mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 5 Feb 2026

515 papers

  1. Visual Exclusivity Attacks: Automatic Multimodal Red Teaming via Agentic PlanningLLM agents and tool use → Agent threats, guardrails and governance +1
  2. AriadneMem: Threading the Maze of Lifelong Memory for LLM AgentsLLM agents and tool use → Agent memory systems
  3. TRACE: Trajectory-Aware Comprehensive Evaluation for Deep Research AgentsLLM agents and tool use → Web, search, and research agents
  4. From Bias Mitigation to Bias Negotiation: Governing Identity and Sociocultural Reasoning in Generative AILLM reasoning → Reasoning benchmarks and evaluation
  5. The Story is Not the Science: Execution-Grounded Evaluation of Mechanistic Interpretability ResearchMechanistic interpretability → Circuits and mechanistic analysis
  6. Beyond single-channel agentic benchmarkingLLM agents and tool use → Agent threats, guardrails and governance
  7. AnCoder: Anchored Code Generation via Discrete Diffusion ModelsDiffusion models → Discrete and text diffusion
  8. BRIDGE: Bridging Reasoning In Distillation Gap Elimination via Structure-Aware MaskingLLM reasoning → Prompting and chain-of-thought reasoning
  9. ProMoral-Bench: Evaluating Prompting Strategies for Moral Reasoning and Safety in LLMsLLM reasoning → Reasoning benchmarks and evaluation +2
  10. TemporalBench: A Benchmark for Evaluating LLM-Based Agents on Contextual and Event-Informed Time Series TasksLLM agents and tool use → Financial trading and forecasting agents
  11. interwhen: A Generalizable Framework for Steering Reasoning Models with Test-time VerificationLLM reasoning → Test-time compute and efficient thinking
  12. Bird-SR: Bidirectional Reward-Guided Diffusion for Real-World Image Super-ResolutionDiffusion models → Inverse problems and image restoration
  13. TACIT: Transformation-Aware Capturing of Implicit ThoughtLLM reasoning → Multimodal reasoning +1
  14. Is my model "mind blurting"? Interpreting the dynamics of reasoning tokens with Recurrence Quantification Analysis (RQA)LLM reasoning → Test-time compute and efficient thinking
  15. GRP-Obliteration: Unaligning LLMs With a Single Unlabeled PromptLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  16. Steering Safely or Off a Cliff? Rethinking Specificity and Robustness in Inference-Time InterventionsLLM reasoning → Test-time compute and efficient thinking
  17. REBEL: Hidden Knowledge Recovery via Evolutionary-Based Evaluation LoopLLM safety and security → Machine unlearning
  18. Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distributionLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  19. RuleSmith: Multi-Agent LLMs for Automated Game BalancingLLM agents and tool use → Reinforcement learning for LLM agents
  20. Do It for HER: First-Order Temporal Logic Reward Specification in Reinforcement Learning (Extended Version)Deep reinforcement learning methods → Interpretable and logic-guided RL
  21. Coupled Local and Global World Models for Efficient First Order RLWorld models → Embodied and robot world models
  22. Cross-Modal Redundancy and the Geometry of Vision-Language EmbeddingsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  23. Addressing the Waypoint-Action Gap in End-to-End Autonomous Driving via Vehicle Motion ModelsEnd-to-end autonomous driving → End-to-end system architecture
  24. DeDPO: Debiased Direct Preference Optimization for Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics +1
  25. f-FUM: Federated Unlearning via min--max and f-divergenceLLM safety and security → Federated unlearning and poisoning +1
  26. PhenoLIP: Integrating Phenotype Ontology Knowledge into Medical Vision-Language PretrainingMultimodal LLMs / vision-language models → Medical vision-language models
  27. Large Language Model Reasoning FailuresLLM reasoning → Reasoning benchmarks and evaluation
  28. M3: High-fidelity Text-to-Image Generation via Multi-Modal, Multi-Agent and Multi-Round Visual ReasoningLLM reasoning → Multimodal reasoning +1
  29. Stop the Flip-Flop: Context-Preserving Verification for Fast Revocable Diffusion DecodingDiffusion models → Discrete and text diffusion
  30. Driving with DINO: Vision Foundation Features as a Unified Bridge for Sim-to-Real Generation in Autonomous DrivingDiffusion models → Diffusion and flow policies for robotics
  31. Latent Structure Emergence in Diffusion Models via Confidence-Based FilteringDiffusion models → Diffusion foundations and sampling
  32. MoSE: Mixture of Slimmable Experts for Efficient and Adaptive Language ModelsMixture-of-experts → MoE large language models
  33. Optimistic Training and Convergence of Q-Learning -- Extended VersionDeep reinforcement learning methods → RL theory and sample complexity
  34. Flow Matching for Offline Reinforcement Learning with Discrete ActionsDiffusion models → Diffusion and flow policies for robotics +1
  35. Self-Improving World Modelling with Latent ActionsWorld models → Latent predictive world models +2
  36. Urban Spatio-Temporal Foundation Models for Climate-Resilient Housing: Scaling Diffusion Transformers for Disaster Risk PredictionDiffusion models → Flow matching, time series and science
  37. Jackpot: Optimal Budgeted Rejection Sampling for Extreme Actor-Policy Mismatch Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  38. ALIEN: Analytic Latent Watermarking for Controllable GenerationLLM safety and security → Watermarking generated content and models
  39. SVRepair: Structured Visual Reasoning for Automated Program RepairLLM reasoning → Reasoning for agents, planning and code
  40. Transformer-Based Reinforcement Learning for Autonomous Orbital Collision Avoidance in Partially Observable EnvironmentsDeep reinforcement learning methods → RL for robot navigation and UAV control
  41. Predicting Camera Pose from Perspective Descriptions for Spatial ReasoningLLM reasoning → Spatial and embodied reasoning +1
  42. SwimBird: Eliciting Switchable Reasoning Mode in Hybrid Autoregressive MLLMsLLM reasoning → Multimodal reasoning +1
  43. DyTopo: Dynamic Topology Routing for Multi-Agent Reasoning via Semantic MatchingLLM reasoning → Reasoning for agents, planning and code +1
  44. CommCP: Efficient Multi-Agent Coordination via LLM-Based Communication with Conformal PredictionLLM agents and tool use → General LLM agent frameworks and benchmarks
  45. Thinking with Geometry: Active Geometry Integration for Spatial ReasoningLLM reasoning → Spatial and embodied reasoning +1
  46. DFlash: Block Diffusion for Flash Speculative DecodingDiffusion models → Discrete and text diffusion +1
  47. InterPrior: Scaling Generative Control for Physics-Based Human-Object InteractionsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  48. V-Retrver: Evidence-Driven Agentic Reasoning for Universal Multimodal RetrievalLLM reasoning → Multimodal reasoning +2
  49. Can Vision Language Models Learn Intuitive Physics from Interaction?Multimodal LLMs / vision-language models → Embodied and 3D vision-language models
  50. Splat and Distill: Augmenting Teachers with Feed-Forward 3D Reconstruction For 3D-Aware DistillationKnowledge distillation → Detection and dense prediction distillation
