mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 9 Jun 2026

521 papers

  1. Stability-Aware Feature Design for Robust Watermark Detection in Machine-Generated TextLLM safety and security → Watermarking generated content and models
  2. FinSkillBench: Evaluating AI Agents and Domain Skills for Investment ManagementLLM agents and tool use → Financial trading and forecasting agents
  3. Fractional Decay KV-Cache: Ownership-Aware Memory Management for Improved Inference Relevancy in Dialog SystemsEfficient LLM inference and serving → KV cache optimization
  4. Evaluating XAI Support From A Hierarchical Reinforcement Learning Policy in Human-Agent CollaborationDeep reinforcement learning methods → Interpretable and logic-guided RL
  5. ProcAgent: An Agentic Framework for Procedural Task Guidance on Edge with Human-in-the-LoopLLM agents and tool use → Multimodal and embodied agents
  6. MM-ShiftKV: Decode-Aware Prefill-Stage KV Selection for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  7. Geometry-Guided Constraint Learning for LLM Safety ClassificationLLM safety and security → Safety alignment, refusal and guardrails +1
  8. How Do LLMs Cite? A Mechanistic Interpretation of Attribution in Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  9. From Knowing to Acting: Benchmarking Self-Awareness Capability of LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  10. Skill Coverage: A Test Adequacy Metric for Agent SkillsLLM agents and tool use → Agent skill learning and evolution
  11. Agentomics: Economic Foundations for the Valuation, Attribution, and Pricing of AI Agents in Human-AI WorkflowsLLM agents and tool use → General LLM agent frameworks and benchmarks
  12. Identifiability Without Gaussianity: Symbolic World Models and Near-Infinite Temporal ConsistencyWorld models → Latent predictive world models
  13. Influence Factors on RAG PoisoningRetrieval-augmented generation → Privacy and security of RAG
  14. Search Discipline for Long-Horizon Research AgentsLLM agents and tool use → Web, search, and research agents
  15. Counterexample Guided Learning in the Large using Reasoning AgentsLLM reasoning → Reasoning benchmarks and evaluation +1
  16. ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent TrajectoriesLLM agents and tool use → Tool learning and function calling
  17. SAGE: Answer-Conditioned Uncertainty Targets for Verbal Uncertainty AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  18. FlexiBrain: Resolution-Agnostic Voxel-Level Encoding for Native fMRIState-space sequence models (S4, Mamba) → Physiological signal modeling
  19. Building Social World Models with Large Language ModelsWorld models → World models for language agents
  20. The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure ModesLLM reasoning → Reasoning benchmarks and evaluation +1
  21. AI Coding Agents in Social Science: Methodologically Diverse, Empirically Consistent, Interpretively VulnerableLLM agents and tool use → Social simulation and multi-agent debate
  22. AI Coding Agents Can Reproduce Social Science FindingsLLM agents and tool use → Web, search, and research agents
  23. INFRAMIND: Infrastructure-Aware Multi-Agent OrchestrationLLM agents and tool use → Software engineering coding agents
  24. Agent Skill Evaluation and Evolution: Frameworks and BenchmarksLLM agents and tool use → Agent skill learning and evolution
  25. JailbreakOPT: Tool-Assisted Iterative Jailbreak Prompt OptimizationLLM safety and security → Jailbreaking
  26. Risk Under Pressure: Compute-Aware Evaluation of Adversarial Robustness in Language ModelsLLM safety and security → Jailbreaking
  27. Steering Where to Listen: Instruction-Based Activation Steering Redirects Temporal Attention in Large Audio-Language ModelsMechanistic interpretability → Activation steering methods
  28. PLUME: Probabilistic Latent Unified World Modeling and Parameter Estimation for Multi-Finger ManipulationWorld models → Embodied and robot world models
  29. Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation SteeringMechanistic interpretability → Activation steering methods
  30. DeceptionX: From Multimodal Evidence to Explainable Deception DetectionLLM reasoning → Prompting and chain-of-thought reasoning
  31. When More Documents Hurt RAG: Mitigating Vector Search Dilution with Domain-Scoped, Model-Agnostic RetrievalRetrieval-augmented generation → RAG pipeline design and evaluation
  32. Knowing When to Ask: Self-Gated Clarification for Hierarchical Language AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  33. Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation ModelsLLM reasoning → Spatial and embodied reasoning
  34. Sch"utzen: Evaluating LLM Safety in Bulgarian and German ContextsLLM safety and security → Safety alignment, refusal and guardrails
  35. FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-ReuseLLM agents and tool use → Software engineering coding agents
  36. i1: A Simple and Fully Open Recipe for Strong Text-to-Image ModelsDiffusion models → Image generation, text-to-image and editing
  37. Phi-Actor-Critic: Steering General-Sum Games to Pareto-Efficient Correlated EquilibriaDeep reinforcement learning methods → RL for games and combinatorial optimization
  38. Least-Action-Guided Diffusion for Physical ExtrapolationDiffusion models → Flow matching, time series and science
  39. Seeing Before Colliding: Anticipatory Safe RL with Frozen Vision-Language ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  40. When Poison Fails After Retrieval: Revisiting Corpus Poisoning under Chunking and Reranking PipelinesRetrieval-augmented generation → Privacy and security of RAG
  41. RAIL: Rethinking Auditory Intelligence in Large Audio-Language Models with a CHC-Grounded BenchmarkLLM reasoning → Audio-language model reasoning
  42. Energy-Efficient On-Device RAG on a Mobile NPU: System Design and Benchmark on Snapdragon X EliteRetrieval-augmented generation → RAG pipeline design and evaluation
  43. ARM: An AutoRegressive Large Multimodal Model with Unified Discrete RepresentationsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  44. Next Forcing: Causal World Modeling with Multi-Chunk PredictionWorld models → Video-generation world models and simulators
  45. TacForeSight: Force-Guided Tactile World Model for Contact-Rich ManipulationWorld models → Embodied and robot world models
  46. EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  47. Lip Forcing: Few-Step Autoregressive Diffusion for Real-time Lip SynchronizationDiffusion models → Audio, speech and music
  48. The Role of Feedback Alignment in Self-DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  49. Predicting Future Behaviors in Reasoning Models Enables Better SteeringLLM reasoning → Test-time compute and efficient thinking
  50. ReasonAlloc: Hierarchical Decoding-Time KV Cache Budget Allocation for Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking +1
  51. Mean Flow Distillation: Robust and Stable Distillation for Flow Matching ModelsDiffusion models → Flow matching, time series and science
