mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 4 Feb 2026

503 papers

  1. ARIA: Adaptive Retrieval Intelligence Assistant -- A Multimodal RAG Framework for Domain-Specific Engineering EducationRetrieval-augmented generation → Agentic RAG, agents and memory
  2. Scaling DPPs for RAG: Density Meets DiversityRetrieval-augmented generation → RAG pipeline design and evaluation
  3. Not All Denoising Steps Are Equal: Model Scheduling for Faster Masked Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  4. Rethinking Personalization in Large Language Models at the Token LevelLLM reasoning → Reinforcement learning for reasoning
  5. A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial RobustnessLLM safety and security → Safety alignment, refusal and guardrails
  6. Hierarchical Embedding Fusion for Retrieval-Augmented Code GenerationRetrieval-augmented generation → RAG for code
  7. Hierarchical Latent Structures in Data Generation Process Unify Mechanistic Phenomena across ScaleMechanistic interpretability → Knowledge and representations inside LLMs
  8. Dual Tuning for Reasoning Efficacy-Driven Data Curation in Multimodal LLM TrainingLLM reasoning → Reasoning benchmarks and evaluation +1
  9. GRIP: Geometric Refinement and Adaptive Information Potential for Data EfficiencyMixture-of-experts → MoE large language models
  10. SimpleTool: Parallel Decoding for Real-Time LLM Function CallingLLM agents and tool use → Software engineering coding agents +1
  11. ActMem: Bridging the Gap Between Memory Retrieval and Reasoning in LLM AgentsLLM reasoning → Reasoning for agents, planning and code +1
  12. ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction FollowingLLM reasoning → Reasoning benchmarks and evaluation
  13. Budget-Aware Agentic Routing via Boundary-Guided TrainingLLM agents and tool use → General LLM agent frameworks and benchmarks
  14. Optimal Multi-Debris Mission Planning in LEO: A Deep Reinforcement Learning Approach with Co-Elliptic Transfers and RefuelingDeep reinforcement learning methods → RL for robot navigation and UAV control
  15. CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward ModelsLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  16. BioBridge: Bridging Proteins and Language for Enhanced Biological Reasoning with LLMsLLM reasoning → Clinical and biomedical applications
  17. Mechanistic Evidence for Faithfulness Decay in Chain-of-Thought ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  18. Reliable and Responsible Foundation Models: A Comprehensive SurveyMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  19. SPARE: Self-distillation for PARameter-Efficient RemovalDiffusion models → Robustness, privacy and adversarial aspects +2
  20. RECITYGEN -- Interactive and Generative Participatory Urban Design Tool with Latent Diffusion and Segment AnythingDiffusion models → 3D, point cloud and scene generation
  21. AVERE: Improving Audiovisual Emotion Reasoning with Preference OptimizationLLM reasoning → Audio-language model reasoning +1
  22. Neural Sentinel: Unified Vision Language Model (VLM) for License Plate Recognition with Human-in-the-Loop Continual LearningMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  23. Interpreting Physics in Video World ModelsWorld models → Latent predictive world models
  24. VLRS-Bench: A Vision-Language Reasoning Benchmark for Remote SensingLLM reasoning → Spatial and embodied reasoning +1
  25. Communication Enhances LLMs' Stability in Strategic ThinkingLLM reasoning → Reasoning for agents, planning and code
  26. CausalRAG2: Hierarchical Causal Knowledge Graph Design for RAGRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  27. Rethinking Rubric Generation for Improving LLM Judge and Reward Modeling for Open-ended TasksLLM reasoning → Reinforcement learning for reasoning +1
  28. Certifiable Boolean Reasoning Is UniversalLLM reasoning → Reasoning benchmarks and evaluation
  29. SocialVeil: Probing Social Intelligence of Language Agents under Communication BarriersLLM agents and tool use → Social simulation and multi-agent debate
  30. Democratic Preference Alignment via Sortition-Weighted RLHFLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  31. Data Kernel Perspective Space Performance Guarantees for Synthetic Data from Transformer ModelsSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  32. Rule-Based Spatial Mixture-of-Experts U-Net for Explainable Edge DetectionMixture-of-experts → Vision mixture-of-experts
  33. Visual concept ranking uncovers medical shortcuts used by large multimodal modelsMultimodal LLMs / vision-language models → Medical vision-language models
  34. Beware Untrusted Simulators -- Reward-Free Backdoor Attacks in Reinforcement LearningDeep reinforcement learning methods → Adversarial robustness and RL in finance
  35. Autodiscover: A reinforcement learning recommendation system for the cold-start imbalance challenge in active learning, powered by graph-aware thompson samplingDeep reinforcement learning methods → RL for clinical treatment and surgery
  36. Reinforcement Learning Enhancement Using Vector Semantic Representation and Symbolic Reasoning for Human-Centered Autonomous Emergency BrakingLLM reasoning → Chain-of-thought reasoning for driving
  37. Optimizing Mission Planning for Multi-Debris Rendezvous Using Reinforcement Learning with Refueling and Adaptive Collision AvoidanceDeep reinforcement learning methods → RL for robot navigation and UAV control
  38. Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and OpportunitiesLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  39. Bypassing AI Control Protocols via Agent-as-a-Proxy AttacksLLM agents and tool use → Agent threats, guardrails and governance +1
  40. Grounded but Misleading: Evaluating Semantic Alignment in AI-Generated Security ExplanationsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  41. ReFORM: Reflected Flows for On-support Offline RL via Noise ManipulationOffline RL and imitation learning from data → Diffusion and flow policies for offline RL
  42. VISTA: Enhancing Visual Conditioning via Track-Following Preference Optimization in Vision-Language-Action ModelsVision-language-action models → Reinforcement learning and post-training +1
  43. MINT: Minimal Information Neuro-Symbolic Tree for Objective-Driven Knowledge-Gap Reasoning and Active ElicitationLLM reasoning → Reasoning for agents, planning and code
  44. Laplacian Representations for Decision-Time PlanningDeep reinforcement learning methods → Deep RL algorithms and representations
  45. AudioSAE: Towards Understanding of Audio-Processing Models with Sparse AutoEncodersMechanistic interpretability → SAE features and their applications
  46. Do Vision-Language Models Respect Contextual Integrity in Location Disclosure?LLM reasoning → Spatial and embodied reasoning +1
  47. DeepRead: Document Structure-Aware Reasoning to Enhance Agentic SearchLLM reasoning → Knowledge- and tool-augmented reasoning +2
  48. CoWork-X: Experience-Optimized Co-Evolution for Multi-Agent Collaboration SystemLLM agents and tool use → Agent skill learning and evolution
  49. Entropy Aware Reward Guidance for Diffusion Language Model AlignmentDiffusion models → Discrete and text diffusion +1
  50. Privileged Information Distillation for Language ModelsKnowledge distillation → On-policy and self-distillation for LLMs
  51. Linear Model Merging Unlocks Simple and Scalable Multimodal Data Mixture OptimizationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  52. ASA: Backbone-Training-Free Representation Engineering for Tool-Calling AgentsLLM agents and tool use → Tool learning and function calling +1
  53. Attack Selection Reduces Safety in Concentrated AI Control Settings against Trusted MonitoringLLM safety and security → Prompt injection and agent security
