mlsanityData to 14 Oct 2026

Papers

New on arXiv

Fri 29 May 2026

683 papers

  1. Detecting Hidden Behaviors in LLMs via Activation-matched FinetuningLLM safety and security → Backdoor and data poisoning attacks
  2. Position: Profiling Game Worlds by Transition ComplexityWorld models → Video-generation world models and simulators +1
  3. Position: Collusion Risks Among AI Reasoning Agents Justify Certification Requirements for Making Market DecisionsLLM reasoning → Reasoning for agents, planning and code +1
  4. Position: Evaluations of AI Moral Reasoning Still Miss Half of the PictureLLM reasoning → Reasoning benchmarks and evaluation
  5. Why Do AI Agents Break Rules? How Framing, Context, and Social Signals Shape ComplianceLLM agents and tool use → Agent threats, guardrails and governance
  6. What Drives LLM Self-Reflection? A Controlled Ablation of Uncertainty Routing in Armed Conflict ForecastingLLM reasoning → Test-time compute and efficient thinking
  7. LLMs Know the Constraint But Do Not Use It: Activation Bottlenecks in Pragmatic Constraint ReasoningLLM reasoning → Test-time compute and efficient thinking
  8. Carefully Considering Culture: Analyzing LLM Alignment in Single- and Multi-Cultural Settings using Cultural Consensus TheoryLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  9. Cost-Effective Automated Judging of Natural-Language Mathematical ProofsLLM reasoning → Mathematical reasoning
  10. Beyond Memory: A Templated Substrate for Heterogeneous Collaborative Knowledge Work with LLM AgentsLLM agents and tool use → Agent memory systems
  11. Synthetic Scenario Generation for Evaluation of Industry 4.0 AgentsLLM agents and tool use → Financial trading and forecasting agents
  12. SF-AMS: Strategic Forgetting for Structured Memory in LLM AgentLLM agents and tool use → Agent memory systems
  13. Do VLMs Read or Rewrite? On Transcription Faithfulness in Vision-Language ModelsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  14. Lost in Context: Addressing Context Anxiety in Large Language ModelsLLM reasoning → Test-time compute and efficient thinking
  15. Verifier-First Evaluation of Agentic LLMs for Infrastructure-as-Code GenerationLLM agents and tool use → Software engineering coding agents
  16. LISA: Linear-Indexed Sparse Attention for Efficient Long-Context ReasoningLLM reasoning → Test-time compute and efficient thinking
  17. A Systems-Level Analysis of Sensitivity, Robustness, and Stability in Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  18. Harnessing Agent Skills: Architectural Patterns and a Reference Architecture for Skill-Mediated LLM AgentsLLM agents and tool use → Agent skill learning and evolution
  19. Physical Atari: A Robust and Accessible Platform for Real-time Reinforcement Learning on RobotsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  20. LEAF: Growing Trees Without Branching for Speech-Aware Large Language Model Post-TrainingLLM reasoning → Audio-language model reasoning
  21. SRT: Super-Resolution for Time Series via Disentangled Rectified FlowDiffusion models → Inverse problems and image restoration
  22. MetaEvo: A Meta-Optimization Framework for Experience-Driven Agent EvolutionLLM reasoning → Reasoning for agents, planning and code +1
  23. Sample-Efficient Post-Training for LEGO Spatial-Physics ReasoningLLM reasoning → Spatial and embodied reasoning
  24. VisualLeakBench: Reproducible Action-Boundary Propagation Failures in Vision-Language AgentsLLM agents and tool use → Multimodal and embodied agents
  25. TadA-Bench: A Million-Variant Benchmark for Future-Round Discovery Toward Agentic Protein EngineeringLLM agents and tool use → Medical and scientific domain agents
  26. Detect Before You Leap: Mirage Detection in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  27. Grounded Decoding: Retrieval-Anchored Probability Fusion for Faithful RAGRetrieval-augmented generation → RAG robustness and adaptive retrieval
  28. Topology-Aware State Abstraction with Tangle Cores for Markov Decision ProcessesDeep reinforcement learning methods → Deep RL algorithms and representations
  29. AgentxGCore: Agentic AI for Next-Generation Mobile Core NetworkLLM agents and tool use → Agentic AI for wireless networks
  30. Multi-Objective Reference-Aligned Machine UnlearningLLM safety and security → Machine unlearning
  31. PR2: Predictive Routing Replay for MoE-Based LLM Reinforcement LearningMixture-of-experts → MoE in reinforcement learning and robotics
  32. Zamba2-VL Technical ReportMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  33. VESTA: Visual Exploration with Statistical Tool AgentsLLM agents and tool use → Multimodal and embodied agents
  34. SUPREME: A Multi-GPU Framework for Reproducible Image Unlearning Method EvaluationLLM safety and security → Machine unlearning
  35. Score-Control for Hallucination Reduction in Diffusion ModelsDiffusion models → Medical imaging and segmentation
  36. The Deterministic Horizon: When Extended Reasoning Fails and Tool Delegation Becomes NecessaryLLM reasoning → Prompting and chain-of-thought reasoning
  37. Constrained Whole-Body Tracking for Humanoid RobotsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  38. LFA: Layer Feature Attention for Run-Time Introspection of 2D Object Detectors in Automated DrivingEnd-to-end autonomous driving → VLMs for autonomous driving
  39. Agentic Authoring of Interactive Multiview Visualizations in GenomicsLLM agents and tool use → Multimodal and embodied agents
  40. Quantifying the Salience of Geo-Cultural Values for Pluralistic Safety AlignmentLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  41. Reinforcement Learning with Pairwise Preferences in Long-Term Decision ProblemsDeep reinforcement learning methods → RL training of language and agent models
  42. GLENS: Global Search via Learning from Solver Iterates with Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  43. From "Weak" Signals to Strong Models: Preference Delta Aggregation with LoRA MergingLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  44. How Far Do Auto-Interpretation Labels Generalize: A Controlled Study Across Languages, Scripts, and RewordingsMechanistic interpretability → SAE features and their applications
  45. Drift Q-LearningOffline RL and imitation learning from data → Diffusion and flow policies for offline RL +1
  46. (HB-ARFM) History-Bootstrapped Flow Matching for Inverse Boiling ReconstructionDiffusion models → Flow matching, time series and science
  47. From Noise to Control: Parameterized Diffusion PoliciesDiffusion models → Diffusion and flow policies for robotics
  48. Isolating LLM Lexical Bias: A Curation-Free Triangulated Metric for Preference-Stage LearningLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  49. LLMs Need Encoders for Semantic IDs TooMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  50. DRL-Based Pose Control for Double-Ackermann Robots Under Actuation UncertaintiesDeep reinforcement learning methods → RL for robot locomotion and manipulation
  51. How Generation Architecture Shapes Code Complexity in Multi-Agent LLM Systems: A Paired Study on HumanEvalLLM agents and tool use → Software engineering coding agents
  52. Rethinking the Role of Temperature in Large Language Model DistillationLLM reasoning → Prompting and chain-of-thought reasoning
  53. Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future GuidanceLLM reasoning → Prompting and chain-of-thought reasoning +1
  54. Real2SAM2Real: Generative 3D Caches as Complementary Context for Video DiffusionDiffusion models → 3D, point cloud and scene generation
  55. Adaptive Order Policies for Masked DiffusionDiffusion models → Discrete and text diffusion
  56. The Representation-Rationalizability Tradeoff in Reward LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  57. Synthetic Data from Cross-Domain Events for Large-Scale Recommendation SystemsSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  58. Flow Matching for Convective-Scale Precipitation DownscalingDiffusion models → Flow matching, time series and science
  59. Hyperbolic and Evidence-Prioritized Experts for Large Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  60. Robust Shielding for Safe Reinforcement LearningDeep reinforcement learning methods → Safe and constrained RL
  61. Closed-Loop Neural Activation Control in Vision-Language-Action ModelsVision-language-action models → Efficient VLA inference and adaptation
  62. StressDream: Steering Video World Models for Robust Policy Evaluation and ImprovementWorld models → Embodied and robot world models
  63. Per-Group Error, Not Total MSE: Fine-Tuning Vision-Language-Action Models for 11-DoF Mobile ManipulationVision-language-action models → Generalist VLA models and benchmarks
  64. Geodesic Flow Matching for Denoising High-Dimensional Structured RepresentationsLLM reasoning → Spatial and embodied reasoning +1
  65. MindZero: Learning Online Mental Reasoning With Zero AnnotationsLLM reasoning → Reasoning benchmarks and evaluation
  66. Continuous Reasoning for Vision-Language-ActionLLM reasoning → Spatial and embodied reasoning +2
  67. LithoGRPO: Fast Inverse Lithography via GRPO Reinforced Flow MatchingDiffusion models → Diffusion and flow policies for robotics