  52. P3D-Bench: Benchmarking MLLMs for Parametric 3D Generation and Structural ReasoningLLM reasoning → Spatial and embodied reasoning +1
  53. ABC-Bench: An Agentic Bio-Capabilities Benchmark for BiosecurityLLM agents and tool use → Medical and scientific domain agents
  54. Data assimilation for subsurface flow using latent diffusion model parameterization: performance of ensemble-Kalman and Monte Carlo techniquesDiffusion models → Flow matching, time series and science
  55. WorldOlympiad: Can Your World Model Survive a Triathlon?World models → Video-generation world models and simulators
  56. Provenance-Grounded Gating and Adaptive Recovery in Synthetic Post-Training Data CurationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  57. Monte Carlo Pass Search: Using Trajectory Generation for 3D Counterfactual Pass Evaluation in FootballWorld models → World models for autonomous driving
  58. TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents
  59. RoboNaldo: Accurate, Stable and Powerful Humanoid Soccer Shooting via Motion-Guided Curriculum Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  60. Test-Time Gradient Guidance of Flow Policies in Reinforcement LearningOffline RL and imitation learning from data → Diffusion and flow policies for offline RL +1
  61. The Shibboleth Effect: Auditing the Cross-Lingual Distributional Skew of Large Language ModelsLLM reasoning → Reasoning for agents, planning and code
  62. A History-Aware Visually Grounded Critic for Computer Use AgentsLLM agents and tool use → GUI and mobile agents
  63. Exploring the Design Space of Reward Backpropagation for Flow MatchingDiffusion models → Diffusion and flow policies for robotics +1
  64. Modeling Complex Behaviors: Multi-Personality Composition and Dynamic Switching in Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  65. T1-Bench: Benchmarking Multi-Scenario Agents in Real-World DomainsLLM agents and tool use → General LLM agent frameworks and benchmarks
  66. Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix ItLLM reasoning → Test-time compute and efficient thinking
  67. Does Reasoning Preserve Alignment? On the Trustworthiness of Large Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  68. What Fits (Into Few Tokens) Doesn't Overfit: Compression and Generalization in ML Research AgentsLLM agents and tool use → Agent memory systems
  69. Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional FieldsLLM agents and tool use → GUI and mobile agents
  70. Flow-DPPO: Divergence Proximal Policy Optimization for Flow Matching ModelsDiffusion models → Diffusion and flow policies for robotics +1
  71. Diffusion Forcing Planner: History-Annealed Planning with Time-Dependent Guidance for Autonomous DrivingEnd-to-end autonomous driving → Imitation-learning end-to-end planners
  72. Null-Space Constrained Low-Rank Adaptation for Response-Specified Large Language Model UnlearningLLM safety and security → Machine unlearning
  73. Language-Driven Cost Optimization for Autonomous DrivingEnd-to-end autonomous driving → Large language models for driving
  74. Beyond Uniform Token-Level Trust Region in LLM Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  75. WorldKernel: A World Model is the Coupling Kernel of Admissible Possible WorldsWorld models → World models for language agents
  76. Frontier Coding Agents Use Metaprogramming to Adapt to Unfamiliar Programming LanguagesLLM agents and tool use → Software engineering coding agents
  77. It Takes One to Bias Them All: Breaking Bad with One-Shot GRPOLLM reasoning → Reinforcement learning for reasoning
  78. Recoverable but Not Stationary:Local Linear Structures in Weights and ActivationsMechanistic interpretability → Circuits and mechanistic analysis
  79. AllDayNav: Lifelong Navigation via Real-World Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  80. Trace Only What You Need: Structure-Aware On-Demand Hypergraph Memory for Long-Document Question AnsweringRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  81. Role-Agent: Bootstrapping LLM Agents via Dual-Role EvolutionLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  82. Pushing the Limits of LLM Tool Calling via Experiential Knowledge Integration and ActivationLLM agents and tool use → Tool learning and function calling
  83. LIBERO-Occ: Evaluating and Improving Vision-Language-Action Models under Scene-Induced Occlusion via Viewpoint ImaginationVision-language-action models → Failure recovery and robustness
  84. Training LLMs to Enforce Multi-Level Instruction Hierarchies via Gravity-Weighted Direct Preference OptimizationLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  85. An Exposure-Time-Aligned Primary-Path Architecture for Autonomous-Driving ECUsEnd-to-end autonomous driving → End-to-end system architecture
  86. Securing Code Understanding: Detecting Natural Backdoor Vulnerability in Code Language ModelsLLM safety and security → Backdoor and data poisoning attacks
  87. Geometrically Averaged Hard Target Updates for Linear Q-LearningDeep reinforcement learning methods → RL theory and sample complexity
  88. Do VLMs Reason Like Engineers? A Benchmark and a Stage-wise EvaluationLLM reasoning → Multimodal reasoning +1
  89. GUIDE: Goal-Initialized Directional Understanding for End-to-End Legged NavigationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  90. Attention-Discounted Adaptive Sampler for Masked Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  91. MODIP: Efficient Model-Based Optimization for Diffusion PoliciesDiffusion models → Diffusion and flow policies for robotics +1
  92. Earth-OneVision: Extending Remote Sensing Multimodal Large Language Models to More Sensor Modalities and TasksLLM reasoning → Spatial and embodied reasoning +1
  93. RedAct: Redacting Agent Capability Traces for Procedural Skill ProtectionLLM safety and security → Prompt injection and agent security
  94. Beyond APIs: Probing the Limits of MLLMs in Physical Tool UseMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  95. Dep-LLM: Training-Free Depression Diagnosis via Evidence-Guided Structured Multi-factor with Reliable LLM ReasoningLLM reasoning → Clinical and biomedical applications
  96. On-sky demonstration of reinforcement learning for adaptive optics controlDeep reinforcement learning methods → RL for robot navigation and UAV control
  97. N-GRPO: Embedding-Level Neighbor Mixing for Enhanced Policy OptimizationLLM reasoning → Reinforcement learning for reasoning
  98. miniReranker: Efficient Multimodal Reranking through Visual Cache Reuse and Interaction SparsityMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  99. AutoPDE: Reliable Agentic PDE Solving via Explicitly Represented Solver StrategiesLLM agents and tool use → Web, search, and research agents
  100. Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and EvaluationLLM agents and tool use → Agent threats, guardrails and governance
All 521
  1. The Arbiter Agent: Continually Monitoring Multi-Agent Conversations to Detect Emergent MisalignmentLLM agents and tool use → General LLM agent frameworks and benchmarks