  54. Euphonium: Steering Video Flow Matching via Process Reward Gradient Guided Stochastic DynamicsDiffusion models → Diffusion and flow policies for robotics +1
  55. Pruning Minimal Reasoning Graphs for Efficient Retrieval-Augmented GenerationLLM reasoning → Knowledge- and tool-augmented reasoning +1
  56. Internalizing LLM Reasoning via Discovery and Replay of Latent ActionsLLM reasoning → Test-time compute and efficient thinking
  57. Gradually Compacting Large Language Models for Reasoning Like a Boiling FrogLLM reasoning → Test-time compute and efficient thinking
  58. Atomic Information Flow: A Network Flow Model for Tool Attributions in RAG SystemsRetrieval-augmented generation → Agentic RAG, agents and memory
  59. Learning Where It Matters: Geometric Anchoring for Robust Preference AlignmentLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  60. Temporal Pair Consistency for Variance-Reduced Flow MatchingDiffusion models → Flow matching, time series and science
  61. Reinforced Attention LearningLLM reasoning → Multimodal reasoning
  62. Capturing Visual Environment Structure Correlates with Control PerformanceVision-language-action models → World model-based VLA
  63. Rethinking the Trust Region in LLM Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  64. Laminating Representation Autoencoders for Efficient DiffusionDiffusion models → Diffusion foundations and sampling
  65. Multi-Head LatentMoE and Head Parallel: Communication-Efficient and Deterministic MoE ParallelismMixture-of-experts → Efficient MoE training and inference systems
  66. CRoSS: A Continual Robotic Simulation Suite for Scalable Reinforcement Learning with High Task Diversity and Realistic Physics SimulationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  67. When LLaVA Meets Objects: Token Composition for Vision-Language-ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  68. CoT is Not the Chain of Truth: An Empirical Internal Analysis of Reasoning LLMs for Fake News GenerationLLM reasoning → Prompting and chain-of-thought reasoning
  69. El Agente Quntur: A research collaborator agent for quantum chemistryLLM agents and tool use → Medical and scientific domain agents
  70. Fluid Reasoning RepresentationsLLM reasoning → Reasoning benchmarks and evaluation
  71. Group-Evolving Agents: Open-Ended Self-Improvement via Experience SharingSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
  72. Safe Urban Traffic Control via Uncertainty-Aware Conformal Prediction and World-Model Reinforcement LearningWorld models → World models for autonomous driving +1
  73. XtraLight-MedMamba for Classification of Neoplastic Tubular AdenomasState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  74. X2HDR: HDR Image Generation in a Perceptually Uniform SpaceDiffusion models → Inverse problems and image restoration
  75. Agentic AI in Healthcare & Medicine: A Seven-Dimensional Taxonomy for Empirical Evaluation of LLM-based AgentsLLM agents and tool use → Medical and scientific domain agents
  76. Beyond Rewards in Reinforcement Learning for Cyber DefenceDeep reinforcement learning methods → Adversarial robustness and RL in finance
  77. OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language ModelsEfficient LLM inference and serving → Audio and omni-modal token compression
  78. VISTA-Bench: Do Vision-Language Models Really Understand Visualized Text as Well as Pure Text?Multimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  79. Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse AttentionDiffusion models → Video generation
  80. Dynamical Regimes of Multimodal Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  81. Mitigating Long-Tail Bias via Prompt-Controlled Diffusion AugmentationDiffusion models → Inverse problems and image restoration
  82. Inference-Time Reasoning Selectively Reduces Implicit Social Bias in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  83. Alignment Drift in Multimodal LLMs: A Two-Phase, Longitudinal Evaluation of Harm Across Eight Model ReleasesMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +2
  84. Rationality Measurement and Theory for Reinforcement Learning AgentsDeep reinforcement learning methods → RL theory and sample complexity
  85. DMFlow: Disordered Materials Generation by Flow MatchingDiffusion models → Flow matching, time series and science
  86. Supporting software engineering tasks with agentic AI: Demonstration on document retrieval and test scenario generationLLM agents and tool use → Software engineering coding agents
  87. Superposition Without Interference? Towards Isolated Interventions via Almost Orthogonal Features in Language ModelsMechanistic interpretability → Sparse autoencoder training and evaluation
  88. SAR-RAG: ATR Visual Question Answering by Semantic Search, Retrieval, and MLLM GenerationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  89. Addressing Corpus Knowledge Poisoning Attacks on RAG Using Sparse AttentionRetrieval-augmented generation → Privacy and security of RAG
  90. ERNIE 5.0 Technical ReportMixture-of-experts → MoE large language models
  91. Annotation Free Spacecraft Detection and Segmentation using Vision Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  92. Multi-Source Retrieval and Reasoning for Legal Sentencing PredictionLLM reasoning → Reasoning for agents, planning and code
  93. Let Experts Feel Uncertainty: A Multi-Expert Label Distribution Approach to Probabilistic Time Series ForecastingMixture-of-experts → MoE for time series and graphs
  94. REDistill: Robust Estimator Distillation for Balancing Robustness and EfficiencyKnowledge distillation → General knowledge distillation methods
  95. AGILE: Hand-Object Interaction Reconstruction from Video via Agentic GenerationLLM agents and tool use → Multimodal and embodied agents
  96. Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss DesignLLM reasoning → Reinforcement learning for reasoning +2
  97. TRIO: Token Reduction via Inference-Objective Guidance for Efficient Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  98. Inference-Time Backdoors via Chat Templates: From LLM Supply Chains to Agentic System CompromiseLLM agents and tool use → Agent threats, guardrails and governance +1
  99. SAFE: Stable Alignment Finetuning with Entropy-Aware Predictive Control for Reinforcement Learning from Human Feedback (RLHF)LLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  100. Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward ModelsLLM reasoning → Reinforcement learning for reasoning +1
All 503
  1. Towards Structured, State-Aware, and Execution-Grounded Reasoning for Software Engineering AgentsLLM agents and tool use → Software engineering coding agents
  2. Relational Scene Graphs for Object Grounding of Natural Language CommandsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  3. WideSeek-R1: Exploring Width Scaling for Broad Information Seeking via Multi-Agent Reinforcement LearningLLM agents and tool use → General LLM agent frameworks and benchmarks
  4. QUATRO: Query-Adaptive Trust Region Policy Optimization for LLM Fine-tuningLLM reasoning → Reinforcement learning for reasoning
  5. Translation Heads: Disentangling meaning from language in LLM-based machine translationMechanistic interpretability → Knowledge and representations inside LLMs
  6. Stochastic Decision Horizons for Survival-Based Constrained Reinforcement LearningDeep reinforcement learning methods → Safe and constrained RL
  7. VILLAIN at AVerImaTeC: Verifying Image-Text Claims via Multi-Agent CollaborationLLM agents and tool use → Web, search, and research agents
  8. Trust The TypicalLLM safety and security → Safety alignment, refusal and guardrails