  68. Quantized Reasoning Models Think They Need to Think Longer, but They Do NotLLM reasoning → Test-time compute and efficient thinking
  69. APE: Agentic Prompt Enhancer for Image Generation and EditingLLM agents and tool use → Multimodal and embodied agents
  70. BAGEN: Are LLM Agents Budget-Aware?LLM agents and tool use → General LLM agent frameworks and benchmarks
  71. Safe2Drive: Evaluating Safe Driving Behaviors of E2E Autonomous Driving ModelsEnd-to-end autonomous driving → Adversarial scenarios and safety testing
  72. Learning to Construct Practical Agentic SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  73. Agentic Transformers Provably Learn to Search via Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents
  74. CAST: Non-Privileged Clipped Asymmetric Self-Teaching with Advantage Flipping for GRPOLLM reasoning → Reinforcement learning for reasoning +1
  75. Benchmarking Multimodal LLMs on Code Generation for Complex Interactive WebpagesLLM reasoning → Multimodal reasoning +1
  76. DiffCrossGait: Trajectory-Level Alignment for 2D-3D Cross-Modal Gait Recognition via Latent DiffusionDiffusion models → Video generation
  77. PrivacyPeek: Auditing What LLM-Based Agents Acquire, Not Just What They SayLLM agents and tool use → Agent threats, guardrails and governance
  78. Emergence of Exploration in Policy Gradient Reinforcement Learning via RetryingDeep reinforcement learning methods → Deep RL algorithms and representations
  79. Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language ModelsLLM safety and security → Jailbreaking
  80. StemBind: When MLLMs Get Lost Between Rules and Instances in Abstract Visual ReasoningLLM reasoning → Multimodal reasoning +1
  81. BudgetDraft: Acceptance-Aware Multi-View Training for Sparse-KV Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  82. GEM: Geometric Erasure by Contrastive Velocity Matching in Rectified FlowsDiffusion models → Robustness, privacy and adversarial aspects +1
  83. Linear Scaling Video VLMs for Long Video UnderstandingMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  84. KLIP: localized distribution shift detection via KL-divergence with diffusion priors in Inverse ProblemsDiffusion models → Medical imaging and segmentation
  85. Stateful Online Monitoring Catches Distributed Agent AttacksLLM agents and tool use → Agent threats, guardrails and governance +1
  86. TunerDiT: Training-free Progressive Steering of Diffusion Transformer for Multi-Event Video GenerationDiffusion models → Video generation
  87. LongTraceRL: Learning Long-Context Reasoning from Search Agent Trajectories with Rubric RewardsLLM reasoning → Test-time compute and efficient thinking +1
  88. nuReasoning: A Reasoning-Centric Dataset and Benchmark for Long-Tail Autonomous DrivingEnd-to-end autonomous driving → VLMs for autonomous driving
  89. What Gets Unmasked First? Trajectory Analysis of Diffusion Models for Graph-to-Text GenerationDiffusion models → Discrete and text diffusion
  90. What Am I Missing? Question-Answering as Hidden State ProbingLLM reasoning → Reasoning benchmarks and evaluation
  91. EGOSTREAM: A Diagnostic Benchmark for Streaming Episodic Memory in Egocentric VisionEfficient LLM inference and serving → Visual token pruning in multimodal models
  92. Vision-Language Models Suppress Female Representations Under Ambiguous InputMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  93. Preference-Aware Rubric Learning for Personalized EvaluationLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  94. UNISON: A Unified Sound Generation and Editing Framework via Deep LLM FusionDiffusion models → Audio, speech and music
  95. SVI-Bench: A Dynamic Microworld for Strategic Video IntelligenceLLM agents and tool use → Multimodal and embodied agents
  96. On the Relationship Between Activation Outliers and Feature Death in Sparse AutoencodersMechanistic interpretability → Sparse autoencoder training and evaluation
  97. If LLMs Have Human-Like Attributes, Then So Does Age of Empires IILLM agents and tool use → Social simulation and multi-agent debate
  98. Personalize Your Large Vision-language Models With In-context Prompt TuningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  99. Skill Reuse as Compression in Agentic RLLLM agents and tool use → Agent skill learning and evolution
  100. Evaluating Factual Density in Multi-Source RAG: A Study in Medical AI AccuracyRetrieval-augmented generation → RAG robustness and adaptive retrieval
All 683
  1. LinTree: Improving LLM Reasoning with Explicitly Structured Search HistoriesLLM reasoning → Test-time compute and efficient thinking
  2. Are Full Rollouts Necessary for On-Policy Distillation?Knowledge distillation → On-policy and self-distillation for LLMs
  3. Batched Differentiable Rigid Body Dynamics in PyTorch for GPU-Accelerated Robot LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  4. IDOL: Inverse-Dynamics-Guided Future Prediction for End-to-End Autonomous DrivingWorld models → World models for autonomous driving +1
  5. AutoSci: A Memory-Centric Agentic System for the Full Scientific Research LifecycleLLM agents and tool use → Web, search, and research agents
  6. VolFill: Single-View Amodal 3D Scene Reconstruction with Volumetric Flow MatchingDiffusion models → 3D, point cloud and scene generation
  7. GPU Forecasters: Language Models as Selective Surrogates for Kernel Runtime OptimizationLLM agents and tool use → Software engineering coding agents
  8. PithTrain: A Compact and Agent-Native MoE Training SystemLLM agents and tool use → General LLM agent frameworks and benchmarks +1
  9. VisionPulse: Dynamic Visual Sparsity for Efficient Multimodal ReasoningLLM reasoning → Multimodal reasoning +1
  10. Fine-grained Verification via Diagnostic Reasoning Supervision for Aspect Sentiment Triplet ExtractionLLM reasoning → Audio-language model reasoning
  11. Used Car Salesbots? Honesty and Credulity of LLMs as Bargaining Agents under Partial InformationLLM agents and tool use → Financial trading and forecasting agents
  12. Answer-Set-Programming-based Abstractions for Reinforcement LearningDeep reinforcement learning methods → Interpretable and logic-guided RL
  13. SCOPE: Self-Play via Co-Evolving Policies for Open-Ended TasksSynthetic data and self-improvement for LLMs → Self-play RL for reasoning
  14. YARD: Y-Architecture Register Decoding for Efficient Hallucination Mitigation in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  15. FAM-Bench: A Multimodal Benchmark for Condition-Aware Food-as-Medicine ReasoningLLM reasoning → Clinical and biomedical applications
  16. Skill Availability and Presentation Granularity in Large-Language-Model Agents: A Controlled SkillsBench StudyLLM agents and tool use → Agent skill learning and evolution
  17. The Sword, Shield, and Achilles' Heel: Characterizing the Linguistic Inductive Bias of Large Language Models for Spatial Reasoning in Navigation PlanningLLM reasoning → Spatial and embodied reasoning
  18. "Inctelegi Romanecste?'' A Recipe for Romanian Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  19. Constrained Multi-Objective Reinforcement Learning with Max-Min CriterionDeep reinforcement learning methods → RL for games and combinatorial optimization
  20. Multi-Turn Multi-Agent Dialogue for Collaborative Reconstruction Improves VLM Performance on Spatial Reasoning, But Only BarelyLLM reasoning → Spatial and embodied reasoning +1
  21. Unlocking Fine-Grained Translation Quality Estimation in LRMs through Mutually Boosting Implicit and Explicit ReasoningLLM reasoning → Reasoning benchmarks and evaluation
  22. DynaTree: Dynamic Agentic Retrieval Tree for Time-Sensitive News RetrievalRetrieval-augmented generation → Agentic RAG, agents and memory +1
  23. HypoAgent: An Agentic Framework for Interactive Abductive Hypothesis Generation over Knowledge GraphsLLM reasoning → Reasoning benchmarks and evaluation +1
  24. Learning to Adapt: Self-Improving Web Agent via Cognitive-Aware ExplorationLLM agents and tool use → Web, search, and research agents +1
  25. Dreaming Of Others: Latent Teammate Modeling In World Models For Multi-Agent Reinforcement LearningWorld models → World models for language agents
  26. Diagnosing Failure Modes of Shared-State Collaboration in Resource-Constrained Visual AgentsLLM reasoning → Multimodal reasoning
  27. FBHM: Functional Benchmarking and Steering of VLMs for Hateful Meme DetectionMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  28. DecMem: Towards Minute-Long Consistent World Generation with Decoupled MemoryWorld models → Video-generation world models and simulators
  29. Reinforcement Learning Can Amplify Emergent Misalignment from Harmless RewardsDeep reinforcement learning methods → RL training of language and agent models
  30. Surface Constraint Policy for Learning Surface-Constrained and Dynamically Feasible Robot SkillsOffline RL and imitation learning from data → Robot learning from demonstration
  31. Forgetting Has Neighbors: Localized Collateral Forgetting in Machine UnlearningLLM safety and security → Machine unlearning
