mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 10 Jun 2026

496 papers

  1. The Artificial Experimentalist: Discovery and Control of Self-Organizing Phenomena with Autotelic Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  2. StocksTalk: A Voice-Enabled Conversational Agent for Structured Query Generation over Web DataLLM agents and tool use → Financial trading and forecasting agents
  3. Self-Evolving Agents as Dynamic Graph Transformation: A Survey and New PerspectiveLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  4. MemoryForge: Synthesize Lifelong Memory for Human-Like LLM AgentsLLM agents and tool use → Agent memory systems
  5. Structure Over Scale: Schema-Constrained Causal Graphs for RAGRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  6. Closing the Social-Semantic Gap: SPSD for Edge-Based Prompt Compression in Cloud LLM InferenceEfficient LLM inference and serving → Prompt and context compression
  7. When to Trust, How to Distill: Multi-Foundation Model Guidance for Lightweight, Robust Scientific Time Series ForecastingKnowledge distillation → General knowledge distillation methods
  8. Breaking the Solver Bottleneck: Training Task Generators at the Learnable FrontierDeep reinforcement learning methods → RL training of language and agent models
  9. CMIP-Forge: An Agentic System that Retrieves, Computes, and Self-Reviews Climate ScienceLLM agents and tool use → Multimodal and embodied agents
  10. Unifying Acoustic Features and Text with Multimodal LLMs for Neurodegenerative ScreeningMultimodal LLMs / vision-language models → Medical vision-language models
  11. MatchLM2Lite: A Scalable MLLM-to-Lite Framework for Reproduced Content IdentificationKnowledge distillation → Multimodal distillation
  12. The Vision Encoder as a Privacy Boundary: Visual-Token Side Channels in Encoder-Free Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  13. Last But Not Least: Boundary Attention CalibratiON for Multimodal KV Cache CompressionLLM reasoning → Test-time compute and efficient thinking +2
  14. Variational Deep Unfolding with Mamba-Based Nonlocal Modeling for Underwater Image EnhancementState-space sequence models (S4, Mamba) → Mamba for image restoration
  15. Unified KV Pooling to Accelerate Long-Context LLM ServingEfficient LLM inference and serving → KV cache optimization
  16. LoMC: Localized Multidirectional Correction for Refusal Suppression in Routed Foundation ModelsMixture-of-experts → Expert routing strategies
  17. Tiara: A Programmable Line-Rate ISA for Remote Memory AccessEfficient LLM inference and serving → Serving systems and request scheduling
  18. Orchestra-o1: Omnimodal Agent OrchestrationLLM agents and tool use → General LLM agent frameworks and benchmarks
  19. Agent-based models for the evolution of morphological alternation patternsLLM agents and tool use → General LLM agent frameworks and benchmarks
  20. Prefill Awareness in Large Language ModelsLLM safety and security → Safety alignment, refusal and guardrails
  21. GRIP: Feedback-Guided Prompt Retrieval for Large Multimodal ModelsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  22. PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt InjectionsLLM agents and tool use → Agent threats, guardrails and governance +1
  23. Normative Robustness as a Frontier for Non-Verifiable Reasoning in LLMsLLM reasoning → Reasoning benchmarks and evaluation
  24. Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict BehaviorLLM reasoning → Reasoning benchmarks and evaluation
  25. Does AI Reviewer See the Full Picture? Attacking and Defending Multimodal Peer ReviewLLM safety and security → Prompt injection and agent security
  26. A Stabilized Path-Space Approach to Diffusion-Based Posterior SamplingDiffusion models → Inverse problems and image restoration
  27. Smarter Saboteurs, Better Fixers: Scaling & Security in Linear Multi-Agent WorkflowsLLM agents and tool use → Agent threats, guardrails and governance
  28. VLADriveBench: Evaluating CoT-Action Relationship in VLA for Autonomous DrivingLLM reasoning → Chain-of-thought reasoning for driving +2
  29. SMSR: Certified Defence Against Runtime Memory Poisoning in Persistent LLM Agent SystemsRetrieval-augmented generation → Privacy and security of RAG +1
  30. Deployment-Centered Evaluation: Predicting Query-Level Rejection Risk in a Clinical LLM SystemLLM safety and security → Safety alignment, refusal and guardrails
  31. EWAM: An Enhanced World Action Model for Closed-Loop Online Adaptation in Embodied IntelligenceWorld models → Embodied and robot world models
  32. Observable Patterns Are Not Explanations: A Causal-Geometric Analysis of Latent Reasoning ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  33. M*: A Modular, Extensible, Serving System for Multimodal ModelsWorld models → World models for language agents
  34. Fed-FBD: Federated Functional Block Diversification for Isolation, Privacy, and Surgical UnlearningLLM safety and security → Federated unlearning and poisoning
  35. Evoflux: Inference-Time Evolution of Executable Tool Workflows for Compact AgentsLLM agents and tool use → Tool learning and function calling
  36. SalArt-VQA: Diagnosing Whether VLMs Understand Salient Artifacts in Generated ImagesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  37. TrajGenAgent: A Hierarchical LLM Agent for Human Mobility Trajectory GenerationLLM agents and tool use → Multimodal and embodied agents
  38. Individual Control Barrier Functions-Guided Diffusion Model for Safe Offline Multi-Agent Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +1
  39. Keep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  40. "Did you lie?" Evaluating Lie Detectors across Model Scale and Belief-Verified Model OrganismsLLM reasoning → Prompting and chain-of-thought reasoning
  41. PersonaDrive: Human-Style Retrieval-Augmented VLA Agents for Closed-Loop Driving SimulationEnd-to-end autonomous driving → Imitation-learning end-to-end planners +1
  42. Shopping Reasoning Bench: An Expert-Authored Benchmark for Multi-Turn Conversational Shopping AssistantsLLM reasoning → Reasoning for agents, planning and code
  43. Pythagoras-Prover: Advancing Efficient Formal Proving via Augmented Lean FormalisationLLM reasoning → Mathematical reasoning
  44. Analyzing and Improving Fine-grained Preference Optimization in Medical LVLMsMultimodal LLMs / vision-language models → Medical vision-language models +1
  45. Beyond Attack Success Rate: Examining Trigger Leakage in Vision-Language Agentic SystemsLLM agents and tool use → Agent threats, guardrails and governance +1
  46. MARD: Mirror-Augmented Reasoning Distillation for Mechanism-Level Drug-Drug Interaction PredictionLLM reasoning → Clinical and biomedical applications +1