  9. AIANO: Enhancing Information Retrieval with AI-Augmented AnnotationRetrieval-augmented generation → RAG pipeline design and evaluation
  10. Reinforcement Learning-based Home Energy Management with Heterogeneous Batteries and Stochastic EV BehaviourDeep reinforcement learning methods → RL for energy, networks and operations
  11. Semantic Self-Distillation for Language Model UncertaintyKnowledge distillation → Knowledge distillation for LLMs
  12. Vibe AIGC: A New Paradigm for Content Generation via Agentic OrchestrationLLM agents and tool use → Software engineering coding agents
  13. Dual Mind World Model Inspired Network Digital Twin for Access SchedulingWorld models → World models for language agents
  14. Understanding Degradation with Vision Language ModelMultimodal LLMs / vision-language models → Image editing and quality assessment
  15. Rethinking Weight Tying: Pseudo-Inverse Tying for LM Stable Training and UpdatesLLM reasoning → Test-time compute and efficient thinking
  16. Nix and Fix: Targeting 1000x Compression of 3D Gaussian Splatting with Diffusion ModelsDiffusion models → 3D, point cloud and scene generation
  17. LycheeDecode: Accelerating Long-Context LLM Inference via Hybrid-Head Sparse DecodingEfficient LLM inference and serving → KV cache optimization
  18. Learning the Value Systems of Agents with Preference-based and Inverse Reinforcement LearningDeep reinforcement learning methods → Interpretable and logic-guided RL
  19. EgoActor: Grounding Task Planning into Spatial-aware Egocentric Actions for Humanoid Robots via Visual-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  20. Model-Dowser: Data-Free Importance Probing to Mitigate Catastrophic Forgetting in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  21. ReThinker: Scientific Reasoning by Rethinking with Guided Reflection and Confidence ControlLLM reasoning → Knowledge- and tool-augmented reasoning
  22. PersoDPO: Scalable Preference Optimization for Instruction-Adherent, Persona-Grounded Dialogue via Multi-LLM EvaluationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  23. The Supportiveness-Safety Tradeoff in LLM Well-Being AgentsLLM agents and tool use → Medical and scientific domain agents
  24. Beyond Unimodal Shortcuts: MLLMs as Cross-Modal Reasoners for Grounded Named Entity RecognitionLLM reasoning → Multimodal reasoning
  25. ProAgentBench: Evaluating LLM Agents for Proactive Assistance with Real-World DataLLM agents and tool use → General LLM agent frameworks and benchmarks
  26. Vision-aligned Latent Reasoning for Multi-modal Large Language ModelLLM reasoning → Multimodal reasoning +1
  27. CC-Pan: Channel-wise Compression based Diffusion for Efficient Pan-SharpeningDiffusion models → Inverse problems and image restoration
  28. Seg-ReSearch: Segmentation with Interleaved Reasoning and External SearchLLM reasoning → Multimodal reasoning
  29. RASA: Routing-Aware Safety Alignment for Mixture-of-Experts ModelsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +2
  30. AgenticAKM : Enroute to Agentic Architecture Knowledge ManagementLLM agents and tool use → Software engineering coding agents
  31. SynthVerse: A Large-Scale Diverse Synthetic Dataset for Point TrackingSynthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data
  32. MaMa: A Game-Theoretic Approach for Designing Safe Agentic SystemsLLM agents and tool use → Agent threats, guardrails and governance
  33. Fine-Grained Activation Steering: Steering Less, Achieving MoreMechanistic interpretability → Activation steering methods
  34. EMA Policy Gradient: Taming Reinforcement Learning for LLMs with EMA Anchor and Top-k KLLLM reasoning → Reinforcement learning for reasoning +1
  35. History-Guided Iterative Visual Reasoning with Self-CorrectionLLM reasoning → Multimodal reasoning +1
  36. HoRD: Robust Humanoid Control via History-Conditioned Reinforcement Learning and Online DistillationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  37. LCUDiff: Latent Capacity Upgrade Diffusion for Faithful Human Body RestorationDiffusion models → Inverse problems and image restoration
  38. Interactive Spatial-Frequency Fusion Mamba for Multi-Modal Image FusionState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing
  39. Theory of Speciation Transitions in Diffusion Models with General Class StructureDiffusion models → Diffusion foundations and sampling
  40. Swordsman: Entropy-Driven Adaptive Block Partition for Efficient Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  41. Evaluating the Presence of Sex Bias in Clinical Reasoning by Large Language ModelsLLM reasoning → Clinical and biomedical applications
  42. Beyond Rejection Sampling: Trajectory Fusion for Scaling Mathematical ReasoningLLM reasoning → Mathematical reasoning
  43. Beyond KL Divergence: Policy Optimization with Flexible Bregman Divergences for LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  44. EXaMCaP: Subset Selection with Entropy Gain Maximization for Probing Capability Gains of Large Chart Understanding Training SetsMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  45. Stage-wise Attention-Guided Region Sequencing for Adversarial Attacks on Large Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  46. Can Vision Replace Text in Working Memory? Evidence from Spatial n-Back in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  47. UnMaskFork: Test-Time Scaling for Masked Diffusion via Deterministic Action BranchingLLM reasoning → Diffusion reasoning and test-time scaling +1
  48. Explicit Uncertainty Modeling for Active CLIP Adaptation with Dual Prompt TuningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  49. Fine-tuning Pre-trained Vision-Language Models in a Human-Annotation-Free MannerMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  50. Safe and Stylized Trajectory Planning for Autonomous Driving via Diffusion ModelDiffusion models → Diffusion and flow policies for robotics +1
  51. From Assumptions to Actions: Turning LLM Reasoning into Uncertainty-Aware Planning for Embodied AgentsLLM reasoning → Spatial and embodied reasoning +1
  52. GeneralVLA: Generalizable Vision-Language-Action Models with Knowledge-Guided Trajectory PlanningVision-language-action models → 3D and spatial-aware VLA
  53. Beyond Static Cropping: Layer-Adaptive Visual Localization and Decoding EnhancementMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  54. Light Up Your Face: A Physically Consistent Dataset and Diffusion Model for Face Fill-Light EnhancementDiffusion models → 3D, point cloud and scene generation
  55. How Few-shot Demonstrations Affect Prompt-based Defenses Against LLM Jailbreak AttacksLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  56. Event-T2M: Event-level Conditioning for Complex Text-to-Motion SynthesisDiffusion models → Video generation
  57. Guided Verifier: Collaborative Multimodal Reasoning via Dynamic Process SupervisionLLM reasoning → Multimodal reasoning +1
  58. Contextual Drag: How Errors in the Context Affect LLM ReasoningLLM reasoning → Test-time compute and efficient thinking
  59. Agent-Omit: Adaptive Context Omission for Efficient LLM AgentsLLM agents and tool use → Reinforcement learning for LLM agents
  60. KVSmooth: Mitigating Hallucination in Multi-modal Large Language Models through Key-Value SmoothingMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  61. Boosting LLM Reasoning via Human-Inspired Reward ShapingLLM reasoning → Reinforcement learning for reasoning
  62. AppleVLM: End-to-end Autonomous Driving with Advanced Perception and Planning-Enhanced Vision-Language ModelsMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +1
  63. From Ambiguity to Action: A POMDP Perspective on Partial Multi-Label Ambiguity and Its Horizon-One ResolutionDeep reinforcement learning methods → Deep RL algorithms and representations
