scalable Data Generator and Benchmark for Affordance-Aware Robotic Manipulation
  244. NetworkNet: A Deep Neural Network Approach for Random Networks with Sparse Nodal Attributes and Complex Nodal Heterogeneity
  245. UNIGEOCLIP: Unified Geospatial Contrastive Learning
  246. Beyond LLMs, Sparse Distributed Memory, and Neuromorphics <A Hyper-Dimensional SRAM-CAM "VaCoAl" for Ultra-High Speed, Ultra-Low Power, and Low Cost>
  247. A Robust Evaluation of Probe Robustness: Lessons for Reliable OOD Uncertainty Quantification
  248. GPU Acceleration of Sparse Fully Homomorphic Encrypted DNNs
  249. GazeVaLM: A Multi-Observer Eye-Tracking Benchmark for Evaluating Clinical Realism in AI-Generated X-Rays
  250. CodeTracer: Towards Traceable Agent States
  251. Inter-Layer Hessian Analysis of Neural Networks with DAG Architectures
  252. STS-Mixer: Spatio-Temporal-Spectral Mixer for 4D Point Cloud Video Understanding
  253. MorphoFlow: Sparse-Supervised Generative Shape Modeling with Adaptive Latent Relevance
  254. SCNO: Spiking Compositional Neural Operator -- Towards a Neuromorphic Foundation Model for Nuclear PDE Solving
  255. CUTEv2: Unified and Configurable Matrix Extension for Diverse CPU Architectures with Minimal Design Overhead
  256. Symmetry Reveals Layerwise Dynamics: How Transformers Perform In-Context Classification
  257. Utilizing and Calibrating Hindsight Process Rewards via Reinforcement with Mutual Information Self-Evaluation
  258. Intersectional Sycophancy: How Perceived User Demographics Shape False Validation in Large Language Models
  259. Learning Robustness at Test-Time from a Non-Robust Teacher
  260. GeomPrompt: Geometric Prompt Learning for RGB-D Semantic Segmentation Under Missing and Degraded Depth
  261. Computation of Least Trimmed Squares: A Branch-and-Bound framework with Hyperplane Arrangement Enhancements
  262. Hidden Measurement Error in LLM Pipelines Distorts Annotation, Evaluation, and Benchmarking
  263. Seeing Through Touch: Tactile-Driven Visual Localization of Material Regions
  264. Minimizing classical resources in variational measurement-based quantum computation for generative modeling
  265. MIXAR: Scaling Autoregressive Pixel-based Language Models to Multiple Languages and Scripts
  266. Phonological distances for linguistic typology and the origin of Indo-European languages
  267. Training-Free Model Ensemble for Single-Image Super-Resolution via Strong-Branch Compensation
  268. Synthius-Mem: Brain-Inspired Hallucination-Resistant Persona Memory Achieving 94.4% Memory Accuracy and 99.6% Adversarial Robustness on LoCoMo
  269. The Impact of Federated Learning on Distributed Remote Sensing Archives
  270. bacpipe: a Python package to make bioacoustic deep learning models accessible
  271. Progressively Texture-Aware Diffusion for Contrast-Enhanced Sparse-View CT
  272. MimicLM: Zero-Shot Voice Imitation through Autoregressive Modeling of Pseudo-Parallel Speech Corpora
  273. Human Centered Non Intrusive Driver State Modeling Using Personalized Physiological Signals in Real World Automated Driving
  274. SemaClaw: A Step Towards General-Purpose Personal AI Agents through Harness Engineering
  275. NovBench: Evaluating Large Language Models on Academic Paper Novelty Assessment
  276. CLAY: Conditional Visual Similarity Modulation in Vision-Language Embedding Space
  277. TempusBench: An Evaluation Framework for Time-Series Forecasting
  278. Limited Perfect Monotonical Surrogates constructed using low-cost recursive linkage discovery with guaranteed output
  279. PAC-BENCH: Evaluating Multi-Agent Collaboration under Privacy Constraints
  280. Triviality Corrected Endogenous Reward
  281. Generative Path-Finding Method for Wasserstein Gradient Flow
