mlsanityData to 14 Oct 2026

Papers

New on arXiv

Mon 29 Jun 2026

536 papers

  1. CARE: Causally-Aligned Reasoning Exploration for Medical Large Language ModelsLLM reasoning → Clinical and biomedical applications
  2. Decoupled Vision-Language System for Multimodal Understanding and GenerationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  3. EditPPT: Faithful Long-Deck Slide Editing via Structured Tool-Using Multi-Agent with Dual-Modal ValidatorsLLM agents and tool use → Multimodal and embodied agents
  4. Does a Language Server Save Tokens for Coding Agents? A Measurement Methodology and Preliminary StudyLLM agents and tool use → Software engineering coding agents
  5. PIVOT: Preference-based Intervention Vectors for Pedagogical Tutor SteeringLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  6. Autonomous Research Agents: A Survey of AI Scientists and the Verification GapLLM agents and tool use → Web, search, and research agents
  7. Memory Reward Inflation in Self-Improving LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  8. Beyond Block Boundaries: Multi-Block Editing for Diffusion Large Language ModelsDiffusion models → Discrete and text diffusion +1
  9. TRE: Training-Free Hallucination Detection for Diffusion Language ModelsDiffusion models → Medical imaging and segmentation
  10. Preference-based Antibody Expression Ranking: Scaling with Large-scale Weak SupervisionLLM alignment / RLHF / preference optimisation → Preference optimization for molecular design
  11. SPINE: Bridging the Cyber-Physical Gap with Agentic AILLM agents and tool use → Multimodal and embodied agents
  12. ATM: CID-Brokered Pre-Write Admission for Multi-Agent Code Co-SynthesisLLM agents and tool use → Software engineering coding agents
  13. The Organizational Behavior of Agentic AI: Collective Intelligence in Human-Agent WorkflowsLLM agents and tool use → General LLM agent frameworks and benchmarks
  14. AgRefactor: Self-Evolving Agentic Workflow for HLS Compatibility and PerformanceLLM agents and tool use → Software engineering coding agents +1
  15. Quality-Aware Modulation for Diffusion TransformersDiffusion models → Diffusion foundations and sampling
  16. Behavior Cloning is Not All You Need: The Optimality of On-Policy Distillation for Noisy Expert FeedbackOffline RL and imitation learning from data → Imitation learning methods +1
  17. Investigating Multi-Agent Deliberation in LawLLM agents and tool use → Social simulation and multi-agent debate
  18. How Human Feedback Shapes AI-generated Community NotesLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  19. Curvature-Guided Module Localization for Low-Rank Detoxification of Backdoored Large Language ModelsLLM safety and security → Backdoor and data poisoning attacks
  20. Sampling-Based Coordination-Informed Multi-Objective Multi-Robot Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
  21. Training Therapeutic Judges and Multi-Agent Systems for Human-Aligned Mental Health SupportLLM agents and tool use → Medical and scientific domain agents
  22. A Systematic Approach to Multi-Agent AI from Advanced Regulatory Control Theory: Safe and Auditable LLM Operator Agents for Process ControlLLM agents and tool use → General LLM agent frameworks and benchmarks
  23. When Does Learning to Stop Help? A Cost-Aware Study of Early Exits in Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking +1
  24. Test-Time Verification for Text-to-SQL via Outcome Reward ModelsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  25. SyncCache: Exploiting Asymmetric Dynamics for Fast Audio-Driven Portrait AnimationDiffusion models → Audio, speech and music
  26. Contrastive Reflection for Iterative Prompt OptimizationLLM agents and tool use → Web, search, and research agents
  27. Joint Chance Constrained Safe-Optimal ControlDeep reinforcement learning methods → RL theory and sample complexity
  28. Towards Knowledge Alignment in Code LLMs: Contrastive Unlearning for Evolving APIsLLM safety and security → Machine unlearning
  29. Off the Rails: Hijacking the Scoring Head in Generative End-to-End Driving Planners with Safety-Violating Adversarial PerturbationsEnd-to-end autonomous driving → Adversarial scenarios and safety testing
  30. Simple Supervision Is Hard to Beat: A Bitter Lesson from Sparse Target Labels in Domain-Adaptive Object DetectionKnowledge distillation → Detection and dense prediction distillation
  31. Security--Fidelity Tradeoffs: The Hidden Cost of Prompt Injection DefenseLLM safety and security → Prompt injection and agent security
  32. Diffusion-warm sampling of the XY model enables fast thermalization at scaleDiffusion models → Diffusion foundations and sampling
  33. Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems LensLLM agents and tool use → Agent threats, guardrails and governance
  34. Vision-Language Procedural Reasoning for Context-Aware Reward Modeling of Robotic Endovascular Guidewire NavigationLLM reasoning → Clinical and biomedical applications
  35. ViTL: Temporal Logic-Guided Zero-Shot Natural Language Navigation via Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  36. Self-Evolving World Models for LLM Agent PlanningWorld models → World models for language agents +2
  37. GROW2: Grounding Which and Where for Robot Tool UseLLM agents and tool use → Multimodal and embodied agents
  38. Pessimism's Paradox: Conservative Offline Training Amplifies Reward Hacking During Online Adaptation in Reasoning ModelsLLM reasoning → Reinforcement learning for reasoning +1
  39. DOPD: Dual On-policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  40. Scaling the Horizon, Not the Parameters: Reaching Trillion-Parameter Performance with a 35B AgentLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  41. Sequential Planning via Anchored Robotic KeypointsVision-language-action models → Failure recovery and robustness
  42. C2R: Cross-sample Consistency Regularization Mitigates Feature Splitting and Absorption in Sparse AutoencodersMechanistic interpretability → SAE features and their applications
  43. MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent SystemsLLM agents and tool use → Agent threats, guardrails and governance
  44. The Fundamental Limits of Valid Transport Map EstimationDiffusion models → Flow matching, time series and science
  45. SWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding SessionsLLM agents and tool use → Software engineering coding agents
  46. A Multi-task Mixture of Experts Framework for Malware Classification, Packing Detection, and Family AttributionMixture-of-experts → Expert routing strategies
  47. Forensic Trajectory Signatures for Agent Memory Poisoning DetectionLLM agents and tool use → Agent threats, guardrails and governance
  48. TraceLab: Characterizing Coding Agent Workloads for LLM ServingLLM agents and tool use → Software engineering coding agents +1
  49. Linguistic Firewall: Geometry as Defense in Multi-Agent Systems RoutingLLM agents and tool use → General LLM agent frameworks and benchmarks
  50. Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought SupervisionLLM reasoning → Spatial and embodied reasoning +2
  51. MAS-Lab: A Specification-Driven Validation Framework for Reliable Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  52. Learning from Mistakes: Rollout-Retrieval Lifelong Policy Learning for Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  53. Entity Binding Failures in Tool-Augmented AgentsLLM agents and tool use → Tool learning and function calling
  54. μFlow: Leveraging Average Images for Improving Generalisation of Deepfake Faces DetectorsDiffusion models → Image generation, text-to-image and editing
  55. The Illusion of Agentic Complexity in README.md Generation: Evaluating Single-Agent vs. Multi-Agent RAG SystemsRetrieval-augmented generation → RAG for code +1
  56. Staged Hybridisation for Visual Quantum Reinforcement Learning via Knowledge DistillationKnowledge distillation → Graph neural network distillation +1