  2. Hand-centric Human-to-Robot Trajectory Transfer from Video Demonstrations via Object Category-agnostic Temporal LocalizationOffline RL and imitation learning from data → Robot manipulation imitation learning
  3. MemVenom: Triggered Poisoning of Multimodal Memories in Web AgentsLLM agents and tool use → Agent threats, guardrails and governance
  4. When the Chain of Thought Knows Better: Failure Modes in Multi-Turn Reasoning ModelsLLM reasoning → Reasoning for agents, planning and code
  5. Spatial-Omni: Spatial Audio Understanding Integration in Multimodal LLMs via FOA EncodingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  6. The Agentic Web Requires New Normative InfrastructureLLM agents and tool use → General LLM agent frameworks and benchmarks
  7. Effective Reinforcement Learning for Agentic Search by Recycling Zero-Variance Queries During TrainingLLM reasoning → Reinforcement learning for reasoning +1
  8. Event-Driven Reinforcement Learning Enables Long-Horizon Control in Semiconductor FabricationDeep reinforcement learning methods → RL for energy, networks and operations
  9. From Observation to Intervention: A Causal Audit of Expert Importance in Mixture-of-Experts ModelsMixture-of-experts → Expert routing strategies
  10. Watts and Debts of Agentic Frameworks: An Empirical Study (Registered Report)LLM agents and tool use → Software engineering coding agents
  11. REAL: A Reasoning-Enhanced Graph Framework for Long-Term Memory Management of LLMsLLM reasoning → Reasoning for agents, planning and code
  12. Self-Supervised Relevance Modelling in Autonomous Driving via Counterfactual AnalysisEnd-to-end autonomous driving → End-to-end system architecture
  13. Divide and Cooperate: Role-Decomposed Multi-Agent LLM Training with Cross-Agent Learning SignalsLLM agents and tool use → Web, search, and research agents
  14. Infini Memory: Maintainable Topic Documents for Long-Term LLM Agent MemoryLLM agents and tool use → Agent memory systems
  15. FadeMem: Distance-Aware Memory Consolidation for Autoregressive Video DiffusionDiffusion models → Video generation +1
  16. Decentralized Multi-Agent Systems with Shared ContextLLM reasoning → Reasoning for agents, planning and code +1
  17. STEDiff: Strengthening Text Embedding for Text-to-Image Alignment in Diffusion ModelDiffusion models → Image generation, text-to-image and editing
  18. Kwai Keye-VL-2.0 Technical ReportLLM agents and tool use → Multimodal and embodied agents +2
  19. How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMsLLM reasoning → Test-time compute and efficient thinking
  20. Can Image Models Imagine Time? ImageTime: A Novel Benchmark for Probing Visual World Modeling Through Spatiotemporal ConsistencyWorld models → Video-generation world models and simulators
  21. SSR-Merge: Subspace Signal Routing for Training-Free LoRA Merging in Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  22. Learning What to Remember: Observability-Safe Memory Retention via Constrained Optimization for Long-Horizon Language AgentsLLM reasoning → Reasoning for agents, planning and code
  23. Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstrapped Flow Q-LearningOffline RL and imitation learning from data → Diffusion and flow policies for offline RL
  24. GaussTrace: Provenance Analysis of 3D Gaussian Splatting Models with Evidence-based LLM ReasoningLLM reasoning → Spatial and embodied reasoning
  25. Geometry-Aware Reinforcement Learning for 2D Irregular NestingDeep reinforcement learning methods → RL with diffusion and flow models
  26. Causal Ensemble Agent: Hierarchical Causal Discovery with LLM-guided Expert ReweightingLLM agents and tool use → Medical and scientific domain agents
  27. AgenticNav: Zero-Shot Vision-and-Language Navigation as a Tool-Calling HarnessMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  28. One Token per Multimodal Evidence: Latent Memory for Resource-Constrained QAMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  29. Improving Adversarial Transferability on Vision-Language Pre-training Models via Surrogate-Specific Bias CorrectionMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  30. Hidden Consensus:Preference-Validity Compression in Human FeedbackLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  31. VeriSpace: Spatially Grounded Action Verification for Vision-Language-Action ModelsVision-language-action models → 3D and spatial-aware VLA
  32. SkillAxe: Sharpening LLM-Authored Agent Skills Through Evaluation-Guided Self-RefinementLLM agents and tool use → Agent skill learning and evolution
  33. Prefilling-dLLM: Predictive Prefilling for Long-Context Inference in Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  34. Audio-Visual Exchange-Aware Token Pruning for Efficient Audio-Visual CaptioningEfficient LLM inference and serving → Visual token pruning in multimodal models
  35. ActiveMem: Distributed Active Memory for Long-Horizon LLM ReasoningLLM reasoning → Reasoning for agents, planning and code
  36. Representation-Aware Advantage Estimation: Your Reward Model Provides More Than A Scalar OutputLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  37. Assessing Automated Prompt Injection Attacks in Agentic EnvironmentsLLM agents and tool use → Agent threats, guardrails and governance +1
  38. GUI-AC: Enhancing Continual Learning in GUI AgentsLLM agents and tool use → GUI and mobile agents
  39. UniSVQ: 2-bit Unified Scalar-Vector QuantizationEfficient LLM inference and serving → KV cache quantization
  40. LAFP: Preserving Latent Action Structure in Latent Policy Learning via Flow MatchingDiffusion models → Diffusion and flow policies for robotics
  41. HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent LearningLLM agents and tool use → Reinforcement learning for LLM agents
  42. Cross-Modal Knowledge Distillation without Paired Data: Theoretical Foundation and AlgorithmKnowledge distillation → Multimodal distillation
  43. Uncovering Vulnerability of Vision-Language-Action Models under Joint-Level Physical FaultsVision-language-action models → Failure recovery and robustness
  44. MoE Enhanced Federated Learning for Spatiotemporal PredictionMixture-of-experts → MoE for time series and graphs
  45. Act on What You See: Unlocking Safe Social Navigation in Vision-Language-Action ModelsVision-language-action models → Safety and adversarial attacks
  46. Achieving Cloud-Grade SLOs for Local Mixture-of-Experts Inference through CPU-GPU Hybrid DesignMixture-of-experts → Efficient MoE training and inference systems
  47. ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level CombinatoricsLLM reasoning → Mathematical reasoning
  48. Decoupling Thought from Speech: Knowledge-Grounded Counterfactual Reasoning for Resilient Multi-Agent ArgumentationLLM reasoning → Reasoning for agents, planning and code +1
  49. Trace2Policy: From Expert Behavior Traces to Self-Evolving Decision AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  50. Entropy-Aware Domain-Routed Mixture-of-Experts Speech-LLM Framework: A Case Study of Multi-Domain Child-Adult ASRMixture-of-experts → Multimodal MoE models
  51. Few-step Generative Models as Lossy CompressionDiffusion models → Diffusion for compression and wireless