  282. DuET: Dual Execution for Test Output Prediction with Generated Code and Pseudocode
  283. Machine-learning modeling of magnetization dynamics in quasi-equilibrium and driven metallic spin systems
  284. EdgeCIM: A Hardware-Software Co-Design for CIM-Based Acceleration of Small Language Models
  285. Policy Split: Incentivizing Dual-Mode Exploration in LLM Reinforcement with Dual-Mode Entropy Regularization
  286. Not All Forgetting Is Equal: Retention Dynamics in Fine-Tuned Image Classifiers
  287. Deep Learning for Sequential Decision Making under Uncertainty: Foundations, Frameworks, and Frontiers
  288. Lectures on AI for Mathematics
  289. TAG-Head: Time-Aligned Graph Head for Plug-and-Play Fine-grained Action Recognition
  290. ADD for Multi-Bit Image Watermarking
  291. NTIRE 2026 Challenge on Robust AI-Generated Image Detection in the Wild
  292. PACO: Proxy-Task Alignment and Online Calibration for On-the-Fly Category Discovery
  293. On the Complexity of the Discussion-based Semantics in Abstract Argumentation
  294. Structural Consequences of Policy-Based Interventions on the Global Supply Chain Network
  295. Beyond Model Design: Data-Centric Training and Self-Ensemble for Gaussian Color Image Denoising
  296. SLALOM: Simulation Lifecycle Analysis via Longitudinal Observation Metrics for Social Simulation
  297. Low-rank Optimization Trajectories Modeling for LLM RLVR Acceleration
  298. HuiYanEarth-SAR: A Foundation Model for High-Fidelity and Low-Cost Global Remote Sensing Imagery Generation
  299. METRO: Towards Strategy Induction from Expert Dialogue Transcripts for Non-collaborative Dialogues
  300. Emulating Non-Differentiable Metrics via Knowledge-Guided Learning: Introducing the Minkowski Image Loss
  301. Efficient Emotion-Aware Iconic Gesture Prediction for Robot Co-Speech
  302. Exact Certification of Neural Networks and Partition Aggregation Ensembles against Label Poisoning
  303. Observe Less, Understand More: Cost-aware Cross-scale Observation for Remote Sensing Understanding
  304. Online Reasoning Video Object Segmentation
  305. Active Bayesian Inference for Robust Control under Sensor False Data Injection Attacks
  306. GlobalCY I: A JAX Framework for Globally Defined and Symmetry-Aware Neural K"ahler Potentials
  307. SCD4VPR: Multi-modal Scene Change Detection for Long-term Visual Place Recognition Database Update
  308. GS4City: Hierarchical Semantic Gaussian Splatting via City-Model Priors
  309. EagleVision: A Multi-Task Benchmark for Cross-Domain Perception in High-Speed Autonomous Racing
  310. Video-based Heart Rate Estimation with Angle-guided ROI Optimization and Graph Signal Denoising
  311. Beyond Reconstruction: Reconstruction-to-Vector Diffusion for Hyperspectral Anomaly Detection
  312. ConvFormer3D-TAP: Phase/Uncertainty-Aware Front-End Fusion for Cine CMR View Classification Pipelines
  313. From Redaction to Restoration: Deep Learning for Medical Image Anonymization and Reconstruction
  314. Minimal Embodiment Enables Efficient Learning of Number Concepts in Robot
  315. CoRe-ECG: Advancing Self-Supervised Representation Learning for 12-Lead ECG via Contrastive and Reconstructive Synergy
  316. LEADER: Learning Reliable Local-to-Global Correspondences for LiDAR Relocalization
  317. LoGo-MR: Screening Breast MRI for Cancer Risk Prediction by Efficient Omni-Slice Modeling
  318. Geometry-Aware Localized Watermarking for Copyright Protection in Embedding-as-a-Service
  319. Governance by Design: A Parsonian Institutional Architecture for Internet-Wide Agent Societies
  320. Dynamic Summary Generation for Interpretable Multimodal Depression Detection