  51. PhysicsAgentABM: Physics-Guided Generative Agent-Based ModelingLLM agents and tool use → Social simulation and multi-agent debate
  52. Learning Query-Aware Budget-Tier Routing for Runtime Agent MemoryLLM agents and tool use → Agent memory systems
  53. Diffusion Model's Generalization Can Be Characterized by Inductive Biases toward a Data-Dependent Ridge ManifoldDiffusion models → Diffusion foundations and sampling
  54. Multi-Token Prediction via Self-DistillationEfficient LLM inference and serving → Speculative decoding +1
  55. GenArena: How Can We Achieve Human-Aligned Evaluation for Visual Generation Tasks?Multimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  56. AgenticPay: A Multi-Agent LLM Negotiation System for Buyer-Seller TransactionsLLM agents and tool use → Financial trading and forecasting agents
  57. Visuo-Tactile World ModelsWorld models → Embodied and robot world models
  58. On the Role of Computation in Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  59. Diamond Maps: Efficient Reward Alignment via Stochastic Flow MapsDiffusion models → Diffusion and flow policies for robotics
  60. DSB: Dynamic Sliding Block Scheduling for Diffusion LLMsEfficient LLM inference and serving → Diffusion LLM and MoE inference
  61. From Human-Human Collaboration to Human-Agent Collaboration: A Vision, Design Philosophy, and an Empirical Framework for Achieving Successful Partnerships Between Humans and LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  62. SAGE: Benchmarking and Improving Retrieval for Deep Research AgentsLLM agents and tool use → Web, search, and research agents
  63. Learning to Share: Selective Memory for Efficient Parallel Agentic SystemsLLM agents and tool use → Agent memory systems
  64. Discrete diffusion samplers and bridges: Off-policy algorithms and applications in latent spacesDiffusion models → Diffusion foundations and sampling
  65. Better Source, Better Flow: Learning Condition-Dependent Source Distribution for Flow MatchingDiffusion models → Flow matching, time series and science
  66. f-GRPO and Beyond: Divergence-Based Reinforcement Learning Algorithms for General LLM AlignmentLLM reasoning → Reinforcement learning for reasoning +1
  67. AgenticTagger: Structured Item Representation for Recommendation with LLM AgentsLLM agents and tool use → Agentic recommender systems
  68. R3S: Refining and Recovering Reinforcement Signals for Multilingual Understanding and ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  69. Polyglots or Multitudes? Multilingual LLM Answers to Value-laden Multiple-Choice QuestionsLLM reasoning → Reasoning benchmarks and evaluation
  70. KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMsEfficient LLM inference and serving → KV cache optimization
  71. Quantum Reinforcement Learning with Transformers for the Capacitated Vehicle Routing ProblemDeep reinforcement learning methods → Quantum reinforcement learning
  72. Verification of the Implicit World Model in a Generative Model via Adversarial SequencesWorld models → World models for language agents
  73. Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning ModelsLLM reasoning → Reinforcement learning for reasoning
  74. Residual Reinforcement Learning for Waste-Container Lifting Using Large-Scale Cranes with Underactuated ToolsDeep reinforcement learning methods → RL for robot navigation and UAV control
  75. ContextBench: A Benchmark for Context Retrieval in Coding AgentsLLM agents and tool use → Software engineering coding agents
  76. When Elo Lies: Hidden Biases in Codeforces-Based Evaluation of Large Language ModelsLLM reasoning → Reasoning for agents, planning and code
  77. Dr. Kernel: Reinforcement Learning Done Right for Triton Kernel GenerationsDeep reinforcement learning methods → RL training of language and agent models
  78. Contour Refinement using Discrete Diffusion in Low Data RegimeDiffusion models → Medical imaging and segmentation
  79. Agent2Agent Threats in Safety-Critical LLM Assistants: A Human-Centric TaxonomyLLM agents and tool use → Agent threats, guardrails and governance
  80. Pathwise Test-Time Correction for Autoregressive Long Video GenerationDiffusion models → Video generation
  81. Constrained Group Relative Policy OptimizationLLM reasoning → Reinforcement learning for reasoning
  82. DLM-Scope: Mechanistic Interpretability of Diffusion Language Models via Sparse AutoencodersDiffusion models → Discrete and text diffusion +1
  83. BABE: Biology Arena BEnchmarkLLM reasoning → Clinical and biomedical applications
  84. OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality AttentionLLM reasoning → Audio-language model reasoning
  85. Reinforcement World Model Learning for LLM-based AgentsWorld models → World models for language agents +1
  86. UI-Mem: Self-Evolving Experience Memory for Online Reinforcement Learning in Mobile GUI AgentsLLM agents and tool use → GUI and mobile agents +1
  87. Weaver: End-to-End Agentic System Training for Video Interleaved ReasoningLLM reasoning → Multimodal reasoning +1
  88. TKG-Thinker: Towards Dynamic Reasoning over Temporal Knowledge Graphs via Agentic Reinforcement LearningLLM reasoning → Knowledge- and tool-augmented reasoning +1
  89. Bifrost: Steering Strategic Trajectories to Bridge Contextual Gaps for Self-Improving AgentsSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
  90. Focus-Scan-Refine: From Human Visual Perception to Efficient Visual Token PruningMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  91. NEX: Neuron Explore-Exploit Scoring for Label-Free Chain-of-Thought Selection and Model RankingLLM reasoning → Test-time compute and efficient thinking
  92. Allocentric Perceiver: Disentangling Allocentric Reasoning from Egocentric Visual Priors via Frame InstantiationLLM reasoning → Spatial and embodied reasoning +1
  93. Distributional Reinforcement Learning with Diffusion Bridge CriticsDeep reinforcement learning methods → RL with diffusion and flow models
  94. Cross-Domain Offline Policy Adaptation via Selective Transition CorrectionDeep reinforcement learning methods → Deep RL algorithms and representations
  95. Variational Speculative Decoding: Rethinking Draft Training from Token Likelihood to Sequence AcceptanceLLM reasoning → Test-time compute and efficient thinking +1
  96. PMT Waveform Simulation and Reconstruction with Conditional Diffusion NetworkDiffusion models → Inverse problems and image restoration
  97. RL-VLA3: A Flexible and Asynchronous Reinforcement Learning Framework for VLA TrainingVision-language-action models → Reinforcement learning and post-training
  98. LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility RewardsLLM reasoning → Test-time compute and efficient thinking
  99. FMPose3D: monocular 3D pose estimation via flow matchingDiffusion models → 3D, point cloud and scene generation
  100. LeakBoost: Perceptual-Loss-Based Membership Inference AttackLLM safety and security → Membership inference attacks
All 515
  1. Learning to Inject: Automated Prompt Injection via Reinforcement LearningLLM agents and tool use → Agent threats, guardrails and governance +2
  2. CompactRAG: Reducing LLM Calls and Token Overhead in Multi-Hop Question AnsweringRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  3. Mitigating Hallucination in Financial Retrieval-Augmented Generation via Fine-Grained Knowledge VerificationRetrieval-augmented generation → Legal and financial RAG
