mlsanityData to 14 Oct 2026

Papers

New on arXiv

Thu 28 May 2026

759 papers

  1. TreeGraft: Adaptive Multi-Drafter Grafting for Tree-Based Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  2. RAIL Guard: Closing the Evaluation-to-Remediation Gap in Responsible AI for LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance +1
  3. Specialize Roles, Mix Deployments: Pushing the Cost-Accuracy Frontier of LLM Agent TeamsLLM agents and tool use → General LLM agent frameworks and benchmarks
  4. DC-Motion: Decoupling Structure and Details via Discrete-Continuous Tokens for Human Motion GenerationDiffusion models → Video generation
  5. UNIQ: Conformal Calibration for Adaptive Conservatism in Offline Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  6. ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific ResearchLLM agents and tool use → Web, search, and research agents
  7. The Score Hamiltonian: Mapping Diffusion Models to Adiabatic TransportDiffusion models → Diffusion foundations and sampling
  8. A Multi-AI-agent Framework Enabling End-to-end Finite Element Analysis for Solid Mechanics ProblemsLLM agents and tool use → Multimodal and embodied agents
  9. On Effectiveness and Efficiency of Agentic Tool-calling and RL TrainingLLM agents and tool use → Reinforcement learning for LLM agents
  10. World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and ApplicationsWorld models → World models for language agents
  11. CardioLens: Revealing the Clinical Reality Gap of MLLMs via Multi-Sequence Cardiac MRI EvaluationsMultimodal LLMs / vision-language models → Medical vision-language models
  12. The Tutoring Effectiveness Index: Predicting LLM Math Tutor Quality from Four Conversation SignalsLLM alignment / RLHF / preference optimisation → Process reward models for reasoning
  13. BOKBO (Best of K Bad Options): Calibrated Abstention for VLA PoliciesLLM reasoning → Reinforcement learning for reasoning +1
  14. Learning to Perceive the World Through Control: Empowerment-Based Representation LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  15. Counterfactual Graph for Multi-Agent LLM CalibrationLLM agents and tool use → General LLM agent frameworks and benchmarks
  16. LARK: Learnability-Grounded Trajectory Selection for Efficient Reasoning DistillationLLM reasoning → Prompting and chain-of-thought reasoning +1
  17. Convergence of Steepest Descent and Adam under Non-Uniform SmoothnessDeep reinforcement learning methods → RL theory and sample complexity
  18. Diffusion Models Preferentially Memorize Prototypical Examples or: Why Does My Diffusion Model Love Slop?Diffusion models → Diffusion foundations and sampling
  19. COFT: Counterfactual-Conformal Decoding for Fair Chain-of-Thought Reasoning in Large Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  20. Rationalize: Shared Semantic Reasoning for Human-AI AlignmentLLM reasoning → Reasoning benchmarks and evaluation
  21. Controllable Lung Nodule Synthesis via Histogram-Regularized Latent Diffusion ModelsDiffusion models → Medical imaging and segmentation
  22. Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM AgentsLLM agents and tool use → Software engineering coding agents +1
  23. Reward Learning from Best-of-N Preference Data: Targets, Tradeoffs, and Design PrinciplesLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  24. Audio Pirates: Black-box Audio Watermark Removal via Diffusion PriorsLLM safety and security → Watermarking generated content and models
  25. ZAPS-DA: Zero-Phase Action Policy Smoothing with Decoupled Actor for Continuous Control in Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  26. An Organization-Scoped LLM Agent Runtime Architecture for Regulated Cybersecurity OperationsLLM agents and tool use → Agent threats, guardrails and governance
  27. AMNESIA: A Large Scale Medical Unlearning Benchmark Suite with Disease-Informed AnalysisLLM safety and security → Machine unlearning
  28. ReGuLaR: Relation-Grounded Latent Reasoning for Large Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  29. Speculative Decoding and the Curse of MultilingualityEfficient LLM inference and serving → Speculative decoding
  30. Uncertainty-Aware and Temporally Regulated Expert Advice in Reinforcement Learning for Autonomous DrivingEnd-to-end autonomous driving → Reinforcement learning for driving +1
  31. Probing the Prompt KV Cache: Where It Becomes DispensableEfficient LLM inference and serving → KV cache optimization
  32. Memory-Bound but Not Bandwidth-Limited: The Physical AI Inference Gap in Batch-1 LLM DecodeEfficient LLM inference and serving → Serving systems and request scheduling
  33. VLM3: Vision Language Models Are Native 3D LearnersMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  34. Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?LLM reasoning → Spatial and embodied reasoning +1
  35. Destruction is a General Strategy to Learn Generation; Diffusion's Strength is to Take it Seriously; Exploration is the FutureDiffusion models → Diffusion and flow policies for robotics
  36. Physically Viable World Models: A Case for Query-Conditioned Embodied AIWorld models → World models for navigation
  37. A Theory-Guided LLM Pedagogical Agent for STEM+C Scaffolding Without Over-RelianceLLM agents and tool use → Educational agents and math problem solving
  38. DisasterLex: An Expert Concept-to-Schema Knowledge Graph for Geospatial Reasoning in Disaster AnalyticsLLM reasoning → Spatial and embodied reasoning
  39. Strengthening Polymorphic Prompt Assembling: Dynamic Separator Generation Against Emerging Prompt Injection AttacksLLM agents and tool use → Agent threats, guardrails and governance +1
  40. Measuring, Localizing, and Ablating Alignment Signatures in LLMsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  41. OmniMem: Scalable and Adaptive Memory Retrieval for Long Video GenerationEfficient LLM inference and serving → Fast autoregressive visual generation
  42. MAAT: Multi-phase Adapter-Aware Targeted UnlearningLLM safety and security → Machine unlearning
  43. VLM-GLoc: Vision-Language Model Enhanced Monte Carlo Localization for Robust Semantic Global Localization in Cluttered Quasi-Static EnvironmentsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  44. Physics-informed Goal-Conditioned Reinforcement Learning under Hybrid Contact DynamicsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  45. Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMsLLM safety and security → Watermarking generated content and models
  46. CanLegalRAGBench: Evaluating Retrieval-Augmented Generation on Canadian Case LawRetrieval-augmented generation → Legal and financial RAG
  47. Configurable Reward Model for Balanced Safety AlignmentLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks
  48. Graph-Conditioned Mixture of Graph Neural Network Experts for Traffic ForecastingMixture-of-experts → MoE for time series and graphs
  49. ELAN4D: Embodiment-Centric 4D Supervision for Vision-Language-Action Models via Plug-and-Play AdaptationVision-language-action models → 3D and spatial-aware VLA
  50. Discovering a Zeta Map Algorithm on Dyck Paths via Mechanistic InterpretabilityMechanistic interpretability → Circuits and mechanistic analysis
  51. idSCD: Identifying Training Datasets through Semantic Correlation DescriptorsLLM safety and security → Machine unlearning
  52. The Surface You Test Is Not the Surface That BreaksLLM agents and tool use → Agent threats, guardrails and governance
  53. VeriGate: Verifier-Gated Step-Level Supervision for GRPOLLM reasoning → Reinforcement learning for reasoning
  54. Bounded Behavioral Indistinguishability for Black-Box LLM DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  55. LongDS-Bench: On the Failure of Long-Horizon Agentic Data AnalysisLLM agents and tool use → Web, search, and research agents
  56. DTG-Restore: Training-Free Diffusion Refinement for Generative Video Super-ResolutionDiffusion models → Inverse problems and image restoration
  57. Domain Adaptation and Reasoning Frameworks in Language Models: A Controlled Experiment with Historical CosmologyLLM reasoning → Reasoning benchmarks and evaluation
  58. SANA-Streaming: Real-time Streaming Video Editing with Hybrid Diffusion TransformerDiffusion models → Video generation
  59. Exploring Autonomous Agentic Data Engineering for Model SpecializationLLM agents and tool use → Web, search, and research agents