  321. A Compact and Efficient 1.251 Million Parameter Machine Learning CNN Model PD36-C for Plant Disease Detection: A Case Study
  322. Select Smarter, Not More: Prompt-Aware Evaluation Scheduling with Submodular Guarantees
  323. BRIDGE and TCH-Net: Heterogeneous Benchmark and Multi-Branch Baseline for Cross-Domain IoT Botnet Detection
  324. Do LLMs Know Tool Irrelevance? Demystifying Structural Alignment Bias in Tool Invocations
  325. S3: Structured Sparsity Specification
  326. Collective Opinion Dynamics in Structured LLM Populations
  327. Learning to Forget -- Hierarchical Episodic Memory for Lifelong Robot Deployment
  328. Beyond Fixed False Discovery Rates: Post-Hoc Conformal Selection with E-Variables
  329. The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping
  330. Consistency of AI-Generated Exercise Prescriptions: A Repeated Generation Study Using a Large Language Model
  331. A Deep Equilibrium Network for Hyperspectral Unmixing
  332. Representation-Aligned Multi-Scale Personalization for Federated Learning
  333. Dynamic Sheaf Diffusion Networks with Adaptive Local Structure for Heterogeneous Spatio-Temporal Graph Learning
  334. Mycelium-Index: A Streaming Approximate Nearest Neighbor Index with Myelial Edge Decay, Traffic-Driven Reinforcement, and Adaptive Living Hierarchy
  335. AbLWR:A Context-Aware Listwise Ranking Framework for Antibody-Antigen Binding Affinity Prediction via Positive-Unlabeled Learning
  336. Signal-Aware Conditional Diffusion Surrogates for Transonic Wing Pressure Prediction
  337. Inspectable AI for Science: A Research Object Approach to Generative AI Governance
  338. Unified Graph Prompt Learning via Low-Rank Graph Message Prompting
  339. Trustworthy Feature Importance Avoids Unrestricted Permutations
  340. Variational Latent Entropy Estimation Disentanglement: Controlled Attribute Leakage for Face Recognition
  341. Evolving Many Worlds: Towards Open-Ended Discovery in Petri Dish NCA via Population-Based Training
  342. Judge Like Human Examiners: A Weighted Importance Multi-Point Evaluation Framework for Generative Tasks with Long-form Answers
  343. Bridging the RGB-IR Gap: Consensus and Discrepancy Modeling for Text-Guided Multispectral Detection
  344. RUMLEM: A Dictionary-Based Lemmatizer for Romansh
  345. Seg2Change: Adapting Open-Vocabulary Semantic Segmentation Model for Remote Sensing Change Detection
  346. NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: AI Flash Portrait (Track 3)
  347. RECIPER: A Dual-View Retrieval Pipeline for Procedure-Oriented Materials Question Answering
  348. Regional Explanations: Bridging Local and Global Variable Importance
  349. H-SPAM: Hierarchical Superpixel Anything Model
  350. Measuring the Authority Stack of AI Systems: Empirical Analysis of 366,120 Forced-Choice Responses Across 8 AI Models
  351. 3DTV: A Feedforward Interpolation Network for Real-Time View Synthesis
  352. LoViF 2026 Challenge on Human-oriented Semantic Image Quality Assessment: Methods and Results
  353. CapBench: A Multi-PDK Dataset for Machine-Learning-Based Post-Layout Capacitance Extraction
  354. ShapShift: Explaining Model Prediction Shifts with Subgroup Conditional Shapley Values
  355. From Time Series to State: Situation-Aware Modeling for Air Traffic Flow Prediction
  356. Towards Adaptive Open-Set Object Detection via Category-Level Collaboration Knowledge Mining
  357. Taking a Pulse on How Generative AI is Reshaping the Software Engineering Research Landscape
  358. Evaluating Memory Capability in Continuous Lifelog Scenario
  359. NeuVolEx: Implicit Neural Features for Volume Exploration
  360. Development and evaluation of CADe systems in low-prevalence setting: The RARE25 challenge for early detection of Barrett's neoplasia