  47. High-Fidelity Two-Step Image Generation via Teacher-Aligned End-to-End DistillationDiffusion models → Diffusion foundations and sampling
  48. Arbor: Tree Search as a Cognition Layer for Autonomous AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  49. AudioX-Turbo: A Unified Framework for Efficient Anything-to-Audio GenerationDiffusion models → Audio, speech and music
  50. Foresight: Iterative Reasoning About Clues that Matter for NavigationLLM reasoning → Spatial and embodied reasoning
  51. Rubric-Guided Self-Distillation: Post-Training Without Rubric VerifiersKnowledge distillation → On-policy and self-distillation for LLMs
  52. Boosting Direct Preference Optimization with PenalizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  53. μVLA: On Recurrent Memory for Partially Observable Manipulation in VLA ModelsVision-language-action models → Reasoning and chain-of-thought in VLA
  54. DynamicPTQ: Mitigating Activation Quantization Collapse via Residual-Stream DynamicsEfficient LLM inference and serving → KV cache quantization
  55. Speculative Rollback Correction for Quality-Diverse Web Agent ImitationLLM agents and tool use → Web, search, and research agents +1
  56. Representing Time Series as Structured Programs for LLM ReasoningLLM reasoning → Time series reasoning
  57. ReCal: Reward Calibration for RL-based LLM RoutingLLM reasoning → Reinforcement learning for reasoning
  58. SAIGuard: Communication-State Simulation for Proactive Defense of LLM Multi-Agent SystemsLLM agents and tool use → Agent threats, guardrails and governance
  59. Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  60. World Pilot: Steering Vision-Language-Action Models with World-Action PriorsWorld models → Embodied and robot world models +1
  61. DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?LLM reasoning → Spatial and embodied reasoning +1
  62. Doc-to-Atom: Learning to Compile and Compose Memory AtomsLLM reasoning → Knowledge- and tool-augmented reasoning
  63. Redesign Mixture-of-Experts Routers with Manifold Power IterationMixture-of-experts → Expert routing strategies
  64. VLGA: Vision-Language-Geometry-Action Models for Autonomous DrivingVision-language-action models → VLA for autonomous driving +1
  65. APPO: Agentic Procedural Policy OptimizationLLM agents and tool use → Reinforcement learning for LLM agents
  66. Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning GeneralizationLLM reasoning → Reinforcement learning for reasoning
  67. UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement LearningLLM agents and tool use → Multimodal and embodied agents
  68. Should LLM Agents Decide in Social Simulations? Comparing Finite-State and LLM-Based Decision PoliciesLLM agents and tool use → Social simulation and multi-agent debate
  69. APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action PoliciesMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  70. Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in RoboticsDiffusion models → Diffusion and flow policies for robotics +1
  71. CHORUS: Decentralized Multi-Embodiment Collaboration with One VLA PolicyVision-language-action models → Generalist VLA models and benchmarks
  72. ALIGNBEAM : Inference-Time Alignment Transfer via Cross-Vocabulary Logit MixingLLM safety and security → Safety alignment, refusal and guardrails
  73. OCELOT: Inference-Leakage Budgets for Privacy-Preserving LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  74. Fourier Features Let Agents Learn High Precision Policies with Imitation LearningLLM reasoning → Spatial and embodied reasoning +1
  75. PROJECTMEM: A Local-First, Event-Sourced Memory and Judgment Layer for AI Coding AgentsLLM agents and tool use → Software engineering coding agents
  76. Slots, Transitions, Loops: Learning Composable World Models for ARCWorld models → World models for language agents
  77. Learning What to Say to Your VLA: Mostly Harmless Vision Language Action Model SteeringVision-language-action models → Generalist VLA models and benchmarks
  78. PianoKontext: Expressive Performance Rendering from Deadpan ContextDiffusion models → Audio, speech and music
  79. CCKS: Consensus-based Communication and Knowledge SharingDeep reinforcement learning methods → RL for games and combinatorial optimization
  80. Holding the FP8 Quality Ceiling at 8-Bit Weights and Activations: INT8 and GGUF Post-Training Quantization of Ideogram 4.0 for Consumer GPUsDiffusion models → Diffusion foundations and sampling
  81. Beyond Fully Random Masking: Attention-Guided Denoising and Optimization for Diffusion Language ModelsDiffusion models → Discrete and text diffusion +1
  82. VOID: Defeating Unauthorized Mimicry in Latent Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects
  83. Reinforcement Learning Disrupts Gradient-Based Adversarial OptimizationDeep reinforcement learning methods → Adversarial robustness and RL in finance
  84. DiffCold: A Diffusion-based Generative Model for Cold-Start Item RecommendationDiffusion models → Diffusion recommenders
  85. VIA-SD: Verification via Intra-Model Routing for Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  86. Multi-Rate Mixture of Experts for Accelerating Liquid Neural Network TrainingMixture-of-experts → MoE theory and gating functions
  87. DrivingAgent: Design and Scheduling Agents for Autonomous Driving SystemsEnd-to-end autonomous driving → Large language models for driving +1
  88. Re-evaluating Confidence Remasking in Masked Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  89. Making Foresight Actionable: Repurposing Representation Alignment in World Action ModelsWorld models → Embodied and robot world models
  90. Which Speech Representation Better Matches Text-Native Reasoning? A Study of Speech-Text Alignment on Frame Rate and RepresentationLLM reasoning → Audio-language model reasoning
  91. LLM-Based User Personas for Recommendations at ScaleLLM reasoning → LLM reasoning for recommendation
  92. InternVideo3: Agentify Foundation Models with Multimodal Contextual ReasoningLLM agents and tool use → Multimodal and embodied agents
  93. Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and ApplicationLLM agents and tool use → General LLM agent frameworks and benchmarks
  94. Beyond Dark Knowledge: Mixup-Based Distillation for Reliable PredictionsKnowledge distillation → General knowledge distillation methods
  95. OpenMedReason: Scientific Reasoning Supervision for Medical Vision-Language ModelsLLM reasoning → Clinical and biomedical applications +1
  96. AerialClaw: An Open-Source Framework for LLM-Driven Autonomous Aerial AgentsLLM agents and tool use → Multimodal and embodied agents
  97. Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse AutoencodersMechanistic interpretability → Sparse autoencoder training and evaluation