  32. AR Forcing: Towards Long-Horizon Robot Navigation World ModelWorld models → World models for navigation
  33. Learning from Fine-Grained Visual Discrepancies: Mitigating Multimodal Hallucinations via In-Context Visual Contrastive OptimizationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs +1
  34. Model-free LQG Control with Chance ConstraintsDeep reinforcement learning methods → RL for games and combinatorial optimization
  35. Non-Asymptotic Convergence of Stochastic Iterative Algorithms: A Lyapunov FrameworkDeep reinforcement learning methods → RL theory and sample complexity
  36. MoE-dqINR: A Unified Mixture-of-Experts Implicit Neural Representation Framework for Scan-Specific Dynamic and Quantitative MRI ReconstructionMixture-of-experts → Medical and biomedical MoE
  37. Latent Space Disentanglement via Activation Steering for Interpretable Attribute Control in Symbolic Music GenerationMechanistic interpretability → Activation steering methods
  38. Divergence Decoding: Inference-Time Unlearning via Auxiliary ModelsLLM safety and security → Machine unlearning
  39. The Terminal Representation in Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  40. DeMaVLA: A Vision-Language-Action Foundation Model for Generalizable Deformable ManipulationVision-language-action models → 3D and spatial-aware VLA
  41. Industrializing Prediction-Powered Inference: The GLIDE Library for Reliable GenAI and Agentic Systems EvaluationLLM agents and tool use → General LLM agent frameworks and benchmarks
  42. Survival Reinforcement Learning: Toward Scalable Self-Supervised RLDeep reinforcement learning methods → Deep RL algorithms and representations
  43. DriveMA: Driving Vision-Language-Action Models with verifiable Meta-ActionsVision-language-action models → VLA for autonomous driving +1
  44. Mellum2 Technical ReportMixture-of-experts → MoE large language models
  45. COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge DistillationLLM agents and tool use → Agent skill learning and evolution +1
  46. Why Linear Recurrent Memory Works in Partially Observable Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  47. Before Parc Ferm'e: RL-Time Pruning for Efficient Embodied LLMs in Autonomous DrivingLLM reasoning → Spatial and embodied reasoning +1
  48. ERGeoBench:A Comprehensive Benchmark for Embodied Reasoning and Geo-localization in Multimodal Large Language ModelsLLM reasoning → Spatial and embodied reasoning +1
  49. BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt LearningLLM safety and security → Backdoor and data poisoning attacks
  50. Toward Identifiable Sparse AutoencodersMechanistic interpretability → Sparse autoencoder training and evaluation
  51. Scaling Multi-Hop Training Data via Graph-Constrained Path SelectionLLM reasoning → Knowledge- and tool-augmented reasoning
  52. HARP-VLA: Human-Robot Aligned Representation Learning for Vision-Language-Action ModelVision-language-action models → Human-video and latent-action pretraining
  53. Beyond Classification: Dynamic Adapter Routing for Continual Multimodal RetrievalMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  54. EchoRL: Reinforcement Learning via Rollout EchoingLLM reasoning → Reinforcement learning for reasoning +1
  55. Multivariate Distributional Reinforcement Learning Using Sliced DivergencesDeep reinforcement learning methods → RL theory and sample complexity
  56. Fixed-Point Masked Generative ModelingEfficient LLM inference and serving → Diffusion LLM and MoE inference
  57. Probabilistic Precipitation Nowcasting with Rectified Flow TransformersDiffusion models → Flow matching, time series and science
  58. Point-in-Time Financial RAG with Frozen LLMs and Market-Feedback Adaptive RetrievalRetrieval-augmented generation → Legal and financial RAG
  59. Probing Collision Grounding in Vision-Language Models for Safe Human-Robot CollaborationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  60. Student Capacity Moderates Knowledge Distillation Effectiveness: A Systematic Study Across ResNet Teacher-Student Pairs on CIFAR-10Knowledge distillation → General knowledge distillation methods
  61. Steering LLMs? Actually, Sparse Autoencoders can outperform simple baselinesMechanistic interpretability → SAE features and their applications
  62. Retriever Portfolios: A Principled Approach to Adaptive RAGLLM reasoning → Knowledge- and tool-augmented reasoning +1
  63. Detect in Any Scene: An Agentic Framework for Object Detection with Experience-Aware ReasoningLLM reasoning → Multimodal reasoning +1
  64. Convergence of Two-Timescale Markovian Stochastic Approximations with Applications in Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  65. Emergent Languages in Populations of Language Model Agents: From Token Efficiency to Oversight EvasionLLM agents and tool use → General LLM agent frameworks and benchmarks
  66. Guidance for Low-Level Perceptual Editing in Unconditional Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  67. Trust-Region Behavior Blending for On-Policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  68. Light Interaction: Training-Free Inference Acceleration for Interactive Video World ModelsWorld models → Video-generation world models and simulators +1
  69. SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D ScenesLLM reasoning → Spatial and embodied reasoning +1
  70. Not All Synthetic Data Is Yours to Learn FromLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +2
  71. SWIM: Compact Environment Representation for Reinforcement Learning Human SwimmingDeep reinforcement learning methods → RL for robot navigation and UAV control
  72. Don't Fool Me Twice: Adapting to Adversity in the Wild with Experience-Driven ReasoningLLM reasoning → Spatial and embodied reasoning
  73. NTR: Neural Token Reconstruction for Scene Token Bottleneck in End-to-End DrivingEnd-to-end autonomous driving → VLMs for autonomous driving
  74. Subspace-Decomposed JEPAs: Disentangling Progression and Content in Latent World ModelsWorld models → Latent predictive world models
  75. Riemannian Diffusion Models on General Manifolds via Physics-Informed Neural NetworksDiffusion models → Diffusion foundations and sampling
  76. GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMsEfficient LLM inference and serving → KV cache optimization
  77. iVGR: Internalizing Visually Grounded Reasoning for MLLMs with Reinforcement LearningLLM reasoning → Multimodal reasoning +1
  78. A Pilot Study on Curator-Guided Multilingual Art Description for Blind and Low-Vision Audiences with Small Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  79. Task-Focused Memorization for Multimodal AgentsLLM agents and tool use → Agent memory systems
  80. ConsisGuard: Aligning Safety Deliberation with Policy Enforcement in LLM GuardrailsLLM reasoning → Reasoning for agents, planning and code +1
  81. AdaptR1: Reinforcement Learning Based Adaptive Interleaved Thinking in Multi-hop Question AnsweringLLM reasoning → Knowledge- and tool-augmented reasoning +1
  82. LVSA: Training-Free Sparse Attention for Long Video DiffusionDiffusion models → Video generation
  83. The Challenges of Using Reinforcement Learning for Controlling Industrial Energy SystemsDeep reinforcement learning methods → RL for energy, networks and operations
  84. From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan BackdoorsLLM agents and tool use → Agent threats, guardrails and governance +1
  85. Does Visual Information Play a Decisive Role in Vision-Language-Action Model Driving Behavior?Vision-language-action models → VLA for autonomous driving +1
  86. GraphARC: A Comprehensive Benchmark for Graph-Based Abstract ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning
  87. PEEK: Picking Essential frames via Efficient Knowledge distillationKnowledge distillation → Multimodal distillation
  88. MoG: Mixture of Experts for Graph-based Retrieval-Augmented GenerationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG +1
  89. Graph-GRPO: Dependency-Aware Credit Assignment for Generative E-commerce Search RelevanceLLM reasoning → Knowledge- and tool-augmented reasoning
  90. Eigenvectors of Experts are Training-free Non-collapsing RoutersMixture-of-experts → Expert routing strategies
  91. Generating Reports or Repeating Templates? Measuring and Mitigating Template Collapse in 3D CT Report GenerationMultimodal LLMs / vision-language models → Medical vision-language models
  92. BiSegMamba: Efficient Bidirectional Tri-Oriented Mamba for 3D Medical Image SegmentationState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  93. Variational Adapter for Cross-modal Similarity RepresentationMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  94. ImmersiveTTS: Environment-Aware Text-to-Speech with Multimodal Diffusion Transformer and Domain-Specific Representation AlignmentDiffusion models → Audio, speech and music
  95. RDGen: Demonstration Generation for High-Quality Robot Learning via Reinforcement LearningVision-language-action models → Reinforcement learning and post-training +1
  96. Extending AI for Research to the Humanities: A Multi-Agent Framework for Evidence-Grounded ScholarshipLLM agents and tool use → Web, search, and research agents