  57. Regime-Aware Peer Specialization for Robust RAG under Heterogeneous Knowledge ConflictsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  58. On the Faithfulness of Post-Hoc Concept Bottleneck ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  59. MuonSSM: Orthogonalizing State Space Models for Sequence ModelingState-space sequence models (S4, Mamba) → Core SSM architectures for language
  60. Vision-Language-Action Models: Experimental Insights from a Real-World UR5 PlatformVision-language-action models → Generalist VLA models and benchmarks
  61. Collective cooperation without individual fidelity in LLM agentsLLM agents and tool use → Social simulation and multi-agent debate
  62. Internal-State Probes Read the Situation, Not the Action: Three Negative Results for Pre-Action Misalignment MonitoringLLM agents and tool use → Agent threats, guardrails and governance
  63. When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond HorizonOffline RL and imitation learning from data → Imitation learning methods +1
  64. OWMDrive: Causality-Aware End-to-End Autonomous Driving via 4D Occupancy World ModelWorld models → World models for autonomous driving +1
  65. Experience Augmented Policy Optimization for LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  66. Beyond Point Estimates for Glaucoma Visual Field Forecasting with Diffusion ModelsDiffusion models → Medical imaging and segmentation
  67. Diffusion Fine-tuning with Rewarded Moment Matching DistillationDeep reinforcement learning methods → RL with diffusion and flow models
  68. MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-TrainingKnowledge distillation → On-policy and self-distillation for LLMs
  69. Energy-Aware Scheduling for Serverless LLM Serving on Shared GPUsEfficient LLM inference and serving → Serving systems and request scheduling
  70. OmniCoT: A Benchmark for Global and Multi-Step Panoramic ReasoningLLM reasoning → Spatial and embodied reasoning +1
  71. FlowAWR: Online Adaptive Flow Reinforcement via Advantage-Weighted RectificationDeep reinforcement learning methods → RL with diffusion and flow models
  72. MUSE: Unlocking Timestep as Native Task Steering for One-Step Dense PredictionDiffusion models → Diffusion foundations and sampling
  73. FutureNav: Unified World-Action Modeling for Vision-and-Language NavigationWorld models → World models for navigation
  74. CouCE: A Unified Causal Framework for Debiased Deep Metric LearningLLM safety and security → Machine unlearning
  75. DRIFT: Difficulty Routing Self-DIstillation with Rhythm-Gated Exploration and Success BuFfer TrainingKnowledge distillation → On-policy and self-distillation for LLMs
  76. REAR: Test-time Preference Realignment through Reward DecompositionLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  77. UniGP: Taming Diffusion Transformer for Prior-Preserved Unified Generation and PerceptionDiffusion models → Image generation, text-to-image and editing
  78. MCP Server Architecture Patterns for LLM-Integrated ApplicationsLLM agents and tool use → Agent threats, guardrails and governance
  79. Toward an Energy-Optimized Operation of Data Centers Located in Wind Farms Using Reinforcement LearningOffline RL and imitation learning from data → Decision transformers and sequence modeling +1
  80. The Surprising Effectiveness of Video Diffusion Models for Hand Motion ReconstructionDiffusion models → Diffusion and flow policies for robotics
  81. ManimAgent: Self-Evolving Multimodal Agents for Visual EducationLLM agents and tool use → Multimodal and embodied agents +1
  82. DreamForge-World 0.1 Preview: A Low-Compute Real-Time Controllable World ModelWorld models → Video-generation world models and simulators
  83. VisReflect: Latent Visual Reflection for Fine-Grained Perception in Long Visual ContextMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  84. Towards Continual Motion-Language Agents: LoRA Variants for Incremental Motion Understanding and GenerationLLM agents and tool use → Multimodal and embodied agents
  85. When Is a Draft Accepted? A Theory of Acceptance in Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  86. Defending Against Harmful Supervision Hidden in Benign SamplesLLM safety and security → Safety alignment, refusal and guardrails
  87. Intermediate Text Representation Guided Text-to-Image Generation for Enhancing One-and-Only AlignmentDiffusion models → Image generation, text-to-image and editing +1
  88. Multi-Agentic System Leveraging Open-Source LLMs to Mitigate Disinformation ThreatsLLM agents and tool use → Web, search, and research agents
  89. TACO: Tool-Augmented Credit Optimization for Agentic Tool UseLLM agents and tool use → Multimodal and embodied agents
  90. Your Data Manifold is Secretly a Reward Model: Shell-LCC for Text-to-Video GenerationDiffusion models → Video generation +1
  91. Grounding LLM Reasoning under Incomplete Graph EvidenceLLM reasoning → Knowledge- and tool-augmented reasoning
  92. Clarus: Coordinating Autonomous Research Agents toward Web-Scale Scientific CollaborationLLM agents and tool use → Web, search, and research agents
  93. Before Thinking, Learn to Decide: Proactive Routing for Efficient Visual ReasoningLLM reasoning → Multimodal reasoning +1
  94. SHOVIR: A Benchmark for Evaluating Vision Shortcut Learning in Radiology Report GenerationMultimodal LLMs / vision-language models → Medical vision-language models
  95. Domain Adaptation with Adaptive Imagination for Visual Reinforcement Learning under Limited Target DataDeep reinforcement learning methods → RL for robot locomotion and manipulation
  96. DAIN: Dynamic Agent-Based Interaction Network for Efficient and Collaborative Multimodal ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  97. Dynamo: Dynamic Skill-Tool Evolution for Vision-Language AgentsLLM reasoning → Multimodal reasoning +2
  98. Latent Noise Mask for Reducing Visual Redundancy in Multimodal Large Language ModelsLLM reasoning → Multimodal reasoning +1
  99. T2LDM++: A Self-Conditioned Representation Guided Diffusion Model for Realistic Text-to-LiDAR Scene GenerationWorld models → World modeling from LiDAR generation +1
  100. Query-Aware Spreading Activation for Multi-Hop Retrieval over Knowledge GraphsRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
All 536
  1. Does Verbose Chain-of-Thought Really Help? In-Distribution Evidence that Content, Not Length, MattersLLM reasoning → Prompting and chain-of-thought reasoning
  2. SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning GenerationLLM reasoning → Multimodal reasoning
  3. On the Internet, Nobody Knows You're an LLM Bot: Unmasking Web Agents with Multi-Layer FingerprintingLLM agents and tool use → Agent threats, guardrails and governance
  4. Open Problems in Constitutional Preference ReconstructionLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  5. SA-VLA: State-aware tokenizer for improving Vision-Language-Action Models' performanceVision-language-action models → Efficient VLA inference and adaptation
  6. Efficient Retrieval-Augmented Generation via Token Co-occurrence GraphsRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  7. Hierarchical Reinforcement Learning in StarCraft Micromanagement with Influence Maps and Cluster-based ScriptsDeep reinforcement learning methods → RL for games and combinatorial optimization
  8. Discard the Dross and Select the Essential: Pre-query Sample Selection for Black-box Membership Inference AttacksLLM safety and security → Membership inference attacks
  9. Little Brains, Big Feats: Exploring Compact Language ModelsRetrieval-augmented generation → RAG pipeline design and evaluation
  10. Notes on generative modeling: flow matching, diffusion, optimal transport and Schr"odinger bridgeDiffusion models → Flow matching, time series and science
  11. Building Multi-Task Agentic LLMs via Two-Phase DistillationLLM agents and tool use → Reinforcement learning for LLM agents +1