  98. ReUnit: Multi-Granularity Visual Unitization for Long Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  99. InDex: Empowering VLA Models with Intent-Conditioned Arm-Hand Coordination for Dexterous ManipulationVision-language-action models → Human-video and latent-action pretraining
  100. DAM-VLA: Decoupled Asynchronous Multimodal Vision Language Action modelMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
All 496
  1. Deep Reinforcement Learning for Adaptive Power Allocation in ISAC Systems with Mobile TargetDeep reinforcement learning methods → RL for energy, networks and operations
  2. World Model Self-Distillation: Training World Models to Solve General TasksWorld models → Latent dynamics models and model-based RL +3
  3. Metadata-Aware Multi-Prompt Reasoning for Zero-Shot Accident UnderstandingLLM reasoning → Chain-of-thought reasoning for driving
  4. KinematicRL: A Sim-to-Real Reinforcement Learning Framework For Social Navigation With Kinodynamic FeasibilityDeep reinforcement learning methods → RL for robot navigation and UAV control
  5. MODF-SIR: A Multi-agent Omni-modal Distilled Framework for Social Intelligence ReasoningLLM reasoning → Reasoning for agents, planning and code +2
  6. Generalization Hacking: Models Can Game Reinforcement Learning by Preventing Behavioral GeneralizationDeep reinforcement learning methods → RL training of language and agent models
  7. Agreement in Representation Space for Open-Ended Self-ConsistencyLLM reasoning → Test-time compute and efficient thinking
  8. PAWS: Preference Learning with Advantage-Weighted SegmentsDeep reinforcement learning methods → RL training of language and agent models
  9. ParseFixer: An Agentic Framework for Document Parsing via Selective Multimodal CorrectionLLM agents and tool use → Web, search, and research agents
  10. Exploration Structure in LLM Agents for Multi-File Change LocalizationLLM agents and tool use → Software engineering coding agents
  11. SpecLoR: Spectral Lookahead Rectification for Motion-Coherent Text-to-Video GenerationDiffusion models → Video generation
  12. Online Shift Detection and Conformal Adaptation for Deployed Safety ClassifiersLLM reasoning → Reasoning for agents, planning and code +1
  13. The Art of Interrogation: Consistency Amplifies Factuality in Spatial ReasoningLLM reasoning → Spatial and embodied reasoning
  14. Tail-Aware Adaptive-k: Query-Adaptive Context Selection for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  15. When Does Language Matter? Multilingual Instructions Reveal Step-wise Language Sensitivity in Vision-Language-Action ModelsVision-language-action models → Failure recovery and robustness
  16. Beyond representational alignment with brain-guided language models for robust reasoningLLM reasoning → Reasoning benchmarks and evaluation
  17. Critic Architecture Matters: Dual vs. Unified Critics for Humanoid Loco-ManipulationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  18. Task-Aligned Stability Analysis of Vision-Language Models for Autonomous Driving Hazard DetectionMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  19. Harnessing Routing Foresight for Micro-step-level MoE load balancing in RL Post-trainingMixture-of-experts → MoE in reinforcement learning and robotics
  20. CORE-Bench: A Comprehensive Benchmark for Code Retrieval in the Era of Agentic CodingLLM agents and tool use → Software engineering coding agents
  21. Fine-tuning Multi-modal LLMs with ART: Art-based Reinforcement TrainingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  22. Task-Aware Structured Memory for Dynamic Multi-modal In-Context LearningMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  23. Plan-and-Verify Video Reward Reasoning with Spatio-Temporal Scene Graph GroundingLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  24. Flow Matching with In-Context Priors for Out-of-Distribution Brain DynamicsDiffusion models → Medical imaging and segmentation
  25. Skill-Augmented AI Agents for Medical Research Analysis: An Exploratory Multi-Model Human Evaluation in an NSCLC Transcriptomic Biomarker TaskLLM agents and tool use → Medical and scientific domain agents
  26. Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious CodeLLM safety and security → Jailbreaking
  27. WorldReasoner: Evaluating Whether Language Model Agents Forecast Events with Valid ReasoningLLM agents and tool use → Financial trading and forecasting agents
  28. Deterministic Policy Gradient for Learning Equilibrium in Time-Inconsistent Control ProblemsDeep reinforcement learning methods → Adversarial robustness and RL in finance
  29. Space-sampled Value Decay: Forgetting Mechanisms for Non-stationary Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  30. MultiToP: Learning to Patch Visual Tokens to Mitigate Hallucinations in Video Large Multimodal ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  31. SVoT: State-aware Visualization-of-Thought for Spatial Reasoning via Reinforcement LearningLLM reasoning → Spatial and embodied reasoning +1
  32. Acoda: Adversarial Code Obfuscation for Defending against LLM-based AnalysisLLM reasoning → Reasoning for agents, planning and code
  33. From Prompts to Tokens: Internalizing Causal Supervision in Vision-Language Model for Multi-Image Causal ReasoningLLM reasoning → Multimodal reasoning +1
  34. TacCoRL: Integrating Tactile Feedback into VLA via SimulationVision-language-action models → Tactile, force-aware and humanoid VLA
  35. Mind the Perspective: Let's Reason Recursively for Theory of MindLLM reasoning → Reasoning benchmarks and evaluation
  36. Ouroboros-Spatial: Closing the Data-Model Loop for Spatial ReasoningLLM reasoning → Spatial and embodied reasoning +1
  37. RLCSD: Reinforcement Learning with Contrastive On-Policy Self-DistillationLLM reasoning → Prompting and chain-of-thought reasoning +2
  38. CompRank: Efficient LLM Reranking via Token-Level Compression and Decoding-Free ScoringRetrieval-augmented generation → Generation and context integration
  39. T2S: A Rehearsal-Based Approach for Extraction-Resistant Model WatermarkingLLM safety and security → Watermarking generated content and models
  40. Evaluation of Alternative-Based Information Systems for Deliberative Polling using an Agentic SimulatorLLM agents and tool use → Social simulation and multi-agent debate
  41. Spectrally Regularized Latent Flow Matching for Turbulence GenerationDiffusion models → Flow matching, time series and science
  42. Goal-Autopilot: A Verifiable Anti-Fabrication Firewall for Unattended Long-Horizon AgentsLLM agents and tool use → Agent threats, guardrails and governance