  64. Scaling Agentic Verifier for Competitive CodingLLM agents and tool use → Software engineering coding agents
  65. Empirical-MCTS: Continuous Agent Evolution via Dual-Experience Monte Carlo Tree SearchLLM reasoning → Reasoning for agents, planning and code +1
  66. CoLT: Reasoning with Chain of Latent Tool CallsLLM reasoning → Test-time compute and efficient thinking
  67. Viewpoint Matters: Dynamically Optimizing Viewpoints with Masked Autoencoder for Visual ManipulationOffline RL and imitation learning from data → Robot manipulation imitation learning
  68. When Does Multi-Agent Collaboration Help? An Entropy PerspectiveLLM agents and tool use → General LLM agent frameworks and benchmarks
  69. Reshaping Action Error Distributions for Reliable Vision-Language-Action ModelsVision-language-action models → Generalist VLA models and benchmarks
  70. Why Agentic-PRs Get Rejected: A Comparative Study of Coding AgentsLLM agents and tool use → Software engineering coding agents
  71. Following the TRAIL: Predicting and Explaining Tomorrow's Hits with a Fine-Tuned LLMLLM reasoning → LLM reasoning for recommendation
  72. RAPO: Risk-Aware Preference Optimization for Generalizable Safe ReasoningLLM reasoning → Reasoning for agents, planning and code +2
  73. Adaptive 1D Video Diffusion AutoencoderDiffusion models → Diffusion foundations and sampling
  74. InterPReT: Interactive Policy Restructuring and Training Enable Effective Imitation Learning from LaypersonsOffline RL and imitation learning from data → Imitation learning methods
  75. Language Models Struggle to Use Representations Learned In-ContextWorld models → World models for language agents
  76. SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action ModelsLLM reasoning → Spatial and embodied reasoning +1
  77. From Helpfulness to Toxic Proactivity: Diagnosing Behavioral Misalignment in LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  78. The Missing Half: Unveiling Training-time Implicit Safety Risks Beyond DeploymentLLM safety and security → Safety alignment, refusal and guardrails +1
  79. Semantic Consensus Decoding: Backdoor Defense for Verilog Code GenerationLLM safety and security → Backdoor and data poisoning attacks
  80. Continuous Degradation Modeling via Latent Flow Matching for Real-World Super-ResolutionDiffusion models → Inverse problems and image restoration
  81. Beyond Accuracy: Evaluating Posterior Fidelity of Diffusion Inverse SolversDiffusion models → Inverse problems and image restoration
  82. DiMo: Discrete Diffusion Modeling for Motion Generation and UnderstandingDiffusion models → Video generation
  83. Natural Language Instructions for Scene-Responsive Human-in-the-Loop Motion Planning in Autonomous Driving using Vision-Language-Action ModelsVision-language-action models → VLA for autonomous driving +1
  84. Improving 2D Diffusion Models for 3D Medical Imaging with Inter-Slice Consistent StochasticityDiffusion models → Medical imaging and segmentation
  85. A Modern System Recipe for Situated Embodied Human-Robot Conversation with Real-Time Multimodal LLMs and Tool-CallingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  86. Training Data Efficiency in Multimodal Process Reward ModelsLLM reasoning → Multimodal reasoning +1
  87. OMG-Agent: Toward Robust Missing Modality Generation with Decoupled Coarse-to-Fine Agentic WorkflowsLLM agents and tool use → Multimodal and embodied agents
  88. Generative Neural Operators through Diffusion Last LayerDiffusion models → Diffusion foundations and sampling
  89. LC-SAC: Lyapunov-Constrained Soft Actor-Critic via Koopman Operator Theory for Trajectory Tracking and StabilizationDeep reinforcement learning methods → RL theory and sample complexity
  90. Decoupling Time and Risk: Risk-Sensitive Reinforcement Learning with General DiscountingDeep reinforcement learning methods → RL theory and sample complexity
  91. Learning to Reason in 13 ParametersLLM reasoning → Test-time compute and efficient thinking
  92. Expert Selections In MoE Models Reveal (Almost) As Much As TextMixture-of-experts → Expert routing strategies
  93. Making Videos Accessible for Blind and Low Vision Users Using a Multimodal Agent Video PlayerLLM agents and tool use → Multimodal and embodied agents
  94. DMS2F-HAD: A Dual-branch Mamba-based Spatial-Spectral Fusion Network for Hyperspectral Anomaly DetectionState-space sequence models (S4, Mamba) → Hyperspectral image analysis with Mamba
  95. Rethinking Perplexity: Revealing the Impact of Input Length on Perplexity Evaluation in LLMsLLM reasoning → Test-time compute and efficient thinking
  96. CORE: Context-Robust Remasking for Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  97. VideoBrain: Learning Adaptive Frame Sampling for Long Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs
  98. LABBench2: An Improved Benchmark for AI Systems Performing Biology Research
  99. DF-ACBlurGAN: Structure-Aware Conditional Generation of Internally Repeated Patterns for Biomaterial Microtopography Design
  100. VeriInteresting: An Empirical Study of Model Prompt Interactions in Verilog Code Generation
  101. What Makes Position Zero Special? A Mechanistic Study of Position Zero Attention Sinks in LLMs
  102. ARC-AGI-2 Technical Report
  103. Same Input, Different Scores: A Multi Model Study on the Inconsistency of LLM Judge
  104. Optimizing What We Trust: Reliability-Guided QUBO Selection of Multi-Agent Weak Framing Signals for Arabic Sentiment Prediction
  105. Embracing Anisotropy: Turning Massive Activations into Interpretable Control Knobs for Large Language Models
  106. EPPCMinerBen: A Novel Benchmark for Evaluating Large Language Models on Electronic Patient-Provider Communication via the Patient Portal
  107. Bilevel Optimization with Lower-Level Uniform Convexity: Theory and Algorithm
  108. Forecasting Future Language: Context Design for Mention Markets
  109. VISION-ICE: Video-based Interpretation and Spatial Identification of Arrhythmia Origins via Neural Networks in Intracardiac Echocardiography
  110. Exploring the Ethical Concerns in User Reviews of Mental Health Apps using Topic Modeling and Sentiment Analysis
  111. LLM-Assisted Replication for Quantitative Social Science
  112. RA-QA: A Benchmarking System for Respiratory Audio Question Answering Under Real-World Heterogeneity
  113. Probabilistic NDVI Forecasting from Sparse Satellite Time Series and Weather Covariates
  114. Duality Models: An Embarrassingly Simple One-step Generation Paradigm
  115. LATMiX: Learnable Affine Transformations for Microscaling Quantization of LLMs
  116. Joint Parameter and State-Space Bayesian Optimization: Using Process Expertise to Accelerate Manufacturing Optimization
  117. Combining scEEG and PPG for reliable sleep staging
  118. Symmetric Composition of Anisotropic Operators for Global Subseasonal-to-Seasonal Climate Forecasting
  119. Human-Centered Explainable AI for Security Enhancement: A Deep Intrusion Detection Framework
  120. Deep Learning CNN for Pneumonia Detection: Advancing Digital Health in Society 5.0
  121. Expected Moral Shortfall for Ethical Competence in Decision-making Models
  122. SOAR: Regression-based LiDAR Relocalization for UAVs
  123. Directional Concentration Uncertainty: A representational approach to uncertainty quantification for generative models
  124. AM-FM: A Foundation Model for Ambient Intelligence Through WiFi
  125. When and What to Ask: AskBench and Rubric-Guided RLVR for LLM Clarification
  126. Windowed SummaryMixing: An Efficient Fine-Tuning of Self-Supervised Learning Models for Low-resource Speech Recognition
  127. MTS-CSNet: Multiscale Tensor Factorization for Deep Compressive Sensing on RGB Images
  128. Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?