  52. Mitigating Bias in Low-SNR Financial Reinforcement Learning via Quantum RepresentationsDeep reinforcement learning methods → Adversarial robustness and RL in finance
  53. Enhancing Multilingual LLM-based ASR with Mixture of Experts and Dynamic DownsamplingMixture-of-experts → Multimodal MoE models
  54. WebChallenger: A Reliable and Efficient Generalist Web AgentLLM reasoning → Reasoning for agents, planning and code +1
  55. Soul Computing: A Theoretical Framework and Technical Architecture for Intelligent Agents with Independent ConsciousnessLLM agents and tool use → General LLM agent frameworks and benchmarks
  56. A Unified Multi-Modal Framework for Intelligent Financial Systems: Integrating Reinforcement Learning, High-Frequency Trading, and Game-Theoretic Approaches with Cross-Modal Sentiment AnalysisDeep reinforcement learning methods → Adversarial robustness and RL in finance
  57. KCSAT-ML: Probing Reasoning Models with Nationwide-Cohort Human DifficultyLLM reasoning → Mathematical reasoning
  58. CoCoSI: Collaborative Cognitive Map Construction for Spatial IntelligenceMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  59. Do Vision-Language Models See or Guess? Measuring and Reducing Textual-Prior Reliance with a Phrasing-Controlled BenchmarkMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  60. STAGE-Claw: Automated State-based Agent Benchmarking for Realistic ScenariosLLM agents and tool use → General LLM agent frameworks and benchmarks
  61. Instruction Finetuning DeepSeek-R1-8B Model Using LoRA and NEFTuneLLM reasoning → Reasoning for agents, planning and code
  62. Beyond Absolute Imitation: Anchored Residual Guidance for Privileged On-Policy DistillationLLM reasoning → Prompting and chain-of-thought reasoning +1
  63. Agentic Hybrid RAG for Evidence-Grounded Muon Collider AnalysisRetrieval-augmented generation → Agentic RAG, agents and memory +1
  64. Test-time Adversarial Takeover: A Real-time Hijacking Interface against Robotic Diffusion PoliciesDiffusion models → Diffusion and flow policies for robotics
  65. PADD: Path-Aligned Decompression Distillation for Non-Router Teacher to Guide MoE Student LearningMixture-of-experts → MoE large language models +1
  66. A Practical Recipe Towards Improving Sim-and-Real Correlation for VLA EvaluationVision-language-action models → Failure recovery and robustness
  67. HiMem-WAM: Hierarchical Memory-Gated World Action Models for Robotic ManipulationWorld models → Embodied and robot world models
  68. ReflectiChain: Epistemic Grounding in LLM-Driven World Models for Supply Chain ResilienceWorld models → World models for language agents
  69. Atomic Intent Reasoning: Bringing LLM Semantics to Industrial Cross-Domain RecommendationsLLM reasoning → LLM reasoning for recommendation
  70. Reasoning or Memorization? Direction-Aware Diversity Exploration in LLM Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  71. Routing-Aware Expert Calibration for Machine Unlearning in Mixture-of-Experts Language ModelsMixture-of-experts → Expert routing strategies +1
  72. Self-Distillation Policy Optimization via Visual Feedback: Bridging Code and Visual ArtifactsKnowledge distillation → Multimodal distillation
  73. Semantic Multi-Agent Intrusion Detection for IoT:Zero-Day and Adversarial Threats with Risk-Aware ReasoningLLM agents and tool use → Agent threats, guardrails and governance
  74. Game-Theoretic Multi-Agent Control for Robust Contextual Reasoning in LLMsLLM reasoning → Reasoning for agents, planning and code +1
  75. Baseline-Free Policy Optimization for Neural Combinatorial OptimizationLLM reasoning → Reinforcement learning for reasoning
  76. TabClaw: An Interactive and Self-Evolving Agent for Spreadsheet Manipulation and Table ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning +2
  77. Catching One in Five: LLM-as-Judge Blind Spots in Production Multi-Turn Transaction AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  78. Early-Token Confidence Predicts Reasoning Quality in Multi-Agent LLM DebateLLM reasoning → Reasoning for agents, planning and code +1
  79. SARM2: Multi-Task Stage Aware Reward Modeling for Self Improving Robotic ManipulationVision-language-action models → Reinforcement learning and post-training
  80. MIRAGE: A Polarity-Flipping Encoding Subspace in LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  81. The Confident Liar: Diagnosing Multi-Agent Debate with Log-Probabilities and LLM-as-JudgeLLM agents and tool use → Social simulation and multi-agent debate
  82. MARCH: Model-Assisted Reinforcement Learning for the Perceptive Control of Humanoids over Sparse FootholdsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  83. What Matters in Orchestrating Robot Policies: A Systematic Study of Hierarchical VLA AgentsVision-language-action models → Generalist VLA models and benchmarks +1
  84. BERTilda: Explainable Topic Lifecycle Tracking with Split/Merge Detection via Similarity-and-Flow Temporal Graphs
  85. Computational Orientalism: Measuring Structural Discourse Bias in Large Language Models Using the Middle East Cultural Sensitivity Score (MECSS)
  86. From Reactive to Autonomous: Evolution of AI Operations in Cloud Network Infrastructure
  87. Cross-Model Humor Preference Modeling with Cards Against Humanity
  88. Emotion in an active inference model of human driving
  89. Mobile Interaction for Assessing Fatigue, Sleep, and Activity in Neurodegenerative and Chronic Diseases
  90. LLM Scheming Inversely Scales with Pretraining Language Coverage
  91. PATHFinder Agent for Tailored Prenatal Care
  92. ParBench: A Benchmark for Reliable Evaluation of LLM Parallel Code Translation
  93. TriSP: Tri-Signal Structured Pruning for Large Language Models
  94. Automated Recommendation of Programming Learning Content Using Pattern-based Knowledge Components
  95. Life Cycle Assessment of Pre-training the Lucie 7B Open-Source Large Language Model on the Jean Zay Supercomputer
  96. Position: Preventing AI-Generated CSAM Necessitates New Approaches to AI Safety
  97. A Guiding Framework for K-12 Teachers in Creating AI-powered Learning Technologies through Vibe Coding
  98. The Voronoi Bottleneck: Capacity-Aware Dense Retrieval for Product Search
  99. Physics-Constrained Neural Surrogate for Domain Growth Prediction in Systems with Conserved Kinetics
  100. Confidence Laundering in Agent Systems: Why Uncertainty Needs a Latent Carrier
  101. Expected Free Energy-based Planning as Variational Inference
  102. A-Evolve-Training: Autonomous Post-Training of a 30B Model
  103. Learning Splitting Heuristics for Parallel String Solvers
  104. Gaussian Mixture Attention: Linear-Time Sequence Mixing via Probabilistic Latent Routing
  105. Double-Helix Vision (DH-V2): A Geometry-Based Visual Sampler for Bandwidth-Constrained Perception
  106. ScoutVLA: UAV-Centric Active Perception via a Dual-Expert VLA Model for Open-World Embodied Question Answering
  107. An Empirical Analysis of Optimization Dynamics and Sparsity Boundaries in Large-Scale Pedestrian Attribute Recognition