  43. Layer-Isolated Evaluation: Gating the Deterministic Scaffold of a Production LLM Agent with a No-LLM, Regression-Locked Test HarnessLLM agents and tool use → General LLM agent frameworks and benchmarks
  44. Reason, Then Re-reason: Cross-view Revisiting Improves Spatial ReasoningLLM reasoning → Spatial and embodied reasoning
  45. Organize then Retrieve: Hierarchical Memory Navigation for Efficient AgentsLLM agents and tool use → Agent memory systems
  46. Can AI Reason Like an Urban Planner? Benchmarking Large Language Models Against Professional JudgmentLLM reasoning → Reasoning for agents, planning and code
  47. Lung-R1: A Knowledge Graph-Guided LLM for Pulmonary Diagnostic ReasoningLLM reasoning → Clinical and biomedical applications
  48. Can Open-Source LLM Agents Replace Static Application Security Testing Tools? An Empirical AssessmentLLM agents and tool use → Agent threats, guardrails and governance
  49. Runtime Skill Audit: Targeted Runtime Probing for Agent Skill SecurityLLM agents and tool use → Agent threats, guardrails and governance
  50. Sparse probes and murky physics: a case study of interpretability challenges in a foundation model for continuum dynamicsMechanistic interpretability → Sparse autoencoder training and evaluation
  51. IAPO: Input Attribution-Aware Policy Optimization for Tool Use in Small Multimodal AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  52. Dummy Backdoor as a Defense: Removing Unknown Backdoors via Shared Internal Mechanisms for Generative LLMsLLM safety and security → Backdoor and data poisoning attacks
  53. TouchThinker: Scaling Tactile Commonsense Reasoning to the Open World with Large-scale Data and Action-aware RepresentationLLM reasoning → Spatial and embodied reasoning
  54. Are LLMs Bad at Moral Reasoning?LLM reasoning → Reasoning benchmarks and evaluation
  55. Architecture-Aware Reinforcement Learning Makes Sliding-Window Attention Competitive in Math ReasoningLLM reasoning → Reinforcement learning for reasoning +1
  56. When Context Returns: Toward Robust Internalization in On-Policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  57. Adapting Vision-Language Models from Iconic to Inclusive for Multi-Label Recognition Without LabelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  58. TimeRouter: Efficient and Adaptive Routing of Time-Series Foundation ModelsLLM agents and tool use → Financial trading and forecasting agents
  59. Adv-TGD: Adversarial Text-Guided Diffusion for Face Recognition Impersonation AttacksDiffusion models → Robustness, privacy and adversarial aspects
  60. Multi-Agent Reasoning with Adaptive Worker Allocation for Stance DetectionLLM reasoning → Causal reasoning in LLMs +1
  61. Physics-Distilled Neural Network enabled by Large Language Models for Manufacturing Process-Property Predictive ModelingKnowledge distillation → General knowledge distillation methods
  62. When is Your LLM Steerable?Mechanistic interpretability → Activation steering methods
  63. Distortion-Resilient Robotic Imitation Learning for Autonomous Cable RoutingOffline RL and imitation learning from data → Imitation learning methods
  64. AVIS: Adaptive Test-Time Scaling for Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  65. FreqKD: Frequency-Decoupled Cross-Modal Knowledge Distillation for Infrared Object DetectionKnowledge distillation → Detection and dense prediction distillation
  66. ConsistencyPlanner: Real-time Planning with Fast-Sampling Consistency ModelsDiffusion models → Diffusion and flow policies for robotics
  67. 4DP-QA: Scalable QA for 4D Perception in Vision Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  68. LLMs+Graphs: Toward Graph-Native, Synergistic AI SystemsLLM reasoning → Knowledge- and tool-augmented reasoning
  69. HERO: Hindsight-Enhanced Reflection from Environment Observations for Agentic Self-DistillationLLM agents and tool use → Reinforcement learning for LLM agents +1
  70. VL-DINO: Leveraging CLIP Vision-Language Knowledge for Open-Vocabulary Object DetectioMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  71. SkillJuror: Measuring How Agent Skill Organization Changes Runtime BehaviorLLM agents and tool use → Agent skill learning and evolution
  72. Learning Object Manipulation from Scratch via Contrastive InteractionDeep reinforcement learning methods → RL for robot locomotion and manipulation
  73. Towards Sustainable Hydrogen Systems: Supply Chain Optimization with Model Predictive Control and Reinforcement Learning
  74. Distinguishing Revision and Delayed Elaboration in Incremental Narrative Interpretation
  75. Asymmetric Attention Heads: Structured Head-Wise Context Allocation for Transformer Attention
  76. Same Facts, Different Updates: Inference Setup Shapes LLM Behavior in Medical Allocation
  77. Institutional Prestige as Geographic Bias in Large Language Models: Evidence from Three Factorial Experiments with Bootstrap Confidence Intervals
  78. Different Facets of Verbalised Overconfidence: an Interpretability Study
  79. DeepTCM1.0: A Multi-Expert AI Agent for Deciphering Mechanisms of Chinese Herbal Formulae Based on General Large Language Models
  80. RoCo-ACE: Rollout-Conditioned Online Distillation for Retention-Aware Knowledge Injection
  81. Lexical discovery in unknown environments orchestrated by Large Language Models
  82. DRP-FLR: Data-Driven Assessment of Demand Response Potential for Flexible Load Regulation in Smart Grids
  83. DFAH-Bench: Benchmarking Observable Agent Instability in Financial Decision-Making
  84. Why does AI unlock new possibilities in STEM education? A Bibliometric Analysis of Trends and Future Agenda
  85. The GenAI Skill Bypass: Mapping Divergent Pathways of University Students and Staff AI Literacy
  86. CANONIC: Governance Is Compilation
  87. AI Tokenomics: The Economics of Tokens, Computation, and Pricing in Foundation Models
  88. DrugBench: Evaluating AI Control Protocols for Medication Harm Mitigation
  89. Artemis: Anatomy-Resolved inTervention for Eliminating Multimodal NeuroImage confounderS
  90. CODEBLOCK: Learning to Supervise Code at the Right Granularity
  91. Comprehensive pKa Data Augmentation from Limited Real Data through an Engineered Models-Quantum Framework
  92. Surveying GenAI-based Automation in Printed Circuit Board Design and Test
  93. Extracting Semantics: LLM-Guided Automatic Population of Robot Ontology from URDF
  94. Vision-Encoder Behavioral Fingerprints of Image-to-Image Generative Models: A Training-Paradigm-Driven Taxonomy of Six Commercial APIs
  95. LLM-Based Synthetic Ground Truth Generation for Audio-Based Emotion Classification via In-Context Learning
  96. YTClickbait21K: Human-Annotated Multimodal Dataset for YouTube Clickbait Detection Across Diverse Channels and Content Categories