  129. Markerless Head Tracking for Accurate and Accessible Neuronavigation
  130. Enhancing IMU-Based Online Handwriting Recognition via Contrastive Learning with Zero Inference Overhead
  131. ShapBPT: Image Feature Attributions Using Data-Aware Binary Partition Trees
  132. PipeMFL-240K: A Large-scale Dataset and Benchmark for Object Detection in Pipeline Magnetic Flux Leakage Imaging
  133. COMBOOD: A Semiparametric Approach for Detecting Out-of-distribution Data for Image Classification
  134. Point Virtual Transformer
  135. Canzona: A Unified, Asynchronous, and Load-Balanced Framework for Distributed Matrix-based Optimizers
  136. Allocate Marginal Reviews to Borderline Papers Using LLM Comparative Ranking
  137. Adaptive Exploration for Latent-State Bandits
  138. Decoupled Orthogonal Dynamics: Regularization for Deep Network Optimizers
  139. SemPipes -- Optimizable Semantic Data Operators for Tabular Machine Learning Pipelines
  140. CAST-CKT: Chaos-Aware Spatio-Temporal and Cross-City Knowledge Transfer for Traffic Flow Prediction
  141. ARGaze: Autoregressive Transformers for Online Egocentric Gaze Estimation
  142. CLEAR-HPV: Interpretable concept discovery for human-papillomavirus-associated morphology in whole-slide histology
  143. Unbiased Single-Queried Gradient for Combinatorial Objective
  144. Understanding LLM Evaluator Behavior: A Structured Multi-Evaluator Framework for Merchant Risk Assessment
  145. Multilingual Extraction and Recognition of Implicit Discourse Relations in Speech and Text
  146. GAMMS: Graph based Adversarial Multiagent Modeling Simulator
  147. Evaluating Robustness and Adaptability in Learning-Based Mission Planning for Active Debris Removal
  148. AI Chatbot Suicide Risk Detection and Response: Human Validation Study of the Open-Source VERA-MH Safety Evaluation
  149. Locas: Your Models are Principled Initializers of Locally-Supported Parametric Memories
  150. Individual Fairness In Strategic Classification
  151. Large-Ensemble Simulations Reveal Links Between Atmospheric Blocking Frequency and Sea Surface Temperature Variability
  152. Reliable Explanations or Random Noise? A Reliability Metric for XAI
  153. Gabor Fields: Orientation-Selective Level-of-Detail for Volume Rendering
  154. Food Portion Estimation: From Pixels to Calories
  155. E-Globe: Scalable ε-Global Verification of Neural Networks via Tight Upper Bounds and Pattern-Aware Branching
  156. Does SGD Seek Flatness or Sharpness? An Exactly Solvable Model
  157. Scaling Laws for Embedding Dimension in Information Retrieval
  158. StagePilot: Stage-Level Planning for Long-Horizon Dialogue Simulation in Cybergrooming
  159. Evaluating Large Language Models on Solved and Unsolved Problems in Graph Theory: Implications for Computing Education
  160. Learning fermionic linear optics with Heisenberg scaling and physical operations
  161. Quantile-Physics Hybrid Framework for Safe-Speed Recommendation under Diverse Weather Conditions Leveraging Connected Vehicle and Road Weather Information Systems Data
  162. Learning, Solving and Optimizing PDEs with TensorGalerkin: an efficient high-performance Galerkin assembly algorithm
  163. QuantumGS: Quantum Encoding Framework for Gaussian Splatting
  164. Quality Model for Machine Learning Components
  165. UniTrack: Differentiable Graph Representation Learning for Multi-Object Tracking
  166. Feedback Control for Multi-Objective Graph Self-Supervision
  167. Capacity Constraints and the Multilingual Penalty for Lexical Disambiguation
  168. Causal Representation Meets Stochastic Modeling under Generic Geometry
  169. Differentiable Inverse Graphics for Zero-shot Scene Reconstruction and Robot Grasping
  170. Laws of Learning Dynamics and the Core of Learners
  171. A Simple Reduction Scheme for Constrained Contextual Bandits with Adversarial Contexts via Regression
  172. From Fragmentation to Integration: Exploring the Design Space of AI Agents for Human-as-the-Unit Privacy Management
  173. Untwisting RoPE: Frequency Control for Shared Attention in DiTs
  174. Private PoEtry: Private In-Context Learning via Product of Experts
  175. Enhanced QKNorm normalization for neural transformers with the Lp norm
  176. Learning Rate Matters: Vanilla LoRA May Suffice for LLM Fine-tuning
  177. SIDeR: Semantic Identity Decoupling for Unrestricted Face Privacy
  178. Position: Machine Learning for Heart Transplant Allocation Policy Optimization Should Account for Incentives
  179. Near-Optimal Dynamic Matching via Coarsening with Application to Heart Transplantation
  180. Artificial Intelligence as Strange Intelligence: Against Linear Models of Intelligence
  181. AI-Based Detection of Temporal Changes in MR-Linac Images Acquired During Routine Prostate Radiotherapy
  182. BioACE: An Automated Framework for Biomedical Answer and Citation Evaluations