  4. A Dual-Loop Agent Framework for Automated Vulnerability ReproductionLLM agents and tool use → Agent threats, guardrails and governance
  5. OmniMoE: An Efficient MoE by Orchestrating Atomic Experts at ScaleMixture-of-experts → Efficient MoE training and inference systems
  6. Ethology of Latent SpacesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  7. Cost-Efficient RAG for Entity Matching with LLMs: A Blocking-based ExplorationLLM reasoning → Knowledge- and tool-augmented reasoning +1
  8. Graph-based Agent Memory: Taxonomy, Techniques, and ApplicationsLLM agents and tool use → Agent memory systems
  9. UAV Trajectory Optimization via Improved Noisy Deep Q-NetworkDeep reinforcement learning methods → RL for robot navigation and UAV control
  10. Structural Disentanglement in Bilinear MLPs via Architectural Inductive BiasLLM safety and security → Machine unlearning
  11. Rewards as Labels: Revisiting RLVR from a Classification PerspectiveLLM reasoning → Reinforcement learning for reasoning
  12. Mode-Dependent Rectification for Stable PPO TrainingDeep reinforcement learning methods → RL theory and sample complexity
  13. Path-Guided Flow Matching for Dataset DistillationDiffusion models → Flow matching, time series and science
  14. ADCA: Attention-Driven Multi-Party Collusion Attack in Federated Self-Supervised LearningLLM safety and security → Federated unlearning and poisoning
  15. Shiva-DiT: Residual-Based Differentiable Top-k Selection for Efficient Diffusion TransformersDiffusion models → Diffusion foundations and sampling
  16. Emulating Aggregate Human Choice Behavior and Biases with GPT Conversational AgentsLLM agents and tool use → Social simulation and multi-agent debate
  17. TOLEBI: Learning Fault-Tolerant Bipedal Locomotion via Online Status Estimation and Fallibility RewardsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  18. TangramSR: Can Vision-Language Models Reason in Continuous Geometric Space?LLM reasoning → Spatial and embodied reasoning +1
  19. VLN-Pilot: Large Vision-Language Model as an Autonomous Indoor Drone OperatorMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  20. Logical Guidance for the Exact Composition of Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  21. Unveiling Implicit Advantage Symmetry: Why GRPO Struggles with Exploration and Difficulty AdaptationLLM reasoning → Reinforcement learning for reasoning
  22. Multi-Task GRPO: Reliable LLM Reasoning Across TasksLLM reasoning → Reinforcement learning for reasoning
  23. Reasoning-guided Collaborative Filtering with Language Models for Explainable RecommendationLLM reasoning → LLM reasoning for recommendation
  24. Steering Large Reasoning Models towards Concise Reasoning via Flow MatchingLLM reasoning → Test-time compute and efficient thinking +1
  25. Detecting Misbehaviors of Large Vision-Language Models by Evidential Uncertainty QuantificationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  26. Conditional Diffusion Guidance under Hard Constraint: A Stochastic Analysis ApproachDiffusion models → Diffusion foundations and sampling
  27. AI Agent Systems for Supply Chains: Structured Decision Prompts and Memory RetrievalLLM agents and tool use → Social simulation and multi-agent debate
  28. Capture the Flags: Family-Based Evaluation of Agentic LLMs via Semantics-Preserving TransformationsLLM agents and tool use → Agent threats, guardrails and governance
  29. DECO: Decoupled Multimodal Diffusion Transformer for Bimanual Dexterous Manipulation with a Plugin Tactile AdapterDiffusion models → Diffusion and flow policies for robotics
  30. SDFP: Speculative Decoding with FIT-Pruned Models for Training-Free and Plug-and-Play LLM AccelerationEfficient LLM inference and serving → Speculative decoding
  31. A Unified Framework for Rethinking Policy Divergence Measures in GRPOLLM reasoning → Reinforcement learning for reasoning
  32. Clouding the Mirror: Stealthy Prompt Injection Attacks Targeting LLM-based Phishing DetectionLLM safety and security → Prompt injection and agent security
  33. ALIVE: Awakening LLM Reasoning via Adversarial Learning and Instructive Verbal EvaluationLLM reasoning → Reinforcement learning for reasoning
  34. Beyond Success Rates: Trainability and Extractability for Offline GCRLOffline RL and imitation learning from data → Diffusion and flow policies for offline RL +1
  35. DisCa: Accelerating Video Diffusion Transformers with Distillation-Compatible Learnable Feature CachingDiffusion models → Diffusion foundations and sampling
  36. BlitzRank: Principled Zero-shot Ranking Agents with Tournament GraphsLLM agents and tool use → Web, search, and research agents
  37. Structured Context Engineering for File-Native Agentic Systems: Evaluating Schema Accuracy, Format Effectiveness, and Multi-File Navigation at ScaleLLM agents and tool use → Agent memory systems
  38. DiLLS: Interactive Diagnosis of LLM-based Multi-agent Systems via Layered Summary of Agent BehaviorsLLM agents and tool use → Software engineering coding agents
  39. Causal Front-Door Adjustment for Robust Jailbreak Attacks on LLMsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +2
  40. Benchmarking Affordance Generalization with BusyBoxVision-language-action models → Generalist VLA models and benchmarks
  41. Once Correct, Still Wrong: Counterfactual Hallucination in Multilingual Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  42. Stable Velocity: A Variance Perspective on Flow MatchingDiffusion models → Flow matching, time series and science
  43. M2-Miner: Multi-Agent Enhanced MCTS for Mobile GUI Agent Data MiningLLM agents and tool use → GUI and mobile agents
  44. Multi-AD: Cross-Domain Unsupervised Anomaly Detection for Medical and Industrial ApplicationsKnowledge distillation → Detection and dense prediction distillation
  45. H-AdminSim: A Multi-Agent Simulator for Realistic Hospital Administrative Workflows with FHIR IntegrationLLM agents and tool use → Medical and scientific domain agents
  46. BadTemplate: A Training-Free Backdoor Attack via Chat Template Against Large Language ModelsLLM safety and security → Backdoor and data poisoning attacks
  47. Explainable Pathomics Feature Visualization via Correlation-aware Conditional Feature EditingDiffusion models → Medical imaging and segmentation
  48. Efficient Dataset Distillation for Pre-Trained Self-Supervised Models via Statistical Flow MatchingDiffusion models → Flow matching, time series and science
  49. Spider-Sense: Intrinsic Risk Sensing for Efficient Agent Defense with Hierarchical Adaptive ScreeningLLM agents and tool use → Agent threats, guardrails and governance
  50. IESR:Efficient MCTS-Based Modular Reasoning for Text-to-SQL with Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
  51. VRIQ: Benchmarking and Analyzing Visual-Reasoning IQ of VLMsLLM reasoning → Multimodal reasoning +1
  52. SAIL: Self-Amplified Iterative Learning for Diffusion Model Alignment with Minimal Human FeedbackDiffusion models → Diffusion and flow policies for robotics +1
  53. Variance Reduction Based Experience Replay for Policy OptimizationDeep reinforcement learning methods → Deep RL algorithms and representations