  97. FactCheck: Feasibility-aware Long-term Action Anticipation with Multi-agent Collaboration
  98. JoyAI-VL-Interaction: Real-Time Vision-Language Interaction Intelligence
  99. Deep Learning-Based Lunar Crater Terrain Relative Navigation
  100. WorkBench Revisited: Workplace Agents Two Years On
  101. TSA: Temporal Slot Activation for Persistent Object-Centric Video Representation
  102. CisTransCell: Single-Cell Perturbation Prediction via Gene Function, Regulatory Control, and Cellular Context
  103. Multimodal Speaker Identification in Classroom Environments
  104. Hybrid Open-Ended Tri-Evolution Makes Better Deep Researcher
  105. LLMs Can Better Capture Human Judgments--With the Right Prompts
  106. Reducing the Complexity of Deep Learning Models for EEG Analysis on Wearable Devices
  107. Deep Unfolded Latent Optimally Partitioned-l2/l1 Networks for Data-driven Block-Sparse Recovery
  108. Benchmarking AI Agents for Addressing Scientific Challenges Across Scales
  109. Physics-Informed Neural Networks and Radial Basis Functions for PDEs with Dirac Delta Sources
  110. Let's Ask Gauss: Improved One-Run Privacy Auditing
  111. EquiDexFlow: Contact-Grounded SE(3)-Equivariant Dexterous Grasp Generative Flows
  112. The Theory of Mind Utility: A Formal Account of Mentalizing
  113. On McDiarmid's Inequality under Dependence via Approximate Tensorization of Entropy
  114. Out-of-Distribution (OOD) Detectors for Open-Set RF Fingerprinting
  115. Definitional alignment before capability alignment: a Design-Science framework for adjudicating claims about AGI
  116. AfriSUD: A Dependency Treebank Collection for Evaluating Models on African Languages
  117. LLM-Powered Personalized Glycemic Assessment in Type 2 Diabetes with Wearable Sensor Data
  118. A unified complexity bound for logconcave sampling
  119. Two-Layer Linear Auto-Regressive Models Estimate Latent States
  120. Forecasting Is Not Attribution: Localizing Decoder Bypass in Graph-Based Neural Marketing Mix Models
  121. From AGI to ASI
  122. How Useful is Causal Invariance for Domain Adaptation in Finite-Sample Settings?
  123. A Zero-shot Generalized Graph Anomaly Detection Framework via Node Reconstruction
  124. Free-Placement Optimization of Ground Station Locations for Low-Earth Orbit Satellites
  125. CAPED: Context-Aware Privacy Exposure Defense for Mobile GUI Agents
  126. BASENet: Band-Adapted Speech Enhancement Network with Cross-Band Attention
  127. Physics-Informed Neural Networks for Chemotherapy Pharmacokinetics: Benchmarking the Clinical Estimator and Exposing Parameter Identifiability
  128. Amnesia: A Stealthy Replay Attack on Continual Learning Dreams
  129. Computationally tractable robust differentially private mean estimation
  130. Physics-Aware Auxiliary Losses Improve Out-of-Distribution Generalization of a GNN Synthesizability Filter
  131. MentalMARBERT: Domain-Adaptive Pre-training and Two-Stage Fine-Tuning for Arabic Mental Health Disorders Detection
  132. Token Complexity Theory for AI-Augmented Computing
  133. Epistemic Uncertainty Is Not the Reducible Kind
  134. TEDD: Robust Detection of Unstable Temporal Features
  135. The Metric Picks the Winner: Evaluation Choice Flips Model Rankings for Drug-Response Prediction in Unseen Chemistry
  136. CD-RCM: Generalizable Continuous-Depth Novel View Synthesis for Reflectance Confocal Microscopy
  137. ECA: Efficient Continual Alignment for Open-Ended Image-to-Text Generation
  138. The Signs Were Always There: Training-Free Concept Detection and Steering in Raw Transformer Dimensions
  139. Context-Aware Feature-Fusion for Co-occurring Object Detection in Autonomous Driving
  140. Estimating Individualized Treatment Effects in Acute Ischemic Stroke with Causal Transformation Models (TRAM-DAG): A Multi-Centre Observational Study with External RCT Validation
  141. HybridCodeAuthorship: A Benchmark Dataset for Line-Level Code Authorship Detection
  142. Towards Provably Fair Machine Learning: Bayesian Approaches For Consistent and Transparent Predictions
  143. Evaluation of AutoML Frameworks for IDS under Imbalanced Data Conditions of the NSL-KDD Dataset
  144. The Mathematics of AI Winters: The mathematical Taxonomy of Paradigm Fragility in AI Winter
  145. Viral Proteins Reveal Geometry of Protein Language Models
  146. From Imitation to Alignment: Human-Preference Flow Policies for Long-Horizon Sidewalk Navigation
  147. Dual-State Slot Attention: Decoupling Appearance and Identity for Video Object-Centric Learning
  148. Constrained Semantic Decompression in LLMs through Persian Proverb-Conditioned Story Generation
  149. Emerging Flexible Designs for Geospatial Multimodal Foundation Models
  150. Strategic Decision Support for AI Agents
  151. Graph Reduction in Multirelational Networks: A Spreading-Oriented Reduction Benchmark
  152. Helping Figures Tell their Story! Paper-Grounded Video Generation Explaining Complex Scientific Figures
  153. eCREAM-MedCorpus A Large-Scale Corpus of Clinical Notes for Italian
  154. HairPort: In-context 3D-aware Hair Import and Transfer for Images
  155. Feature-preserving Latent-EnKF for Data Assimilation of Flows with Shocks
  156. Crossing the Validation Crisis: Cross-Validation Reduces Benchmarking Variance Surprisingly Well
  157. Dolph2Vec: Self-Supervised Representations of Dolphin Vocalizations
  158. A Mathematical Theory of Value: a synthesis on goal-directed agency under resource constraints
  159. Policy-driven Conformal Prediction for Trustworthy QoT Estimation
  160. Improving Crash Frequency Prediction from Simulated Traffic Conflicts Using Machine Learning Based Microsimulation
  161. From Parameters to Feature Space: Task Arithmetic for Backdoor Mitigation in Model Merging
  162. Net-Ev2: A Generative Simulator for Network Event Evolution
  163. Robustness Verification of Recurrent Neural Networks with Abstraction Refinement
  164. Masked Neural Detection for Run-Length-Limited Channel Coding in Molecular Communication
  165. A Stationary (and Therefore Compatible) Representation is All You Need
  166. An Empirical Study on Predictive Maintenance for Component X in Heavy-Duty Scania Trucks
  167. Scalable anomaly detection via a univariate Christoffel function
  168. Boltzmann Attention: Learnable Ising Couplings for Cooperative Attention
  169. Quickest Detection of Hallucination Onset: Delay Bounds and Learned CUSUM Statistics
  170. Stereo Vision-Based Fall Prediction and Detection using Human Pose Estimation on the AMD Kria K26 SOM
  171. Context-Driven Incremental Compression for Multi-Turn Dialogue Generation
  172. How Seemingly Inconsequential Design Choices Dictate Performance of LLMs in Pathology
  173. FACTR 2: Learning External Force Sensing for Commodity Robot Arms Improves Policy Learning
  174. System Report for CCL25-Eval Task 5: New Dataset and LoRA-Fine-Tuned Qwen2.5
  175. TAHOE: Text-to-SQL with Automated Hint Optimization from Experience
  176. ATLAS: Active Theory Learning for Automated Science
  177. Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMs
  178. SPEA2^+: Improved Density Estimation in SPEA2 with Provable Runtime Guarantees
  179. Illumination-Robust Camera-Based Heart-Rate Estimation for Physiological Sensing in Robots
  180. Semantically-Aware Diver Activity Recognition Framework for Effective Underwater Multi-Human-Robot Collaboration
  181. A Turbo-Inference Strategy for Object Detection and Instance Segmentation
  182. Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling
  183. DepthMaster: Unified Monocular Depth Estimation for Perspective and Panoramic Images