  60. Social Reasoning in Machines: Investigating Collective Truth-Seeking Dynamics in Large Language Model DebateLLM reasoning → Reasoning for agents, planning and code
  61. Functional MRI Time Series Generation via Wavelet-Based Image Transform and Spectral Flow Matching for Brain Disorder IdentificationDiffusion models → Medical imaging and segmentation
  62. Linear Separability of Activation Representations after Supervised Fine-Tuning on Incorrect Responses: A Study of Synthetic Dishonesty in Large Language ModelsMechanistic interpretability → Probing deception, bias and beliefs
  63. VideoMLA: Low-Rank Latent KV Cache for Minute-Scale Autoregressive Video DiffusionDiffusion models → Video generation +1
  64. AdaState: Self-Evolving Anchors for Streaming Video GenerationDiffusion models → Video generation
  65. YoCausal: How Far is Video Generation from World Model? A Causality PerspectiveWorld models → Video-generation world models and simulators +1
  66. Tiny but Trusted: Efficient Vision-Language Reasoning for Time-Series Anomaly DetectionLLM reasoning → Chain-of-thought reasoning for driving +1
  67. Unlocking the Working Memory of Large Language Models for Latent ReasoningLLM reasoning → Test-time compute and efficient thinking
  68. Locally Coherent, Globally Incoherent: Bounding Compositional Incoherence in Multi-Component LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  69. Colored Noise Diffusion SamplingDiffusion models → Diffusion foundations and sampling
  70. When, why, and how do diffusion posterior samplers fail? A finite-sample lensDiffusion models → Inverse problems and image restoration
  71. SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?LLM agents and tool use → Web, search, and research agents
  72. Reasoning with Sampling: Cutting at Decision PointsLLM reasoning → Test-time compute and efficient thinking
  73. Veda: Scalable Video Diffusion via Distilled Sparse AttentionDiffusion models → Video generation
  74. In-Context Reward Adaptation for Robust Preference ModelingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  75. Gram: Assessing sabotage propensities via automated alignment auditingLLM agents and tool use → Agent threats, guardrails and governance
  76. SpecBench: Evaluating Specification-Level Reasoning for Software Engineering LLM AgentsLLM reasoning → Reasoning for agents, planning and code +1
  77. Grounded 3D-Aware Spatial Vision-Language ModelingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  78. MedCase-Structured: A Text-to-FHIR Dataset for Benchmarking Diagnostic Reasoning in Clinically Realistic EHR SettingsLLM reasoning → Clinical and biomedical applications
  79. Self-Trained Verification for Training- and Test-Time Self-ImprovementLLM reasoning → Test-time compute and efficient thinking
  80. Gaze2Act: Gaze-Conditioned Vision-Language-Action Policies for Interactive Robot ManipulationVision-language-action models → Failure recovery and robustness
  81. Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot EmbodimentsVision-language-action models → Human-video and latent-action pretraining
  82. Loong: A Human-Like Long Document Translation Agent with Observe-and-Act Adaptive Context SelectionLLM agents and tool use → General LLM agent frameworks and benchmarks
  83. LLUMI: Improving LLM Writing Assistance for Mental Health Support with Online Community FeedbackLLM alignment / RLHF / preference optimisation → Medical LLM alignment
  84. LoMo: Local Modality Substitution for Deeper Vision-Language FusionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  85. minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World ModelsWorld models → Video-generation world models and simulators +1
  86. Stable-Layers: Fine-Tuning Image Layer Decomposition Models with VLM-Scored Reinforcement LearningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  87. Same Evidence, Different Answers: Canonical-Context On-Policy Distillation for Multi-Turn Language ModelsKnowledge distillation → On-policy and self-distillation for LLMs
  88. GenClaw: Code-Driven Agentic Image GenerationLLM agents and tool use → Multimodal and embodied agents
  89. Knowing What to Solve Before How: Preplan Empowered LLM Mathematical ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  90. Reinforcement Learning with Robust Rubric RewardsLLM reasoning → Reinforcement learning for reasoning +1
  91. Beyond 3D VQAs: Injecting 3D Spatial Priors into Vision-Language Models for Enhanced Geometric ReasoningLLM reasoning → Spatial and embodied reasoning +1
  92. IP-Adapter Is All You Need: Towards Fine-Tuning-Free Diffusion-Based Talking Face GenerationDiffusion models → Audio, speech and music
  93. Unifying Temporal and Structural Credit Assignment in LLM-Based Multi-Agent Prompt OptimizationLLM reasoning → Reasoning for agents, planning and code +1
  94. BORA: Bridging Offline Reinforcement Learning and Online Residual Adaptation for Real-World Dexterous VLA ModelsVision-language-action models → Reinforcement learning and post-training +1
  95. TriSearch: Learning to Optimize Triangulations via Bistellar FlipsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  96. GRUFF: LLM Pronoun Fidelity, Reasoning, and Biases in GermanLLM reasoning → Reasoning benchmarks and evaluation
  97. Persona Conditioning of Brand Recommendations in Retrieval-Augmented Commercial Chat: A Prominence-Stratified Cross-Provider AuditRetrieval-augmented generation → RAG pipeline design and evaluation
  98. A Bayesian Approach to Membership Inference for Statistical ReleaseLLM safety and security → Membership inference attacks
  99. Mean-Field Diffuser: Scaling Offline MARL to Thousands of AgentsOffline RL and imitation learning from data → Diffusion and flow policies for offline RL
  100. Token-Level Generalization in LoRA Adapter Backdoors: Attack Characterization and Behavioral DetectionLLM safety and security → Backdoor and data poisoning attacks
All 759
  1. LiveSVG: Zero-Shot SVG Animation via Video GenerationDiffusion models → Video generation
  2. Unveiling the Visual Counting Bottleneck in Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  3. Dissociative Identity: Language Model Agents Lack Grounding for Reputation MechanismsLLM agents and tool use → Social simulation and multi-agent debate
  4. BioRefusalAudit: Auditing Biosecurity Refusal Depth Using General and Domain-Fine-Tuned Sparse AutoencodersMechanistic interpretability → Steering and probing for LLM safety
  5. Why Far Looks Up: Probing Spatial Representation in Vision-Language ModelsLLM reasoning → Spatial and embodied reasoning +1
  6. On Distributional Reinforcement Learning in Chaotic Dynamical SystemsDeep reinforcement learning methods → RL theory and sample complexity
  7. Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM AgentsLLM agents and tool use → Agent memory systems
  8. RL2ML: Finite-Rollout Surrogate Objectives from Reinforcement Learning to Maximum LikelihoodDeep reinforcement learning methods → RL training of language and agent models
  9. Diffusion Models Are Statistically Optimal for Learning Low-Dimensional Multi-Modal DistributionsDiffusion models → Diffusion foundations and sampling
  10. Do Proactive Agents Really Need an LLM to Decide When to Wake and What to Anchor?LLM agents and tool use → General LLM agent frameworks and benchmarks
  11. AgentSchool: An LLM-Powered Multi-Agent Simulation for EducationLLM agents and tool use → Educational agents and math problem solving
  12. AnomalyAgent: Training-Free Agentic Models for Zero-/Few-Shot Anomaly DetectionMultimodal LLMs / vision-language models → Chart understanding and anomaly detection +1
  13. Enhancing Multi-Agent Communication through Attention Steering with Context RelevanceLLM agents and tool use → General LLM agent frameworks and benchmarks
  14. PARCEL: Pool-Anchored Resampling with Conditioned Elastic Queries for Efficient Vision-Language UnderstandingMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  15. VLA-Trace: Diagnosing Vision-Language-Action Models through Representation and Behavior TracingVision-language-action models → VLA architectures and generalization
  16. SGMD: Score Gradient Matching Distillation for Few-Step Video Diffusion DistillationDiffusion models → Diffusion foundations and sampling
  17. xModel-KD: Cross-modal Knowledge Distillation for 3D Scene Perception using LiDARKnowledge distillation → Detection and dense prediction distillation
  18. EvoRepair: Enhancing Vulnerability Repair Agents Through Experience-Based Self-EvolutionLLM agents and tool use → Agent threats, guardrails and governance