  97. Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion TransformerDiffusion models → Audio, speech and music
  98. Do Large Language Models Encode Institutional Experience? Evidence from Cross-Linguistic Moral Reasoning Under AmbiguityLLM reasoning → Reasoning benchmarks and evaluation
  99. MineExplorer: Evaluating Open-World Exploration of MLLM Agents in MinecraftLLM agents and tool use → Reinforcement learning for LLM agents
  100. Enhancing Human-Likeness in Reinforcement Learning Agents via Hierarchical Macro Action QuantizationDeep reinforcement learning methods → RL training of language and agent models
  101. EMBGuard: Constructing Hazard-Aware Guardrails for Safe Planning in Embodied AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  102. De-attribute to Forget for LLM UnlearningLLM safety and security → Machine unlearning
  103. DiTTo: Scalable Order-aware All-in-One Image Restoration AgentMultimodal LLMs / vision-language models → Image editing and quality assessment +1
  104. Automating Formal Verification with Reinforcement Learning and Recursive InferenceDeep reinforcement learning methods → RL training of language and agent models
  105. Attend to Evidence: Evidence-Anchored Spatial Attention Supervision for Multimodal RLVRMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  106. What Makes LVLMs Hallucinate Less? Unveiling the Architectural Factors Behind Hallucination RobustnessMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  107. BlueFin: Benchmarking LLM Agents on Financial SpreadsheetsLLM agents and tool use → Financial trading and forecasting agents
  108. MergeTok: Unified Continuous and Discrete Visual Tokenization via Token MergingEfficient LLM inference and serving → Token pruning and merging for ViTs
  109. Inverse Reinforcement Learning without an Optimal Demonstrator: A Feasible Reward Set ApproachOffline RL and imitation learning from data → Inverse reinforcement learning +1
  110. BilliardPhys-Bench: Benchmarking Physical Reasoning and Visual Dynamics of Multimodal LLMsLLM reasoning → Spatial and embodied reasoning +1
  111. UniScale: Adaptive Unified Inference Scaling via Online Joint Optimization of Model Routing and Test-Time ScalingLLM reasoning → Test-time compute and efficient thinking
  112. Zero Collapse: A Failure Mode of Policy Gradient Methods in Discontinuous Reward EnvironmentsDeep reinforcement learning methods → Adversarial robustness and RL in finance
  113. MLIPilot: LLM-Driven Auto-Research for Machine-Learned Interatomic PotentialsLLM agents and tool use → Medical and scientific domain agents
  114. The Flip Side of RLHF: On-Policy Feedback for Reward Model Self-Supervised ImprovementLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  115. GUI-C2: Coarse-to-Fine GUI Grounding via Difficulty-Aware Reinforcement LearningLLM agents and tool use → GUI and mobile agents +1
  116. TRACE: Task-Aware Adaptive Self-Evolving Agentic JailbreakingLLM agents and tool use → Agent threats, guardrails and governance +1
  117. PatchWorld: Gradient-Free Optimization of Executable World Models for Agent EnvironmentsWorld models → World models for language agents +1
  118. Wall-OSS-0.5 Technical ReportVision-language-action models → Generalist VLA models and benchmarks
  119. dMoE: dLLMs with Learnable Block ExpertsMixture-of-experts → MoE large language models +1
  120. Federated Variational Preference Alignment with Gumbel-Softmax Prior for Personalized User PreferencesLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  121. Sophrosyne: Agentic Exploration of Relational Data Systems Needs ModerationLLM agents and tool use → Web, search, and research agents
  122. Distilling LLM Feedback for Lean Theorem ProvingLLM reasoning → Mathematical reasoning +1
  123. ForecastCompass: Guiding Agentic Forecasting with Adaptive Factor MemoryLLM agents and tool use → Financial trading and forecasting agents
  124. Safe Equilibrium Policy Optimization for Strategic Agent PoliciesLLM agents and tool use → Reinforcement learning for LLM agents
  125. Speculative Pipeline Decoding: Higher-Accuracy Drafting with Hidden Latency via Pipeline ParallelismEfficient LLM inference and serving → Speculative decoding
  126. LLM Anonymization Against Agentic Re-IdentificationLLM agents and tool use → Agent threats, guardrails and governance
  127. A Lecture Note on Offline RL and IRL, Part II: Foundations of Inverse Reinforcement Learning and Dynamic Discrete Choice ModelsOffline RL and imitation learning from data → Inverse reinforcement learning
  128. CoMem: Context Management with A Decoupled Long-Context ModelLLM agents and tool use → Agent memory systems
  129. COMPASS: Cognitive MCTS-Guided Process Alignment for Safe Search AgentsLLM agents and tool use → Agent threats, guardrails and governance
  130. Send a SCOUT First: Pre-hoc Reasoning for Adaptive Detector Allocation in Prompt-Injection DefenseLLM reasoning → Reasoning for agents, planning and code
  131. Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime MonitoringVision-language-action models → Failure recovery and robustness
  132. Your Teacher Can't Help You Here: Combating Supervision Fidelity Decay in On-Policy DistillationLLM reasoning → Prompting and chain-of-thought reasoning +1
  133. SLAT: Segment-Level Adaptive Trimming for Efficient CoT ReasoningLLM reasoning → Test-time compute and efficient thinking
  134. Unlearning in Diffusion Models: A Unified Framework with KL Divergence and Likelihood ConstraintsDiffusion models → Robustness, privacy and adversarial aspects +1
  135. Planner-Centric Reinforcement Learning for Deep Research with Structure-Aware RewardDeep reinforcement learning methods → RL training of language and agent models
  136. Differentially Private Preference Data Synthesis for Large Language Model AlignmentLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment +1
  137. Design and Evaluation of Multi-Agent AI Oracle Systems for Prediction Market ResolutionLLM agents and tool use → Financial trading and forecasting agents
  138. Feat2Go: Visual Feature-Grounded Value Estimation for Embodied Reinforcement LearningVision-language-action models → Reinforcement learning and post-training +2
  139. MechVQA: Benchmarking and Enhancing Multimodal LLMs on Comprehensive Mechanical Drawing UnderstandingMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  140. On the impact of retrieved content representations in RAG PipelinesRetrieval-augmented generation → RAG robustness and adaptive retrieval
  141. Smaller Models are Natural Explorers for Policy-Level Diversity in GRPOLLM reasoning → Reinforcement learning for reasoning
  142. Learning Agent-Compatible Context Management for Long-Horizon TasksLLM agents and tool use → Agent memory systems
  143. What Breaks When LLMs Code? Characterizing Operational Safety Failures of Agentic Code AssistantsLLM agents and tool use → Software engineering coding agents
  144. Efficient and Uncertainty-Aware Diffusion Framework for Offline-to-Online Reinforcement LearningDiffusion models → Diffusion and flow policies for robotics +1
  145. CameraNoise: Enabling Faithful Camera Control in Video Diffusion through Geometry-Flow-Guided Noise WarpingDiffusion models → Video generation
  146. Eywa: Provenance-Grounded Long-Term Memory for AI AgentsLLM agents and tool use → Agent memory systems
  147. Pairwise Reference Alignment as a Model-Level Ordinal ObservableLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  148. Chain-of-Thought and Compressed Looped Transformers: A Memory-Budget SeparationLLM reasoning → Prompting and chain-of-thought reasoning
  149. Efficient Diffusion LLMs via Temporal-Spatial Parallel Decoding and Confidence ExtrapolationEfficient LLM inference and serving → Diffusion LLM and MoE inference
  150. FLAG: Flow Policy MaxEnt-RL by Latent Augmented GuidanceDeep reinforcement learning methods → RL with diffusion and flow models
  151. Immuno-VLM: Immunizing Large Vision-Language Models via Generative Semantic Antibodies for Open-World TrustworthinessMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  152. MAVEN: Improving Generalization in Agentic Tool CallingLLM agents and tool use → General LLM agent frameworks and benchmarks
  153. MosaicLeaks:Privacy Risks in Querying-in-the-Open for Deep Research AgentsLLM agents and tool use → Agent threats, guardrails and governance
  154. Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM AgentsLLM agents and tool use → Agent skill learning and evolution
  155. Simple Token-Efficient Vision-Language Model for Case-level Pathology Synoptic Report GenerationMultimodal LLMs / vision-language models → Medical vision-language models
  156. Diversity Matters: Revisiting Test-Time Compute in Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  157. ExpGraph: Model-Agnostic Experience Learning with Graph-Structured Memory for LLM AgentsLLM agents and tool use → Agent memory systems
  158. SAGE: A Novelty Gate for Efficient Memory Evolution in Agentic LLMsLLM agents and tool use → Agent memory systems
  159. Equivariant Latent Alignment via Flow Matching under Group SymmetriesDiffusion models → Flow matching, time series and science