  54. Erase at the Core: Representation Unlearning for Machine UnlearningLLM safety and security → Machine unlearning
  55. Mining or Synthesis? Rethinking Exploration Efficiency in Iterative Alignment of Mathematical ReasoningLLM reasoning → Mathematical reasoning +1
  56. Multimodal Latent Reasoning via Hierarchical Visual Cues InjectionLLM reasoning → Multimodal reasoning +1
  57. Do Web Agents Investigate Before They Decide?LLM agents and tool use → Web, search, and research agents
  58. AgentXRay: White-Boxing Agentic Systems via Workflow ReconstructionLLM agents and tool use → Software engineering coding agents
  59. Consistency-Preserving Concept Erasure via Unsafe-Safe Pairing and Directional Fisher-weighted AdaptationDiffusion models → Robustness, privacy and adversarial aspects +1
  60. ProAct: Agentic Lookahead in Interactive EnvironmentsLLM agents and tool use → Reinforcement learning for LLM agents
  61. GAS: Enhancing Reward-Cost Balance of Generative Model-assisted Offline Safe RLOffline RL and imitation learning from data → Safe offline RL
  62. Accelerated Sequential Flow Matching: A Bayesian Filtering PerspectiveDiffusion models → Flow matching, time series and science
  63. Formal Synthesis of Certifiably Robust Neural Lyapunov-Barrier CertificatesDeep reinforcement learning methods → Safe and constrained RL
  64. MentorCollab: Large-to-Small Inference-Time Mentorship for Concise Reasoning in Language ModelsLLM reasoning → Test-time compute and efficient thinking
  65. FlashBlock: Attention Caching for Efficient Long-Context Block DiffusionDiffusion models → Video generation +1
  66. PieArena: Ranking and Profiling Language Agents in Realistic Negotiation ScenariosLLM agents and tool use → Social simulation and multi-agent debate
  67. Towards a Science of Collective AI: LLM-based Multi-Agent Systems Need a Transition from Blind Trial-and-Error to Rigorous ScienceLLM agents and tool use → General LLM agent frameworks and benchmarks
  68. Robust Inference-Time Steering of Protein Diffusion Models via Embedding OptimizationDiffusion models → Flow matching, time series and science
  69. Back to Basics: Revisiting Exploration in Reinforcement Learning for LLM Reasoning via Generative ProbabilitiesLLM reasoning → Reinforcement learning for reasoning
  70. Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  71. Affordance-Aware Interactive Decision-Making and Execution for Ambiguous InstructionsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  72. Length-Unbiased Sequence Policy Optimization: Revealing and Controlling Response Length Variation in RLVRLLM reasoning → Reinforcement learning for reasoning +1
  73. RFM-Pose:Reinforcement-Guided Flow Matching for Fast Category-Level 6D Pose EstimationDiffusion models → 3D, point cloud and scene generation +1
  74. Copyright Detective: A Forensic System to Evidence LLMs Flickering Copyright Leakage RisksLLM safety and security → Watermarking generated content and models
  75. EGSS: Entropy-guided Stepwise Scaling for Reliable Software EngineeringLLM reasoning → Reasoning for agents, planning and code +1
  76. FedMosaic: Federated Retrieval-Augmented Generation via Parametric AdaptersRetrieval-augmented generation → RAG pipeline design and evaluation
  77. MobileManiBench: Simplifying Model Verification for Mobile ManipulationVision-language-action models → Generalist VLA models and benchmarks
  78. Balanced Anomaly-guided Ego-graph Diffusion Model for Inductive Graph Anomaly DetectionDiffusion models → Flow matching, time series and science
  79. Surgery: Mitigating Harmful Fine-Tuning for Large Language Models via Attention SinkLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  80. Disentangled Representation Learning via Flow MatchingDiffusion models → Diffusion foundations and sampling
  81. ARCHI-TTS: A flow-matching-based Text-to-Speech Model with Self-supervised Semantic Aligner and Accelerated InferenceDiffusion models → Audio, speech and music
  82. Aligning Large Language Model Behavior with Human Citation PreferencesLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  83. GT-SVJ: Generative-Transformer-Based Self-Supervised Video Judge For Efficient Video Reward ModelingMultimodal LLMs / vision-language models → Video understanding with MLLMs +1
  84. Diffusion-aided Extreme Video Compression with Lightweight Semantics GuidanceDiffusion models → Diffusion for compression and wireless
  85. Traceable Cross-Source RAG for Chinese Tibetan Medicine Question AnsweringRetrieval-augmented generation → Medical and biomedical RAG
  86. Double-P: Hierarchical Top-P Sparse Attention for Long-Context LLMsEfficient LLM inference and serving → KV cache optimization
  87. Are Open-Weight LLMs Ready for Social Media Moderation? A Comparative Study on BlueskyLLM safety and security → Safety alignment, refusal and guardrails
  88. Data-Centric Interpretability for LLM-based Multi-Agent Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents +1
  89. The Single-Multi Evolution Loop for Self-Improving Model Collaboration SystemsSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training
  90. Among Us: Measuring and Mitigating Malicious Contributions in Model Collaboration SystemsLLM agents and tool use → Agent threats, guardrails and governance
  91. Total Variation Rates for Riemannian Flow MatchingDiffusion models → Flow matching, time series and science
  92. EBPO: Empirical Bayes Shrinkage for Stabilizing Group-Relative Policy OptimizationLLM reasoning → Reinforcement learning for reasoning
  93. RAG without Forgetting: Continual Query-Infused Key MemoryRetrieval-augmented generation → RAG pipeline design and evaluation
  94. TIDE: Temporal Incremental Draft Engine for Self-Improving LLM InferenceSynthetic data and self-improvement for LLMs → Self-rewarding alignment and self-training +1
  95. Linear Programming for Multi-Criteria Assessment with Cardinal and Ordinal Data: A Pessimistic Virtual Gap Analysis
  96. MedRoute: RL-Based Dynamic Specialist Routing in Multi-Agent Medical Diagnosis
  97. Impact of AI Search Summaries on Website Traffic: Evidence from Google AI Overviews and Wikipedia
  98. IRPAPERS: A Visual Document Benchmark for Scientific Retrieval and Question Answering
  99. Distributed physics-informed neural networks via domain decomposition for fast flow reconstruction
  100. PACT-WAM: Predicting Actions and Visual Foresight with Compact Temporal Encoding for Robot Manipulation
  101. VQ-DSC-R: Robust Vector Quantized-Enabled Digital Semantic Communication With OFDM Transmission
  102. Artificial Organisations
  103. MergePipe: A Budget-Aware Parameter Management System for Scalable LLM Merging
  104. TokaMark: A Comprehensive Benchmark for MAST Tokamak Plasma Models
  105. Artificial Intelligence in Open Source Software Engineering: A Foundation for Sustainability
  106. Hybrid Dual-Path Linear Transformations for Efficient Transformer Architectures
  107. MRI Cross-Modal Synthesis: A Comparative Study of Generative Models for T1-to-T2 Reconstruction
  108. Contactless estimation of continuum displacement and mechanical compressibility from image series using a deep learning based framework