  19. When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  20. Chess-World-Model: A 10M-Game Benchmark for Exact State Tracking from Chess Move SequencesWorld models → World models for language agents
  21. Geometry Matters: 3D Foundation Priors for Learning Semantic CorrespondenceDiffusion models → 3D, point cloud and scene generation
  22. DirectorBench: Diagnosing Long-Form Video Generation with Personalized Multi-Agent EvaluationLLM agents and tool use → Multimodal and embodied agents
  23. Conformal Certification of Reasoning Trace PrefixesLLM reasoning → Test-time compute and efficient thinking
  24. Future Forcing: Future-aware Training-free KV Cache Policy for Autoregressive Video GenerationEfficient LLM inference and serving → Fast autoregressive visual generation
  25. UniSteer: Text-Guided Flow Matching in Activation Space for Versatile LLM SteeringDiffusion models → Discrete and text diffusion
  26. A Predictive Law for On-Policy Self-Distillation From World FeedbackKnowledge distillation → On-policy and self-distillation for LLMs
  27. HEART-Bench: Do LLM Agents Exhibit Human-like Psychology?LLM agents and tool use → Social simulation and multi-agent debate
  28. Sample-Efficient Diffusion-based Reinforcement Learning with Critic GuidanceDiffusion models → Diffusion and flow policies for robotics +1
  29. REPOT: Recoverable Program-of-Thought via Checkpoint RepairLLM reasoning → Reasoning for agents, planning and code
  30. Robust and Generalizable Safety Steering for Text-to-Image Diffusion TransformersDiffusion models → Robustness, privacy and adversarial aspects
  31. Masked Diffusion Modeling for Anomaly DetectionDiffusion models → Flow matching, time series and science
  32. Learning to Choose: An Empowerment-Guided Multi-Agent System with semantic communication for Adaptive Method SelectionLLM agents and tool use → General LLM agent frameworks and benchmarks
  33. Domain-Specific Data Synthesis for LLMs via Minimal Sufficient Representation LearningSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  34. Alignment-Guided Score Matching for Text-to-Image Alignment in Diffusion ModelsDiffusion models → Image generation, text-to-image and editing +1
  35. Audio Jailbreaks in Large Audio-Language Models: Taxonomy, Attack-Defense Analysis, and Cost-Aware EvaluationLLM safety and security → Audio jailbreaks and speech backdoors
  36. RAISE: RAG Design as an Architecture Search ProblemRetrieval-augmented generation → RAG pipeline design and evaluation +1
  37. Recovering Diversity Without Losing Alignment: A DPO Recipe for Post-Trained LLMsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  38. VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action PoliciesVision-language-action models → Reasoning and chain-of-thought in VLA
  39. EarlyTom: Early Token Compression Completes Fast Video UnderstandingEfficient LLM inference and serving → Visual token pruning in multimodal models
  40. KairosAgent: Agentic Time Series Forecasting with Fused Semantic ReasoningLLM reasoning → Time series reasoning +1
  41. Adapting Multilingual Embedding Models to Turkish via Cross-Lingual Tokenizer Surgery and Offline DistillationRetrieval-augmented generation → Generation and context integration
  42. EVL-ECG: Efficient ECG Interpretation With Multi-Aspect Heterogeneous Knowledge DistillationKnowledge distillation → Distillation for medical imaging
  43. Causal Interventions on Continuous Variables: A Case Study on Verb Bias in Steering Vectors for In-Context LearningMechanistic interpretability → Activation steering methods
  44. Hijacking Agent Memory: Stealthy Trojan Attacks Through Conversational InteractionLLM agents and tool use → Agent threats, guardrails and governance +1
  45. Uncertainty Quantification for Multimodal Retrieval Augmented GenerationMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
  46. MuPHI: Learning Implicit Multimodal Harm Reasoning via Semantically Grounded Reward OptimizationLLM reasoning → Reasoning for agents, planning and code
  47. Fisher-Preserving Guidance: Training-Free Manifold Constraints for Safe Diffusion ControlDiffusion models → Diffusion and flow policies for robotics
  48. Toward AI That Understands Self and Others: A World-Model Theory of Cognitive Diversity and AlignmentWorld models → World models for language agents
  49. Does The Way You Plan Matter? An Empirical Study of Planning Representations for LLM Web AgentsLLM agents and tool use → Web, search, and research agents
  50. Midpoint Generative ModelsDiffusion models → Flow matching, time series and science
  51. Agora: Toward Autonomous Bug Detection in Production-Level Consensus Protocols with LLM AgentsLLM agents and tool use → Software engineering coding agents
  52. Dissecting the Black Box: Circuit-Level Analysis of LLM Vulnerability DetectionMechanistic interpretability → Steering and probing for LLM safety
  53. Train the Agent, Not the Expert: Learning to Harness Heterogeneous Experts for Multi-Turn Visual ReasoningLLM reasoning → Multimodal reasoning
  54. Redundant or Necessary? A Benchmark for Detecting Redundant Steps in Agent TrajectoriesLLM agents and tool use → Software engineering coding agents
  55. LaRA: Layer-wise Representation Analysis for Detecting Data Contamination in RL Post-TrainingLLM reasoning → Reinforcement learning for reasoning
  56. CRITIC-R1: Learning Structured Critics for Retrieval-Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  57. Mitigating Hallucination in Vision-Language Models through Barrier-Regulated Adaptive Closed-form SteeringMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  58. Evolutionary Dynamics of Cooperation in Next-Generation LLM Agent Systems: A Cross-Provider Empirical ExtensionLLM agents and tool use → Social simulation and multi-agent debate
  59. Moment-KV: Momentum-Based Decode-Time KV Cache Compression for Long GenerationEfficient LLM inference and serving → KV cache optimization
  60. Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report GenerationLLM agents and tool use → Web, search, and research agents
  61. ESPO: Early-Stopping Proximal Policy OptimizationLLM reasoning → Reinforcement learning for reasoning +1
  62. Masked Diffusion Vision-Language Models for Temporal Action LocalizationMultimodal LLMs / vision-language models → Video understanding with MLLMs +1
  63. EvoRubric: Self-Evolving Rubric-Driven RL for Open-Ended GenerationSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
  64. OmniMatBench: A Human-Calibrated Multimodal Reasoning Benchmark Across 19 Materials Science SubfieldsLLM reasoning → Clinical and biomedical applications
  65. Towards Localized and Disentangled Knowledge Editing for Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Image editing and quality assessment
  66. Cert-LAS: Toward Certified Model Ownership Verification for Text-to-Image Diffusion Models via Layer-Adaptive SmoothingDiffusion models → Robustness, privacy and adversarial aspects +1
  67. AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and SecurityLLM agents and tool use → Agent threats, guardrails and governance +1
  68. SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic SearchLLM agents and tool use → Web, search, and research agents
  69. SkillsInjector: Dynamic Skill Context Construction for LLM AgentsLLM agents and tool use → Agent skill learning and evolution
  70. Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  71. Improving CLIP Adaptation by Breaking Tail Alignment for Source-Free Cross-Domain Few-Shot LearningMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  72. MARS Policy: Multimodality Only When It MattersOffline RL and imitation learning from data → Robot manipulation imitation learning
  73. Why Specialist Models Still Matter: A Heterogeneous Multi-Agent Paradigm for Medical Artificial IntelligenceLLM agents and tool use → Medical and scientific domain agents
  74. Multi-Legal-Bench: Evaluating LLMs on Legal Reasoning Across Jurisdictions, Languages, and Legal TraditionsLLM reasoning → Reasoning for agents, planning and code
  75. Bastion: Budget-Aware Speculative Decoding with Tree-structured Block Diffusion DraftingEfficient LLM inference and serving → Speculative decoding
  76. SLAD : Shared LoRA Adapters for Task Specific DistillationKnowledge distillation → General knowledge distillation methods
  77. User-Aware Active Knowledge Acquisition for Emotional Support DialogueLLM reasoning → Audio-language model reasoning