  160. Seeing Before Agreeing: Aligning Multi-Agent Consensus with Visual EvidenceMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  161. Primitive Subspaces Mediate Few-Shot Transfer in VLAsVision-language-action models → Generalist VLA models and benchmarks
  162. Universal Decision LearnersDeep reinforcement learning methods → Deep RL algorithms and representations
  163. Triaging Threats to Specialized GuardrailsLLM safety and security → Safety alignment, refusal and guardrails
  164. ElasticMem: Latent Memory as a Learnable Resource for LLM AgentsLLM agents and tool use → Agent memory systems
  165. Depth-Dependent Indirect Prompt Injection in Tool-Calling ReAct Agents: Injection Depth, Payload Framing, and Turn-Budget SensitivityLLM reasoning → Reasoning for agents, planning and code +2
  166. Investigating Detection and Obfuscation of Prompt Injection Attacks Against Software Reverse Engineering AI AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  167. Reinforcement Learning for Special Education: Aligning LLM Tutors to Diverse Learners through Disability-Adaptive TrainingLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  168. From Doyle to AGM: A Survey and an Implementation Roadmap for Belief Change
  169. Position: Reasoning is a Learnable Rule-Based Process
  170. When AI Is Your Pastor: A Benchmark for Theological Triage and Pastoral Guidance in Large Language Models
  171. Conflict or Strategy? Asymmetric Role Framing of La France insoumise and Rassemblement National in French News Headlines, 2022-2025
  172. Looks Right, Works Right: A Project-Level Benchmark for Multi-Screen Mobile App Generation
  173. Loss-Aware Feature-Map Pruning in Convolutional Neural Networks Using Multi-Armed Bandits
  174. Codifying the Judge: Scalable Evaluation via Program Distillation
  175. Beyond Liars' Bench: The Impact of Lie Typology, Depth, and Sparsity on Deception Detection in LLMs
  176. Office Comprehension Benchmark
  177. LLMs in the Real World: Evaluating "AI" in Emergency Contexts
  178. HyBIRD: Hyperbolic Bridge Retrieval and Diagnosis for Methodology Inspiration Retrieval
  179. AgentOdyssey: Open-Ended Long-Horizon Text Game Generation for Test-Time Continual Learning Agents
  180. ReviewGuard: Aligning LLM-Assisted Peer Review with Long-Term Scientific Impact
  181. EMORSION: Examining the Impact of Audio Parameters on Emotional Responses and Immersion in Film
  182. Physically Constrained Ensemble Gaussian Process Modelling for Expensive Quantum Systems with Heteroskedastic Noise
  183. Artificial Intelligence in Ship Finance: Applications, Opportunities, and a Case Study in AI-Augmented Loan Origination
  184. A2SG:Adaptive and Asymmetric Surrogate Gradients for Training Deep Spiking Neural Networks
  185. Few-Shot Resampling for Scalable Statistically-Sound Data Mining
  186. OSCS-SupCon: Orthogonal Sigmoid-based Common and Style Supervised Contrastive Learning for Robust Feature Disentanglement
  187. Every Act Has Its Price: Compressed Moral Composition in Frontier LLMs
  188. Item Response Scaling Laws: A Measurement Theory Approach for Efficient and Generalizable Neural Scaling Estimation
  189. Structured Neuron Pruning in Deep Neural Networks Using Multi-Armed Bandits
  190. Measuring Poverty and Inequality with Reduced Data: A Machine Learning Approach Using Nigerian Household Data
  191. Can You Trust What You See? Human and AI Detection of Synthetic Legal Evidence
  192. Position: Anthropomorphic Misalignment Research Needs Stronger Evidence
  193. MIRAGE: Metadata-Integrated Repository Analysis and Guided Enhancement for MSR Datasets
  194. Subtitle-Aligned Fine-Tuning of Whisper for Swiss German ASR: Benchmark Contamination, Convention Mismatch, and an Honest Baseline at 25.6% WER (13.8% cWER)
  195. Position: Genomic Model Research Must Move Beyond Anecdotal Evaluation of Interpretability Methods
  196. QDSP: An Interpretable Structured Learning Framework for Predicting Death or Cerebral Palsy in Very Low Birth Weight Infants
  197. Contribution Weights: A Geometrical Analysis of Self-Attention Transformers
  198. LFNO: Bridging Laplace and Fourier via Transient-Steady Decomposition
  199. Reachability and asymptotics of Gaussian Transformer dynamics
  200. DiffoR: A Unified Continuous Generative Framework for Universal Ordinal Regression
  201. A Topological Characterization of Graph Neural Networks via Stochastic Block Model Embeddings on the n-Sphere
  202. Repetition Mismatch: Why Data Mixture Experiments Don't Scale and How to Fix Them
  203. Shortcuts in the Tail: Debiasing via Post-Hoc Spectral Compression of Fine-Tuning Updates
  204. Gradient Descent with Large Step Size Restores Symmetry in Deep Linear Networks with Multi-Pathway
  205. The Variance Brain Foundation Models Forgot: Third-Order Statistics Predict Cognition Where Billion-Parameter Models Fail
  206. Counterfactual Explanations for Deep Two-Sample Testing
  207. Neural Radiated-Noise Fields for Unmanned Underwater Vehicle Noise Spectrum Prediction in Three-Dimensional Scenes
  208. The Shape of Addition: Geometric Structures of Arithmetic in Large Language Models
  209. Spatial Transcriptomics-Guided Alignment Enhances Molecular Profiling in Pathology Foundation Model
  210. DXA-Derived Skeletal Phenotypes and Hip Fracture Risk: A Backdoor-Adjusted Causal Analysis
  211. Oscillatory State-Space Models as Inductive Biases for Physics-Informed Neural PDE Solvers
  212. Ego-METAS: Egocentric online Multimodal Energy-efficient Temporal Action Segmentation benchmark
  213. Weighted Conformal Clustering
  214. Variance-sensitive Thompson sampling for generalised linear bandits, revisited
  215. Finer Parameter Steps for Low-Rank PEFT: A Controlled Study with CP Tensor Adapters
  216. Canonicalized Stable-List Replay for Private Federated Continual Learning over Language-Model Embeddings
  217. Empirical Likelihood with Generative AI
  218. Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight
  219. UniPinRec: Unifying Generative Retrieval and Ranking at Pinterest Scale
  220. Parameter-Free and Group Conditional Online Conformal Prediction
  221. 4D Radar Meets LiDAR and Camera: Cooperative Perception under Adverse Weather
  222. Auditing Near-Optimal Policies Can Be Exponentially Hard: Conditional Query Lower Bounds via Occupancy Rashomon Capacity
  223. Riemannian Stochastic Optimization for Sufficient Dimension Reduction
  224. Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism
  225. Rethinking Amortized Neural Representations for High-Resolution Terrain Elevation Data
  226. A Distribution-Free Framework for Rewrite-Based Human-text Detection via Knockoff Filtering
  227. Data-Driven Spectral Prediction for Accelerating Large-Scale Electronic Structure Calculations
  228. Dynamic Proxy-Mixing: Transferring Replay Controllers from Small to Large Models for Continual Instruction Tuning
  229. AutoIQ: An Ensemble Framework for Automatic Assessment of Geometric Distortion in Prostate Diffusion-Weighted Imaging
  230. Detector-Evasive LLM Paraphrasing via Constrained Policy Optimization
  231. αDepth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion
  232. Behavior Cloning of MPC for 3-DOF Robotic Manipulators
  233. CRMA: A Spectrally-Bounded Backbone for Modular Continual Fine-Tuning of LLMs
  234. Non-Learning Low-Light Stereo Vision
  235. How Much Orthogonalization Does Muon Need?
  236. HiGS: A Hierarchical Rendering Architecture for Real-Time 3D Gaussian Splatting
  237. UniVerse: A Unified Modulation Framework for Segmentation-Free,Disentangled Multi-Concept Personalization
  238. Longitudinal Multimodal Sensing of Physical Activity and Well-Being in Older Adults
  239. The role of class encoding in neural collapse
  240. Polar Depth for Potentially Heavy-Tailed Data
  241. PE-means: Improved Differentially Private k-means Clustering through Private Evolution
  242. ROGUE: Evaluating Corrigibility Failures in Frontier Computer-Use Agents
  243. Balancing Learning Rates Across Layers: Exact Two-Step Dynamics and Optimal Scaling in Linear Neural Networks
  244. CHAM-net: A Contrastive Hierarchical Adaptive Meta-network for Robust Global Methane Flux Prediction
  245. Which Institutional Frameworks Do Chatbots Assume? Auditing Jurisdictional Defaults in Multilingual LLMs
  246. Benchmarking Recursive-Collapse Warning Claims Under Matched False-Positive Control
  247. KG-Guard: Graph-Based Hallucination Detection for Knowledge Base Question Answering
  248. Cluster Analysis with Resampling for Validation and Exploration (CARVE)
  249. Perturbative methods for non-parametric instrumental variable
  250. Training-Free Object-Agnostic Jam Detection in Fulfillment Centers
  251. Adversarially Robust Control of Conditional Value-at-Risk via Rockafellar-Uryasev Conformal Inference
  252. Belief Consistency Between Foundation-Model Evidence and Geometric Perception in Persistent Robotic Maps
  253. Coupling Language Models with Physics-based Simulation for Synthesis of Inorganic Materials
  254. Stochastic Rounding Increases Small Singular Values
  255. Where to Refine, When to Stop: Rethinking Redundancy via Latent Discrepancy for Efficient Visual Autoregressive Generation