  12. LLM Agents Are Latent Context Managers: Eliciting Self-Managed Context via State ProprioceptionLLM agents and tool use → Agent memory systems
  13. HBM Is Not All You Need: Efficient Disaggregated LLM Serving across Memory-heterogeneous AcceleratorsEfficient LLM inference and serving → Serving systems and request scheduling
  14. Are We Measuring Strategy or Phrasing? The Gap Between Surface- and Approach-Level Diversity in LLM Math ReasoningLLM reasoning → Mathematical reasoning
  15. Be Faithful When Response: Returning Fluent and Grounded Answers for Vision-Language Models Reinforcement LearningLLM reasoning → Multimodal reasoning +1
  16. Beyond Uniform Experts: Cost-Aware Expert Execution for Efficient Multi-Device MoE InferenceMixture-of-experts → Efficient MoE training and inference systems
  17. Exploration and Online Transfer with Behavioral Foundation ModelsDeep reinforcement learning methods → Deep RL algorithms and representations
  18. NeuReasoner: Theory-grounded Mapping of Reasoning Elicitation BoundariesLLM reasoning → Reasoning benchmarks and evaluation
  19. RiverONE: Generating Knowledge-Intensive VLM by Simulated Quantum MachinesMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  20. Variance Reduction on the Camera Axis: Multi-View Score Distillation for 3DDiffusion models → 3D, point cloud and scene generation
  21. DuoMem: Towards Capable On-Device Memory Agents via Dual-Space DistillationLLM agents and tool use → Agent memory systems
  22. Know Before You Fetch: Calibrated Retrieval-Budget Allocation for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  23. SWE-Together: Evaluating Coding Agents in Interactive User SessionsLLM agents and tool use → Software engineering coding agents
  24. SpreadsheetBench 2: Evaluating Agents on End-to-End Business Spreadsheet WorkflowsLLM agents and tool use → Financial trading and forecasting agents
  25. OpenSPM: An Environment-Transferable Robotic Key Spatial Pose Memory and Closed-Loop High-Frequency Flow-Matching Action Generation ModelDiffusion models → Diffusion and flow policies for robotics
  26. RoamFlow: Reinforcement-Aligned One-Step Action MeanFlow Policy for Image-Goal NavigationDeep reinforcement learning methods → RL for robot navigation and UAV control
  27. Towards Physical Intuitions for Alignment Dynamics: A Case Study With Randomness CrystallizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  28. SAGA: Scene-Aware, Goal-Evolving Agents for Long-Horizon Strategy Game PlanningLLM agents and tool use → Reinforcement learning for LLM agents
  29. HippoSpark: An On-Demand Experience System for LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
  30. Can LLM-as-a-Judge Reliably Verify Rubrics in Agentic Scenarios?LLM agents and tool use → General LLM agent frameworks and benchmarks
  31. H-GRPO: Permutation-Invariant Reinforcement Learning for Grounded Visual ReasoningLLM reasoning → Multimodal reasoning +1
  32. MemDelta: Controlled Baselines and Hidden Confounds in Agent Memory EvaluationLLM agents and tool use → Agent memory systems
  33. Pondering the Way: Spatial-perceiving World Action Model for Embodied NavigationWorld models → World models for navigation
  34. Timesteps of Mamba Align with Human Reading TimesState-space sequence models (S4, Mamba) → Core SSM architectures for language
  35. SABER-Math: Automated Benchmark for Information Retrieval Evaluation in MathematicsLLM agents and tool use → Educational agents and math problem solving
  36. Trust Your Instincts: Confidence-Driven Test-Time RL for Vision-Language-Action ModelsVision-language-action models → Reinforcement learning and post-training +2
  37. Same Concept, Different Directions: Cross-Modal Feature Heterogeneity in Sparse AutoencodersMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  38. SafePyramid: A Hierarchical Benchmark for In-context Policy GuardrailingLLM safety and security → Safety alignment, refusal and guardrails
  39. IREU: Identity-Related Encoder-Only Unlearning for Customized Portrait GenerationLLM safety and security → Machine unlearning
  40. LWDrive: Layer-Wise World-Model-Guided Vision-Language Model Planning for Autonomous DrivingWorld models → World models for autonomous driving +3
  41. Clinical Reasoning Graphs: Structured Evaluation of LLM Diagnostic Reasoning Reveals Competence Without ConsistencyLLM reasoning → Clinical and biomedical applications
  42. ARKD: Adaptive Reinforcement Learning-Guided Bidirectional KL Divergence Distillation for Text GenerationKnowledge distillation → Knowledge distillation for LLMs
  43. RoAd-RL: A Unified Library and Benchmark for Robust Adversarial Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
  44. KbSD: Knowledge Boundary aware Self-Distillation for Behavioral Calibration in Agentic SearchLLM agents and tool use → Web, search, and research agents +1
  45. Active Learning for Channel Knowledge Map Construction via Bayesian Inference Diffusion ModelsDiffusion models → Diffusion for compression and wireless
  46. See Only When Needed: Context-Aware Attention Intervention for Mitigating Hallucinations in LVLMsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  47. Theory of Continual Learning Against Data Poisoning AttacksLLM safety and security → Backdoor and data poisoning attacks
  48. Robust Trajectory Distillation: Hybrid Reweighting Meets Teacher-Inspired TargetsKnowledge distillation → On-policy and self-distillation for LLMs
  49. The Forgetting-Retention Dilemma: Certified Unlearning Theory in Continual LearningLLM safety and security → Machine unlearning
  50. HomeDiffusion: Zero-Shot Object Customization with Multi-View Representation Learning for Indoor ScenesDiffusion models → 3D, point cloud and scene generation
  51. Neural Procedural Memory: Empowering LLM Agents with Implicit Activation SteeringLLM agents and tool use → Agent memory systems +1
  52. Experience Graphs: The Data Foundation for Self-Improving AgentsSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
  53. Dual-Flow Reinforcement Learning with State-Aware ExplorationDeep reinforcement learning methods → RL with diffusion and flow models
  54. Nemotron-Labs-Diffusion-Image: Advancing Masked Discrete Diffusion for High-Resolution Image SynthesisDiffusion models → Diffusion foundations and sampling
  55. Consistency as Inductive Bias: Learning Cross-View Invariance for Robust Multimodal ReasoningLLM reasoning → Multimodal reasoning
  56. Making Multimodal LLMs Reliable Chart Data Extractors: A Benchmark and Training FrameworkMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  57. Rethinking Forgery Attacks on Semantic Watermarks in Black-Box Settings: A Geometric Distortion PerspectiveDiffusion models → Robustness, privacy and adversarial aspects
  58. Accelerating Q-learning through Efficient Value-Sharing across ActionsDeep reinforcement learning methods → Deep RL algorithms and representations
  59. Clearer Sight, Fewer Lies: Oriented Pickup Preference Optimization for Multimodal Hallucination MitigationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  60. Concept Removal Guidance: Evidence-Calibrated Negative Guidance for Safe Diffusion SamplingDiffusion models → Robustness, privacy and adversarial aspects +1
  61. The CRISTAL Method: Neurosymbolic analysis from AI-synthesized world modelsWorld models → World models for language agents
  62. MemLeak: Diagnosing Information Leaks in Multimodal Agent MemoryLLM agents and tool use → Agent memory systems
  63. Mandol: An Agglomerative Agent Memory System for Long-Term ConversationsLLM agents and tool use → Agent memory systems
  64. Analytic Concept-Centric Memory for Agentic Embodied ManipulationLLM agents and tool use → Multimodal and embodied agents
  65. CLQT: A Closed-Loop, Cost-Aware, Strategy-Consistent Benchmark for Diagnostic Evaluation of LLM Portfolio-Management AgentsLLM agents and tool use → Financial trading and forecasting agents