  78. Leveraging Routing Dynamics in Mixture-of-Experts Models for Efficient Language AdaptationMixture-of-experts → Expert routing strategies
  79. Teaching Language Models to Check Grounded Claim Factuality with Human Test-Taking StrategiesRetrieval-augmented generation → RAG robustness and adaptive retrieval
  80. PhAIL: A Real-Robot VLA Benchmark and Distributional MethodologyVision-language-action models → Failure recovery and robustness
  81. RASET: Router-Agnostic Safety-Critical Expert Tuning Exposes Localized Safety Enforcement Failures in Mixture-of-Experts LLMsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +2
  82. Domino: Decoupling Causal Modeling from Autoregressive Drafting in Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  83. Beyond Trajectory Rewards: Step-level Credit Assignment for Agentic Search via Graph ModelingLLM agents and tool use → Reinforcement learning for LLM agents
  84. Reliable Reasoning with Large Language Models via Preference-Based Maximum SatisfiabilityLLM reasoning → Reasoning benchmarks and evaluation
  85. A Unified Two-Stage Generative Diffusion Framework for Channel Estimation and Port Selection in Multiuser MIMO-FASDiffusion models → Diffusion for compression and wireless
  86. Notation Matters: A Benchmark Study of Token-Optimized Formats in Agentic AI SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  87. GRASP: Gated Regression-Aware Skill Proposer for Self-Improving LLM AgentsLLM agents and tool use → Agent skill learning and evolution +1
  88. Beyond English and Evasion: A Human-Annotated Multi-Domain Benchmark for High-Stakes LLM Safety Evaluation in ChineseLLM safety and security → Safety alignment, refusal and guardrails
  89. SAFE-Pruner: Semantic Attention-Guided Future-Aware Token Pruning for Efficient Vision-Language-Action ManipulationVision-language-action models → Efficient VLA inference and adaptation +1
  90. Opir: Efficient Multi-Task Safety Classification for Toxicity, Jailbreaks, Hate Speech, and Harmful ContentLLM safety and security → Safety alignment, refusal and guardrails
  91. OccamToken: Efficient VLM Inference with Training-Free and Budget-Adaptive Token PruningMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  92. TRACE: Toulmin-based Reasoning Assessment through Constructive Elements for LLM CoT EvaluationLLM reasoning → Prompting and chain-of-thought reasoning
  93. SuperVoxelGPT: Adaptive and Ordered 3D Tokenization for Autoregressive Shape GenerationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  94. PTCG-Bench: Can LLM Agents Master Pok'emon Trading Card Game?LLM agents and tool use → Reinforcement learning for LLM agents
  95. Think Fast, Talk Smart: Partitioning Deterministic and Neural Computation for Structured Health Text GenerationLLM reasoning → Clinical and biomedical applications
  96. Beyond Math and Code: Lightweight Corpus-Grounded Process Rewards for Factual Question AnsweringDeep reinforcement learning methods → RL training of language and agent models
  97. AgentCVR: Active Multi-Agent Cross-Video Reasoning via Script-Simulated Reinforcement LearningLLM reasoning → Multimodal reasoning +1
  98. Matching Rates and Optimal Allocation for Federated Probe-Logit Distillation under Heterogeneous Bandwidth BudgetsKnowledge distillation → Federated, robust and private distillation
  99. Beyond Attack Success Rate: Temporal Logit Observability for LLM Safety FailuresLLM safety and security → Jailbreaking
  100. DLM-SWAI: Steering Diffusion Language Models Before They UnmaskDiffusion models → Discrete and text diffusion
  101. Improving Collaborative Storytelling with a Multi-Agent Framework Based on Large Language ModelsLLM agents and tool use → Multimodal and embodied agents
  102. DiffSpot: Can VLMs Spot Fine-Grained Visual Differences in Web Interfaces?Multimodal LLMs / vision-language models → Chart understanding and anomaly detection
  103. CONCAT: Consensus- and Confidence-Driven Ad Hoc Teaming for Efficient LLM-Based Multi-Agent SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  104. Cluster-Level Attention-Guided Parallel Decoding for Masked Diffusion Language ModelsDiffusion models → Discrete and text diffusion +1
  105. HiKEY: Hierarchical Multimodal Retrieval for Open-Domain Document Question AnsweringRetrieval-augmented generation → Multimodal RAG
  106. VLAConf: Calibrated Task-Success Confidence for Vision-Language-Action ModelsVision-language-action models → Failure recovery and robustness +1
  107. CogniVerse: Revolutionizing Multi-Modal Retrieval-Augmented Generation with Cognitive Reflection and Geometric ReasoningLLM reasoning → Knowledge- and tool-augmented reasoning +2
  108. Mind-Omni: A Unified Multi-Task Framework for Brain-Vision-Language Modeling via Discrete DiffusionMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning +1
  109. World Models in Words: Auditing Physical State-Transition Commitments in Vision-Language ModelsWorld models → World models for language agents +1
  110. GAPD: Gold-Action Policy Distillation for Agentic Reinforcement Learning in Knowledge Base Question AnsweringLLM agents and tool use → Web, search, and research agents +1
  111. PEARL: Training Socratic Tutors with Pedagogically Aligned Reinforcement LearningLLM alignment / RLHF / preference optimisation → Process reward models for reasoning +1
  112. ReactBench: A Cause-Driven Benchmark for Multimodal Hallucination via Systematic EvaluationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  113. Mitigating State Aliasing in Vision-Language-Action Models via Inverse Dynamics LearningMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  114. LoRA-Key: User-Centric LoRA Watermarking for Text-to-Image Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  115. DeepTool: Scaling Interleaved Deliberation in Tool-Integrated Reasoning via Process-Supervised Reinforcement LearningLLM reasoning → Reasoning for agents, planning and code +1
  116. VE2VF: Vision-Enabled to Vision-Free Distillation via Real-world Reinforcement Learning for Robust Contact-Rich ManipulationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  117. VLA-Pro: Cross-Task Procedural Memory Transfer for Vision-Language-Action ModelsVision-language-action models → Reasoning and chain-of-thought in VLA
  118. ParaTool: Shifting Tool Representations from Context to ParametersLLM agents and tool use → Tool learning and function calling
  119. Battery-Sim-Agent: Leveraging LLM-Agent for Inverse Battery Parameter EstimationLLM agents and tool use → Medical and scientific domain agents
  120. GiPL: Generative augmented iterative Pseudo-Labeling for Cross-Domain Few-Shot Object DetectionMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  121. AsymVLM: Asymmetric Token Pruning for Efficient Vision-Language Model InferenceMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  122. UI-KOBE: Knowledge-Oriented Behavior Exploration for Lightweight Graph-Guided GUI AgentsLLM agents and tool use → GUI and mobile agents
  123. GUITestScape: Towards Open-set Evaluation on Exploratory GUI TestingLLM agents and tool use → GUI and mobile agents
  124. K-FinHallu: A Hallucination Detection Benchmark for Multi-Turn RAG in Korean FinanceRetrieval-augmented generation → Hallucination detection in RAG
  125. MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMsLLM reasoning → Reasoning for agents, planning and code +1
  126. KGEdit: Ambiguity-Aware Knowledge Graphs for Training-Free Precise Video Generation and EditingDiffusion models → Video generation
  127. On Asymmetric Optimization of Reasoning and Perception in Vision-Language Model Post-TrainingLLM reasoning → Multimodal reasoning +1
  128. On-Policy Replay for Continual Supervised Fine-TuningKnowledge distillation → On-policy and self-distillation for LLMs
  129. The Curse of Helpfulness: Inverse Scaling Law in Robustness to Distractor Instructions via DistractionIFRetrieval-augmented generation → Agentic RAG, agents and memory +1
  130. V2VCrafter: Consistent Street-View Image Generation Across VehiclesDiffusion models → Diffusion and flow policies for robotics
  131. Benchmarking Large Vision-Language Models on CFMME: A Comprehensive Chinese Financial Multimodal Evaluation DatasetMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  132. Adaptive Interviewing for Persona Simulation in LLMs: Evidence-Grounded Reasoning Improves Decision AlignmentLLM reasoning → Reasoning benchmarks and evaluation