  256. Large-scale Uncertainty Quantification for Latent Variable Models Using Subsampling Markov Chain Monte Carlo
  257. Modeling Spectral Energy Shifts in Spatio-Temporal Graph Anomaly Detection
  258. ERICA: Quantifying Replicability of Cluster Analysis
  259. FLaG: Fine-Grained Latent Grouping for Hallucination Detection
  260. Symmetric Hermite quadrature-based balanced truncation for learning linear dynamical systems from derivative data
  261. Is Zero-Shot Super-Resolution Possible in Operator Learning?
  262. Uncovering Temporal Framing in the News
  263. Accurate Large-sample Uncertainty Quantification using Stochastic Gradient Markov Chain Monte Carlo
  264. Inner Product Aware Quantization: Provably Fast, Accurate, and Adaptive Algorithms
  265. Model-Native Computing Architecture: Envisioning Future System Architecture Through the Lens of Computer Architecture
  266. Model-Based Quality Assessment for Massively Multilingual Parallel Data
  267. Specializing Without Forgetting: Analyzing Knowledge Preservation in Multilingual Model Adaptation
  268. Bit-Exact AI Inference Verification Without Performance Tradeoffs
  269. Evaluating Bivariate Causal Statements Based on Mutual Compatibility
  270. On Wednesdays, We Ask Questions: Optimizing "Active Listening" in Automated Legal Triage and Referral
  271. KISS: Keeping it Simple and Slotted when Learning to Communicate over Wireless
  272. Out-of-Distribution generalization of quantile regression with heavy tailed inputs: an SVM approach
  273. ReFLEX: Length-Generalizable CSI Denoising for MIMO-OFDM via Relative-Frequency Bias
  274. When Softmax Fails at the Top: Extreme Value Corrections for InfoNCE
  275. The Harsh Truth: Segment-Level Analysis of Harsh Driving Events in Milan Using Large-Scale Telematics, Street Networks, and Google Street View
  276. LastAct: Trajectory-Guided Latest-Activity Localization for Real-Time Smart-Home Activity Recognition
  277. ARCA: Adapter-Residual Credit Assignment When Token Signals Degenerate
  278. HOIST: Humanoid Optimization with Imitation and Sample-efficient Tuning for Manipulating Suspended Loads
  279. Capability Self-Assessment in Large Language Models
  280. Effects of Varying LLM Access on Essay Writing Behavior
  281. Dynamics and Representation Structure of Local Approximations to Gradient-Based Learning in Linear Recurrent Neural Networks
  282. InfoAtlas: A Foundation Model for Zero-Shot Statistical Dependence Estimate
  283. Civilizational Metamaterials: Engineering Coordination Under Capability Gradients and Structural Turbulence
  284. Self-Correction Can Amplify Hallucinations: Fact-Level Repair with Graph-Based Evidence Routing in Multimodal Generation
  285. A Pre-Training Analogue of Grokking in Language Models: Tracing Delayed Grammatical Generalization
  286. SEMBridge: Tagless-Final Program Semantics with Weakest-Precondition and Bounded-Checking Interpretations
  287. 21cmEMUv3: a hybrid diffusion-LSTM emulator of 21cmFAST summary observables
  288. DeSQ: Decomposition-based SPARQL Query Generation
  289. From Rashomon Theory to PRAXIS: Efficient Decision Tree Rashomon Sets
  290. BOUTEF: A Multilingual Corpus for FakeNews in North Africa -- Language as a Weapon
  291. PaintBench: Deterministic Evaluation of Precise Visual Editing
  292. AI-Guided Design and Optimization of Graphite-Based Anodes via Iterative Experimental Feedback
  293. The New Social Image: How AI Competency and AI Proactivity Influence Self- and Peer-Perceptions in the Workplace
  294. Beyond Augmentation: Score-Guided Pathological Prior for EEG-based Depression Detection
  295. MyoSem: Aligning Electromyography with Natural-Language Action Semantics
  296. UF-AMA: A unified framework for cross-domain emotion recognition via adaptive multimodal alignment
  297. ChurnNet: A Optimized Modern AI for Churn Prediction
  298. RealityTest: How People Probe AI Identity and Whether Models Disclose It
  299. Modeling Robotics Dataset Construction as an Artifact-Based Build Process
  300. Improving IoT Intrusion Detection Through SMOTE-Based Oversampling and Extended Multi-Model Evaluation on Side-Channel Power Data
  301. DataShield: Safety-degrading Data Filtering for LLM Benign Instruction Fine-Tuning
  302. Digital-to-Physical Transfer of Adversarial Patches for Aerial Vehicle Detection
  303. Training-Free Continuous Bitrate Control for Scalable Image Coding for Humans and Machines
  304. Interpreting FCDNNs via RG on Exponential Family
  305. A physics-informed foundation model for quantitative diffusion MRI
  306. A Protocol-Language Model for Network Intrusion (Without Deep Packet Inspection)
  307. RAFT: Data Refinement and Adaptive Distillation for Domain Fine-Tuning with Alleviated Forgetting
  308. Multi-Contrast MRI Motion Correction via Parameter-Informed Disentanglement and Adaptive Experts
  309. Completion at the Boundary (CaB): Deployable Switching with Completion-Aware Control under Limited Calibration
  310. Regime-Adaptive Continual Learning for Portfolio Management
  311. Adaptive data selection improves wearable prediction under low baseline performance
  312. Representation Forcing for Bottleneck-Free Unified Multimodal Models
  313. Lumos-Nexus: Efficient Frequency Bridging with Homogeneous Latent Space for Video Unified Models
  314. SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models
  315. Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstruction
  316. A Tight Theory of Error Feedback Algorithms in Distributed Optimization
  317. CoFiDA-M: Concept-Aware Feature Modulation for Cross-Domain Adaptation with Image-Only Inference
  318. Recognizing Co-Speech Gestures in-the-Wild
  319. Language Models Learn Constructional Semantics, Not To Mention Syntax: Investigating LM Understanding of Paired-Focus Constructions
  320. Choosing the Lens: Strategic Perspective Activation in Context-Dependent Argumentation
  321. Giving Sensors a Voice: Multimodal JEPA for Semantic Time-Series Embeddings
  322. SurGe: Improved Surface Geometry in Point Maps
  323. Joint Multi-Camera LiDAR Extrinsic Calibration via Learned Pairwise Initialization and Geometric Refinement
  324. SPECTRA: Synthetic IR Test Collections with Relevance Oracles and Controlled Distractor Diagnostics
  325. Disagreeing Rationales: Rethinking Classification and Explainability Evaluation in Hate Speech Detection
  326. Effective Biological Representation Learning by Masking Gene Expression
  327. Functional Attention: From Pairwise Affinities to Functional Correspondences
  328. Positional versus Symbolic Attention Heads: Learning Dynamics, RoPE Geometry, and Length Generalization
  329. SMART: SMPLest-X Mesh Adaptation and RAFT Tracking for Soccer Pose Estimation
  330. Semantic Triplet Restoration: A Novel Protocol for Hierarchical Table Understanding in Large Language Models
  331. The Dynamic-Probabilistic Consistency Gap in Chaotic Surrogate Modeling
  332. Automated Prediction of Postoperative Pancreatic Fistula Using Preoperative Computed Tomography
  333. RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video
  334. Feature-Optimized Vision for Adaptive 3D Scene Reconstruction
  335. Discovering Thermodynamically Admissible Dissipation Potentials via Grammar-Based Symbolic Regression
  336. Value Functions as Supermartingale Certificates
  337. Chem-PerturBridge: a harmonized compendium of small molecule perturbation transcriptomic effects
  338. UniAudio-Token: Empowering Semantic Speech Tokenizers with General Audio Perception
  339. Separating Secrets from Placeholders: A Hybrid CNN-CodeBERT Framework for Three-Class Credential Leakage Detection
  340. Reliable Multilingual Orthopedic Decision Support from Clinical Narratives: Language-Aware Adaptation and Verification-Guided Deferral
  341. Internalizing Temporal Consistency in Video Object-Centric Learning without Explicit Regularization
  342. When Are Multimodal Predictions Biologically Supported? A Diagnostic Evaluation Framework
  343. How can embedding models bind concepts?
  344. On Efficient Scaling of GNNs via IO-Aware Layers Implementations
  345. Scalable Inference-Time Annealing with Surrogate Likelihood Estimators
  346. Assign and Add: A Mechanistic Study of Compositional Arithmetic
  347. Consolidating Rewarded Perturbations for LLM Post-Training
  348. Enhancing Computer Vision Model Generalization in Warehouse Facilities: A Case Study on Anomaly Detection in Vertical Material Handling Systems
  349. Graphical einops: bridging tensor networks and computation graphs
  350. Balanced LoRA: Removing Parameter Invariance to Accelerate Convergence
  351. BenHalluEval: A Multi-Task Hallucination Evaluation Framework for Large Language Models on Bengali
  352. Language Models Can Resolve Reference Compositionally, But It's Not Their Native Strength: The Case of the Personal Relation Task
  353. Knowledge boundary probing and demand-guided intervention for LLM-based power system code generation
  354. Scaling Conversational Hungarian ASR: The BEA-Dialogue+ Corpus
  355. DRIFT: Decoupled Rollouts and Importance-Weighted Fine-Tuning for Efficient Multi-Turn Optimization
  356. Translation Analytics for Freelancers II: Benchmarking Local LLMs for Confidential Translation Workflows
  357. Modeling Covariate Transition for Efficient Estimation of Longitudinal Treatment Effects in Randomized Experiments
  358. Flow map learning in nonlinear vector autoregressive models: influence of the feature-library structure on the training error
  359. Astra: a generalizable report generation foundation model for 3D computed tomography
  360. DOA: Training-Free Decoder-Only Attention Policy for Long-Form Simultaneous Translation with SpeechLLMs
  361. DG-CoLearn: An Efficient Collaborative Learning Framework for Dynamic Graphs
  362. Self-Tuning Regularization for Image Scanning Microscopy
  363. Fixed Universal Transformers