  184. On Subquadratic Architectures: From Applications to Principles
  185. Latent World Recovery for Multimodal Learning with Missing Modalities
  186. Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal
  187. Nonslop: A Gamified Experiment in Human-AI Collaborative Writing
  188. Atlas H&E-TME: Scalable AI-Based Tissue Profiling at Expert Pathologist-Level Accuracy
  189. Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks
  190. Echoes of the Prior: A Computational Phenomenology of Forgetting
  191. Adjoint Method versus Physics-Informed Neural Networks in PDE-Constrained Inverse Problems
  192. Measuring Semantic Progress in Multi-turn Dialogue via Information Gain
  193. A Five-Plane Reference Architecture for Runtime Governance of Production AI Agents
  194. Anatomically Conditioned Recurrent Refinement for Topology-Aware Circle of Willis Segmentation
  195. Chain of Operators: An Inference-Time Harness for In-Context Operator Learning
  196. From 2D Grids to 1D Tokens: Reforming Shared Representations for Multimodal Image Fusion
  197. Natural-Language Temporal Grounding in Hour-Long Videos is a Search Problem: A Benchmark and Empirical Decomposition
  198. Findings of the MAGMaR 2026 Shared Task
  199. Bridging the Modality Gap in Forensic Image Retrieval
  200. Measuring Epistemic Resilience of LLMs Under Misleading Medical Context
  201. The Standard Interpretable Model: A general theory of interpretable machine learning to deductively design interpretable methods using Lagrangian mechanics
  202. SpikeDecoder: Realizing the GPT Architecture with Spiking Neural Networks
  203. CellNet -- Localizing Cells using Sparse and Noisy Point Annotations
  204. Genetic Algorithms with Optimization Guided Operators
  205. Finding Sparse Subnetworks in One Training Cycle via Progressive Magnitude-Based Pruning
  206. Finding Multiple Interpretations in Datasets
  207. The Impossibility of Eliciting Latent Knowledge
  208. Market Design for AI: Beyond the Copyright Binary
  209. Bridging Day and Night: Unsupervised Cross-Domain Re-Identification with Synergistic Prompt and Prototype Learning
  210. Using Explainability as a Training-Time Reliability Signal for Efficient ECG Classification
  211. Reassessing High-Performing LLMs on Polish Medical Exams: True Competence or Bias-Driven Performance?
  212. Damage-TriageFormer: A Foundation-Model Framework for Typology-Based Building Damage Assessment from Mono-Temporal Imagery
  213. Beyond Third-Person Audits: Situated Interaction Auditing for User-Centered LLM Bias Research
  214. On The Effectiveness-Fluency Trade-Off In LLM Conditioning: A Systematic Study
  215. Rule Taxonomy and Evolution in AI IDEs: A Mining and Survey Study
  216. An Electric Potential-Augmented Benchmark Dataset for Physics-Guided Image Reconstruction of Electrical Capacitance Tomography
  217. Adapting Prithvi-EO for Fallow Detection for Food-Water Nexus: ViT-Adapter Necks and Parameter-Efficient Backbone tuning of Geospatial Foundation Model
  218. MLT-Dedup: Efficient Large-Scale Online Video Deduplication via Multi-Level Representations and Spatial-Temporal Matching
  219. SHERPA: Seam-aware Harmonized ERP Adaptation for Open-Domain 360^circ Panorama Generation
  220. Quantum Occam Learning: Sample-Supported Expressibility for Circuit-Based Quantum Learning
  221. Can News Predict the Market? Limits of Zero-Shot Financial NLP and the Role of Explainable AI
  222. Intelligent Automation for Embodied Benchmark Construction: Pipelines, Embodiments, Simulators, and Trends
  223. Adaptive Multi-Resolution Procedural Knowledge Compression for Large Language Models
  224. Implicit Neural Representations of Individual Behavior
  225. DynaTok: Token-Based 4D Reconstruction from Partial Point Clouds
  226. A Resource for Enthymeme Detection in Controversial Political Discourse
  227. How Low Can You Go? Active Learning for Sparse Model Discovery in the Ultra-Low-Data Limit
  228. A Controlled Study of Decoding-Time Truthfulness Methods on Instruction-Tuned LLMs
  229. TopoCap: Learning Topology-Agnostic Motion Priors for Monocular Video-to-Animation
  230. Towards Responsibly Non-Compliant Machines
  231. nD-RoPE: A Generalized RoPE for n-Dimensional Position Embedding
  232. PCA-Enhanced Adaptive NVAR Framework for High-Resolution Sea Surface Temperature Forecasting in the East Sea
  233. Time-Conditioned and Multi-Time Survival Prediction from 2D PET/CT Projections in Lung Cancer
  234. AGE-MIL: Anchor-Guided Evidence Learning for Patient-Level Prediction
  235. A Riemannian Approach to Low-Rank Optimal Transport
  236. Soft-Prompt Tuning for Fair and Efficient LLM Benchmark Evaluation
  237. Detecting Sensitive Personal Information in Japanese Pre-Training Corpora for Large Language Models
  238. Augmenting Molecular Language Models with Local n-gram Memory
  239. MSUE: Multi-Modal Soccer Understanding Expert
  240. ISAP-3D: Identity-Slot Aligned Part-Aware 3D Generation
  241. Debiasing Without Protected Attributes: Latent Concept Erasure from Textual Profiles
  242. FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents
  243. IntElicit: Eliciting and Assessing Contextualized Creativity via Dialogue Policy Optimization
  244. Efficient Time Series Clustering from Multiscale Reservoir Dynamics with Granular-Ball Anchoring Graph Optimization
  245. Categorical Robustness Assessment for Machine Learning based Network Intrusion Detection Systems
  246. Non-frontal face recognition using GANs and memristor-based classifiers
  247. "That's AI Slop, You Bot!" Studying Accusations, Evidence, and Credibility in Online Discourse Towards LLM-Generated Comments
  248. On the Limits of LLM-as-Judge for Scientific Novelty Assessment
  249. Tac-DINO: Learning Vision-Tactile Features with Patch Alignment
  250. StanceNakba Shared Task: Actor and Topic-Aware Stance Detection in Public Discourse
  251. Performance Analysis of YOLOv11 and YOLOv8 for Mixed Traffic Object Detection under Adverse Weather Conditions in Developing Countries
  252. Automating Geometry-Intensive Compliance Checking in BIM: Graph-Based Semantic Reasoning Framework
  253. Attention by Synchronization in Coupled Oscillator Networks
  254. Phase Transitions in Attention: A Bayesian Theory of Copy Head Emergence
  255. Simplicity Suffices for Parameter Noise Injection in Stochastic Gradient Descent
  256. MFEN:Multi-Frequency Expert Network for Visible-Infrared Person Re-ID
  257. Reliable Error Estimation for PINNs: Lower and Upper A Posteriori Bounds
  258. A Lightweight Multi-Agent Framework for Automated Concrete Barrier Design
  259. Vision Transformers for Face Recognition Need More Registers
  260. SpikeTAD: Spiking Neural Networks for End-to-End Temporal Action Detection
  261. Existential Indifference: Self-Nonpreservation as a Necessary Architectural Condition for Aligned Superintelligence (or: The Suicidal AI)
  262. Human-Enhanced Loop Modeling (HELM): Agent-Based Finite Element Modeling of Concrete Bridge Barriers
  263. ViT-FREE: Efficient Face Recognition via Early Exiting and Synthetic Adaptation
  264. Runtime Enforcement of Hybrid System Properties
  265. FitVTON: Fit-aware Virtual Try-On via Body-Garment Size Control
  266. Tabular Foundation Models for Clinical Survival Analysis via Survival-Aware Adaptation
  267. Bootstrapped Monitoring: Leveraging Transparent Reasoning to Oversee Stronger AI Agents
  268. Time-Series Foundation Model Embeddings for Remaining Useful Life Estimation
  269. From Nominal Intensity to Equivalent Rainfall: A Path-Based Credibility Evaluation Framework for Simulated Rainfall in Autonomous-Driving Perception Tests