  133. A Full-Pipeline Framework for Evaluating Membership Inference Attacks in Machine LearningLLM safety and security → Membership inference attacks
  134. Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI AgentsLLM agents and tool use → GUI and mobile agents
  135. How Coding Agents Fail Their Users: A Large-Scale Analysis of Developer-Agent Misalignment in 20,574 Real-World SessionsLLM agents and tool use → Software engineering coding agents
  136. SkillBrew: Multi-Objective Curation of Skill Banks for LLM AgentsRetrieval-augmented generation → Agentic RAG, agents and memory +1
  137. ElegantVLA: Learning When to Think for Efficient Vision-Language-Action ModelsLLM reasoning → Spatial and embodied reasoning +1
  138. AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text ParaphrasingLLM safety and security → Watermarking generated content and models
  139. Towards Human-Like Interactive Speech Recognition With Agentic Correction and Semantic EvaluationLLM agents and tool use → General LLM agent frameworks and benchmarks
  140. ReasonLight: A Multimodal Foundation Model-Enhanced Reinforcement Learning Framework for Zero-Shot Traffic Signal ControlDeep reinforcement learning methods → RL for autonomous driving and traffic
  141. 3DVLA: Enhancing Vision-Language-Action Models via 3D Spatial and Instance UnderstandingVision-language-action models → 3D and spatial-aware VLA
  142. Phase-Conditioned Imitation Learning with Autonomous Failure Recovery for Robust Deformable Object ManipulationOffline RL and imitation learning from data → Robot manipulation imitation learning
  143. Information-Directed Offline-to-Online Reinforcement LearningOffline RL and imitation learning from data → Offline RL algorithms
  144. Semantic and Visual Evidence for Efficient Long-Video Reasoning: A Solution for the HD-EPIC VQA ChallengeLLM reasoning → Multimodal reasoning +1
  145. Rethinking Post-Training Recipes for Multimodal Time-Series ForecastingLLM reasoning → Time series reasoning
  146. GDSD: Reinforcement Learning as Guided Denoiser Self-Distillation for Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  147. Revisiting Observation Reduction for Web Agents: Comprehensive Evaluation with a Lightweight FrameworkLLM agents and tool use → Web, search, and research agents
  148. Aligned but Fragile: Enhancing LLM Safety Robustness via Zeroth-Order OptimizationLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  149. EvoMD-LLM: Learning the Language of Species Evolution in Reactive Molecular DynamicsLLM reasoning → Clinical and biomedical applications
  150. SURGENT: A Surgical Multi-Agent Assistance System Across the Perioperative WorkflowLLM agents and tool use → Medical and scientific domain agents
  151. MiraBench: Evaluating Action-Conditioned Reliability in Robotic World ModelsWorld models → Embodied and robot world models
  152. Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 SonnetMechanistic interpretability → SAE features and their applications
  153. Harmless Yet Harmful: Neutral Prompting Attacks for Stealthy Hallucination Steering in Agent SkillsLLM agents and tool use → Agent threats, guardrails and governance
  154. ConMoE: Expert-Pool Consolidation via Prototype Reassignment for MoE CompressionMixture-of-experts → MoE large language models
  155. Draft-OPD: On-Policy Distillation for Speculative Draft ModelsEfficient LLM inference and serving → Speculative decoding +1
  156. WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World InteractionMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  157. DMC-CF: Dynamic Multimodal CounterFactual QA benchmark for Causal ReasoningLLM reasoning → Multimodal reasoning +1
  158. Reasoning-preserved Efficient Distillation of Large Language Models via Activation-aware InitializationLLM reasoning → Test-time compute and efficient thinking
  159. STAMP: Training Explicit Memory for Mobile GUI Agents in Controllable and Scalable Virtual EnvironmentsLLM agents and tool use → GUI and mobile agents
  160. Rethinking Stepwise Model Routing: A Cost-Efficient Table Reasoning PerspectiveLLM reasoning → Test-time compute and efficient thinking
  161. PatchBoard: Schema-Grounded State Mutation for Reliable and Auditable LLM Multi-Agent CollaborationLLM agents and tool use → Software engineering coding agents
  162. Rubric-Guided Process Reward for Stepwise Model RoutingLLM reasoning → Reinforcement learning for reasoning +1
  163. GrepSeek: Training Search Agents for Direct Corpus InteractionLLM agents and tool use → Web, search, and research agents
  164. Pocket-Dentist: On-Device Dental Image Understanding via Efficient Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  165. LLM-ALSO: LLM-Driven Adaptive Learning-Signal Optimization for Multi-Agent Reinforcement LearningLLM agents and tool use → Reinforcement learning for LLM agents
  166. Diagnosing Harmful Continuation in Answer-Correct Long-CoT Training TracesLLM reasoning → Test-time compute and efficient thinking
  167. LoopFM: Learning frOm HistOrical RePresentations of Foundation Model for RecommendationKnowledge distillation → Distillation for recommender systems
  168. Code-QA-Bench: Separating Code Reasoning from Documentation Memorization in Repository-Level QALLM reasoning → Reasoning for agents, planning and code
  169. Prompt-Level Reward Specifications for Open-Ended Post-TrainingLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification
  170. CoHyDE: Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool RetrievalLLM agents and tool use → Tool learning and function calling
  171. Indexing the Unreadable: LLM-Native Recursive Construction and Search of Service TaxonomiesLLM agents and tool use → General LLM agent frameworks and benchmarks
  172. Compute Allocation for Self-Evolving LLMs: From Depth-Breadth to Multi-Armed BanditsSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
  173. Harmonizing Real-Time Constraints and Long-Horizon Reasoning: An Asynchronous Agentic Framework for Dynamic SchedulingLLM reasoning → Reasoning for agents, planning and code +1
  174. DynSess: Dynamic Session-Level Evaluation and Optimization Framework for Role-Playing AgentsLLM agents and tool use → Social simulation and multi-agent debate
  175. Provably Secure Agent GuardrailLLM agents and tool use → Agent threats, guardrails and governance +1
  176. DenseSteer: Steering Small Language Models towards Dense Math ReasoningLLM reasoning → Mathematical reasoning
  177. Implicit Identity Technologies for LLMs: Fingerprinting and Watermarking across Datasets, Models, and Generated ContentLLM safety and security → Watermarking generated content and models
  178. Evolving Skill-Structured Attack Memory Enhances LLM JailbreakingLLM safety and security → Jailbreaking
  179. Rethinking Literature Search Evaluation: Deep Research Helps, and Human Citation Lists Are Not a Ground TruthLLM reasoning → Knowledge- and tool-augmented reasoning
  180. BlockBatch: Multi-Scale Consensus Decoding for Efficient Diffusion Language Model InferenceDiffusion models → Discrete and text diffusion +1
  181. Tailoring the Curriculum: Student-Centered Reasoning Distillation via Dynamic Data-Model CompatibilityLLM reasoning → Prompting and chain-of-thought reasoning +1
  182. BenchTrace: A Benchmark for Testing Reflection Ability and Controlled Evolution in LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  183. Relevance as a Vulnerability: How Web Retrieval Degrades Safety Alignment in LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance +2
  184. GTA: Generating Long-Horizon Tasks for Web Agents at ScaleLLM agents and tool use → Web, search, and research agents
  185. Auditing Training Data in Generative Music Models via Black-Box Membership InferenceLLM safety and security → Membership inference attacks
  186. Guidance Contrastive Token Credit Assignment for Discrete Policy OptimizationLLM reasoning → Reinforcement learning for reasoning
  187. ReasonOps: Operator Segmentation for LLM Reasoning TracesLLM reasoning → Reasoning benchmarks and evaluation
  188. When RL Suppresses Its Own Vocabulary: Recovering Reasoning Diversity in Puzzle-to-Math TransferLLM reasoning → Reinforcement learning for reasoning
  189. PICasso: An AI-Enabled Design Framework for Autonomous Optimization of Silicon Photonic Devices
  190. Position: AI Lock-In Is in Progress, and We Must Be Prepared
  191. Designing for Ethical AI: HCI Feature Considerations to Improve Fairness and User Experience in AutoML use for Human Resources