  364. Neuro-symbolic Syntactic Parsing: Shaping a Neural Network with the CYK Algorithm
  365. Triangle Splatting SLAM
  366. Improved Guarantees for Langevin Monte Carlo with Average Smoothness
  367. FSM-Net: An Efficient Frequency-Spatial Network for Real-World Deblurring
  368. Target-Side Paraphrase Augmentation for Sign Language Translation with Large Language Models
  369. Deep-learning-based low-energy trigger algorithms for the Hyper-Kamiokande experiment
  370. LLM Judges Inconsistently Disagree Across Safety Criteria and Harm Categories
  371. LiftNav: Path Planning via Semantic Lifting in TSDF-Guided Gaussian Splatting
  372. Scaling Higher-Order Graph Learning with Maximal Clique Complexes
  373. Softsign: Smooth Sign in Your Optimizer For Better Parameter Heterogeneity Handling
  374. A Unifying View of Variational Generative Wasserstein Flows
  375. Trading Complexity for Expressivity Through Structured Generalized Linear Token Mixing
  376. The Latin Substrate: How Language Models Represent and Mediate Script Choice
  377. dashi: A Python library for Dataset Shift Characterization to Support Trustworthy AI Development and Deployment
  378. VIABLE: A Visually Impaired Assistance Benchmark for VLM-as-a-Judge Evaluation
  379. Wall-Clock Complexity for Zeroth-Order Optimization with Tunable Oracle Fidelity
  380. Log-Ratio Propagation on the Simplex: A Theory of Cellwise Contamination for Compositional Data
  381. Appropriateness of Empathy in AI: A Signal-Cost Perspective
  382. Bundesrecht: An Open Library and Corpus for German Statutory Reference Processing
  383. Social welfare optimisation under institutional reward and punishment
  384. Inconsistency-Aware Minimization: Improving Generalization with Unlabeled Data
  385. Generalized Intention Modeling in Multi-Agent Reinforcement Learning
  386. Graph Neural Networks Are Not Continuous Across Graph Resolutions
  387. S3LDBO: A Snapshot Single-Loop Algorithm for Decentralized Bilevel Optimization
  388. TraceGraph: Shared Decision Landscapes for Diagnosing and Improving Agent Trajectories
  389. Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance
  390. mRNAutilus: Multi-Objective-Guided Discrete Generation of mRNA with Optimized Therapeutic Properties
  391. TokTalk: Expressive Real-time Facial Animation from Audio-LLM Tokens
  392. Authentication of Copy Detection Patterns via Cross-Camera Dual-Synthetic Referencing
  393. Contextual Scalarisation Thompson Sampling for multi-objective decisions in public media
  394. Neither Replacement nor Panacea: Comparing LLM-Based Conversational and Graphical Decision Support in Industrial Tasks
  395. SAM for Robust Mitochondria Instance Segmentation in Fluorescence Microscopy
  396. Topologically Consistent Multi-view 3D Head Reconstruction via Coarse-Guided Layered Surface Sampling
  397. Wind Turbine Maintenance Log Labelling Framework: LLM-Driven Data Correction and Enrichment via Semantic Extraction of Reliability Intelligence
  398. Practical Cross-Band Channel Prediction for AI-RAN via Physics-Guided Deep Unfolding
  399. GETA: Generalized Encrypted Traffic Analysis
  400. Learning Parametric Nitrogen Fertilizer Response Curves Using Neuro Symbolic Regression
  401. Personalized to Persuade: The Effects of Contextualization and Warmth on Trust and Reliance in Conversational AI
  402. Algorithmic Recourse of In-Context Learning for Tabular Data
  403. Envisioning Beyond the Few: Disentangled Semantics and Primitives for Few-Shot Atypical Layout-to-Image Generation
  404. Lightweight CNN-Based Anomaly Detection for High Voltage Converter Modulators in the Spallation Neutron Source
  405. Fraud Type Decomposition and the Observation-Mechanism Taxonomy:Class-Specific Detection Limits in Payment Networks
  406. Formalizing and falsifying causal pathways of rare events
  407. Entropic Projection Alignment: Estimating, Explaining, and Improving Model Performance Under Distribution Shift
  408. LVCG: Learning ECG Representations in the Latent Vectorcardiogram Space
  409. Spectral Reach: Understanding Neural Scaling as Progress into the Spectral Tail
  410. Bifurcated Remaining Useful Life Prediction: A Hybrid Approach for Realistic Uncertainty Characterization
  411. Correcting Split Selection in Online Decision Trees via Anytime-Valid Inference
  412. A holomorphic neural network framework for 3D boundary value problems governed by harmonic potentials
  413. HiERO-StepG @ Ego4D Step Grounding Challenge: hierarchical activity understanding enables zero-shot step grounding
  414. What changes after deployment? A survey on On-device Learning in TinyML
  415. Comparing LLM-Based Conversational and Graphical Interfaces for Industrial Decision Tasks: An Exploratory Mixed-Methods Study
  416. Shared Doubt: Zero-Shot Cross-Lingual Confidence Estimation for Language Models
  417. Latent Geometric Chords for Query-Efficient Decision-Based Adversarial Attacks
  418. TALON: Token-Aligned Lightweight Adapters for 6-DoF Spacecraft Pose Estimation
  419. Benchmarking and Enhancing Text-to-Image Models for Generating Visual Representations in Early Arithmetic Education
  420. Simulation of collision avoidance behavior in crowd movement by data-driven approach
  421. Beyond Additive Decompositions: Interpretability Through Separability
  422. MAECO-Lite: Modular Ontology for Dynamic Malware Analysis
  423. Geometry-based Schr"odinger Bridges for Trustworthy Multimodal Fusion
  424. Specialist-Generalist Fusion with Outcome-Supervised Rationales for Deepfake Detection
  425. FlagGAM: Rule-Basis Generalized Additive Models for Explainable Tabular Prediction
  426. From Local Geometry to Global Pseudo Labeling for Robust Positive Unlabeled Learning under Covariate Shift
  427. How well does Classification Accuracy capture Concept Drift Detection Quality? An overview of Concept Drift Detection evaluation
  428. On public and private binary classification with metric space valued predictors
  429. Vanilla ViT for Automotive Point Cloud Semantic Segmentation
  430. Towards Efficient LLMs Annealing with Principled Sample Selection
  431. MindVoice: Reconstructing Intelligible Speech from Non-invasive Neural Signals with Pretrained Priors
  432. MIMO: Multilingual Information Retrieval via Monolingual Objectives
  433. LLM-FACETS: A Privacy-Preserving Framework for Evaluating LLM Transparency and Accountability
  434. D3: Dynamic Directional Graph-Constrained Data Scheduling for LLM Training
  435. Memory by Design: Bayesian Layers for Sequence Modeling
  436. TabCausal: Pretraining Across Causal Environments for Tabular Causal Discovery
  437. Learning Hyperspherical Time-Frequency Representations for Time-Series Out-of-Distribution Detection
  438. BIAS-ID: A Framework for Analyzing Transformation Biases in AI-Generated Image Detectors
  439. Approximation and learning of anisotropic and mixed smooth functions by deep ReLU neural networks
  440. Developing a UXR Point of View for Cognitive Accessibility in Mobile Learning with Generative AI
  441. Developing a Culturally Grounded, AI-Augmented UX Research Point of View (POV): An Exemplar Case Study from Telemedicine Dementia Care
  442. From Evidence to Design: Developing an AI-Augmented UX Research Point of View for Digital Wellbeing in Emergency and Public Safety Contexts
  443. FOCUS: Forcing In-Context Object Localization through Visual Support Constraints and Policy Optimization
  444. Extending the UXR Point of View Pyramid: A Generative AI-Augmented Methodology for Human-Centred AI Systems
  445. On the Robustness of Multilingual Text Embedding Rankings Across Learning Tasks, Languages, and Benchmark Datasets
  446. EvoDefense: Co-Evolving Black-Box Defense with Large Language Models
  447. Developing an AI-Powered UX Research Point of View for Digital Health in A Regulatory Context: An Exemplar Case from MSM and Transgender HIV Care in Nigeria
  448. PolSAR Image Classification using a Hybrid Complex-Valued Network (HybridCVNet)
  449. Multilingual and Cross-Lingual Citation Needed Detection on Wikipedia for Lower-Resource Languages
  450. UXR PoV for Neuroinclusive Emotion Regulation
  451. Generalizing Multi-Scale Time-Series Modeling with a Single Operator
  452. Scalable Bayesian Inference for Nonlinear Conservation Laws
  453. QVGGT: Post-Training Quantized Visual Geometry Grounded Transformer
  454. TARIC: Memory-Augmented Traversability-Aware Outdoor VLN under Interrupted Semantic Cues
  455. Polyphony: Diffusion-based Dual-Hand Action Segmentation with Alternating Vision Transformer and Semantic Conditioning
  456. TSM-Bench: Detecting LLM-Generated Text in Real-World Wikipedia Editing Practices
  457. Remembering by Reconstructing: Domain Incremental Learning With Test-Time Training on Video Streams
  458. Model-Agnostic Signal Discovery with Machine Learning: Bridging the Gap Between Theory and Practice
  459. Vector Linking via Cross-Model Local Isometric Consistency
  460. KnowledgeGain: Evaluating and Optimizing Science News Generation for Reader Learning
  461. SpecDB: LLM-Generated Customized Databases via Feature-Oriented Decomposition
  462. Redefining Instance Matching: A Unified Framework for Part-Aware Matching in Panoptic Segmentation Evaluation
  463. Cross-Modal Clinical Knowledge Integration for Mammography Report Generation
  464. On Revisiting Entropy for Identifying Mislabeled Images
  465. On couplings for kinetic Langevin diffusions
  466. Beyond Static Dialogues: Benchmarking Realistic, Heterogeneous, and Evolving Long-Term Memory
  467. Forecasting threshold exceedance of atmospheric variables at a specific location
  468. Learning to Bid in FCR Markets: A Best-of-Both-Worlds Approach
  469. Towards Effective Long-Video Event Prediction via Multi-Level Event Semantics Mining
  470. HQ-JEPA: Hybrid Quantum Joint-Embedding Predictive Architecture for Cross-Modal Remote Sensing Representation Learning