  108. HierSVA: A Data Synthesis Pipeline, Dataset, and Benchmark for LLM-Driven Hierarchical Hardware Formal Verification
  109. When Can One Neuron Fix Repetition Loops in LLMs?
  110. Position: AI Must Become Planet-Centered, Not Just Human-Centered
  111. SirenFNO: Efficient and Full Frequency Learning of Fourier Neural Operators
  112. Continuous biome representations from Earth observation embeddings
  113. Probabilistic Contrastive Pretraining for Multi-task ADME Property Prediction
  114. SceneMiner: Identity-Preserving Multi-Task Fine-Tuning for Unified BEV Scene Mining
  115. On the Study of Biometric Spoofing Detection using Deep Learning
  116. When Role-playing, Do Models Believe What They Say?
  117. Hubs or Fringes: Pretraining Data Selection via Web Graph Centrality
  118. OmniLoc: A Geometry-Aware Foundation Model for Anchor-Free UE Localization Across Diverse Indoor Environments
  119. Unbiased Derivative Estimation for Stationary Mean of Parameterized Markov chains
  120. Accurate and Resource-Efficient Federated Continual Learning
  121. Towards Fully Automated Exam Grading: Fairness-Aware Recognition of Handwritten Answers with Foundation Models
  122. Mahalanobis-Guided Latent OOD Detection for Hybrid ES-DRL Control in Time-Varying Systems
  123. CRUMB: Efficient Prior Fitted Network Inference via Distributionally Matched Context Batching
  124. Evaluating and Combating the Impact of Concept Drift on the Performance of Machine Learning-Based Phishing Detection Systems
  125. Density estimation for Hellinger via minimum-distance estimators: mixtures of Gaussians, log-concave, and more
  126. PT-WNO: Point Transformer with Wavelet Neural Operator for 3D Point Cloud Semantic Segmentation
  127. LSTM-Based Detection of Structural Breaks in Property Insurance Loss Reserving: A Climate-Informed Approach
  128. APEX: Automated Prompt Engineering eXpert with Dynamic Data Selection
  129. Exploring Adaptive Masked Reconstruction for Self-Supervised Skeleton-Based Action Recognition
  130. 3D-CBM: A Framework for Concept-Based Interpretability in Generative 3D Modeling
  131. Forecasting Future Behavior as a Learning Task
  132. The Power of Test-Time Training for Approximate Sampling
  133. Mirror Descent Beyond Euclidean Stability: An Exponential Separation in Initialization Sensitivity
  134. Towards a Bridge Layer Between Bibliographic and Formalized Mathematical Knowledge
  135. Gumbel-BEARD: Automatic Layer Selection for Self-Supervised Adaptation of Whisper in Low-Resource Domains
  136. SOMA-SQL: Resolving Multi-Source Ambiguity in NL-to-SQL via Synthetic Log and Execution Probing
  137. Context-Aware Multimodal Claim Verification in Spoken Dialogues
  138. Signed Compression Progress on a Sealed Audit is Goodhart-Resistant
  139. MPC-Patch-Bench: Security-Aware LLM Code Patch for Multi-Party Computation
  140. Spatially Masked Regression Reveals Local and Distributed Predictability in Electrophysiological Recordings
  141. GraphGP: Scalable Gaussian Processes with Vecchia's Approximation
  142. Scenario-based Probing and Steering Cultural Values in Large Language Models--Extended Version
  143. Recursive Binding on a Budget: Subspace Carving in Order-p Tensor Memories
  144. A Scalable PyTorch Abstraction for Multi-GPU Gaussian Splatting
  145. Small Experiments, Cheaper Decisions: A Case Study in Staged Promotion for Micro-Pretraining
  146. GLACIER: A Multimodal Student-Teacher Foundation Model for Molecular Property Prediction
  147. From Simulation to the Real-World: An In-Field 6D Pose Dataset and Baseline for Robotic Strawberry Harvesting
  148. Automated Mediator for Human Negotiation: Pre-Mediation via a Structured LLM Pipeline
  149. When Probing Accuracy Saturates, Fragility Resolves: A Complementary Metric for LLM Pre-Training Analysis
  150. The Dynamics of Human and AI-Generated Language: How Semantics Fluctuates across Different Timescales
  151. NSVQ: Mitigating Codebook Collapse by Stabilizing Encoder Drift in Vector Quantization
  152. A PubMed-Scale Dataset of Structured Biomedical Abstracts
  153. TileFuse: A Fused Mixed-Precision Kernel Library for Efficient Quantized LLM Inference on AMD NPUs
  154. SwiftCTS: Fast Cross-Design Prediction and Pareto Optimization of Clock Tree Metrics via Few-Shot Calibration
  155. Annealed Entropic Allocation for Ranking and Selection
  156. Energy-Conserved Neural Pipelines: Attenuating Error Propagation in Modular Neural Networks via Physical Conservation Constraints
  157. Quantized Stochastic Primal-Dual Methods for Distributed Optimization under Relaxed Global Geometry
  158. Can AI Agents Synthesize Scientific Conclusions?
  159. DarkVGGT: Seeing Through Darkness Using Thermal Geometry
  160. Semantic Segmentation of Node and Edge Diagrams for Assistive Technology
  161. Learning from almost nothing: How neural networks survive heavy input corruption
  162. TRON: Tracing Rays to Orchestrate a Neural Renderer for 3D Gaussian Reconstructions
  163. SPADE: Split-and-Delay Embeddings for Autoregressive High-Granularity Calorimeter Simulation
  164. Interpretable Neural Marked Statistics for Cosmological Inference
  165. Intelligent Skin Cancer Detection Using a Multispectral Metasurface and a Hybrid
  166. FreeBridge: Variational Schr"odinger Bridges for Cellular Transition Dynamics
  167. EventRadar: Long-Range Visual UAV Discovery through Spatiotemporal Event Sensing
  168. Fixed-Parameter Tractability of Private Synthetic Data Generation
  169. Massive Open-Vocabulary Keyword Spotting
  170. RoVE: Rotary Value Embeddings Attention for Relative Position-dependent Value Pathways
  171. Multi-agent rendezvous in fluid flows via reinforcement learning
  172. Federated continual learning: A comprehensive survey on lifelong and privacy-preserving learning over distributed and non-stationary data
  173. Quantifying Subliminal Behavioral Transfer Ratios in Language Model Distillation
  174. Traits Run Deeper: Trait-Specific Asymmetric Fusion for Multimodal Personality Assessment
  175. LakeFM: Toward a Foundation Model for Aquatic Ecosystems Using Irregular Multivariate Multi-depth Time Series Data
  176. A prior-free blind detection of information leakage from model predictions
  177. OmniBioTwin: A System-of-Twinned-Systems Framework for Health Digital Twins
  178. Geometric bias in eigenspace perturbation under random heterogeneous noise
  179. PermDoRA -- Understanding Adapter Interference in Language Models: Limits of Parameter-Space Geometry
  180. Loss Landscape Diagnosis for Gradient-Based Gray-Scott System Inversion: Disentangling the Roles of PINN Components
  181. When to Align, When to Predict: A Phase Diagram for Multimodal Learning
  182. A Unifying Lens on Supervised Fine-Tuning Through Target Distribution Design
  183. AnyMod-LLVE: Low-Light Video Enhancement with Modality-Agnostic Inference
  184. Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories
  185. Bellman-sufficient Information Complexity
  186. Piper: A Programmable Distributed Training System