  66. Do Recommendation Algorithms Work When Users Are LLM Agents? A Case Study on MoltbookLLM agents and tool use → Agentic recommender systems
  67. GoodDiffusion: Proactive Copyright Protection for Diffusion Bridge Models via Learnable Sample-specific SignaturesLLM safety and security → Watermarking generated content and models
  68. PS-PPO: Prefix-Sampling PPO for Critic-Free RLHFLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  69. DEEPMED Search: An Open-Source Agentic Platform for Medical Deep Research with Introspective VerificationLLM agents and tool use → Medical and scientific domain agents
  70. MicroAgent: Context-Augmented Multi-Agent Framework for Automatic Microservice DecompositionLLM agents and tool use → Software engineering coding agents
  71. DeepTrans Studio: Turning Expert Interventions into Shared Team Knowledge in Agentic Translation WorkflowsLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  72. Simplifying Flow Matching Transformations with Low-Rank Mixture ModelsDiffusion models → Flow matching, time series and science
  73. A Diagnostic Framework and Multi-Evaluator Audit of Evaluator-Driven Preference Dynamics in Self-Adapting LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  74. SEVA: Self-Evolving Verification Agent with Process Reward for Fact AttributionLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  75. Why Struggle with Continuous Latents? Interpretable Discrete Latent Reasoning via Rendered CompressionLLM reasoning → Test-time compute and efficient thinking
  76. ARMOR: Adaptive Retriever Optimization for Low-Resource Telecom Question AnsweringRetrieval-augmented generation → RAG robustness and adaptive retrieval
  77. GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated ScreenshotsLLM agents and tool use → GUI and mobile agents
  78. Toward Secure and Reliable PDDL Formalization of Large Language Models with Planner-in-the-Loop FeedbackLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  79. Can MLLMs Critique Like Humans? Evaluating Open-Ended Aesthetic Reasoning in Multimodal Large Language ModelsLLM reasoning → Multimodal reasoning +1
  80. How LLMs See Creativity: Zero-Shot Scoring of Visual Creativity with Interpretable ReasoningLLM reasoning → Multimodal reasoning +1
  81. Counterfactual Fragility Certificates: Exposing High-Confidence Brittleness under Structured Evidence Failure
  82. Leveraging Generative AI to Design Accessible Interactive Visualizations for Undergraduate Mathematics: A Six-Phase Workflow
  83. Towards Interpretable Depression Detection: Linking Acoustic Features to DSM-5 Indicators
  84. Infrared Hotspot-Guided Early Warning of Lithium-Ion Battery Thermal Runaway Under Mechanical Abuse
  85. Interpretable Information-Decomposed Brain Graph Learning for fMRI-based Disease Diagnosis
  86. Accurate Decoding of Natural Sentences from Non-Invasive Brain Recordings
  87. How sensitive do we want AI to be? Socio-communicative competencies of large language models in healthcare
  88. World Simulator: Queer Erotica and the Absurdity of AI Video Models That Promise the World
  89. CITBench: A Comprehensive Benchmark for Interactive Tabular Data Processing with LLMs
  90. Retrieval, not hallucinations, will be the limiting factor for LLM-based clinical AI tools
  91. CuraWeb: Joint Optimization of Quality, Redundancy, and Diversity for Web-Scale Pretraining Data
  92. Beyond Single-Dimensional Compression: The Compound Sparsity Frontier of Large Language Models
  93. Beyond Output-Space Calibration: Spectral Evidence Bundling for Selective Reliability Estimation in Time-Series Classification
  94. FALCON-Discover: Discovering Concentrated False-Confidence Regions for Calibration
  95. Structure of the Circular-Dyadic Convolution Error
  96. Coordinate Singularities Break Conformal Coverage for Gaze and Head Pose
  97. From Raw Segmentations to Simulation-Ready Cardiac Meshes: An Automated Framework for Anatomical Reconstruction and Virtual Cohort Generation
  98. Fast approximation and learning of binary classification tasks in o-minimal structures using ReLU neural networks
  99. Prompting GPT-5 on Scrum Certification Questions: An Empirical Accuracy Study
  100. Comparing Large Language Models on Scrum Certification-Style Questions: Accuracy, Stability, and Error Patterns
  101. Vertigo Vertigo: Reconstructing a Cinematic Ideal through its Predictive AI Double
  102. Destination-Labeled Self-Looping Systems with Dwell: Intrinsic Characterization, Realization Cost, and Recognition
  103. Measuring Judgment Quality in Natural-Language Explanations: Evidence from Forecasting Tournaments
  104. When Regulation Has Memory: Hysteresis and Control Burden in Artificial Agency
  105. From Propositional to Perceptual Asymmetry: Extending Frictive Policy Optimization to Asymmetric Partial Information Dialogue
  106. Behavioral Governance for Autonomous AI Agents: The AgentBound Framework
  107. PhotoQuilt: Training-Free Arbitrary-Resolution Photomosaics via Bootstrapped Tiled Denoising
  108. HyPOLE: Hyperproperty-Guided Multi-Agent Reinforcement Learning under Partial Observation
  109. Loc2Repair: A Framework for Evaluating the Impact of File-Level Issue Localization in Repo-Level LLM Repair
  110. ElemeNet: Multiscale Molecular Machine Learning with Uncertainty Quantification Across the Periodic Table
  111. Exponential-Family Tensor Completion via Nonconvex Dual Total-Variation Regularization
  112. Linguistic Distancing on Social Media: Indicators of Emotion Regulation Across Age Groups
  113. Neuro-Bayesian-Symbolic Residual Attention Shallow Network: Explainable Deep Learning for Cybersecurity Risk Assessment
  114. Learning Where to Look: A Reinforcement Learning Framework for Robust Micro-Ultrasound Prostate Cancer Detection
  115. Bridging Scientific Heritage: An Arabic--Russian Parallel Corpus and LLM Benchmark for Sustainable Knowledge Transfer
  116. Motion Planning in Compressed Representation Spaces
  117. No Adaptation Without Observation: Observability-Constrained Test-Time Prompt Tuning for LiDAR Semantic Segmentation
  118. Physics-informed Conditional Normalizing Flows for Angles-only Cislunar Orbit Determination
  119. ShardNet: Training Neural Controllers with Hard, Non-Convex Constraints
  120. Personalizing Marketplace Policies with Competing Objectives and Constrained Experiments: Evidence from a Job Marketplace
  121. RoPoLL: Robust Panel of LLM Judges
  122. SGD at the Edge of Stability: Stochastic Stabilization with Large Learning Rates
  123. Conditional Tropical Cyclogenesis Rates via Rare-Event Sampling in a Neural Weather Emulator
  124. Budget-Adaptive Routing: Skipping the Weak When the Strong Answers Anyway
  125. Beyond Clean Text: Evaluating Encoder and Decoder Robustness for Bangla Event Detection in Noisy Text
  126. Why Solve It Twice? Hierarchical Accumulation of Skills for Transfer-Efficient ML Engineering
  127. Structure-Regularized Interpretable TCR-Epitope Prediction
  128. GRAPE: Graph-Augmented Prototype Explanations for Interactive Medical Image Diagnosis
  129. Knowledge-Driven Dimension Estimation from a Single Image -3D Asset Generation Technology for Digital Twin Construction
  130. Dynamic Prediction of Alternating Recurrent Events via Neural Network
  131. The Label Imitation Game: Turing Test Network for Zero-Shot Pseudo-Label Pruning
  132. Beyond expert users: agents should help users construct preferences, not just elicit them
  133. Multilingual Polarization Detection Using Transformer-Based Models with Class Weighting and Threshold Tuning
  134. BayesBench: Evaluating LLM Belief Trajectories Under Multi-Turn Evidence Accumulation
  135. How Can AI Find My Model? A Model-Finding Experimental Study Considering Data Formats, Embeddings, and Retrieval Strategies
  136. A Transferable Learned Temporal Prior for Transmission Reconstruction and Decision-Relevant Uncertainty in Real Outbreak Labels