  471. DRIFT: Joint Channel Estimation and Prediction Towards Pilotless 6G Non-Terrestrial Networks
  472. Fighting Numerical Hallucinations via Data-centric Compilation for Online Financial QA
  473. Free energy Estimation on Any State Space
  474. STEP: Learning STructured Embeddings for Progressive Time Series
  475. Combinatorial Synthesis: Scaling Code RLVR via Atomic Decomposition and Recombination
  476. How Much Do LLMs Know About Chinese Zero Pronouns?
  477. AnchorSteer: Self-Discovered Concept Injection for Structure-Preserving Music Editing
  478. Linear Ordering Problem: Time for a Change
  479. Trajectory-Aware Best-Arm Identification for Local Search Allocation in Bayesian Optimization and Beyond
  480. Learning to Solve and Optimize by Evolving Code
  481. Rethinking Efficient Crack Segmentation with Task-Aligned Structural-Directional Modeling
  482. Escaping the Capacity Ceiling: Routing on the Stiefel Manifold for Bilinear SPD Layers
  483. UniRTL: Unifying Code and Graph for Robust RTL Representation Learning
  484. GGT-100K: Generative Ground Truth for Generalizable Real-World Image Restoration
  485. Model Monotonicity in Autobidding Auctions: When Do Better Predictions Lead to Better Outcomes?
  486. Annealed Softmax Greedy in Many-Armed Bayesian Bandits
  487. SlotMemory: Object-Centric KV Memory for Streaming Long-Video Generation
  488. Multi-Scale Separable Fourier Neural Networks for Solving High-Frequency PDEs
  489. TRACE: Discovering Task-Specific Parameter via Adaptation-Aware Probing for Continual Fine-Tuning
  490. HADT: A Heterogeneous Multi-Agent Differential Transformer for Autonomous Earth Observation Satellite Cluster
  491. Augmented Lagrangian Predictive Coding
  492. A Persona-Based Evaluation Framework for Pluralistic Alignment in Generative AI
  493. An Efficient and Scalable Graph Condensation with Structure-Preserving
  494. SDM-Q: Cost-Aware Staged Decision-Making for Multi-Omics Classification with Deep Q-Learning
  495. Physics-Informed Coarsening for Multigrid Graph Neural Surrogates
  496. DEM: A Distilled Explanation Model for Interpretable Anomaly Detection in Physiological Sensor Networks
  497. Learning Multi-Agent Coordination via Sheaf-ADMM
  498. Iterative Framework For Data Augmentation Of Segmented Fingerprints
  499. HetCCL: Enabling Collective Communication For Mixed-Vendor Heterogeneous Clusters
  500. Hedging on the Frontier: Learning New Tasks with Few Samples
  501. Traceable by Design: An LLM Pipeline and Dashboard for EU Regulatory Consultation Analysis
  502. Parallel Tempering Initial Sampling in Inference-Time Reward Alignment
  503. Benchmarking Single-Step Inpainting Methods for Multi-Object 3D Gaussian Splatting Scenes
  504. Can BEV Perception Gracefully Degrade under Sensor Failures?
  505. Cognitive Fatigue in Autoregressive Transformers: Formalization and Measurement
  506. Batched Stochastic Linear Bandits with 1-Bit Communication Constraints
  507. Omni-Supervised Motion Editing: Balancing Change and Invariance through Positive-Negative Learning
  508. Reading Between the Citations: A Typed Claim Network for Scientific Literature
  509. AMix-2: Establishing Protein as a Native Modality in Large Language Models
  510. EvoGens: A Population-Based Heuristic Search Framework for Scientific Idea Generation
  511. Revisiting Zeroth-Order Hessian Approximation: A Single-Step Policy Optimization Lens
  512. Spectral Anatomy of Quantum Gaussian Process Kernels
  513. Inspectable Neural Markov Models for Non-Stationary Time Series
  514. PRISM: Progressive Reasoning through Iterative Slot Memory for Vision
  515. IAF-Net: Illumination-Adaptive Fusion for Low-Light Urban Road Segmentation
  516. Local linear convergence of gradient methods for overparameterized Gaussian mixtures
  517. TUX: Measuring Human--AI Tacit Understanding
  518. MultiAct: Text-to-Motion Generation from Composite Text via Tailored Attention Guidance
  519. Unsupervised Diffusion Solver for Combinatorial Optimization via Combinatorial Adjoint Matching
  520. Inference-Free Multimodal Learned Sparse Retrieval for Production-Scale Visual Document Search
  521. Welfare, Improvability, and Variance: A Principal-Agent Approach to Optimal Benchmark Item Aggregation
  522. Toxic HallucinAItions: Perturbing Prompts and Tracing LLM Circuits
  523. PINNs Failure Modes are Overfitting
  524. A Unifying View of Anchoring via Operator-Side Tikhonov Regularization
  525. Density-Guided Robust Counterfactual Explanations on Tabular Data under Model Multiplicity
  526. A Unified and Reproducible Experimentation Framework for Speech Understanding
  527. SteerFace: Debiasing Synthetic Face Generation via Adaptive Residue Perturbation
  528. Foundation VAEs for 3D CT Reconstruction, Augmentation, and Generation
  529. Bandwidth Allocation with Device Partitioning for Federated Learning over Industrial IoT networks
  530. Generative Quantum Data Embeddings for Supervised Learning
  531. GlucoFM: A Dual-Stream Foundation Model for Continuous Glucose Monitoring
  532. DSD-GS: Dynamic-Static Decomposition of Gaussian Splatting for Efficient and High-Fidelity Dynamic Scene Reconstruction
  533. Bayesian Inference with Shaped Deep Non-linear MLPs
  534. DARTS: Distribution-Aware Active Rollout Trajectory Shaping for Accelerating LLM Reinforcement Learning
  535. MADS: Model-Aware Diverse Core Set Selection for Instruction Tuning
  536. Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation
  537. Count Anything
  538. Fine-Tuning Improves Information Conveyance in Language Models
  539. Cross-Layer Subspace Coupling for LLM Compression: A Unifying Framework and Its Empirical Limits
  540. The Geometry of Activity Cliffs: Representation Dependence and Multi-Scale Characterization of Activity Landscapes
  541. LegSegNet: A Public Deep Learning System for Lower Extremity CT Tissue Segmentation and Quantification
  542. Beyond Agreement: Scoring Panel-Surfaced Biomedical Entity Candidates for Curator Triage
  543. Function2Scene: 3D Indoor Scene Layout from Functional Specifications
  544. GaMi: Geometry-Agnostic Material Identification via Cross-Modal Subtractive Disentanglement
  545. Incremental BPE Tokenization
  546. Learning Permutation-invariant Macroscopic Dynamics
  547. Non-destructive Identification of Oyster Species is possible from Hyperspectral Images with Machine Learning
  548. IRIS: time-structured manifold projections
  549. Conformal Reliability: A New Evaluation Metric for Conditional Generation
  550. Anchoring LLM Gender Bias to Human Baselines: A Cross-Lingual Audit
  551. PReMISE: Policy Rubrics as Measurement Specifications for LLM Judges
  552. OpenSTBench: Beyond Semantic Evaluation for Speech Translation
  553. XLGoBench: Detecting cross-lingual skill gaps with algorithmic tasks
  554. AbstainGNN: Teaching Graph Neural Networks to Abstain for Graph Classification
  555. Text-guided Feature Disentanglement for Cross-modal Gait Recognition
  556. Bayesian Classification with Probit-link Split-and-merge Gaussian Process Prior in EEG-based Brain-Computer Interfaces
  557. DisPlace: Discriminative Place Projections for Multi-Reference Visual Place Recognition
  558. SLAP: The Semantic Least Action Principle for Variational Video-Language Modeling
  559. Chatterbox-Flash: Prior-Calibrated Block Diffusion for Streaming Zero-Shot TTS
  560. Generating Graph-Like Logical Rules for Knowledge Graph Reasoning via Diffusion Models
  561. A Padding Method for Enhanced Encoding of Inorganic Structures with Varying Chemical Compositions
  562. Annotations Are Not All You Need: A Cross-modal Knowledge Transfer Network for Unsupervised Temporal Sentence Grounding
  563. Is the Last Layer Sufficient for Uncertainty Quantification?
  564. GSAM: A Generalizable and Safe Robotic Framework for Articulated Object Manipulation
  565. OrcaRouter: A Production-Oriented LLM Router with Hybrid Offline-Online Learning
  566. Beyond Accuracy: Evaluating Efficiency, Robustness and Explainability in Deep Learning for Malaria Diagnosis
  567. SemStruct: Contextualizing Semantic Embeddings with Structural Information for Schema Matching
  568. Reducing the GPU Memory Bottleneck with Lossless Compression for ML -- Extended
  569. Self-Certifying Transport MCMC via Dual Spectral-Gap Certificates
  570. Kalimati Vegetable Price Index Forecasting with a Momentum Corrected Online Stacking Ensemble
  571. When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?
  572. Moment-Based Inference for Regression with Latent Dirichlet Covariates
  573. Neuron-Level Interventions for Gendered and Gender-Neutral Generation in Language Models
  574. Vision-Based Localization in Dense Urban Environments: A Case Study of an Urban Village in China
  575. Mathematical Morphology in Machine Learning
  576. A Context-Aware Middleware for Medical Image Based Reports: An approach based on image feature extraction and association rules
  577. ConTrans: Learning Text-enhanced Local-global Temporal Representations for Zero-shot Temporal Action Localization
  578. How Early Adopters Used Generative AI Worldwide: Variation by Country Income and Language
  579. Healthcare Mechanisms from Policy-as-Code Search under Strategic Provider Response
  580. Human-Alignment, Calibration, and Activation Patterns in Large Language Model Uncertainty
  581. TeachObs: A Human-Validated Benchmark for Multimodal Teaching Observation and Model Evaluation
  582. WristCompass: Kinematic Coupling as a Learnable Visual Concept for Ego-Camera Orientation
  583. CobSeg: Coherence Boundary Modeling for Dialogue Topic Segmentation