  187. Multi-Faceted Interactivity Alignment in Full-Duplex Speech Models
  188. Flaws in the LLM Automation Narrative
  189. COGENT: Continuous Graph Emulators with Neural Ordinary Differential Equations for Long-Term Physical Forecasting
  190. Ito maps for any-step SDEs
  191. Efficiently Learning Drifting Halfspaces with Massart Noise
  192. MOFA-VTON: More Fashion Possibilities with Fine-Grained Adaptations in Virtual Try-On
  193. OncoTraj: a public benchmark for longitudinal resistance prediction in EGFR-mutant non-small-cell lung cancer on osimertinib
  194. First-Order Trajectory Matching: Fast Ensemble Predictions of Chaotic, Turbulent, Stochastic Systems
  195. Conformal Prediction for Dyadic Regression Under Complex Missingness
  196. UniPET: a universal network for high-quality PET image denoising across varied dose reduction factors
  197. Robust Regression of General ReLUs with Queries
  198. DMT: Demographic Conditioning, Morphology-Enhanced Transformer for Cuffless Blood Pressure Estimation from PPG Signals
  199. Overcoming Rank Collapse in Feedback Alignment
  200. Data-Driven Dynamic Assortment in Online Platforms: Learning about Two Sides
  201. Towards Autonomous Accelerator Design: FPGA Accelerator Generation with SECDA
  202. Designed by Journalists, but Is It for Readers? Rethinking AI Disclosures and Transparency in News
  203. Multimodal Brain Tumour Classification Using Feature Fusion
  204. FADA: Accessible fetal ultrasound interpretation and annotation with a selectively distilled unified vision-language model
  205. PhantomBench: Benchmarking the Non-existential Threat of Language Models
  206. Limitations of Learning Tanh Neural Networks with Finite Precision
  207. Do Transformers Actually Help Intrusion Detection? A Temporal Sequence Evaluation on CIC-IDS2017
  208. IDEAL: In-DEpth ALignment Makes A Discrete Representation AutoEncoder
  209. Unifying Local Communications and Local Updates for LLM Pretraining
  210. VISTA: A Versatile Interactive User Simulation Toolkit for Agent Evaluation
  211. GRAFT: Gain-Recalibrated Adapters for Transformer-Based Neural Population Activity Modeling
  212. CIAware-Bench: Benchmarking Control Intervention Awareness Across Frontier LLMs
  213. Flexible Kernels for Protein Property Prediction
  214. Generalized Conformal Predictive Systems Under Distributional Shifts
  215. AuRA: Internalizing Audio Understanding into LLMs as LoRA
  216. U-TTT: Towards Generalizable PET Image Denoising via Test-Time Training
  217. Generative Archetype-Grounded Item Representations for Sequential Recommendation
  218. Measuring Human Value Expression in Social Media Texts: Calibrated LLM Annotation and Encoder Transfer
  219. Data-Driven Runway and Taxiway Exits Prediction of Landing Aircraft: A Case Study at Hartsfield-Jackson Atlanta International Airport
  220. Superficial Beliefs in LLM Decision-Making
  221. Numbers Beat Words: A Rigorous On-Premise Benchmark for Coupled MIMO Controller Tuning
  222. An Uncertainty Estimation Framework for Dose Accumulation in Adaptive Radiotherapy: Application to CBCT-Guided Radiotherapy for Cervical Cancer
  223. Who Brought Easter Eggs to Eid? Auditing LLM-Generated Cultural Translation of Math Word Problems Across Languages and Regions
  224. Understanding and mitigating the risks of OpenClaw for non-technical users: A practical guide with Skill
  225. IPSM-Bench: A New Intermediate Phase Segmentation Benchmark in Microstructure Images of Zinc-Based Absorbable Biomaterials
  226. Analog Quantum Asynchronous Event-Based Graph Neural Network
  227. AnimaSpark: A Feed-Forward Method for Animating Arbitrary 3D Objects
  228. Bellman-Taylor Score Decoding for Markov Decision Processes with State-Dependent Feasible Action Sets
  229. Learning Doubly Sparse Explicitly Conditioned Transforms
  230. Optimizing 2D Input Representations and Sub-phase Fusion Strategies for Differential Diagnosis of Asthma and COPD Using CNN- and GRU-Based Networks
  231. Quo Vadis, Visual In-Context Learning? A Unified Benchmark Across Domains and Tasks
  232. Population-Aware Physics-Informed Neural Particle Flow for Robust Spacecraft Bayesian Navigation
  233. Mind the Gap: Can Frontier LLMs Pass a Standardized Office Proficiency Exam?
  234. Architect-Ant: Editable Automatic Furnishing of Architectural Floor Plans
  235. Recalling Too Well: Sycophancy Evaluation and Mitigation in Memory-Augmented Models
  236. Express Language Modeling
  237. Generative Explainability for Next-Generation Networks: LLM-Augmented XAI with Mutual Feature Interactions
  238. Democratising Camera Trap AI: An Open-Source Model for Detecting UK Mammals
  239. PENet+: A Lightweight Residual Transformer Framework for Efficient Image Steganalysis
  240. A Systematic Approach for Selecting Trajectories for Data Augmentation
  241. Provenance Tracking in AI Compilers through the Lens of Coalgebra
  242. CLP: Collocation-Length Prediction for Zero-Loss Adaptive Multi-Token Inference
  243. A Constrained Natural-Language Interface for Variational Multi-Physics Finite Element Simulations in FEniCS
  244. Task Robustness via Re-Labelling Vision-Action Robot Data
  245. Range Penalization: Theoretical Insights with Applications in Federated Learning
  246. Conservation Laws from Data Symmetry in Neural Networks
  247. What Do Deepfake Speech Detectors Actually Hear?
  248. Ethical and Technical Limits of Deepfake Speech Datasets
  249. Non-linear mechanical field reconstruction coupling recurrent neural networks with physics-informed graph neural networks
  250. RAT: Reference-Augmented Training for ASV Anti-Spoofing
  251. Human-AI Teaming Through the Lens of Calibration
  252. Beyond Model Size: Probing the Gaps in Visual in-Context Learning by Training a Tiny Model
  253. Pose-ICL: 3D-Aware In-Context Learning for Pose-Controllable Subject Customization
  254. Flash-GMM: A Memory-Efficient Kernel for Scalable Soft Clustering
  255. The 1st PortraitCraft Challenge: A CVPR 2026 Workshop Competition on Portrait Composition Understanding and Generation
  256. Improving Text-Instance Alignment Of Foreground Conditioned Out-Painting Via Customized Concept Embedding
  257. Optimal Post-Training Quantization Scales and Where to Find Them
  258. Sleep EEG Signal Criticality as a Non-Invasive Predictor of Cognitive Decline in Dementia
  259. Listen, Look, and Learn: Learning Without Forgetting through SAM-Audio
  260. Large-scale semantic mapping of learner agency and autonomy reveals what measurement and generative AI research overlook
  261. XtrAIn: Training-Guided Occlusion for Feature Attribution
  262. Advancing Wood Identification in the Philippines: Utilizing the Xylorix Platform for Efficient AI Model Development and Deployment for Five Key Species
  263. Schmidt Decomposition-Based Methods for Efficient Quantum Image Encoding
  264. When Do Autoregressive Sequence Models Forecast Physical Wavefields? A Controlled Study on Synthetic Seismograms