  137. A Stationary-Distribution Theory for Triplet-Based Plateau Search in Random Forest Ensemble-Size Selection
  138. Partition-Guided Distance Saliency: Bridging Decision and Objective Spaces in Many-Objective Optimization
  139. Geometric Dyson Brownian Motions and the Free Log-Normal Limit for a Non-Square Gaussian Matrix Product
  140. Information Terra: A Narrative-Anchored Semantic-First Projection of Document Embeddings
  141. Separation Capacity of Scattering Networks
  142. Mind the Residual Gap: Probabilistic Downscaling under Real-World Bias
  143. AI-Generated PowerShell Malware: An Experimental Framework and Dataset
  144. When transformers learn "impossible" languages, what do they learn?
  145. When Calibration Rankings Reverse: Accuracy-Controlled Evaluation for Fair Comparison of LLMs
  146. Gradient Smoothing: Coupling Layer-wise Updates for Improved Optimization
  147. AVTok: 1D Unified Tokenization for Holistic Audio-Video Generation
  148. GaussLite: Online Task-Conditioned 3D Gaussian Splatting for Real-Time Robotic Mapping
  149. Using AI Agents to Automate Black-Box Audits of Personalization Algorithms at Scale
  150. Indi-RomCoM: Code-Mixed Benchmark for Evaluating LLMs on Romanized Indic-English Instructions
  151. Predictable GRPO: A Closed-Form Model of Training Dynamics
  152. Revocable Learned State via Process Sidecars
  153. Detecting Audio Deepfakes on the Edge:Lightweight SSL-Based Detection in a Browser Plugin
  154. ReactionAtlas: Ab origine exploration of chemical reaction networks with machine learning
  155. Unveiling Transferability in Trajectory Prediction via Latent Scene Embeddings
  156. A Single Rewrite Suffices: Empirical Lessons from Production Skill Description Optimization
  157. What Drives Interactive Improvement from Feedback?
  158. Streaming Gaussian Encoding for 4D Panoptic Occupancy Tracking
  159. Hierarchical Global Attention (HGA)
  160. Why Do Few-Step Text Latents Fail When Image Latents Work? Non-Commitment at Sharp Categorical Readouts
  161. From Search to Synthesis: Training LLMs as Zero-Shot Workflow Generators
  162. Accelerometry-Derived Digital Biomarkers for Cardiometabolic Risk: A Population-Representative Tabular Benchmark with Uncertainty Quantification
  163. An AI-Based Solution for Secure Service Provisioning in IoT
  164. BEST-RQ-2: Contextualize-Then-Predict, a Two-Step Approach for Self-Supervised Audio Representations
  165. Joint discovery of governing partial differential equations from multi-source datasets by competitive optimization
  166. LUMOS: A Semantic Operating-System Layer for Accessibility-Grounded AI Agents
  167. Modeling Cell-Cycle-Aware Single-Cell Drug Perturbation Responses
  168. DSIP: A Dynamic Coordination Planner for Signal-Free Intersections using Diffusion-Model-Based Multi-Agent Motion Planning
  169. VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes
  170. LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Training
  171. Open-Vocabulary and Referring Segmentation for 3D Gaussians Using 2D Detectors
  172. One-Step Gradient Delay is Not a Barrier for Large-Scale Asynchronous Pipeline Parallel LLM Pretraining
  173. Optimization Dynamics Imprint Semantic Specificity in Contrastive Embedding Norms
  174. Reweighting Framewise Attention in Video Transformers for Facial Expression Understanding
  175. UnfoldArt: Zero-Shot Recovery of Full Articulated 3D Objects from Text or Image
  176. Goku: A Million-Scale Universal Dataset and Benchmark for Instruction-Based Video Editing
  177. Towards in-the-wild Egocentric 3D Hand-Object Pose Estimation
  178. Learning from Reliable Latent Prompts for Visual Recognition with Missing Modalities
  179. Wireless Backdoor Attack and Defense for Semantic Communications over Multiple Access Channel
  180. Words Speak Louder Than Code: Investigating Cognitive Heuristics in LLM-Based Code Vulnerability Detection
  181. A Hybrid Framework For Crypto-Ransomware Detection In Enterprise Shared Storage
  182. Uncertainty-Aware Generation and Decision-Making Under Ambiguity
  183. APRIL-MedSeg: A Modular Medical Image Segmentation Toolbox Embracing Modern Paradigms
  184. Beyond 2D Matching: A Unified Single-Stage Framework for Geometry-Aware Cross-View Object Geo-Localization
  185. Attractor States Emerge in Multi-Turn LLM Conversations
  186. Morphing into Hybrid Attention Models
  187. The Human Creativity Benchmark
  188. Convergence of Continual Learning in Homogeneous Deep Networks
  189. EcoVideo: Entropy-Orchestrated Video Generation Paradigm in Cloud-Edge Dynamics
  190. Poller: Are LLMs Suitable for Evaluating the Poetry Understanding Task?
  191. Bridging the NISQ and Fault-Tolerant Regimes: Generative-ML-Assisted Quantum Selected CI for Molecular Simulations
  192. To Tab or Not to Tab: Measuring Critical Engagement in AI Code Completion Tools Using Behavioral Signals and Attention Checks
  193. StereoGS: Sparse-View 3D Gaussian Splatting via Stereo Priors
  194. Latent Actions from Factorized Transition Effects under Agent Ambiguity
  195. TRACE: Temporal Relationship-Aware Conversational Entrainment Detection in Dyadic Speech
  196. Orca: The World is in Your Mind
  197. ITSPACE: Monotone Gaussian Optimal Transport Updates
  198. HASTE: A Framework for Training-Free, Dynamic, and Steerable Compression of Pre-Trained Convolutional Neural Networks
  199. 3D Scene-Adaptive Trajectory-Controllable Human Image Animation with Camera Movement
  200. Informational Frustration in Neural Manifolds: Shannon Bottlenecks and the Limits of Learnability
  201. High-Resolution Flood Mapping With Sentinel-1 and Sentinel-2 via Misalignment-Robust Cross-Sensor Learning and Generative Despeckling
  202. Muon learns balanced solutions in matrix factorization without slow saddle-to-saddle dynamics
  203. Doubly Robust Adaptive Conformal Inference for Causal Effects Under Temporal Dependence
  204. Discovering Collaboration from Novelty: Random Network Distillation for Clustered Federated Learning
  205. GPU Parallelization Strategies for Forward and Backward Propagation in Shallow Neural Networks: A CUDA-Based Comparative Study
  206. McMg: A Learned Phase-Space Multi-channel Multigrid Preconditioner for Helmholtz Equation
  207. RBE-Flow: Recurrent Bayesian Estimation on Feature Manifolds for Cross-Modal Registration
  208. SIMAX: A Scalable and Interpretable Framework for Multi-Fidelity and Annotated Clinician-Patient Dialogue Simulation