  109. OmniFysics: Towards Physical Intelligence Evolution via Omni-Modal Signal Processing and Network Optimization
  110. Video-based Music Generation
  111. From Images to Decisions: Assistive Computer Vision for Non-Metallic Content Estimation in Scrap Metal
  112. U-Net Based Image Enhancement for Short-time Muon Scattering Tomography
  113. Assessing Reproducibility in Evolutionary Computation: A Case Study using Human- and LLM-based Assessment
  114. Conformal changepoint localization
  115. Swap Regret Minimization Through Response-Based Approachability
  116. Can One-sided Arguments Lead to Response Change in Large Language Models?
  117. On Randomized Algorithms in Online Strategic Classification
  118. ASMa: Asymmetric Spatio-temporal Masking for Skeleton Action Representation Learning
  119. Adaptive Sparse M"obius Transforms for Learning Polynomials
  120. Inheritance Between Feedforward and Convolutional Networks via Model Projection
  121. A Fast and Generalizable Fourier Neural Operator-Based Surrogate for Melt-Pool Prediction in Laser Processing
  122. ATEX-CF: Attack-Informed Counterfactual Explanations for Graph Neural Networks
  123. SR4-Fit: An Interpretable and Informative Classification Algorithm Applied to Prediction of U.S. House of Representatives Elections
  124. ForeHOI: Feed-forward 3D Object Reconstruction from Daily Hand-Object Interaction Videos
  125. BenchMarker: An Education-Inspired Toolkit for Highlighting Flaws in Multiple-Choice Benchmarks
  126. DroneKey++: A Size Prior-free Method and New Benchmark for Drone 3D Pose Estimation from Sequential Images
  127. Emergent Low-Rank Training Dynamics in MLPs with Smooth Activations
  128. Multi-Way Representation Alignment
  129. Learning Rate Scaling across LoRA Ranks and Transfer to Full Finetuning
  130. AnyThermal: Towards Learning Universal Representations for Thermal Perception
  131. Personagram: Bridging Personas and Product Design for Creative Ideation with Multimodal LLMs
  132. Generics in science communication: Misaligned interpretations across laypeople, scientists, and large language models
  133. To 2:4 Sparsity and Beyond: Neuron-level Activation Function to Accelerate LLM Pre-Training
  134. Investigating Social Bias Changes in Quantized Language Models
  135. STACodec: Semantic Token Assignment for Balancing Acoustic Fidelity and Semantic Information in Audio Codecs
  136. Unsupervised Anomaly Detection of Diseases in the Female Pelvis for Real-Time MR Imaging
  137. Optimal rates for density and mode estimation with expand-and-sparsify representations
  138. Know Your Scientist: KYC as Biosecurity Infrastructure
  139. MetaSSP: Enhancing Semi-supervised Implicit 3D Reconstruction through Meta-adaptive EMA and SDF-aware Pseudo-label Evaluation
  140. MGP-KAD: Multimodal Geometric Priors and Kolmogorov-Arnold Decoder for Single-View 3D Reconstruction in Complex Scenes
  141. SCONE: A Practical, Constraint-Aware Plug-in for Latent Encoding in Learned DNA Storage
  142. Protean Compiler: An Agile Framework to Drive Fine-grain Phase Ordering
  143. EgoAVU: Egocentric Audio-Visual Understanding
  144. Warm Starts, Cold States: Exploiting Adiabaticity for Variational Ground-States
  145. Tempora: Characterising the Time-Contingent Utility of Online Test-Time Adaptation
  146. Hear You in Silence: Designing for Active Listening in Human Interaction with Conversational Agents Using Context-Aware Pacing
  147. Compressing LLMs with MoP: Mixture of Pruners
  148. From Blurry to Believable: Enhancing Low-quality Talking Heads with 3D Generative Priors
  149. Private and interpretable clinical prediction with quantum-inspired tensor train models
  150. Robustness Verification of Polynomial Neural Networks
  151. Pragmatic Curiosity: A Unified Framework for Hybrid Learning and Optimization via Active Inference
  152. Toward Faithful and Complete Answer Construction from a Single Document
  153. A Theoretical Analysis of Test-Driven Code Generation
  154. Agentic Workflow Using RBAθ for Event Prediction
  155. NanoNet: Parameter-Efficient Learning with Label-Scarce Supervision for Lightweight Text Mining Model
  156. Shared LoRA Subspaces for almost Strict Continual Learning
  157. Pseudo-Invertible Neural Networks
  158. AP-OOD: Attention Pooling for Out-of-Distribution Detection
  159. Curiosity is Knowledge: Self-Consistent Learning and No-Regret Optimization with Active Inference
  160. Context Forcing: Consistent Autoregressive Video Generation with Long Context
  161. Developing a Discrete-Event Simulator of School Shooter Behavior from VR Data
  162. Correctness-Optimized Residual Activation Lens (CORAL): Transferrable and Calibration-Aware Inference-Time Steering
  163. Two Stages of Folding: Convergent Mechanisms in AI Protein Folding Trunks
  164. MambaVF: State Space Model for Efficient Video Fusion
  165. A Systematic Evaluation of Large Language Models for PTSD Severity Estimation: The Role of Contextual Knowledge and Modeling Strategies