  265. From Perception to Action: Can UI Interventions Foster Sustainable LLM Chatbot
  266. Embodiment-conditioned Generalist Control for Multirotor Aerial Robots
  267. Janus: A Benchmark for Goal-Conditioned Information Distortion in LLMs
  268. ConvMemory v2: A Recall-Preserving Top-10 Evidence Reranker for Conversational Memory Retrieval
  269. HarmoView: Harmonizing Multi-View Constraints for Identity-Consistent Video Generation
  270. A Unified Siamese Learning Framework for Zero-Day Anomaly Detection and Classification in Optical Networks
  271. Encoding the Euler Characteristic Transform
  272. K-Forcing: Joint Next-K-Token Decoding via Push-Forward Language Modeling
  273. IMPACT: Learning Internal-Model Predictive Control for Forceful Robotic Manipulation
  274. Deep learning for echo sounder data
  275. Moonshine: An Autonomous Mathematical Research Agent Centered on Conjecture Generation
  276. SCAIL-2: Unifying Controlled Character Animation with End-to-End In-Context Conditioning
  277. Boosting ECG Classification Performance by Pre-training with Synthesized Data
  278. Evaluating Research-Level Math Proofs via Strict Step-Level Verification
  279. CITRAS-FM: Tiny Time Series Foundation Model for Covariate-Informed Zero-Shot Forecasting
  280. READER: Dynamic LLM Provenance from Query-Varying Interactions
  281. A Multimodal RGB and Events Dataset for Hand Detection in First-Person View
  282. Closing the Modality Gap in Zero-Shot HAR: Contrastive Training and Separability-Optimized Prototypes on IMU Data
  283. Accelerating NeurASP with vectorization and caching
  284. A Bayesian Network Approach for Enhancing Security-Focused Decision Support Systems
  285. Recovering the Zipfian Distribution in Unsupervised Term Discovery
  286. Secure Aggregation with Top-K Sparsification in Decentralized Federated Learning
  287. From Patches to Patients: A study of the tile-to-slide performance transferability in Digital Pathology
  288. Can we trust our models? Epistemic calibration in second-order classification
  289. Spatially Selective Self-Training for Unsupervised Building Change Detection
  290. Asynchronous Decentralized Federated Learning over Lossy Wireless Links via Reception- and Age-Aware Aggregation
  291. Correcting Variable Importance Scored by Random Forests
  292. ZODS-RS -- Zero-training Oriented Detection & Segmentation for Remote Sensing
  293. ArabiGEE: A Hierarchical Taxonomy for Arabic Grammatical Error Explanation
  294. DD-INR: Dynamics-Driven Implicit Neural Representation for Accelerated Whole-Brain Functional MRI Reconstruction
  295. Detecting Knowledge Gaps from Conversational AI Interactions Using Curriculum Prerequisite Graphs
  296. Patient-Level Diagnosis of Acute Myeloid Leukemia via Deep Learning Analysis of Bone Marrow Smear
  297. SPACR: Single-Pass Adaptive Training of Uncertainty-Aware Conformal Regressors
  298. Pre-AF 13: An Interpretable Atrial Fibrillation Risk Score Mined from Discharge Reports
  299. Continual LLM Upcycling: A Predictor-Gated Bank-Wise Sparsity Training Recipe for Dense-to-Sparse LLMs
  300. Transformer Based Model for Spatiotemporal Feature Learning in EEG Emotion Recognition
  301. Attention Expansion: Enhancing Keyphrase Extraction from Long Documents with Attention-Augmented Contextualized Embeddings
  302. ++nnU-Net: Scaling nnU-Net with Prefix-Based Data Augmentation
  303. Unifying Data, Memory, and Compute Efficiency in LLM training: A Survey
  304. Vector Map as Language: Toward Unified Remote Sensing Vector Mapping
  305. Using the YOLOv12 Model for Verifying the Correct Color Sequence of Wires in Network Cables (Patch Cords) on the Production Line
  306. Efficient AI-Inspired Reduction of Feynman Integrals via Tube Seeding
  307. Don't waste SAM
  308. Do LLMs Make Neural Distinguishers Wise?
  309. An adaptive framework for the axisymmetric pulsar magnetosphere using physics-informed Kolmogorov-Arnold networks
  310. UniDexTok: A Unified Dexterous Hand Tokenizer from Real Data
  311. PL-KKT-hPINN: Enforcing Nonlinear Equality Constraints on Neural Networks via Piecewise-Linear Projection
  312. One Step Closer to Ground Truth: A Multi-Scale Residual-Aware Representation Learning Pipeline for Predicting Time Series Data
  313. Multilingual Word-Level Forced Alignment with Self-Supervised Representations and Learned Dynamic Programming
  314. ClusBench: The Clustering Benchmark Data Resource You've All Been Waiting For (?)
  315. In Defense of Information Leakage in Concept-based Models
  316. Analyzing Training-Free Corruption Detection for Object Detection Datasets
  317. Accounting for AI Inference in Corporate GHG Inventories: A Four-Tier Methodology for Scope 3 Category 1 Reporting
  318. Post-Quantum Secure Federated DeFi for Inclusive Banking
  319. Are We Evaluating Knowledge or Phrasing? Mitigating MCQA Sensitivity with ParaEval
  320. Envision4D: Envisioning Visual Futures via Feed-forward 4D Gaussian Splatting for Autonomous Driving
  321. Speaker Group Encoding in Self-supervised Speech Recognition Models
  322. Dynamic Linear Attention
  323. ManiSplat: Manipulation Trajectory Synthesis from Monocular Video via Decoupled 3D Gaussian Splatting
  324. PhysMetrics.Weather: An Evaluation Framework for Physical Consistency in ML Weather Models
  325. ChartLens: A Dual-Branch Framework for Chart Data Correction and Factual Summary Refinement
  326. Is Fairness Truly Fair? Towards Reliable Lipschitz Fairness in Multi-Task Learning via Fixed-texorpdfstringδdelta Alignment
  327. Leveraging Metric Depth for Relative Depth Prediction
  328. Profy: Interpretable Visualization of Expertise-Dependent Motor Skills Toward Supporting Piano Practice
  329. STORM: Stepwise Token Optimization with Reward-Guided Beam Search
  330. Dexterous Point Policy: Learning Point-based Dexterous Hand Policies from Human Demonstrations
  331. Small Data, Big Noise: Adversarial Training for Robust Parameter-Efficient Fine-Tuning
  332. Globally Localizing Lunar Rover in Pixels via Graph Alignment
  333. Dmsh: A Multi-Agent Reinforcement Learning Framework for All-Quad Mesh Generation
  334. Toward Proactive RF Charging Scheduling: Generative AI for Decision Support
  335. Embedding Hybrid Systems into Continuous Latent Vector Fields
  336. From Data Heterogeneity to Convergence: A Data-Centric Review of Federated Learning
  337. Segment and Select: Vision-Language Segmentation in 3D Scenarios
  338. Dirichlet-Guided Group Forecasting for Alleviating Over-smoothing in Time Series Forecasting
  339. Towards Diverse Scientific Hypothesis Search with Large Language Models
  340. NOVA: Symbolic Regression Discovery of Interpretable Car-Following and Lane-Change Models with Driver Heterogeneity
  341. Drawing with Strangers: Population Scaling Drives Zero-Shot Mutual Intelligibility in Emergent Sketching
  342. ParaBridge: Bridging Paralinguistic Perception and Dialogue Behavior in Speech Language Models
  343. Convergence of Monte Carlo Optimistic Policy Iteration: Beyond Uniform State-Action Updates