  192. Seeing Differently: Modeling Interpretive Perspectives in Computational Creativity using a Four-World Framework
  193. Do Models Fake Alignment Without Clear Consequences?
  194. Efficient multidisciplinary design via Bayesian optimization
  195. Position: Every Ground Truth is a Human Construction, not an Objective Truth
  196. Learning User-Aware Recall: Personalized Retrieval in Long-Term Conversational Memory
  197. Privacy-Aware Agent Collaboration for Dynamic VR Slice Management in 6G SD-RAN
  198. Context-Aware Prediction of Student Quiz Performance with Multimodal Textbook Features
  199. FP8 is All You Need (Part 2): Full-FP64 3-D FFT on FP8-Generation Tensor CoresThe Integer-Epilogue Wall and the Minimal Hardware That Would Remove It
  200. Design Principles for Human-Agent Interaction
  201. AI for Maritime Security: Comparative Evaluation of CNN and Vision Transformer Architectures for Maritime Object Detection
  202. CFCamo: A Counterfactual Detect-or-Abstain Framework for Camouflaged Object Detection
  203. Support sufficiency as action-sufficient compression: a single-cycle rate-regret formulation
  204. Syll: Open-Source Personal Automation with Cross-Surface Execution
  205. A Mechanistic Analysis of Adversarial Fine-tuning of Vision Transformers
  206. SlideCheck: Guiding Self-Supervised Pretraining of Pathology Foundation Models via Dataset Distributions
  207. Optimality of Sequential Filtering Under Independent Cost and Selectivity Models
  208. FP8 is All You Need (Part 1): Debunking Hardware FP64 as the HPC Holy Grail (Sep 3rd version)
  209. Geodesics with Unified Tangent-constrained Priors and Curvature Regularization
  210. Advances in Neural 3D Mesh Texturing: A Survey
  211. Generative AI and Digital Ecosystem Resilience: A Proactive Lifecycle-Based Survey
  212. XAI-SOH-FL: Enhancing SOH-FL with Adaptive Aggregation and Explainable AI for Intrusion Detection in Heterogeneous IoT
  213. Foundation-Preserving Optimization in Generalized Eigenspace
  214. AI-PROPELLER: Warehouse-Scale Interprocedural Code Layout Optimization with AlphaEvolve
  215. Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) for Exponential Parameter Compression of Deep Neural Networks
  216. A Shared Valence Axis Across Modern LLMs and Human EEG: The Saturation Regularity
  217. Multimodal Music Recommendation System using LLMs
  218. Positional Encodings Anchor Spatial Structure in Vision Transformers: A Geometric Perspective on Robustness
  219. Versatile Framework with Semantic and Structural guidance for Image Reconstruction from Brain Activity
  220. SpikeWFM: Spiking-Aided Wireless Foundation Model for Robust Channel Prediction
  221. V2I Work Zone Geometry Reconstruction with Pose-Conditioned UWB Range Denoising
  222. Automatically Attacking Software Reverse Engineering AI Agents
  223. Structure-Induced Information for Rerooting Levin Tree Search
  224. Spatio-temporal stochastic graph-based learning for infectious disease forecasting
  225. EUDAIMONIA: Evaluating Undesirable Dynamics in AI
  226. Bridging the Gap Between Natural Language and Market Dynamics via High-Dimensional Representation Learning
  227. Same Patient, Different Words, Different Diagnosis? Evaluating Semantic Stability in Clinical LLMs
  228. CSULoRA: Closest Safe Update Low-Rank Adaptation
  229. PInVerify: An Offline Embodied Benchmark for Active Instance Verification
  230. Score Broadcast and Decorrelation: A General Framework for Broadcast-Based Credit Assignment
  231. EHRBench: An Automated and Reliable EHR-based Benchmark for Clinical Decision Making with LLMs
  232. CellBRIDGE: Learning Cellular Trajectories via Interaction-Aware Alignment
  233. The Architecture of Errors: From Universal Impossibility to Patch-Local LLM Reliability
  234. Active Timepoint Selection for Learning Measure-Valued Trajectories
  235. Jamming-Resilient PRB Reservation for Latency-Critical O-RAN Network Slicing
  236. Improving Selective Classification with Pairwise Queries for Binary Classification
  237. CacheProbe: Auditing Prompt Cache Isolation in Gateway APIs
  238. Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs
  239. Constrained Flow Optimization via Sequential Fine Tuning for Molecular Design
  240. Semantic Motion Anchors: Bridging Motion and Meaning in Co-Speech Gestures
  241. Learning effective Sargassum transport dynamics from limited drifter observations
  242. TASER: Task-Aware Stein Regularisation for Geometry-Driven Robustness
  243. The Fast Mixing Mechanism for Differential Privacy
  244. ScaleMAP: Preserving Local Density and Neighborhood Structure in Low-Dimensional Embeddings
  245. Improving Relative Representations with Learned Anchors and Whitened Inner Products
  246. Scientific Machine Learning for Engine Health Management and Remaining Useful Life Prediction
  247. Learning Transferable Predictability Representations
  248. Counterfactual Evaluation Reveals Hidden Capability Profiles in Clinical LLMs and Agents
  249. ImmigrationQA: A Source-Grounded Dataset and Small-Model Adaptation for U.S. Immigration Law
  250. Benchmarking Machine Learning Uncertainty Quantification Methodologies for Predicting Turbine Gas Temperature Degradation
  251. AI for Monitoring and Classifying Data Used in Research Literature
  252. Prior Availability in Industrial Visual Sim-to-Real: A Review of CAD-Guided and CAD-Unavailable Regimes
  253. AdvScene: Rethinking Adversarial Patch Evaluation Through Scene Robustness
  254. Zeroth-Order Non-Log-Concave Sampling with Variance Reduction and Applications to Inverse Problems
  255. Procedural Generation of First Person Shooter Maps using Map-Elites
  256. Generating and Refining Dynamic Evaluation Rubrics for LLM-as-a-Judge
  257. Transforming and Encoding FTS for SAT Solving: What Helps, What Hurts (Extended Version)
  258. Supervised Training Rapidly Degrades Early Visual Cortex Alignment Across Biologically Plausible Learning Rules
  259. Early Prediction of Future Behavioral Strategy from Process Traces
  260. Refining Word-Based Grammatical Error Annotation for L2 Korean
  261. On-Device Generative AI for GDPR-Compliant Visual Monitoring: Natural Language Alerts from Local Object Detection
  262. SubsurfaceGen: Procedural Generation of Field-Scale Earth Models and Seismic Data
  263. The Long-Term Effects of Data Selection in LLM Fine-Tuning
  264. True Self-Avoiding Walk for Accelerating Markov-Chain Monte Carlo Integration
  265. Generalistic or Specific Embeddings, Which is Better? An Empirical Study on Search for Clinical Coding in Non-English Languages
  266. Representation Collapse in Sequential Post-Training of Large Language Models
  267. Revisiting Padded Transformer Expressivity: Which Architectural Choices Matter and Which Don't
  268. Evaluating using Mock Tool Calls to Quarantine Untrusted Prompt Inputs
  269. Benchmark of Likelihood-Free Inference Methods based on Neural and Optimal Transport Approaches
  270. PhyDrawGen: Physically Grounded Diagram Generation from Natural Language
  271. A Novel Global Context-aware Deep Neural Network for Enhanced Brain Tumor Segmentation using Magnetic Resonance Images