  166. Optimism Stabilizes Thompson Sampling for Adaptive Inference
  167. Speech Emotion Recognition Leveraging OpenAI's Whisper Representations and Attentive Pooling Methods
  168. VisRefiner: Learning from Visual Differences for Screenshot-to-Code Generation
  169. Causal Inference on Stopped Random Walks in Online Advertising
  170. Orthogonal Self-Attention
  171. Layer-wise LoRA fine-tuning: a similarity metric approach
  172. RISE-Video: Can Video Generators Decode Implicit World Rules?
  173. Geographically-aware Transformer-based Traffic Forecasting for Urban Motorway Digital Twins
  174. Clifford Kolmogorov-Arnold Networks
  175. Characterizing Human Semantic Navigation in Concept Production as Trajectories in Embedding Space
  176. Inverse Depth Scaling From Most Layers Being Similar
  177. A Hybrid Data-Driven Algorithm for Real-Time Friction Force Estimation in Hydraulic Cylinders
  178. LSA: Localized Semantic Alignment for Enhancing Temporal Consistency in Traffic Video Generation
  179. Breaking Symmetry Bottlenecks in GNN Readouts
  180. Orthogonal Model Merging
  181. Multi-Scale Global-Instance Prompt Tuning for Continual Test-time Adaptation in Medical Image Segmentation
  182. Dimensionality Reduction on Riemannian Manifolds in Data Analysis
  183. Tuning Out-of-Distribution (OOD) Detectors Without Given OOD Data
  184. Approximation of Log-Partition Function in Policy Mirror Descent Induces Implicit Regularization for LLM Post-Training
  185. Compound Deception in Elite Peer Review: A Failure Mode Taxonomy of 100 Fabricated Citations at NeurIPS 2025
  186. Transformers Are Born Biased: Structural Inductive Biases at Random Initialization and Their Practical Consequences
  187. Chunky Post-Training: Data Driven Failures of Generalization
  188. CLIP-Map: Structured Matrix Mapping for Parameter-Efficient CLIP Compression
  189. Codified Finite-state Machines for Role-playing
  190. CoreQ: Learning-Free Mismatch Correction and Successive Rounding for Quantization
  191. Universal approximation with signatures of non-geometric rough paths
  192. Parity, Sensitivity, and Transformers
  193. DFPO: Scaling Value Modeling via Distributional Flow towards Robust and Generalizable LLM Post-Training
  194. Metric Hedonic Games on the Line
  195. Escaping Local Minima Provably in Non-convex Matrix Sensing: A Deterministic Framework via Simulated Lifting
  196. Neural Implicit 3D Cardiac Shape Reconstruction from Sparse CT Angiography Slices Mimicking 2D Transthoracic Echocardiography Views
  197. A Guide to Large Language Models in Modeling and Simulation: From Core Techniques to Critical Challenges
  198. EoCD: Encoder only Remote Sensing Change Detection
  199. EuroLLM-22B: Technical Report
  200. Beyond Manual Planning: Seating Allocation for Large Organizations
  201. xList-Hate: A Checklist-Based Framework for Interpretable and Generalizable Hate Speech Detection
  202. Large-scale Score-based Variational Posterior Inference for Bayesian Deep Neural Networks
  203. Wedge Sampling: Efficient Tensor Completion with Nearly-Linear Sample Complexity
  204. Distribution-free two-sample testing with blurred total variation distance
  205. CFRecs: Counterfactual Recommendations on Real Estate User Listing Interaction Graphs
  206. A Hybrid Autoencoder for Robust Heightmap Generation from Fused Lidar and Depth Data for Humanoid Robot Locomotion
  207. RRAttention: Dynamic Block Sparse Attention via Per-Head Round-Robin Shifts for Long-Context Inference
  208. Exact Recovery in the Data Block Model
  209. Visualizing the loss landscapes of physics-informed neural networks
  210. DARWIN: Dynamic Agentically Rewriting Self-Improving Network
  211. Optimal scaling laws in learning hierarchical multi-index models
  212. Self-Supervised Learning with a Multi-Task Latent Space Objective
  213. OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions
  214. FHAIM: Fully Homomorphic AIM For Private Synthetic Data Generation
  215. SecretFan: Synthesizing Realistic Data without Breaking Privacy
  216. Learning Compact Boolean Networks
  217. Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigation
  218. NVS-HO: A Benchmark for Novel View Synthesis of Handheld Objects
  219. Interpreting Manifolds and Graph Neural Embeddings from Internet of Things Traffic Flows
  220. Where Does Warm-Up Come From? Adaptive Scheduling for Norm-Constrained Optimizers
  221. Principled Confidence Estimation for Deep Computed Tomography
  222. STProtein: predicting spatial protein expression from multi-omics data
  223. Non-Stationary Inventory Control with Lead Times
  224. Learning False Discovery Rate Control via Model-Based Neural Networks
  225. Classification Under Local Differential Privacy with Model Reversal and Model Averaging
  226. FiMI: A Domain-Specific Language Model for Indian Finance Ecosystem
  227. Price of metric universality in vector quantization is at most 0.11 bit
  228. Bagging-Based Model Merging for Robust General Text Embeddings
  229. Selecting Hyperparameters for Tree-Boosting
  230. ReText: Text Boosts Generalization in Image-Based Person Re-identification
  231. Automated Customization of LLMs for Enterprise Code Repositories Using Semantic Scopes
  232. How Controlling the Variance can Improve Training Stability of Sparsely Activated DNNs and CNNs
  233. Different Time, Different Language: Revisiting the Bias Against Non-Native Speakers in GPT Detectors
  234. RocqSmith: Can Automatic Optimization Forge Better Proof Agents?
  235. TimelyFreeze: Adaptive Parameter Freezing Mechanism for Pipeline Parallelism
  236. How to Achieve the Intended Aim of Deep Clustering Now, without Deep Learning
  237. Fast Rates for Nonstationary Weighted Risk Minimization
  238. Disc-Centric Contrastive Learning for Lumbar Spine Severity Grading
  239. Neuro-Inspired Visual Pattern Recognition via Biological Reservoir Computing
  240. CSRv2: Unlocking Ultra-Sparse Embeddings
  241. Evaluating the impact of word embeddings on similarity scoring in practical information retrieval
  242. Depth as Prior Knowledge for Object Detection
  243. Adaptive Global and Fine-Grained Perceptual Fusion for MLLM Embeddings Compatible with Hard Negative Amplification
  244. Muon in Associative Memory Learning: Training Dynamics and Scaling Laws
  245. Exploring the Temporal Consistency for Point-Level Weakly-Supervised Temporal Action Localization
  246. Anchored Policy Optimization: Mitigating Exploration Collapse Via Support-Constrained Rectification
  247. Projected Boosting with Fairness Constraints: Quantifying the Cost of Fair Training Distributions
  248. Towards Green AI: Decoding the Energy of LLM Inference in Software Development
  249. Nonlinearity as Rank: Generative Low-Rank Adapter with Radial Basis Functions
  250. Fix Representation (Optimally) Before Fairness: Finite-Sample Shrinkage Population Correction and the True Price of Fairness Under Subpopulation Shift
  251. Poster: Camera Tampering Detection for Outdoor IoT Systems
  252. Limitations of SGD for Multi-Index Models Beyond Statistical Queries
  253. Broken neural scaling laws in materials science