  183. Stochastic hierarchical data-driven optimization: application to plasma-surface kinetics
  184. Instance-optimal high-precision shadow tomography with few-copy measurements: A metrological approach
  185. Smart Diagnosis and Early Intervention in PCOS: A Deep Learning Approach to Women's Reproductive Health
  186. Graph-Theoretic Analysis of Phase Optimization Complexity in Variational Wave Functions for Heisenberg Antiferromagnets
  187. Improving Set Function Approximation with Quasi-Arithmetic Neural Networks
  188. Transolver-3: Scaling Up Transformer Solvers to Industrial-Scale Geometries
  189. SynthForensics: Benchmarking and Evaluating People-Centric Synthetic Video Deepfakes
  190. Comparing Euclidean and Hyperbolic K-Means for Generalized Category Discovery
  191. Emergent Causal-Geometric Dynamics Across Depth in Large Language Models
  192. TurboBoA: Faster and Exact Attention-aware Quantization without Backpropagation
  193. PriMod4AI: Lifecycle-Aware Privacy Threat Modeling for AI Systems using LLM
  194. Knowing When to Answer: Adaptive Confidence Refinement for Reliable Audio-Visual Question Answering
  195. Imposing Boundary Conditions on Neural Operators via Learned Function Extensions
  196. CyIN: Cyclic Informative Latent Space for Bridging Complete and Incomplete Multimodal Learning
  197. Simulated Adoption: Decoupling Magnitude and Direction in LLM In-Context Conflict Resolution
  198. Multi-Aspect Mining and Anomaly Detection for Heterogeneous Tensor Streams
  199. AFD-INSTRUCTION: A Comprehensive Antibody Instruction Dataset with Functional Annotations for LLM-Based Understanding and Design
  200. SLAY: Geometry-Aware Spherical Linearized Attention with Yat-Kernel
  201. A2-LLM: An End-to-end Conversational Audio Avatar Large Language Model
  202. A logical re-conception of neural networks: Hamiltonian bitwise part-whole architecture
  203. Protein Autoregressive Modeling via Multiscale Structure Generation
  204. Contrastive Continual Learning for Model Adaptability in Internet of Things
  205. CoWTracker: Tracking by Warping instead of Correlation
  206. PerpetualWonder: Long-Horizon Action-Conditioned 4D Scene Generation
  207. Multi-layer Cross-attention is Provably Optimal for Multi-modal In-context Learning
  208. Subliminal Effects in Your Data: A General Mechanism via Log-Linearity
  209. From Evaluation to Design: Using Potential Energy Surface Smoothness Metrics to Guide Machine Learning Interatomic Potential Architectures
  210. Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know"
  211. On State Reduction in Linear Attention
  212. PDF-HR: Pose Distance Fields for Humanoid Robots
  213. El Agente Estructural: An Artificially Intelligent Molecular Editor
  214. LitS: A novel Neighborhood Descriptor for Point Clouds
  215. Are AI Capabilities Increasing Exponentially? A Competing Hypothesis
  216. It's Not a Lottery, It's a Race: Understanding How Gradient Descent Adapts the Network's Capacity to the Task
  217. Toward Reliable and Explainable Nail Disease Classification: Leveraging Adversarial Training and Grad-CAM Visualization
  218. Horizon-LM: A RAM-Centric Architecture for LLM Training
  219. Robust Generalizable Heterogeneous Legal Link Prediction
  220. SE-Bench: Benchmarking Self-Evolution with Knowledge Internalization
  221. Evolving Afferent Architectures: Biologically-inspired Models for Damage-Avoidance Learning
  222. Skin Tokens: A Learned Compact Representation for Unified Autoregressive Rigging
  223. Score-Based Change-Point Detection and Region Localization for Spatio-Temporal Point Processes
  224. Maximum-Volume Nonnegative Matrix Factorization
  225. Team, Then Trim: An Assembly-Line LLM Framework for High-Quality Tabular Data Generation
  226. From independent patches to coordinated attention: Controlling information flow in vision transformers
  227. Legendre Memory Unit with A Multi-Slice Compensation Model for Short-Term Wind Speed Forecasting Based on Wind Farm Cluster Data
  228. Speaker-Aware Simulation Improves Conversational Speech Recognition
  229. Interval-Based AUC (iAUC): Extending ROC Analysis to Uncertainty-Aware Classification
  230. Theory of Optimal Learning Rate Schedules and Scaling Laws for a Random Feature Model
  231. Generative Modeling via Drifting
  232. NeuroCanvas: VLLM-Powered Robust Seizure Detection by Reformulating Multichannel EEG as Image
  233. Billion-Scale Graph Foundation Models
  234. Beyond Many-Shot Translation: Scaling In-Context Demonstrations For Low-Resource Machine Translation
  235. Active Asymmetric Multi-Agent Multimodal Learning under Uncertainty
  236. Improved Dimension Dependence for Bandit Convex Optimization with Gradient Variations
  237. A Dual-TransUNet Deep Learning Framework for Multi-Source Precipitation Merging and Improving Seasonal and Extreme Estimates