  272. Improved Distribution Estimation in ℓ_∞
  273. Auditing LLM Benchmarks with Item Response Theory
  274. When English Rewrites Local Knowledge: Global Narrative Dominance in Large Language Models
  275. Universal Multiclass Transductive Online Learning
  276. Improving Small Language Models for Code Generation with Reinforcement Learning from Verification Feedback
  277. Local Differential Privacy with Correlated Noise Achieves Central-DP Optimal Cost
  278. Your Multimodal Speech Model Says I Have a Face for Radio
  279. Can Subgraph Explanations Be Weaponized to Steal Graph Neural Networks?
  280. 3DAE: Binaural Quality Assessment for Audio Novel View Synthesis with Spatial Maps and Benchmark
  281. Clustering Guided Domain-Specific Pretrained Foundation Model for Very High-Resolution Arctic Remote Sensing
  282. Knowledge Graph-Enhanced Zero-Shot Topic Classification: A Multi-Strategy Comparative Study
  283. Scalable Constrained Multi-Agent Reinforcement Learning via State Augmentation and Consensus for Separable Dynamics
  284. Can LLM Teams Play What? Where? When?
  285. Extracting accent features in spoken Brazilian Portuguese without sociolinguistic labels
  286. DisjunctiveNet: Neural Symbolic Learning via Differentiable Convexified Optimization Layers
  287. Generative Models and Statistical Validation
  288. A Unified Framework for Gradient Aggregation in Multi-Objective Optimization
  289. Calibrated Preference Learning: The Case of Label Ranking
  290. Dex2HOI: Dexterous Bimanual Two-Object Interaction Generation
  291. Cross-Lingual Steering for Figurative Language Generation
  292. Mitigating Content Shift and Hallucination in GenAI Image Editing via Structural Refinement
  293. Learning effective models from network dynamics data with multiple initial conditions using weak form SINDy
  294. Attention-based optimizer for symmetry finding
  295. AI Loss of Control Incident Management: Response & Resilience
  296. Protocol for evaluating ChatGPT in biomedical association generation and verification using a RAG-enabled, cross-model majority voting workflow
  297. A Novel Computer Vision Approach for Assessing Fish Responses to Intrusive Objects in Aquaculture
  298. Smaller and Faster 3DGS via Post-Training Dictionary Learning
  299. CodeGolf Bench: A Multi-Language Benchmark for Evaluating Concise Code Generation Capabilities of Large Language Models
  300. NumLeak: Public Numeric Benchmarks as Latent Labels in Foundation Models
  301. The Inclusion Depth of Pattern Languages: An Open Problem in Algorithmic Learning Theory
  302. A Novel Evaluation Metric for Unsupervised Learning in AIS-Based Maritime Anomaly Detection: MADQI
  303. LLMs Without Deep Neural Networks: New Architecture, Benefits and Case Study
  304. Structured interactions improve distributed coordination beyond model scaling in a real-world multi-robot system
  305. Physics Is All You Need? A Case Study in Physicist-Supervised AI Development of Scientific Software
  306. GMOS: Grounding Moving Object Segmentation in 3D Space and Time
  307. DynaFLIP: Rethinking Robotics Perception via Tri-Modal-Dynamics Guided Representation
  308. LLMSurgeon: Diagnosing Data Mixture of Large Language Models
  309. NeuROK: Generative 4D Neural Object Kinematics
  310. SchGen: PCB Schematic Generation with Semantic-Grounded Code Representations
  311. Uncertainty-driven 3D Gaussian Splatting Active Mapping via Anisotropic Visibility Field
  312. GPIC: A Giant Permissive Image Corpus for Visual Generation
  313. Benchmarking Single-Factor Physical Video-to-Audio Generation
  314. REST3D: Reconstructing Physically Stable 3D Scenes from a Single Image
  315. Efficient Test-Time Finetuning of LLMs via Convex Reconstruction and Gradient Caching
  316. Fairness-Aware Federated Learning with Trajectory Shapley Value
  317. Demystifying Data Organization for Enhanced LLM Training
  318. COMPOSE: Composing Future Theorems from Citations and Formal Structure
  319. Supercharging Thermal Gaussian Splatting with Depth Estimation
  320. RoboWits: Unexpected Challenges for Robotic Creative Problem Solving
  321. On Language Generation in the Limit with Bounded Memory
  322. MonoPhysics: Estimating Geometry, Appearance, and Physical Parameters from Monocular Videos
  323. Improved Guarantees for Heterogeneous Treatment-Effect Estimation via Matrix Completion
  324. Before the Shutter: Aesthetic and Actionable Portrait Photography Planning in 3D Scenes
  325. VPG: Visual Prefix Guidance for Autoregressive Image and Video Generation
  326. Resolution Diagnostics for Paired LLM Evaluation
  327. Archon: A Unified Multimodal Model for Holistic Digital Human Generation
  328. City-Mesh3R: Simulation-Ready City-Scale 3D Mesh Reconstruction from Multi-View Images
  329. Leave a Window Out: Modifying the Jackknife for Predictive Inference in Time Series
  330. Statistical Embeddings for Similarity, Retrieval, and Interpretable Alignment of Numeric Tabular Datasets
  331. MIRA: Mid-training Rubric Anchoring for Source-Aware Data Selection
  332. ProjectionBench: Evaluating Scientific Hypothesis Generation in LLMs Under Progressive Information Disclosure
  333. mcp-proto-okn: Natural-language access to open scientific knowledge graphs through the Model Context Protocol
  334. Neural Operator-Based Surrogate Model for CFD:Helical Coil Steam Generator in Small Modular Reactor
  335. Digitally enriching a high-risk population for pancreatic cancer using routine blood-based measures and clinical histories