  361. Do Instance Priors Help Weakly Supervised Semantic Segmentation?
  362. Cost-optimal Sequential Testing via Doubly Robust Q-learning
  363. RADA: Region-Aware Dual-encoder Auxiliary learning for Barely-supervised Medical Image Segmentation
  364. Boxes2Pixels: Learning Defect Segmentation from Noisy SAM Masks
  365. rPPG-VQA: A Video Quality Assessment Framework for Unsupervised rPPG Training
  366. SHARE: Social-Humanities AI for Research and Education
  367. Gradient-Variation Regret Bounds for Unconstrained Online Learning
  368. A Full Compression Pipeline for Green Federated Learning in Communication-Constrained Environments
  369. Hierarchical Textual Knowledge for Enhanced Image Clustering
  370. Naka-GS: Naka-Guided Chroma Correction and Point-Prior Compaction for Low-Light 3D Gaussian Splatting
  371. Reducing Hallucination in Enterprise AI Workflows via Hybrid Utility Minimum Bayes Risk (HUMBR)
  372. ViserDex: Visual Sim-to-Real for Robust Dexterous In-hand Reorientation
  373. MADQRL: Distributed Quantum Reinforcement Learning Framework for Multi-Agent Environments
  374. DeCoVec: Building Decoding Space based Task Vector for Large Language Models via In-Context Learning
  375. A Proposed Biomedical Data Policy Framework to Reduce Fragmentation, Improve Quality, and Incentivize Sharing in Indian Healthcare in the era of Artificial Intelligence and Digital Health
  376. Persona Non Grata: Single-Method Safety Evaluation Is Incomplete for Persona-Imbued LLMs
  377. Distributionally Robust K-Means Clustering
  378. Use of AI Tools: Guidelines to Maintain Academic Integrity in Computing Colleges
  379. Record-Remix-Replay: Hierarchical GPU Kernel Optimization using Evolutionary Search
  380. ActorMind: Emulating Human Actor Reasoning for Speech Role-Playing
  381. Generating Hadamard matrices with transformers
  382. Efficient Transceiver Design for Aerial Image Transmission and Large-scale Scene Reconstruction
  383. CDPR: Cross-modal Diffusion with Polarization for Reliable Monocular Depth Estimation
  384. Efficient Training for Cross-lingual Speech Language Models
  385. E2E-REME: Towards End-to-End Microservices Auto-Remediation via Experience-Simulation Reinforcement Fine-Tuning
  386. LDEPrompt: Layer-importance guided Dual Expandable Prompt Pool for Pre-trained Model-based Class-Incremental Learning
  387. CausalGaze: Unveiling Hallucinations via Counterfactual Graph Intervention in Large Language Models
  388. FlowCoMotion: Text-to-Motion Generation via Token-Latent Flow Modeling
  389. MapATM: Enhancing HD Map Construction through Actor Trajectory Modeling
  390. ReSpinQuant: Efficient Layer-Wise LLM Quantization via Subspace Residual Rotation Approximation
  391. Towards Proactive Information Probing: Customer Service Chatbots Harvesting Value from Conversation
  392. Hodoscope: Unsupervised Monitoring for AI Misbehaviors
  393. Lightweight Low-Light Image Enhancement via Distribution-Normalizing Preprocessing and Depthwise U-Net
  394. PRISM Risk Signal Framework: Hierarchy-Based Red Lines for AI Behavioral Risk
  395. ks-pret-5m: a 5 million word, 12 million token kashmiri pretraining dataset
  396. A Faster Path to Continual Learning
  397. Shared Emotion Geometry Across Small Language Models: A Cross-Architecture Study of Representation, Behavior, and Methodological Confounds
  398. A Systematic Analysis of the Impact of Persona Steering on LLM Capabilities
  399. EmergentBridge: Improving Zero-Shot Cross-Modal Transfer in Unified Multimodal Embedding Models
  400. Improving Layout Representation Learning Across Inconsistently Annotated Datasets via Agentic Harmonization
  401. Intelligent Approval of Access Control Flow in Office Automation Systems via Relational Modeling
  402. EgoFun3D: Modeling Interactive Objects from Egocentric Videos using Function Templates
  403. Uncertainty-Aware Web-Conditioned Scientific Fact-Checking
  404. Federated Single-Agent Robotics: Multi-Robot Coordination Without Intra-Robot Multi-Agent Fragmentation
  405. Optimal Stability of KL Divergence under Gaussian Perturbations
  406. Brief2Design: A Multi-phased, Compositional Approach to Prompt-based Graphic Design
  407. NimbusGuard: A Novel Framework for Proactive Kubernetes Autoscaling Using Deep Q-Networks
  408. UHD-GPGNet: UHD Video Denoising via Gaussian-Process-Guided Local Spatio-Temporal Modeling