  344. Accelerating SAV-based optimization via randomized low-rank Hessian approximation
  345. Deterministic Denominator Design for Localized Tamed Stochastic Gradient Langevin Dynamics
  346. Benchmarking Knowledge Editing using Logical Rules
  347. LentiAvatar: Pseudo-Multiview Reconstruction and Subpixel Prism Rendering for Real-Time Stereoscopic Communication
  348. Unsupervised Deep Learning for Limited-Angle STEM-EDX Tomography -- Application to 3D Chemical Analysis of Phase-Change Memory Devices
  349. Flexible Flows for Biological Sequence Design
  350. GRAR: Glass-induced Reflection Artifact Removal in LiDAR Point Clouds
  351. LC-QAT: Data-Efficient 2-Bit QAT for LLMs via Linear-Constrained Vector Quantization
  352. Machine Learning Methods for Studying Latent Neural Activity Dynamics
  353. A Reliable Fault Diagnosis Method Based on Belief Rule Base Consider Robustness Analysis
  354. PathRelax: Parallel-Path Relaxed Speculative Jacobi Decoding for Accelerating Auto-Regressive Text-to-Image Generation
  355. A complementary study on PlanGPT: Evaluation with defined Performance Metrics and comparison with a planner
  356. 5% > 100%: Flatness Preference is All You Need for Multimodal Parameter-Efficient Fine-Tuning
  357. Stop Early, Spend Less: Hidden-State Probes as a Practical Recipe for Streaming Moderation of LLM Outputs
  358. Advancing the State-of-the-Art in Empirical Privacy Auditing
  359. 3D-CoS: A New 3D Reconstruction Paradigm Based on VLM Code Synthesis
  360. Trading Utility for Dynamic Fairness in Multiple Resource Division with Sequential Demand
  361. Detecting Speculative Language in Biomedical Texts using Recurrent Neural Tensor Networks
  362. A Mean-Field Analysis of Multi-Head Self-Attention under Cross-Entropy Training
  363. Geometric Coastline Localization using Vision-Language Models
  364. Large Language Models as Modal Models in Linguistics
  365. UPLOTS: A Unified Pretrained Language Model for Constrained Time-series Generation
  366. ERAlign: Energy-based Representation Alignment of GNNs and LLMs on Text-attributed Graphs
  367. LakeQA: An Exploratory QA Benchmark over a Million-Scale Data Lake
  368. Leveraging Social Media Data for COVID-19 Studies
  369. Minimum Distortion Quantization with Specified Output Distribution
  370. The Distributed Detectability Band Against Marginal-Preserving Attacks
  371. SpenseGPT: Practical One-shot Pruning Enabling Sparse and Dense GEMMs for LLM Inference
  372. ASTRA-sim 3.0: Next-Level Distributed Machine Learning Simulations via High-Fidelity GPU and Infrastructure Modeling
  373. Parallel Causal Associative Fields: Gated Sparse Memory for Long-Context Language Modeling
  374. Vision-Assisted Foundation Model for Solving Multi-Task Vehicle Routing Problems
  375. Which LoRA? An Empirical Study on the Effectiveness of LoRA Techniques During Multilingual Instruction Tuning
  376. A Comprehensive Inference-Time Augmentation Framework in Physiological Signals: Application to PPG-Based AF Detection
  377. Time-frequency localization of bird calls in dense soundscapes
  378. FOGO: Forgetting-aware Orthogonalization Optimizer
  379. Harnessing the Collective Intelligence of AI Agents in the Wild for New Discoveries
  380. Selection, Not Salience: The Shape and Limits of Personalization in Social Highlighting
  381. Efficient RWKV-based Representation Learning for 3D Point Clouds
  382. Validation-Stage Combinatorial Fusion Analysis for Imbalanced Credit-Card Fraud Detection
  383. Beyond Static Evaluation: Co-Evolutionary Mechanisms for LLM-Driven Strategy Evolution in Adversarial Games
  384. Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval
  385. Towards Critical Branching Mechanism in Recurrent Neural Networks
  386. Expert-Level Crisis Detection in Mental Health Conversations
  387. FSS-Net: Frequency-Spatial Synergy Network with Wavelet Attention for Carotid Artery Ultrasound Segmentation
  388. Bidirectional Random Projections
  389. Belief-Space Control for Personalized Cancer Treatment via Active Inference
  390. PF-Trans: Physics-Embedded Frequency-Aware Transformer for Spectral Reconstruction
  391. ClinReadNet: A clinical reading-inspired network for low-dose abdominal CT image quality assessment
  392. Speech Meets ELF: Audio Conditional Continuous-Target Diffusion for Speech Recognition and Translation
  393. Benchmarking stereo reconstruction for 3D printable Martian terrain models
  394. Near-Exponential Convergence Rates for kNN Classification based on Boltzmann Margin
  395. KG-SoftMAP: Soft Knowledge-Graph Priors for Bayesian Network Structure Learning from Sparse Discrete Data
  396. Multi-Angular Reflectance Anisotropy Observed from UAV Multispectral Imagery
  397. Magnetic HIP-NN for spin dynamics in disordered itinerant magnets
  398. Beyond Explaining Predictions: Logic-Based Explanations for Confidence in Machine Learning Models
  399. Privacy-Preserving Credit Risk Prediction with Alternative Data
  400. Building Change Detection in Earthquake: A Multi-Scale Interaction Network and A Change Detection Dataset
  401. Content-Induced Spatial-Spectral Aggregation Network for Change Detection in Remote Sensing Images
  402. The Order Matters: Sequential Fine-Tuning of LLaMA for Coherent Automated Essay Scoring
  403. Rank Collapse, Fixed Points, and the Renormalization Group Structure of MLP Residual Networks
  404. Mobility Anomaly Generation using LLM-Driven Behavior with Kinematic Constraints
  405. Dissect and Prune: Enhancing Robustness in AI-Generated Image Detection
  406. Where You Inject Diversity Matters: A Unified Framework for Diverse Generation
  407. What Spatial Memory Must Store: Occlusion as the Test for Language-Agent Memory
  408. From Context-Aware to Conflict-Aware: Generalizing Contrastive Decoding for Knowledge Conflict in LLMs
  409. k-Nearest Neighbors in Gromov--Wasserstein Space
  410. LLM-Guided Neural Architecture Search for Robust Co-Design of Physical Neural Networks
  411. When Metrics Disagree: A Meta-Analysis of Knowledge-Graph-Completion Model Benchmarking
  412. Sim2Schedule: A Simulator-Guided LLM Framework for Autonomous Open-Pit Mine Scheduling
  413. OpenRTLSet: A Fully Open-Source Dataset for Large Language Model-based Verilog Module Design
  414. Revisiting Positive Samples in Graph Contrastive Learning: From the Perspective of Message Passing
  415. Benchmarking and Exploring the Capabilities of LLMs for Attack Investigations
  416. Overlapped Wavelet Diffusion for Low-Light Image Enhancement
  417. Supervised Fine-tuning with Synthetic Rationale Data Hurts Real-World Disease Prediction
  418. Towards Robust Arabic Speech Emotion Recognition with Deep Learning
  419. Lightweight Adaptive Feature Composition for Heterogeneous Downstream Adaptation of Wireless Foundation Models
  420. Hierarchical Policies from Verbal and Egocentric Human Signals for Natural Human-Robot Interaction
  421. FoA-SR: Faithful or Aesthetic? Profile-Aware Preference Optimization for Real-World Image Super-Resolution