  209. Factorizable Normalizing Flows for parameter-dependent density morphing
  210. Situation Perception: A Necessary Primitive to Artificial Superintelligence
  211. COHORT: Collaborative Orchestration for Hardening via Offensive Replay on Emulated Topologies
  212. PGE-SAM: Prompt-Guided Feature Enhancement for Interactive Segmentation under Degradation
  213. PS-MOT: Cultivating Instance Awareness from Point Seeds for Multi-Object Tracking
  214. Field Order Should Not Matter: Permutation-Invariant Embedding Model Fine-Tuning for Structured Metadata Retrieval
  215. FR-DETR: Frequency and Recurrent Feature Refinement for Robust Object Detection under Adverse Weather
  216. Non-parametric recovery of causal diffusion mechanisms from steady-state observations
  217. HSAP: A Hierarchical Sequence-aware Parallelism for Hybrid-Context Generative Models
  218. Cross-Resolution Semantic Transfer for Robust Text-to-Image Retrieval in Low-Resolution Surveillance
  219. Curvature-Weighted Gradient Diversity: A Noise Measure for Geometry-Adaptive SGD Schedules
  220. Exploring Differences Between Tabular Enterprise Data and Public Benchmarks
  221. SGD Provably Prioritizes a Shortcut Spurious Feature in the XOR Model
  222. The FIL Hypothesis: Inductive Biases Help with Kernel Engineering
  223. Translating Natural Language to Strategic Temporal Specifications via LLMs
  224. Transformer Architectures as Complete Bayes Processes: A Formal Proof in the Measure-Theoretic Kernel Framework
  225. Robust and Efficient Monocular 3D Gaussian SLAM for Kilometer-Scale Outdoor Scenes
  226. CAN We Trust Your Results? A Cross-Dataset Study of Automotive IDS Evaluation
  227. Arko-T: A Foundation Model for Text-to-Structured 3D Generation
  228. Proofs of Ownership for Machine Learning Models
  229. Can LLMs Rank? A Tale of Triads and Triage
  230. Beyond IID: How General Are Tabular Foundation Models, Really?
  231. SA-Homo: Scale Adaptive Homography Estimation for Scale Variation Scenarios
  232. ENC-ODE: Event-level Neurodegenerative Modeling in Continuous Time with Neural ODEs
  233. Model Predictive Current Control with Harmonic Correction for Single-Phase AC-DC EV Charging
  234. Uncovering Salience-Driven Dynamics in Consumer Confidence with Generative Social Simulation
  235. SADL: What to Ignore? A Benchmark for Subject-Aware Distractor Localization
  236. Predict, Reuse, and Repair: Accelerating Dynamic Sparse Attention for Long-Context LLM Decoding
  237. A Stochastic--Geometric Theory of Scaling Laws in Grokking
  238. Scalar Representations of Neural Network Training Dynamics
  239. Whose Side Is Your Agent On? Multi-Party Principal Loyalty in LLM Agents
  240. RenderFormer++: Scalable and Physics-Informed Feed-Forward Neural Rendering
  241. Set-Inclusive Uncertainty Modeling for Robust Brain Tumor Segmentation
  242. Using Large Language Models as Low-Cost Statistical Estimators for Human-Response Data
  243. MaDI-Bench: An End-to-End Data Integration Benchmark
  244. ReactiveBFM: Reactive Closed-Loop Motion Planning Towards Universal Humanoid Whole-Body Control
  245. On the Vulnerability of Parameter-Level Defenses to Model Merging
  246. Learning the structure of open quantum systems
  247. OLIVE: View-Augmented Latent Prediction with Waveform Reconstruction for Speech SSL
  248. Residual-Guided Expert Specialization for Incomplete Multimodal Learning
  249. FastPano3D: Feed-Forward Indoor Panoramic 3D Reconstruction from a Single Image
  250. FFAvatar: Feed-Forward 4D Head Avatar Reconstruction from Sparse Portrait Images
  251. Early Cue Precision Shapes Visual Shortcut Learning in Controlled Cue-Manipulation Benchmarks
  252. A Classifier-Agnostic Zero-Shot Adversarial Attack Detection via CLIP
  253. Sequential Fairness Auditing with Limited Output Access
  254. FlexTab: A Flexible Encoder-Decoder Architecture for In-Context Learning Across Diverse Tabular Tasks
  255. BayesEvolve: Explicit Belief States for Autonomous Scientific Discovery
  256. Local-Minima-Preserving Continuous Relaxation of Ising Problems
  257. Extrapolating from Regularised Solutions for Solving Ill-Conditioned Linear Systems in Machine Learning
  258. Hybrid Active-Online Learning Framework for Label-Efficient Concept Drift Adaptation in Optical Network Failure Detection
  259. Optimizing Image Preparation and Compression for Face Recognition within 1024 Bytes
  260. BrainJanus: A Unified Model for Understanding and Generation across Brain, Vision, and Language
  261. Real-Time Underwater Image Enhancement via Frequency-Guided Dual-Path Attention
  262. TRACE: A Concept Bottleneck Model for Longitudinal 3D Glioblastoma Response Assessment
  263. DialogPII: A multilingual dataset of synthetic dialog transcripts to detect personal information
  264. Highly Data Parallelizable Estimation of the Sliced-Wasserstein Distance Using Cumulative Distribution Functions
  265. A Point Cloud Transformer for Remote Monitoring and Automated Assessment of Physical Rehabilitation Exercises
  266. Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgents
  267. Research Entity Extraction and Topic Detection from UKRI Grant Proposals
  268. Rehearsed Multi-Agent Live Product Demonstrations with Real-Time Voice Question Answering
  269. PromptGNN-sim: Deep Fusion and Alignment of GNN and LLMs for Text-Attributed Graph Learning
  270. KnowsTFM: Knowledge-Informed Fine-Tuning of Small Tabular Foundation Models
  271. EMPATH: A Multilingual Auditor-Judge Benchmark for Safety Evaluation of Emotional-Support Chatbots
  272. Inoculation Adapters: Improved Selective Generalization of Capabilities with Fewer Surprising Backdoors
  273. Curvature-Guided Sheaf Diffusion for Unsupervised Community Detection on Heterophilic Graphs
  274. Semantic-Driven Scale and Spatial Selection for Efficient Cross-Modal Alignment in Referring Remote Sensing Image Segmentation
  275. Comparing Human and Automatic Recognition of Dutch Dysarthric Continuous Speech: A Case Study
  276. CaresAI at CT-DEB26: Detecting Dosing Errors In Clinical Trials Using Domain-Specific Transformer Embeddings and Classification Models
  277. A Distributionally Robust Framework for Learned Reconstructions in Inverse Problems
  278. B3O: Scalable Boltzmann Batch Bayesian Optimization
  279. Characterizing Optimizer-Dependent Training Dynamics Through Hessian Eigenvector Displacement and Localization
  280. From Accuracy to Visual Dependence: Auditing and Filtering Modality Collapse in Traffic VideoQA
  281. EvalSafetyGap: A Hybrid Survey and Conceptual Framework for LLM Evaluation-Safety Failures
  282. Efficient RGB-T Object Detection via Sparse Cross-Modality Fusion
  283. A Multi Center Breast FNAC Whole-Slide Cytology Dataset for AI-Assisted Patch-Wise Classification Using C1 to C5 Reporting Categories
  284. The Many-Body Problem of the Data Centre
  285. Forewarned is Forearmed: When Non-Sequential Embedding Turns Into an Anomaly Detector
  286. From Detecting Agency to Doing Work: Self-Caused Credit Builds a Durable Behavioral Self in a Minimal Spiking Agent