  409. Min-k Sampling: Decoupling Truncation from Temperature Scaling via Relative Logit Dynamics
  410. K-Way Energy Probes for Metacognition Reduce to Softmax in Discriminative Predictive Coding Networks
  411. Byte-level generative predictions for forensics multimedia carving
  412. Data-Efficient Semantic Segmentation of 3D Point Clouds via Open-Vocabulary Image Segmentation-based Pseudo-Labeling
  413. Towards Realistic 3D Emission Materials: Dataset, Baseline, and Evaluation for Emission Texture Generation
  414. Panoptic Pairwise Distortion Graph
  415. Flow-Controlled Scheduling for LLM Inference with Provable Stability Guarantees
  416. When Valid Signals Fail: Regime Boundaries Between LLM Features and RL Trading Policies
  417. LumiMotion: Improving Gaussian Relighting with Scene Dynamics
  418. Examining EAP Students' AI Disclosure Intention: A Cognition-Affect-Conation Perspective
  419. When Verification Fails: How Compositionally Infeasible Claims Escape Rejection
  420. WebForge: Breaking the Realism-Reproducibility-Scalability Trilemma in Browser Agent Benchmark
  421. Enabling and Inhibitory Pathways of Students' AI Use Concealment Intention in Higher Education: Evidence from SEM and fsQCA
  422. Neural Generalized Mixed-Effects Models
  423. Using Deep Learning Models Pretrained by Self-Supervised Learning for Protein Localization
  424. Towards Automated Solar Panel Integrity: Hybrid Deep Feature Extraction for Advanced Surface Defect Identification
  425. Learning to Test: Latent Representation Learning for Dynamic Instability Detection
  426. bioLeak: Leakage-Aware Modeling and Diagnostics for Machine Learning in R
  427. Delving Aleatoric Uncertainty in Medical Image Segmentation via Vision Foundation Models
  428. RAG-KT: Cross-platform Explainable Knowledge Tracing with Multi-view Fusion Retrieval Generation
  429. Continuous-time Online Learning via Mean-Field Neural Networks: Regret Analysis in Diffusion Environments
  430. A molecular clock for writing systems reveals the quantitative impact of imperial power on cultural evolution
  431. Hypergraph Neural Diffusion: A PDE-Inspired Framework for Hypergraph Message Passing
  432. UniPROT: Uniform Prototype Selection via Partial Optimal Transport with Submodular Guarantees
  433. Bootstrapping Video Semantic Segmentation Model via Distillation-assisted Test-Time Adaptation
  434. Learning to Adapt: In-Context Learning Beyond Stationarity
  435. Progressive Deep Learning for Automated Spheno-Occipital Synchondrosis Maturation Assessment
  436. Generative Design for Direct-to-Chip Liquid Cooling for Data Centers
  437. AmodalSVG: Amodal Image Vectorization via Semantic Layer Peeling
  438. QShield: Securing Neural Networks Against Adversarial Attacks using Quantum Circuits
  439. LiveGesture Streamable Co-Speech Gesture Generation Model
  440. From Words to Widgets for Controllable LLM Generation
  441. CSPO: Alleviating Reward Ambiguity for Structured Table-to-LaTeX Generation
  442. ReXSonoVQA: A Video QA Benchmark for Procedure-Centric Ultrasound Understanding
  443. TAMISeg: Text-Aligned Multi-scale Medical Image Segmentation with Semantic Encoder Distillation
  444. EvoNash-MARL: A Closed-Loop Multi-Agent Reinforcement Learning Framework for Medium-Horizon Equity Allocation
  445. STGV: Spatio-Temporal Hash Encoding for Gaussian-based Video Representation
  446. Reasoning as Data: Representation-Computation Unity and Its Implementation in a Domain-Algebraic Inference Engine
  447. Audio Flamingo Next: Next-Generation Open Audio-Language Models for Speech, Sound, and Music
  448. Evaluating the Impact of Medical Image Reconstruction on Downstream AI Fairness and Performance
  449. EviRCOD: Evidence-Guided Probabilistic Decoding for Referring Camouflaged Object Detection
  450. Product Review Based on Optimized Facial Expression Detection
  451. Ambiguity Detection and Elimination in Automated Executable Process Modeling
  452. DIB-OD: Preserving the Invariant Core for Robust Heterogeneous Graph Adaptation via Decoupled Information Bottleneck and Online Distillation
  453. Compliant But Unsatisfactory: The Gap Between Auditing Standards and Practices for Probabilistic Genotyping Software
  454. AOP-Smart: A RAG-Enhanced Large Language Model Framework for Adverse Outcome Pathway Analysis
  455. A Quantitative Definition of Intelligence
  456. Beyond Statistical Co-occurrence: Unlocking Intrinsic Semantics for Tabular Data Clustering