  270. What Uncertainties Do We Need for Dynamical Systems?
  271. Efficient Multinomial Logistic Bandit via Frequent Directions
  272. Feature extraction for plant growth estimation
  273. HAMNO: A Hierarchical Adaptive Multi-scale Neural Operator with Physics-Informed Learning for Dynamical Systems
  274. Categorical Prior Lock-in: Why In-Context Learning Fails for Structured Data
  275. Decoding Multimodal Cues: Unveiling the Implicit Meaning Behind Hateful Videos
  276. Neuro-Relational Programs: Unifying Queries and Neural Computation over Structured Data
  277. uva-irlab-conv at SemEval-2026 Task 8: Multi-Turn RAG with Learned Sparse Retrieval and Listwise Reranking
  278. Semantic Grading of Written Answers in Low-Resource Language Bangla Using a Fine-Tuned Lightweight Language Model
  279. Frozen Multimodal Embeddings for AI-Assisted Interview Assessment of Personality and Cognitive Ability
  280. Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
  281. Corpus Augmentation for Sign Language Translation via LLM-Guided Video Stitching
  282. Lung-SRAD: Spectral-Aware Regularized Audio DASS with Dual-Axis Patch-Mix Contrastive Learning for Respiratory Sound Classification
  283. Characterizing Software Aging in GPU-Based LLM Serving Systems
  284. Quality Adaptive Angular Margin Learning for Respiratory Sound Classification
  285. NARRAS: Edge-Triggered Distributed Inference for CSI-Based Localization in Vehicular IoT Networks
  286. From Content to Knowledge: Lightning Fast Long-Video Understanding with Neural Knowledge Representations
  287. From Persistence to Survival: Hypothesis Testing, Effect Sizes and Vectorisation for Topological Features
  288. An Ontology-Guided Multi-Anchor Graph Retrieval Framework for Traffic Legal Liability Determination
  289. Embodied-BenchClaw: An Autonomous Multi-Agent System for Embodied Spatial Intelligence Benchmark Construction
  290. DuoBench: A Reproducible Benchmark for Bimanual Manipulation in Simulation and the Real World
  291. GraspLLM: Towards Zero-Shot Generalization on Text-Attributed Graphs with LLMs
  292. Notes2Skills: From Lab Notebooks to Certainty-Aware Scientific Agent Skills
  293. Wild3R: Feed-Forward 3D Gaussian Splatting from Unconstrained Sparse Photo Collection
  294. Image Quality Assessment of Identity Cards Using Measures from Open Face Image Quality
  295. SG2Loc: Sequential Visual Localization on 3D Scene Graphs
  296. Seeing Below the Limit of Detection: A Censored-Poisson Bayesian Latent-Growth Change-Point Detector (the Span Detector) for Serial ctDNA in HR+/HER2- Metastatic Breast Cancer
  297. I Understand How You Feel: Enhancing Deeper Emotional Support Through Multilingual Emotional Validation in Dialogue System
  298. AutoMine Solution for AV2 2026 Scenario Mining Challenge
  299. Modelling magnetic material properties with uncertainty-aware neural networks
  300. Agents All the Way Down; A Methodology for Building Custom AI Agents from Substrate to Production
  301. MemNovo: Look Back at the Spectrum for Balanced De Novo Peptide Sequencing from Mass Spectrometry
  302. Conformal Bayes under Label Shift: Post-Hoc Calibration vs. In-Training Adaptation
  303. RePAIR: Predictive Self-Supervised Representation Learning in Chess
  304. REACH: Interpretability-Driven Feature Identification and Architecture Compression for Multi-Channel Vehicular Channel Estimation