  254. SweetSpot: An Analytical Model for Predicting Energy Efficiency of LLM Inference
  255. Consensus-Aligned Neuron Efficient Fine-Tuning Large Language Models for Multi-Domain Machine Translation
  256. FedRandom: Sampling Consistent and Accurate Contribution Values in Federated Learning
  257. MedErrBench: A Fine-Grained Multilingual Benchmark for Medical Error Detection and Correction with Clinical Expert Annotations
  258. Almost Asymptotically Optimal Active Clustering Through Pairwise Observations
  259. Mining Generalizable Activation Functions
  260. Exploring AI-Augmented Sensemaking of Patient-Generated Health Data: A Mixed-Method Study with Healthcare Professionals in Cardiac Risk Reduction
  261. Perception-Based Beliefs for POMDPs with Visual Observations
  262. ShapeUP: Scalable Image-Conditioned 3D Editing
  263. HyperPotter: Spell the Charm of High-Order Interactions in Audio Deepfake Detection
  264. Stable but Wrong: When More Data Degrades Scientific Conclusions
  265. Accelerating Benchmarking of Functional Connectivity Modeling via Structure-aware Core-set Selection
  266. Probabilistic Multi-Regional Solar Power Forecasting with Any-Quantile Recurrent Neural Networks
  267. Tight Long-Term Tail Decay of (Clipped) SGD in Non-Convex Optimization
  268. Alignment Verifiability in Large Language Models: Normative Indistinguishability under Behavioral Evaluation
  269. Enhancing Personality Recognition by Comparing the Predictive Power of Traits, Facets, and Nuances
  270. End-to-End Compression for Tabular Foundation Models
  271. Modelling the Morphology of Verbal Paradigms: A Case Study in the Tokenization of Turkish and Hebrew
  272. Empowering Time Series Analysis with Large-Scale Multimodal Pretraining
  273. Joint Embedding Variational Bayes
  274. SurgMotion: A Video-Native Foundation Model for Universal Understanding of Surgical Videos
  275. Generative Ontology: When Structured Knowledge Learns to Create
  276. CASTLE: A Comprehensive Benchmark for Evaluating Student-Tailored Personalized Safety in Large Language Models
  277. ROMAN: Reward-Orchestrated Multi-Head Attention Network for Autonomous Driving System Testing
  278. AI chatbots versus human healthcare professionals: a systematic review and meta-analysis of empathy in patient care
  279. Reactive Knowledge Representation and Asynchronous Reasoning
  280. Unified Sensor Simulation for Autonomous Driving
  281. Multi-instance robust fitting for non-classical geometric models
  282. On the Superlinear Relationship between SGD Noise Covariance and Loss Landscape Curvature
  283. BhashaSetu: Cross-Lingual Knowledge Transfer from High-Resource to Extreme Low-Resource Languages
  284. CAViT -- Channel-Aware Vision Transformer for Dynamic Feature Fusion
  285. Efficient Algorithms for Robust Markov Decision Processes with s-Rectangular Ambiguity Sets
  286. EgoPoseVR: Spatiotemporal Multi-Modal Reasoning for Egocentric Full-Body Pose in Virtual Reality
  287. A Mixed Reality System for Robust Manikin Localization in Childbirth Training
  288. The Geometric Observability Index: Influence, Fisher Information, and Weak Observability in SE(3) Pose Estimation
  289. LoGoSeg: Integrating Local and Global Features for Open-Vocabulary Semantic Segmentation
  290. LocateEdit-Bench: A Benchmark for Instruction-Based Editing Localization
  291. OpenMAG: A Comprehensive Benchmark for Multimodal-Attributed Graph
  292. A Hybrid CNN and ML Framework for Multi-modal Classification of Movement Disorders Using MRI and Brain Structural Features
  293. Visual Implicit Geometry Transformer for Autonomous Driving
  294. ShapeGaussian: High-Fidelity 4D Human Reconstruction in Monocular Videos via Vision Priors
  295. EdgeMask-DG*: Learning Domain-Invariant Graph Structures via Adversarial Edge Masking
  296. MAGPrompt: Message-Adaptive Graph Prompt Tuning for Graph Neural Networks
  297. Piecewise Deterministic Markov Processes for Bayesian Inference of PDE Coefficients
  298. PIRATR: Parametric Object Inference for Robotic Applications with Transformers in 3D Point Clouds
  299. IndustryShapes: An RGB-D Benchmark dataset for 6D object pose estimation of industrial assembly components and tools
  300. FastVMT: Eliminating Redundancy in Video Motion Transfer
  301. ArkTS-CodeSearch: A Open-Source ArkTS Dataset for Code Retrieval
  302. Reducing the Complexity of Matrix Multiplication by Quantum Computing
  303. A Comparative Study of 3D Person Detection: Sensor Modalities and Robustness in Diverse Indoor and Outdoor Environments
  304. When Shared Knowledge Hurts: Spectral Over-Accumulation in Model Merging
  305. SSG: Scaled Spatial Guidance for Multi-Scale Visual Autoregressive Generation
  306. Split Personality Training: Revealing Latent Knowledge Through Alternate Personalities
  307. Solving Stochastic Variational Inequalities without the Bounded Variance Assumption
  308. Generalization of Self-Supervised Vision Transformers for Protein Localization Across Microscopy Domains
  309. Structure-First Point Cloud Learning with Mapper Region Graphs
  310. A Unified Multimodal Framework for Dataset Construction and Model-Based Diagnosis of Ameloblastoma
  311. A Human-in-the-Loop, LLM-Centered Architecture for Knowledge-Graph Question Answering
  312. VGGT-Motion: Motion-Aware Calibration-Free Monocular SLAM for Long-Range Consistency
  313. XEmoGPT: An Explainable Multimodal Emotion Recognition Framework with Cue-Level Perception and Reasoning
  314. Transport and Merge: Cross-Architecture Merging for Large Language Models
  315. LinguistAgent Technical Report: A Reflective Multi-Model Platform for Automated Linguistic Annotation
  316. Convergence Rate of the Last Iterate of Stochastic Proximal Algorithms
  317. Feature points evaluation on omnidirectional vision with a photorealistic fisheye sequence -- A report on experiments done in 2014
  318. Sovereign-by-Design A Reference Architecture for AI and Blockchain Enabled Systems
  319. SOMA-1M: A Large-Scale SAR-Optical Multi-resolution Alignment Dataset for Multi-Task Remote Sensing
  320. Phi-Former: A Pairwise Hierarchical Approach for Compound-Protein Interactions Prediction
  321. LLM-driven Multimodal Recommendation
  322. Reasoning under Ambiguity: Uncertainty-Aware Multilingual Emotion Classification under Partial Supervision
  323. MerNav: A Highly Generalizable Memory-Execute-Review Framework for Zero-Shot Object Goal Navigation
  324. Semantic Purification for Conditional Representation Learning
  325. Thermodynamic Limits of Physical Intelligence
  326. Ontology-Driven Robotic Specification Synthesis
  327. Attention Retention for Continual Learning with Vision Transformers
  328. Towards Segmenting the Invisible: An End-to-End Registration and Segmentation Framework for Weakly Supervised Tumour Analysis
  329. Synthetic Defect Geometries of Cast Metal Objects Modeled via 2d Voronoi Tessellations
  330. LD-SLRO: Latent Diffusion Structured Light for 3-D Reconstruction of Highly Reflective Objects
  331. Day-Ahead Electricity Price Forecasting for Volatile Markets Using Foundation Models with Regularization Strategy