  238. When Silence Is Golden: Can LLMs Learn to Abstain in Temporal QA and Beyond?
  239. Comparative Insights on Adversarial Machine Learning from Industry and Academia: A User-Study Approach
  240. Decomposing Query-Key Feature Interactions Using Contrastive Covariances
  241. Exploiting contextual information to improve stance detection in informal political discourse with LLMs
  242. Conditional Counterfactual Mean Embeddings: Doubly Robust Estimation and Learning Rates
  243. From Data to Behavior: Predicting Unintended Model Behaviors Before Training
  244. Modular Expert Merging for Biomedical Retrieval
  245. "Be My Cheese?": Cultural Nuance Benchmarking for Machine Translation in Multilingual LLMs
  246. Scalable Cross-Attention Transformer for Cooperative Multi-AP OFDM Uplink Reception
  247. Benchmarking and Enhancing PPG-Based Cuffless Blood Pressure Estimation Methods
  248. How to rewrite the stars: Mapping your orchard over time through constellations of fruits
  249. Linguistically Informed Evaluation of Multilingual ASR for African Languages
  250. Bounded-Abstention Multi-horizon Time-series Forecasting
  251. Adaptive Prompt Elicitation for Text-to-Image Generation
  252. Towards Understanding and Avoiding Limitations of Convolutions on Graphs
  253. LiteToken: Removing Intermediate Merge Residues From BPE Tokenizers
  254. Knowledge Distillation for mmWave Beam Prediction Using Sub-6 GHz Channels
  255. Beyond Learning on Molecules by Weakly Supervising on Molecules
  256. LinGO: A Linguistic Graph Optimization Framework with LLMs for Interpreting Intents of Online Uncivil Discourse
  257. DRMOT: A Dataset and Framework for RGBD Referring Multi-Object Tracking
  258. Static and auto-regressive neural emulation of phytoplankton biomass dynamics from physical predictors in the global ocean
  259. Investigating Disability Representations in Text-to-Image Models
  260. Audio ControlNet for Fine-Grained Audio Generation and Editing
  261. Generalized Schr"odinger Bridge on Graphs
  262. Overstating Attitudes, Ignoring Networks: LLM Biases in Simulating Misinformation Susceptibility
  263. Delving into Muon and Beyond: Deep Analysis and Extensions
  264. Causal explanations of outliers in systems with lagged time-dependencies
  265. Approaches to Semantic Textual Similarity in Slovak Language: From Algorithms to Transformers
  266. Learning to Separate RF Signals Under Uncertainty: Detect-Then-Separate vs. Unified Joint Models
  267. SC-JEPA: Stabilizing Latent Predictive Learning for Time-Series Anomaly Prediction
  268. RIGA-Fold: A General Framework for Protein Inverse Folding via Recurrent Interaction and Geometric Awareness
  269. Mapping the Web of Science, a large-scale graph and text-based dataset with LLM embeddings
  270. A labeled dataset of simulated phlebotomy procedures for medical AI: polygon annotations for object detection and human-object interaction
  271. LEAD: Layer-wise Expert-aligned Decoding for Faithful Radiology Report Generation
  272. A Human-Centered Privacy Approach (HCP) to AI
  273. Targeted Synthetic Control Method
  274. Resilient Load Forecasting under Climate Change: Adaptive Conditional Neural Processes for Few-Shot Extreme Load Forecasting
  275. Jacobian Regularization Stabilizes Long-Term Integration of Neural Differential Equations
  276. Focus-LIME: Surgical Interpretation of Long-Context Large Language Models via Proxy-Based Neighborhood Selection
  277. RexBERT: Context Specialized Bidirectional Encoders for E-commerce
  278. Beyond Holistic Scores: Automatic Trait-Based Quality Scoring of Argumentative Essays
  279. Uncertainty Decomposition for Bayes-Filtered Transformers via Bayesian Predictive Inference
  280. ImmuVis: Hyperconvolutional Foundation Model for Imaging Mass Cytometry
  281. SalFormer360: a transformer-based saliency estimation model for 360-degree videos
  282. PEPR: Privileged Event-based Predictive Regularization for Domain Generalization
  283. Probabilistic Label Spreading: Efficient and Consistent Estimation of Soft Labels with Epistemic Uncertainty on Graphs
  284. From Competition to Collaboration: Designing Sustainable Mechanisms Between LLMs and Online Forums
  285. Can LLMs capture stable human-generated sentence entropy measures?
  286. Textual Planning with Explicit Latent Transitions
  287. Finding Structure in Continual Learning
  288. Gradient Flow Through Diagram Expansions: Learning Regimes and Explicit Solutions
  289. OmniRad: A Radiological Foundation Model for Multi-Task Medical Image Analysis
  290. Unmasking Superspreaders: Data-Driven Approaches for Identifying and Comparing Key Influencers of Conspiracy Theories on X.com
  291. Continual Learning through Control Minimization
  292. PersoPilot: An Adaptive AI-Copilot for Transparent Contextualized Persona Classification and Personalized Response Generation
  293. Forget to Generalize: Iterative Adaptation for Generalization in Federated Learning
  294. SLUM-i: Semi-supervised Learning for Urban Mapping of Informal Settlements and Data Quality Benchmarking
  295. C-DeltaTheta: Circuit-Restricted Weight Arithmetic for Selective Refusal
  296. S-MUSt3R: Sliding Multi-view 3D Reconstruction
  297. ReFRAME or Remain: Unsupervised Lexical Semantic Change Detection with Frame Semantics
  298. BrainVista: Modeling Naturalistic Brain Dynamics as Multimodal Next-Token Prediction
  299. Discovering Mechanistic Models of Neural Activity: System Identification in an in Silico Zebrafish
  300. Greedy-Gnorm: A Gradient Matrix Norm-Based Alternative to Attention Entropy for Head Pruning
  301. LLM surprisal is necessary but not sufficient to capture English garden-path effects: Evidence from joint latent modeling of reading paradigms
  302. Universality of General Spiked Tensor Models
  303. LLM-Empowered Cooperative Content Caching in Vehicular Fog Caching-Assisted Platoon Networks
  304. Is Micro Domain-Adaptive Pre-Training Effective for Real-World Operations? Multi-Step Evaluation Reveals Potential and Bottlenecks
  305. Temporal Slowness in Central Vision Drives Semantic Object Learning
  306. Bayesian PINNs for uncertainty-aware inverse problems (BPINN-IP)
  307. Journey to the Centre of Cluster: Harnessing Interior Nodes for A/B Testing under Network Interference
  308. Growth First, Care Second? Tracing the Landscape of LLM Value Preferences in Everyday Dilemmas
  309. Mixture of Masters: Sparse Chess Language Models with Player Routing
  310. No One-Size-Fits-All: Building Systems For Translation to Bashkir, Kazakh, Kyrgyz, Tatar and Chuvash Using Synthetic And Original Data
  311. TrajVG: 3D Trajectory-Coupled Visual Geometry Learning
  312. Hand Gesture Recognition from Doppler Radar Signals Using Echo State Networks
  313. Machine Learning-Driven Crystal System Prediction for Perovskites Using Augmented X-ray Diffraction Data
  314. SPEAR: An Engineering Case Study of Multi-Agent Coordination for Smart Contract Auditing
  315. Med-MMFL: A Multimodal Federated Learning Benchmark in Healthcare
  316. Self-evolving Embodied AI
  317. Separation-Utility Pareto Frontier: An Information-Theoretic Characterization
  318. Performative Learning Theory
  319. Quantile Transfer for Reliable Operating Point Selection in Visual Place Recognition
  320. Bi-directional Bias Attribution: Debiasing Large Language Models without Modifying Prompts
  321. Optimal Rates for Feasible Payoff Set Estimation in Games
  322. LoRDO: Distributed Low-Rank Optimization with Infrequent Communication