  305. StatefulDiscovery: Evidence-Calibrated Claim Formation in Open-Ended Scientific Discovery
  306. SheafStain: Sheaf-Theoretic Schr"odinger Bridge for Spatially and Biologically Coherent Virtual Staining
  307. TaskFusion: Continual Anomaly Detection for Heterogeneous Tabular Data
  308. Scene-Adaptive Nonlinear Tone Curves for Pseudo Ground-Truth Generation in Low-Light 3D Gaussian Splatting
  309. LASA: A Weak Supervision Method for Open-Vocabulary Scene Sketch Semantic Segmentation
  310. Towards Data-free and Training-free Compression for Speech Foundation Models Using Parameter Clustering
  311. Designing AI-Supported Focus Groups: A Role x Modality Playbook
  312. From Uniform to Learned Graph Priors: Diffusion for Structure Discovery
  313. Feature-Aligned Speech Watermarking for Robustness to Reconstruction Distortions
  314. Sparsified Kolmogorov-Arnold Networks for Interpretable Quantum State Tomography
  315. External Experience Serving in Production LLM Systems: A Deployment-Oriented Study of Quality-Cost Trade-offs
  316. TextHOI-3D: Text-to-3D Hand-Object Interaction via Discrete Multi-View Generation and Joint Mesh Optimization
  317. Toward Trustworthy AI: Multi-Target Adversarial Attacks and Robust Defenses for Continuous Data Summarization
  318. Multimodal Ordinal Modeling of Alzheimer's Disease Severity Using Structural MRI and Clinical Data
  319. Scalable Deep Learning Framework for Global High-Resolution Land Use Reconstruction
  320. Lius: Translation Model Based Instructional Lingustic Using Continual Instruction Tuning In Kupang Malay
  321. A Comprehensive Ecosystem for Open-Domain Customized Video Generation
  322. Seeing What Matters: Perceptual Wrapper with Common Randomness for 3D Gaussian Splatting
  323. What Limits Does Quantization Place on Dense Top-k Retrieval? A Theoretical Study
  324. Battery detection of XRay images using transfer learning
  325. Magnitude-Based Features for Multispecies Spatial Data
  326. Last-Iterate Convergence of Optimistic Multiplicative Weight Update
  327. When Do Data-Driven Systems Exhibit the Capability to Infer?
  328. Blind Dexterous Grasping via Real2Sim2Real Tactile Policy Learning
  329. Fast Speech Foundation Model Distillation Using Interleaved Stacking
  330. Automated Creativity Evaluation of Language Models Across Open-Ended Tasks
  331. RCAP: Robust, Class-Aware, Probabilistic Dynamic Dataset Pruning
  332. AnchorEdit: Maintaining Temporal Consistency in Multi-turn Image Editing via Causal Memory
  333. Time Series Analysis in Machine Learning
  334. Hey Chat, Can You Teach Me? Structuring Socratic Dialogue for Human Learning in the Wild
  335. UniReason-Med: A Shared Grounded Reasoning Interface for 2D-to-3D Transfer in Medical VQA
  336. Multi-View In-Cabin Monitoring System for Public Transport Vehicles
  337. Renewable Lasso without Batch-Number Constraints: A Gradient-Enhanced Approach
  338. Machine-learning clustering of close-in exoplanet populations: links to pebble accretion
  339. ICA Lens: Interpreting Language Models Without Training Another Dictionary
  340. Substrate Asymmetry in User-Side Memory: A Diagnostic Framework
  341. Capacity-Constrained Online Convex Optimization with Delayed Feedback
  342. ERN-Net : Evolving Reason Node-Net for Document Binarization
  343. MedCTA: A Benchmark for Clinical Tool Agents
  344. A Data-Centric Framework for Detecting and Correcting Corrupted Labels
  345. Noise-Aware Framework for Correcting Corrupted Labels
  346. RankVR: Low-Rank Structure Perception and Value Recalibration for Robust Composed Image Retrieval
  347. DroneShield-AI: A Multi-Modal Sensor Fusion Framework for Real-Time Autonomous Drone Threat Detection, Behavioral Intent Classification, and Swarm Intelligence in Contested Airspace
  348. Parameter-Efficient Adapter Tuning for Tabular-Image Multimodal Learning
  349. UR-BERT: Scaling Text Encoders for Massively Multilingual TTS Through Universal Romanization and Speech Token Prediction
  350. Neural-Parameterized Cellular Automata for Wildfire Spread
  351. SpAArSIST: Sparsified AASIST for Efficient and Reliable Anti-Spoofing
  352. Higher-Order Token Interactions via Quantum Attention
  353. ARGUS: Stacked Multi-View Identity Mosaic Injection for Subject-Preserving Video Generation
  354. Probabilistic Salary Prediction with Graph Attention Networks and a Mixture Density Network
  355. TreeSeeker: Tree-Structured Trial, Error, and Return in Deep Search
  356. Learning Instance-Adaptive Low-Rank Orthogonal Subspaces for Clothes-Changing Person Re-Identification
  357. Bergson: An Open Source Library for Data Attribution
  358. The Long Tail, Not the Front Page: Cold-Start Prediction of Crowd Highlight Salience
  359. DeepRHP: A Hybrid Variational Autoencoder for Designing Random Heteropolymers as Protein Mimics
  360. Structure-Preserving Neural Surrogates with Tractable Uncertainty Quantification
  361. Tree-Structured Orthonormal Decomposition of the Aitchison Simplex
  362. Motion Reinforces Appearance: RGB-Skeleton Gated Residual Fusion for Micro-Gesture Online Recognition
  363. Improving Cross-Format Robustness in Language Models with Multi-Format Training
  364. 3-Key-Input: Exploring the Theoretical Minimum Keys for Text Entry
  365. TAROT: Task-Adaptive Refinement of LLM-prior Graphs for Few-shot Tabular Learning
  366. Evaluating Bias in Phoneme-Based Automatic Speech Recognition Systems: An Analysis of IPA Transcription Models
  367. Sovereign Assurance Boundary: Certificate-Bound Admission for Agentic Infrastructure
  368. Integral Formulation of QENDy for Robust Nonlinear System Identification
  369. LUCID: Learning Embodiment-Agnostic Intent Models from Unstructured Human Videos for Scalable Dexterous Robot Skill Acquisition
  370. Family-Aware Residual Architecture for Predicting Quantum Circuit Simulation Performance
  371. Precision-Aware Illumination-Disentangled Vision Transformer for Spacecraft 6D Pose Estimation
  372. DeMix: Debugging Training Data with Mixed Data Error Types by Investigating Influence Vectors
  373. Information-Theoretic Decomposition for Multimodal Interaction Learning
  374. Factions Within, Uncertain Across: Within-Document Reader Sub-Groups in Social Highlighting
  375. Frozen Foundation-Model Embeddings Discard Small-Lesion Signal in Chest Radiography: Implications for Pre-Deployment Evaluation
  376. On Aligning Hierarchical Standardized Embedding for Audio-visual Generalized Zero-shot Learning
  377. Spatially Coupled Phase-to-Depth Calibration for Fringe Projection Profilometry
  378. Model-Based and Data-Driven Hierarchical Control and Topology Co-Design for Robust Networked Systems
  379. Kuramoto Attention: Synchronizing Self-Attention on the Torus
  380. Beyond the Golden Teacher: Enhancing Graph Learning through LLM-GNN Co-teaching
  381. Contactless 3D Human Body Measurement Using Depth Cameras for Smart Health Monitoring
  382. Range-Aware Bayesian Optimization for Discovering Diverse Designs within Target Property Windows
  383. Understanding Cross-Sensor Feature Variations for Generalizable 3D Perception
  384. Enhancing Spectral Embedding through Robust and Flexible Knowledge Transfer in Electronic Health Records
  385. Cross-Modal Benchmarking for Robotic Perception in Natural Environments
  386. GraphInfer-Bench: Benchmarking LLM's Inference Capability on Graphs
  387. Privacy-Preserving Federated Autoencoder for ECG Anomaly Detection on Edge Devices
  388. End-to-End Machine Learning for Depressive State Classification via EEG and fNIRS
  389. APEX: A Network-Native Time-Series Foundation Model for Forecasting and Anomaly Detection for Wireless Edge Operations
  390. Teaching Diffusion to Speculate Left-to-Right
  391. Pretrained self-supervised speech models can recognize unseen consonants
  392. MoCA-Agent: A Market-of-Claims Code Agent for Financial and Numerical Reasoning
  393. Urban Heat MiniCubes: An AI-Ready dataset for urban heat research
  394. AI Researchers Must Help Lead Arms Control to Mitigate Military AI Risks
  395. Measuring language complexity from hierarchical reuse of recurring patterns
  396. XPR: An Extensible Cross-Platform Point-Based Differentiable Renderer