  287. Few-Shot Domain Incremental Learning via Continual Vision-Language Consolidation
  288. DrivenMorph: Bridging Attention Mechanism and Variational Image Registration via Difference Modeling
  289. MirrorCode: AI can rebuild entire programs from behavior alone
  290. HiRes: A Hierarchical Cascaded Method for Resistor Value Identification
  291. CORTEX: High-Quality Cross-Domain Organization of Web-Scale Corpora through Ontological Corpus Graph
  292. Beyond Drug Discovery: The Nanotechnology Molecular Optimization (NMO) Benchmark
  293. Federated Learning with Energy-Based Structured Probabilistic Inference
  294. A Dual-domain Refinement Network with FBP-based Jacobian Learning for Sparse-view Dual-Energy CT Material Decomposition
  295. Physically-Constrained Harmonic Separation for Robust Heart and Respiratory Rate Estimation from Wrist Photoplethysmography
  296. Estimating Grammatical Gender Directions in Contextual Embeddings under Controlled and Natural Contexts
  297. FacePlex: Toward Natural Full-Duplex Conversational Avatars
  298. DNA Language Models: An Assessment of Pre-Training for Fine-Tuning Tasks
  299. Warranted Attention: Learning What to Pass from Attention to Prediction
  300. Robust Strategic Classification under Decision-Dependent Cost Uncertainty
  301. Hyper-Network Neural Functional Maps for Unsupervised Robust 3D Shape Matching
  302. Gravitational Duals from Equations of State II: Large Hierarchies and False Vacua
  303. Automating the Design of Embodied Agent Architectures
  304. LETT-NeXt: A Lightweight RECIST-Guided Model for 3D CT Lesion Segmentation
  305. Structural Certification for Reliable Physical Design with Language Models
  306. Propagation of~Interval Belief Structures and~Imprecise Copulas for~Neural Network Verification
  307. Temporal Feature Extractors in EEG Foundation Models: A Controlled Comparison Including a Pretrained Time-Series Model
  308. SIR: Structured Image Representations for Explainable Robot Learning
  309. CylindTrack: Depth-Aware Cylindrical Motion Modeling for Panoramic Multi-Object Tracking
  310. Information Dynamics of Language Communication
  311. SAT-RTS: A systematic framework for tactical knowledge extraction and visualization-based analysis in real-time strategy games
  312. Tastes without distinction: silicon samples and the synthetic construction of tastes
  313. One Forward Beats Two: InnerZoom for Accurate and Efficient GUI Grounding
  314. Clinical Risk-Aware Multi-Level Grading for Coronary Artery Stenosis through Curved Feature Reconstruction
  315. Online Data Selection for Instruction Tuning via Gaussian Processes
  316. ACPO: Agent-Chained Policy Optimization for Multi-Agent Reinforcement Learning
  317. Predictive Objectives Discard Exogenous Control-Relevant Features: A Controlled Mechanistic Study
  318. Neural Subspace Reallocation: Continual Learning as Retrieval-Based Subspace Memory Management
  319. Data-Driven Energy-Based Learning via Gibbs Measures on Hierarchical Structures
  320. From Failure Taxonomy to Intervention: A Diagnostic Methodology for Industry-Scale AVLM in Video and Live-Streaming Platform Moderation
  321. Emergence of a Shared Canonical Object Frame from In-the-Wild Videos
  322. Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generation
  323. Bridging the Gap Between Image Restoration and Navigational Safety in Hazy Conditions: A New Visibility Estimation Metric for Maritime Surveillance
  324. Argus: Metric Panoramic 3D Reconstruction for Indoor Scenes
  325. Walking in the Implicit: Interactive World Exploration via Neural Scene Representation
  326. Heads, Not Backbones: Output Heads Dominate Architectures on Fat-Tailed Returns
  327. Consensus Clustering of Free-Viewing Gaze Data: New Insights into Human-Information Interaction
  328. CogSENet: Blind Image Deblurring with Blur-Conditioned Semantic Routing and Explicit Frequency Fusion
  329. Cross-Modal Iteration Distillation for Robust IHD Screening: The IDNet Framework and A New Benchmark
  330. MuseBench: Benchmarking Intent-Level Audiovisual Arts Understanding in MLLMs
  331. IBRSteG: Learning a Generalizable Steganography Framework for 3D Gaussian Splatting
  332. Uncertainty Estimation in Pathology Foundation Models via Deep Mutual Learning
  333. OmniDance: Multimodal Driven Dance Video Generation with Large-scale Internet Data
  334. Monte Carlo Energy Aggregation for Mobile 3D Gaussian Splatting
  335. Parametric Skills
  336. Shell-Supervised Gaussian Splatting for Urban Real-to-Sim Reconstruction
  337. SkelEM: Training-Signal Decoupling of Skeleton and Diffusion for Self-supervised Axial Super-Resolution in Volume Microscopy
  338. T3R: Deeper Test-Time Adaptation for Graph Neural Networks via Gradient Rotation
  339. Node-to-Neighborhood Semantic Consistency: Text-Topology Alignment for TAGs Anomaly Detection
  340. GeoEdit: Geometry-Aware Object Editing via Dual-Branch Denoising
  341. SICAGE: Speaker-Independent Culture-Aware Gesture Generation using TED4C-L Dataset
  342. AlgoSkill: Learning to Design Algorithms by Scheduling Human-Like Skills
  343. Rigel: Self-Distilled Score Adaptation for Image and Video Captioning Evaluation
  344. Stabilizing Extrapolation in Looped Transformers via Learned Stochastic Stopping
  345. A multi-architecture study of specificity refinement and false-positive mechanism analysis in prostate MRI
  346. Learning Efficient 4D Gaussian Representations from Monocular Videos with Flow Splatting
  347. Atompack: A Storage and Distribution Layer for Read-Heavy Atomistic ML Training Datasets
  348. First-Order Temporal Logic Tensor Networks
  349. Explainability-Aware Frustum Attack: Exposing Structural Vulnerabilities in LiDAR-Based 3D Object Detectors
  350. IHDec: Divergence-Steered Contrastive Decoding for Securing Multi-Turn Instruction Hierarchies
  351. Exploiting Local Flatness for Efficient Out-of-Distribution Detection
  352. Improved Predictive Performance and Interpretability for Mesomorphic Neural Networks Using Local Fidelity Regularization
  353. Data-Efficient Multimodal Alignment for Histopathology-based Molecular Prediction
  354. Diagnosing and Mitigating Retrieval Bottlenecks in LLM-Based Cold-Start Recommendation
  355. Scene-aware Prediction of Diverse Human Movement Goals
  356. Seeing Touch from Motion: A Unified Modality-Aware Visuo-Tactile Policy with Tactile Motion Correlation
  357. LatentRevise: Learning from Zero-Hit Reasoning
  358. Latent-CURE for Breast Cancer Diagnosis
  359. Bandwidth Selection in Kernel Density Estimation for Model Calibration
  360. DCGrasp: Distance-aware Controllable Grasp Generation
  361. EVAF: A Test-Retest Protocol for Selective Parametric Consolidation
  362. A causal modeling perspective on decision theory
  363. Traffic-CBM: A Structurally Interpretable Multimodal Framework for Encrypted Traffic Classification
  364. CW-B: Class Weighted Boosting Framework for Imbalance Resilient Multi Class Cardiac Phenotyping
  365. StrucTab: A Structured Optimization Framework for Table Parsing
  366. Semi-Supervised Sound Event Detection with Conditional Mixup and Embedding-Level Contrastive Loss