  323. On the use of LLMs to generate a dataset of Neural Networks
  324. Digital Twins & ZeroConf AI: Structuring Automated Intelligent Pipelines for Industrial Applications
  325. Blockchain Federated Learning for Sustainable Retail: Reducing Waste through Collaborative Demand Forecasting
  326. Enabling Real-Time Colonoscopic Polyp Segmentation on Commodity CPUs via Ultra-Lightweight Architecture
  327. Reducing the labeling burden in time-series mapping using Common Ground: a semi-automated approach to tracking changes in land cover and species over time
  328. Multi-scale hypergraph meets LLMs: Aligning large language models for time series analysis
  329. Anytime-Valid Conformal Risk Control
  330. SparVAR: Exploring Sparsity in Visual AutoRegressive Modeling for Training-Free Acceleration
  331. Counterfactual Explanations for Hypergraph Neural Networks
  332. Mosaic Learning: A Framework for Decentralized Learning with Model Fragmentation
  333. VecSet-Edit: Unleashing Pre-trained LRM for Mesh Editing from Single Image
  334. A Bandit-Based Approach to Educational Recommender Systems: Contextual Thompson Sampling for Learner Skill Gain Optimization
  335. MirrorLA: Reflecting Feature Map for Vision Linear Attention
  336. Finding NeMO: A Geometry-Aware Representation of Template Views for Few-Shot Perception
  337. RISE: Interactive Visual Diagnosis of Fairness in Machine Learning Models
  338. Geometry-Aware Optimal Transport: Fast Intrinsic Dimension and Wasserstein Distance Estimation
  339. Multiview Self-Representation Learning across Heterogeneous Views
  340. Efficient Equivariant High-Order Crystal Tensor Prediction via Cartesian Local-Environment Many-Body Coupling
  341. A Domain-Specific Curated Benchmark for Entity and Document-Level Relation Extraction
  342. JOintGS: Joint Optimization of Cameras, Bodies and 3D Gaussians for In-the-Wild Monocular Reconstruction
  343. Universal Robust Speech Adaptation for Cross-Domain Speech Recognition and Enhancement
  344. DeFrame: Debiasing Large Language Models Against Framing Effects
  345. Revisiting Prompt Sensitivity in Large Language Models for Text Classification: The Role of Prompt Underspecification
  346. ProxyWar: Dynamic Assessment of LLM Code Generation in Game Arenas
  347. Disentangling Intrinsic Importance from Emergent Structure in Multi-Expert Orchestration
  348. Proxy Compression for Language Modeling
  349. Convolution Operator Network for Forward and Inverse Problems (FI-Conv): Application to Plasma Turbulence Simulations
  350. ECG-R1: Protocol-Guided and Modality-Agnostic MLLM for Reliable ECG Interpretation
  351. Multi Objective Design Optimization of Non Pneumatic Passenger Car Tires Using Finite Element Modeling, Machine Learning, and Particle swarm Optimization and Bayesian Optimization Algorithms
  352. Bures-Wasserstein Importance-Weighted Evidence Lower Bound: Exposition and Applications
  353. SkeletonGaussian: Editable 4D Generation through Gaussian Skeletonization
  354. Multi-Integration of Labels across Categories for Component Identification (MILCCI)
  355. Aortic Valve Disease Screening from PPG via Physiology-Guided Self-Supervised Learning
  356. Exponential Approximation Rates and Parameter Efficiency of Learnable Bernstein Activations
  357. Decoupled Hierarchical Distillation for Multimodal Emotion Recognition
  358. Depth-Guided Metric-Aware Temporal Consistency for Monocular Video Human Mesh Recovery
  359. ACIL: Active Class Incremental Learning for Image Classification
  360. Towards Next-Generation SLAM: A Survey on 3DGS-SLAM Focusing on Performance, Robustness, and Future Directions
  361. DementiaBank-Emotion: A Multi-Rater Emotion Annotation Corpus for Alzheimer's Disease Speech (Version 1.0)
  362. GraphVec: Cross-Domain Graph Vectorization for Graph-Level Representation Learning
  363. Tokenization and Morphological Fidelity in Uralic NLP: A Cross-Lingual Evaluation
  364. SPOT-Occ: Sparse Prototype-guided Transformer for Camera-based 3D Occupancy Prediction
  365. An Improved Boosted DC Algorithm for Nonsmooth Functions with Applications in Image Recovery
  366. Cascading Robustness Verification: Toward Efficient Model-Agnostic Certification
  367. Provable Target Sample Complexity Improvements as Pre-Trained Models Scale
  368. An Intuitionistic Fuzzy Logic Driven UNet architecture: Application to Brain Image segmentation
  369. Frontend Token Enhancement for Token-Based Speech Recognition
  370. OAT: Ordered Action Tokenization
  371. Steering LLMs via Scalable Interactive Oversight
  372. Enforcing Monotonic Progress in Legal Cross-Examination: Preventing Long-Horizon Stagnation in LLM-Based Inquiry
  373. AGMA: Adaptive Gaussian Mixture Anchors for Prior-Guided Multimodal Human Trajectory Forecasting
  374. VTok: A Unified Video Tokenizer with Decoupled Spatial-Temporal Latents
  375. From Sparse Sensors to Continuous Fields: STRIDE for Spatiotemporal Reconstruction
  376. LORE: Jointly Learning the Intrinsic Dimensionality and Relative Similarity Structure From Ordinal Data
  377. HoloEv-Net: Efficient Event-based Action Recognition via Holographic Spatial Embedding and Global Spectral Gating
  378. Piece of CAKE: Adaptive Execution Engines via Microsecond-Scale Learning
  379. Partial Ring Scan: Revisiting Scan Order in Vision State Space Models
  380. Point2Insert: Video Object Insertion via Sparse Point Guidance
  381. Topology-Aware Revival for Efficient Sparse Training
  382. BPDQ: Bit-Plane Decomposition Quantization on a Variable Grid for Large Language Models
  383. Maximin Relative Improvement: Fair Learning as a Bargaining Problem
  384. Context Determines Optimal Architecture in Materials Segmentation
  385. Pruning for Generalization: A Transfer-Oriented Spatiotemporal Graph Framework
  386. MA3DSG: Multi-Agent 3D Scene Graph Generation for Large-Scale Indoor Environments
  387. JSynFlow: Japanese Synthesised Flowchart Visual Question Answering Dataset built with Large Language Models
  388. KGLAMP: Knowledge Graph-guided Language model for Adaptive Multi-robot Planning and Replanning
  389. From Lemmas to Dependencies: What Signals Drive Light Verbs Classification?
  390. Attack-Resistant Uniform Fairness for Linear and Smooth Contextual Bandits
  391. Scalable Explainability-as-a-Service (XaaS) for Edge AI Systems
  392. Synthesizable Molecular Generation via Soft-constrained GFlowNets with Rich Chemical Priors
  393. Toward Effective Multimodal Graph Foundation Model: A Divide-and-Conquer Based Approach
  394. Turning mechanistic models into forecasters by using machine learning
  395. ZKBoost: Zero-Knowledge Verifiable Training for XGBoost
  396. DELTA: Deliberative Multi-Agent Reasoning with Reinforcement Learning for Multimodal Psychological Counseling
  397. Rate-Optimal Noise Annealing in Semi-Dual Neural Optimal Transport: Tangential Identifiability, Off-Manifold Ambiguity, and Guaranteed Recovery
  398. Tinker Tales: A Tangible Dialogue System for Child-AI Co-Creative Storytelling
  399. SuperPoint-E: local features for 3D reconstruction via tracking adaptation in endoscopy
  400. Supervised Learning as Lossy Compression: Characterizing Generalization and Sample Complexity via Finite Blocklength Analysis
  401. Interfaze: The Future of AI is built on Task-Specific Small Models
  402. A computational account of dreaming: learning and memory consolidation
  403. Federated Concept-Based Models: Interpretable models with distributed supervision