  332. THOR: Inductive Link Prediction over Hyper-Relational Knowledge Graphs
  333. NeVStereo: A NeRF-Driven NVS-Stereo Architecture for High-Fidelity 3D Tasks
  334. Disco: Densely-overlapping Cell Instance Segmentation via Adjacency-aware Collaborative Coloring
  335. Grammatical Error Correction Evaluation by Optimally Transporting Edit Representation
  336. Reduced-Order Surrogates for Forced Flexible Mesh Coastal-Ocean Models
  337. VMF-GOS: Geometry-guided virtual Outlier Synthesis for Long-Tailed OOD Detection
  338. TSBOW -- Traffic Surveillance Benchmark for Occluded Vehicles Under Various Weather Conditions
  339. SciDef: Datasets and Tools for Automated Definition Extraction from Scientific Literature with LLMs
  340. Robust Federated Learning via Byzantine Filtering over Encrypted Updates
  341. Enabling Automatic Disordered Speech Recognition: An Impaired Speech Dataset in the Akan Language
  342. Advancing Opinion Dynamics Modeling with Neural Diffusion-Convection-Reaction Equation
  343. OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration
  344. Optimal Bayesian Stopping for Efficient Inference of Consistent LLM Answers
  345. Late-to-Early Training: LET LLMs Learn Earlier, So Faster and Better
  346. Beyond Length: Context-Aware Expansion and Independence as Developmentally Sensitive Evaluation in Child Utterances
  347. Assessing Electricity Demand Forecasting with Exogenous Data in Time Series Foundation Models
  348. A Decomposition-based State Space Model for Multivariate Time-Series Forecasting
  349. Parallel Swin Transformer-Enhanced 3D MRI-to-CT Synthesis for MRI-Only Radiotherapy Planning
  350. Dolphin-v2: Universal Document Parsing via Scalable Anchor Prompting
  351. Clinical Validation of Medical-based Large Language Model Chatbots on Ophthalmic Patient Queries with LLM-based Evaluation
  352. Cross-Lingual Empirical Evaluation of Large Language Models for Arabic Medical Tasks
  353. Hinge Regression Tree: A Newton Method for Oblique Regression Tree Splitting
  354. RaBiT: Residual-Aware Binarization Training for Accurate and Efficient LLMs
  355. Multi-Field Tool Retrieval
  356. Imagine a City: CityGenAgent for Procedural 3D City Generation
  357. Breaking Semantic Hegemony: Decoupling Principal and Residual Subspaces for Generalized OOD Detection
  358. Bayesian Neighborhood Adaptation for Graph Neural Networks
  359. Smoothness Errors in Dynamics Models and How to Avoid Them
  360. Learning with Adaptive Prototype Manifolds for Out-of-Distribution Detection
  361. How Do Language Models Acquire Character-Level Information?
  362. Decision-Focused Sequential Experimental Design: A Directional Uncertainty-Guided Approach
  363. Pool-based Active Learning as Noisy Lossy Compression: Characterizing Label Complexity via Finite Blocklength Analysis
  364. MTPano: Multi-Task Panoramic Scene Understanding via Label-Free Integration of Dense Prediction Priors
  365. Wid3R: Wide Field-of-View 3D Reconstruction via Camera Model Conditioning
  366. A Short and Unified Convergence Analysis of the SAG, SAGA, and IAG Algorithms
  367. Logarithmic-time Schedules for Scaling Language Models with Momentum
  368. Aspect-Aware MOOC Recommendation in a Heterogeneous Network
  369. Fast-SAM3D: 3Dfy Anything in Images but Faster
  370. Position: Universal Time Series Foundation Models Rest on a Category Error
  371. HealthMamba: An Uncertainty-aware Spatiotemporal Graph State Space Model for Effective and Reliable Healthcare Facility Visit Prediction
  372. Hallucination-Resistant Security Planning with a Large Language Model
  373. Asymptotically optimal sequential change detection for bounded means
  374. Unlocking Prototype Potential: An Efficient Tuning Framework for Few-Shot Class-Incremental Learning
  375. Hybrid Gated Flow (HGF): Stabilizing 1.58-bit LLMs via Selective Low-Rank Correction
  376. Beyond Cosine Similarity
  377. ReGLA: Efficient Receptive-Field Modeling with Gated Linear Attention Network
  378. An Asymptotic Law of the Iterated Logarithm for KLinf
  379. CoPE: Clipped RoPE as A Scalable Free Lunch for Long Context LLMs
  380. TADS: Task-Aware Data Selection for Multi-Task Multimodal Pre-Training
  381. Active Label Cleaning for Reliable Detection of Electron Dense Deposits in Transmission Electron Microscopy Images
  382. Automatic Cognitive Task Generation for In-Situ Evaluation of Embodied Agents
  383. CORP: Closed-Form One-shot Representation-Preserving Structured Pruning for Transformers
  384. Explainable AI: A Combined XAI Framework for Explaining Brain Tumour Detection Models
  385. PatchFlow: Leveraging a Flow-Based Model with Patch Features
  386. Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions
  387. ZeroS: Zero-Sum Linear Attention for Efficient Transformers
  388. Radon--Wasserstein Gradient Flows for Interacting-Particle Sampling in High Dimensions
  389. Metric space valued Fr'echet regression
  390. Bagpiper: Solving Open-Ended Audio Tasks via Rich Captions
  391. Private Prediction via Shrinkage
  392. Boosting SAM for Cross-Domain Few-Shot Segmentation via Conditional Point Sparsification
  393. Cross-Domain Few-Shot Segmentation via Multi-view Progressive Adaptation
  394. Semantic Search over 9 Million Mathematical Theorems
  395. E.M.Ground: A Temporal Grounding Vid-LLM with Holistic Event Perception and Matching
  396. Dual-Representation Image Compression at Ultra-Low Bitrates via Explicit Semantics and Implicit Textures
  397. Quantifying the Knowledge Proximity Between Academic and Industry Research: An Entity and Semantic Perspective
  398. Context-Aware Asymmetric Ensembling for Interpretable Retinopathy of Prematurity Screening via Active Query and Vascular Attention
  399. Extreme Weather Nowcasting via Local Precipitation Pattern Prediction
  400. First Proof
  401. PoseGaussian: Pose-Driven Novel View Synthesis for Robust 3D Human Reconstruction
  402. SpectraKAN: Conditioning Spectral Operators
  403. Towards Worst-Case Guarantees with Scale-Aware Interpretability
  404. Benchmarking Artificial Intelligence Models for Daily Coastal Hypoxia Forecasting
  405. Enhancing Adversarial Robustness with Signed Distance Fields for Harmonizing Geometric Invariance and Texture
  406. Finite-Particle Rates for Regularized Stein Variational Gradient Descent
  407. Path Sampling for Rare Events Boosted by Machine Learning
  408. Position: Capability Control Should be a Separate Goal From Alignment
  409. LOBSTgER-enhance: an underwater image enhancement pipeline
  410. SHaSaM: Submodular Hard Sample Mining for Fair Facial Attribute Recognition
  411. AirGlove: Exploring Egocentric 3D Hand Tracking and Appearance Generalization for Sensing Gloves
  412. GreekMMLU: A Native-Sourced Multitask Benchmark for Evaluating Language Models in Greek
  413. CoSA: Compressed Sensing-Based Adaptation of Large Language Models
  414. Cross-talk based multi-task learning for fault classification of machine system influenced by multiple variables
  415. Fairness Under Group-Conditional Prior Probability Shift: Invariance, Drift, and Target-Aware Post-Processing