  367. LLM-based Multimodal Personality Recognition via Facial Action Unit-Text Semantic Fusion
  368. Critical Interval MSE: Toward Reliable Offline Validation for Robot Manipulation Policies
  369. Child-Centric Voice Anonymization in Single and Multi-Speaker Speech via Domain-Adapted SSL Models
  370. AdaGrad does not adapt to H"older-smoothness for composite objectives
  371. Golden Hour Divide: Trauma Care Accessibility and Resource Vulnerability in Sri Lanka
  372. Building artificial intelligence virtual tissue (AIVT) for tissue state representation, feature prediction, and dynamic simulation
  373. Decision-Value Attribution in Predict-then-Optimize Systems
  374. Implementation of Hyperelastic Physics-Augmented Neural Networks in the Explicit Finite Element Codes Simcenter Radioss and OpenRadioss with Applications to Impact Events
  375. Unveiling Novelty Evolution in the field of Library and Information Science in China
  376. AI Training Manager: Bounded Closed-Loop Control of Adaptive Training Recipes
  377. SUMO: Segment and Track Any Motion with Nonlinear State Space Models
  378. Beyond Triplet Plausibility: Relation Set Completion in Knowledge Graphs
  379. Exploring Motivations for Algorithm Mention in the Domain of Natural Language Processing: A Deep Learning Approach
  380. Smooth Scaling Laws Hide Stepwise Token Learning
  381. Comparing Chatbot Performance Enhanced with Persistent Homology
  382. RainODE: Continuous-Time Precipitation Forecasting with Latent Neural ODEs
  383. Efficient Visual Pointing for Embodied AI:Agent-Driven Data Synthesis, Cross-Block Attention, and Iterative Correction
  384. Bricker to BRACE: A Bracket Exposure RAW Dataset and Restoration Model for Flicker-Banding
  385. MATCH: Modulating Attention via In-Context Retrieval for Long-Context Transformers
  386. Revealing the Technology Development of Natural Language Processing: A Scientific Entity-Centric Perspective
  387. A Sieve-Accelerated Quadrature Method for Exact Privacy Accounting in the 2020 U.S. Decennial Census
  388. Learning Cross-view Correspondences for Geo-localization on Planetary Surfaces
  389. SrDetection: A Self-Referential Framework for Data Leakage Detection in Code Large Language Models
  390. How Far Can You Get Without a GPU? A Systematic Benchmark of Lightweight Hallucination Detection Across Question Answering, Dialogue, and Summarisation
  391. Multi-Level Distributional Entropy from Flow Summary Statistics for Explainable Network Intrusion Detection
  392. UniTriSplat: A Unified 3D Gaussian Splatting Framework with Uniform Spherical Rasterization for Universal Cameras
  393. Fund2Persona: A Framework for Building and Refining Financial Advisor Personas from Fund Disclosure Data
  394. Are Humans Evolved Instruction Followers? An Underlying Inductive Bias Enables Rapid Instructed Task Learning
  395. What Drives the Inlier-Memorization Effect? A Theory of Outlier Detection via Early Training Dynamics
  396. OP3DSG: Open-Vocabulary Part-Aware 3D Scene Graph Generation for Real-World Environments
  397. HERO: Improving the Reliability and Sensitivity of Generative Model Evaluation Using Historical Data
  398. FalconTrack: Photorealistic Auto-Labeled Perception and Physics-Aware Vision-Based Aerial Tracking
  399. Graph-GSReg: Leveraging 3D Scene Graphs for Gaussian Splatting Registration
  400. UrbanCDNet: Appearance-Robust and Boundary-Aware Bitemporal Change Detection for Korean Urban Building Monitoring
  401. Towards Generalizable and Evidential Nuclear Magnetic Resonance-Based Molecular Structure Elucidation via Large Language Model Agent
  402. GLIP: Graph and LLM Joint Pretraining for Graph-Level Tasks
  403. TopoAgent: An Agentic Framework for Automated Topology Learning in Medical Imaging
  404. MR-IQA: A Unified Margin View of Regression and Ranking for Blind Image Quality Assessment
  405. LEIQ-Assessor: Multi-dimensional Quality Assessment of Low-light Enhanced Images via Multi-task Learning
  406. Managing Map Cardinality in Automatic Disease Classification Mapping: Balancing Precision, Recall and Coverage
  407. Rethinking Generative Reconstruction Attacks against Graph Neural Network Models
  408. HTC-SGA Former: A Hybrid Transformer-CNN Network with Self-Guided Attention and a New Boundary-Weighted Adaptive Loss for Coronary DSA Vessel Segmentation
  409. Fast Numbers, Slow Language: Bridging Quantitative and Qualitative Earnings Signals
  410. How Far Do On-Prem Open LLMs Get on Text-to-SQL? A Cross-Family Size x Technique Frontier on BIRD
  411. Testing hypotheses via orthogonalization
  412. From Trait to Behavior: A Cognitive-Affective Personality System (CAPS) Perspective on Multi-Homing Intention in AIGC Platforms
  413. Optimizing Nursing Care Taxi Dispatch Leveraging Integer Linear Programming Solvers and Machine Learning
  414. ScaleAware-JEPA: Latent Representation for Discovery in Multiscale Physical Fields
  415. Redefining Maritime Anomaly Detection via Equation-Grounded Synthetic Anomalies
  416. The Hidden Cost of Resampling: How Imbalance Correction Degrades Probability Calibration in Tree Ensembles
  417. Diagnosing and Mitigating Context Rot in Long-horizon Search
  418. Optimizing Expert-Designed Crystal Graph Networks for Band-Gap Prediction with an Autonomous LLM Research Loop
  419. AerialMetric: Benchmarking and Adapting UAV Monocular Metric Depth Estimation in the Real World
  420. Accurate Recognition of Pneumonia and COVID-19 by Geometric Shape Normalization of Lung Region using Automatic Landmark Detection and Piecewise Affine Warping
  421. UniVAD v2: Unified Visual Anomaly Detection via Support-Conditioned Boundary Construction
  422. Early Warning Signals for OpenVLA Failure under Visual Distribution Shift
  423. MF-UAVPose6D: A Model-Free Monocular 6-DoF Pose Estimation Framework for Fixed-Wing UAVs
  424. Progressive Self-Supervised Learning with Individualized Community Assignment for Brain Network Analysis
  425. IG-Lens: Exact Additive Probability Attribution Across Transformer Layers via Telescoping Integrated Gradients
  426. A Machine-Verified Proof of a Quantum-Optimization Conjecture
  427. PoseShield: Neural Collision Fields for Human Self-Collision Resolution
  428. CAREBench: A Child-Safety Risk Benchmark for Language Models
  429. Evolutionary Hyperparameter Optimization to Find Lightweight CNN Models for Autonomous Steering
  430. Sample-Efficient Learning of Probabilistic Causes for Reachability in Markov Decision Processes with Probabilistic Guarantees
  431. Learning as Observable Matrix Dynamics: Diffusive Relaxations versus Phase Transitions
  432. I-BBS: Coordinate-Free Inference of Latent Sub-Manifolds Using Random Distance Matrix Theory
  433. MatMMExtract: An Open-Source Pipeline for Panel-Level Extraction of Grounded Image-Text Pairs from Materials Science Literature
  434. Adjusted Wasserstein distances for bridging empirical and true distributions with applications to MDS
  435. Benchmarking Geospatial Foundation Models for Agriculture Applications
  436. Diversity is the Strength of the AI Crowd