  336. Boosting Image Quality Assessment Performance: Unsupervised Score Fusion by Deep Maximum a Posteriori Estimation
  337. PhyGenHOI: Physically-Aware 4D Generation of Dynamic Human-Object Interactions
  338. How LoRA Remembers? A Parametric Memory Law for LLM Finetuning
  339. VideoFDB: Evaluating Full-Duplex Vision-Speech Capabilities in Conversational Agents
  340. Wasserstein Contraction of Coordinate Ascent Variational Inference
  341. Ambient-robust Inverse Rendering using Active RGB-NIR Imaging
  342. OOD-GraphLLM: Graph Large Language Model for Out-of-Distribution Generalized Drug Synergy Prediction
  343. CommunityFact: A Dynamic, Multilingual, Multi-domain Benchmark for Misinformation Detection in the Wild
  344. CA-World: Multi-Object Counterfactual Alignment for Efficient Interactive-Ready Reconstruction
  345. GRASP: Plan-Guided Graph Retrieval with Adaptive Fusion and Reranking on Semi-Structured Knowledge Bases
  346. BullingerDB: A Dataset for Handwritten Text Recognition and Writer Retrieval
  347. Do Language Models Track Entities Across State Changes?
  348. How's it going? Reinforcement learning in language models recruits a functional welfare axis
  349. Anti Mode-Collapse in Mean-Field Transformer via Auxiliary Variables
  350. ExDBSCAN: Explaining DBSCAN with Counterfactual Reasoning -- Additional Material
  351. When Should Models Change Their Minds? Contextual Belief Management in Large Language Models
  352. MarginGate: Sparse Margin-Triggered Verification for Batch-Invariant LLM Inference
  353. D'ej`a View: Looping Transformers for Multi-View 3D Reconstruction
  354. Faithful Embeddings of Irregular and Asynchronous Data for Online Log-NCDEs
  355. Cycle Consistency in Video Object-Centric Learning
  356. Automating Low-Risk Code Review at Meta: RADAR, Risk Calibration, and Review Efficiency
  357. A Dual-Path Architecture for Scaling Compute and Capacity in LLMs
  358. HPO: Hysteretic Policy Optimization for Stable and Efficient Training under Sparse-Reward Regime
  359. Double-Edged Sword or Sharp Tool? Designing and Evaluating Triadic LLM-Teacher Collaboration for K-12 Writing at Scale
  360. Active Continual Learning with Metaplastic Binary Bayesian Neural Networks
  361. What drives performance in molecular MPNNs? An operator-level factorial benchmark
  362. CalArena: A Large-Scale Post-Hoc Calibration Benchmark
  363. Modularizing Educational LLM-Agency for Fostering Responsible Learning Assistance
  364. Can AI Weather Models Predict Beyond Two Weeks? A Quantitative Benchmark and Analysis of Long Rollouts
  365. iLoRA: Bayesian Low-Rank Adaptation with Latent Interaction Graphs for Microbiome Diagnosis
  366. A new completely parameter-free clustering algorithm for unsupervised classification of BATSE gamma-ray bursts
  367. OmniCD: A Foundational Framework for Remote Sensing Image Change Detection Guided by Multimodal Semantics
  368. Visual Spatial Learning: Single-Field Spatial Interpolation Using Convolutional Neural Networks
  369. SAHG: Sector-Anisotropic Hyperbolic Graph Model for Social Bot Detection
  370. Neural Network Verification using Partial Multi-Neuron Relaxation
  371. Temporal Stability and Few-Shot Prompting in Math Task Assessment
  372. Anchorless Diversification for Parallel LLM Ideation
  373. Overcoming Forgetting in LLM Fine-Tuning with Evolution Strategies
  374. DAMEL: Dual-Axis Multi-Expert Learning for Class-Imbalanced Learning
  375. CorPipe at CRAC 2026: Empty Nodes and Cross-Lingual Transfer in Multilingual Coreference Resolution
  376. Learning to Extrapolate to New Tasks: A Relational Approach to Task Extrapolation
  377. CCS: Clinical Consensus Selection for Radiology Report Generation
  378. Privacy-Enhanced Zero-Order Federated Learning via xMK-CKKS over Wireless Channels
  379. Beyond MSE: Improving Precipitation Nowcasting with Multi-Quantile Regression
  380. No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval
  381. Evolving Features vs Evolving Entire Trees with GP for Interpretable Survival Analysis
  382. Large Depth Completion Model from Sparse Observations
  383. Striding Across Reynolds Numbers: Representation Geometry in Neural PDE Generalisation
  384. Dial HEALTHDIAL for Advice: A Multilingual and Multi-Parallel Spoken Dialogue Dataset for Knowledge-Grounded Information Seeking
  385. SEAL: Can Saturated Benchmarks Be Revived by LLM-as-a-Meta-Judge?
  386. Convergence Theory for Iterative LLM-Based Neural Architecture Search: A Parametric Cross-Entropy Framework with Closed-Form Proxy Reliability
  387. Evaluation of Conversational Agents: Understanding Culture, Context and Environment in Emotion Detection
  388. How Reliable Are AI Attackers Against a Fixed Vulnerable Target? A 400-Run Empirical Study of LLM Penetration Testing Consistency
  389. PokerSkill: LLMs Can Play Expert-Level Poker without Training or Solvers
  390. Distributionally Robust Set Representation Learning Under Inference-Time Element Corruption
  391. Selective QA over Conflicting Multi-Source Personal Memory: A Diagnostic Testbed and Method Comparison
  392. Adaptive Targeted Dynamic Chunking for Tokenization-Free Hierarchical Model
  393. Q-ANCHOR: Federated Quantum Learning with ZNE-guided Correction
  394. Native Audio-Visual Alignment for Generation
  395. Boosting Zero-Shot 3D Style Transfer with 2D Pre-trained Priors
  396. FakeVLM-R1: Internalizing Physical Laws via CoT for Synthetic Image Detection
  397. Towards Consistent Video Geometry Estimation
  398. Ridge Regression from Poisson Resetting: A Renewal Perspective on Spectral Regularization
  399. Projectional Decoding: Towards Semantic-Aware LLM Generation
  400. Who Am I? History-Aware Profiles for Student Simulation in Tutoring Dialogues
  401. DualEraser: Joint Video Object and Effect Removal via Balanced Text-Mask Guidance and Decoupled Locator-Preserver
  402. Token Inflation: How Dishonest Providers Can Overcharge for Large Language Model Usage
  403. Teaching Values to Machines: Simulating Human-Like Behavior in LLMs
  404. DocRetriever: A Plug-and-Play Framework for Multimodal Document Retrieval with Comprehensive Benchmark
  405. Give it Space! Explicit Disentangling of Positional and Semantic Representations in Encoders
  406. Latent Performance Profiling of Large Language Models
  407. Test Time Training for Supervised Causal Learning
  408. From GPS Points to Travel Patterns: Flexible and Semantic Trajectory Generation with LLMs
  409. Discovering Cooperative Pipelines: Autoresearch for Sequential Social Dilemmas
  410. Cookie-Bench: Continuous On-screen Key Interaction Evaluation for Web Generation
  411. FRUC: Feedforward Dynamic Scene Reconstruction from Uncalibrated Collaborative Driving Views
  412. MIC: Maximizing Informational Capacity in Adaptive Representations via Isotropic Subspace Alignment
  413. Accelerating Constrained Decoding with Token Space Compression
  414. Improving Adversarial Robustness of Attribution via Implicit Regularization
  415. Genetically Aligned Patient Representations Improve Hematological Diagnosis
  416. Fingerprinting Inference Systems of Large Language Models
  417. Evaluating Skill and Stability of ArchesWeather and ArchesWeatherGen under Multi-Decadal Climate Simulations
  418. A Fully Convolutional Approach to Denoising 2D Correlation Spectra
  419. Compass: Navigating Global Marine Lead Data Integration through Expert-Guided LLM Agent
  420. Meta-Programming for Linear-time Temporal Answer Set Programming
  421. Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots
  422. Formalizing Mathematics at Scale
  423. SwInception -- Local Attention Meets Convolutions
  424. Mesh-Aware Epipolar Matching for Multi-View Multi-Person 3D Pose Estimation in Basketball
  425. From Short Histories to Long Futures: Horizon-Aware Graph Neural Networks for Long Horizon Forecasting
  426. HoliTok: A Continuous Holistic Tokenization with Robust Dual Capabilities of Speech Generation and Understanding
  427. A Domain-Informed Multi-Objective Framework for EEG Channel Selection in Motor Imagery BCIs
  428. TraceCodec: A Compiler-Backed Neural Codec for Network Traffic Traces
  429. Make LLM Learn to Synthesize from Streaming Experiences through Feedback
  430. CRB-Guided Framework Design and Resource Allocation for Indoor mmWave ISCC Systems
  431. CityGen: Structure-Guided City-Style Synthesis for Cross-City Autonomous Driving
  432. CLUBench: A Clustering Benchmark
  433. Treatment-Conditioned Diffusion for Forecasting Neurodegenerative Disease Progression
  434. It`s All About Speed: AI`s Impact on Workflow in Music Production
  435. Label Over Logic? How Source Cues Bias Human Fallacy Judgments More Than LLMs
  436. A Triple-Modal Contrastive Learning Framework with Sequence, Graph, and 3D Features for Drug-Target Interaction Prediction
  437. On the Geometry of Games and their Solvers
  438. Selection Hyper-heuristics Can Automatically Adjust the Learning Period to Optimally Solve Pseudo-Boolean Problems
  439. Gesture-Aware Indoor THz ISAC Systems for Adaptive Resource Allocation
  440. Reducing Experimental Testing in Space Propulsion Film Cooling Analyses by Pixelwise Generative Image Interpolation
  441. Joint Model and Data Sparsification via the Marginal Likelihood
  442. Plan, Don't Pose: Long Composite Motion Generation with Text-Aligned BFM
  443. OVA-IB: One vs All Information Bottleneck for Multi-Modal Alignment
  444. ExCAM: Explainable Cultural Awareness Metrics
  445. DVSM: Decoder-only View Synthesis Model Done Right
  446. Where Do Apparent LLM Clinical Triage Failures Arise? Localizing the Multiple-Choice Format Effect
  447. Open Problem: Separating Geometric and Algorithmic Compression via Cayley-Table Completion
  448. DGSG-Mind: Dynamic 3D Gaussian Scene Graphs for Long-Term Scene Understanding and Grounding
  449. Ciphera: A Decentralised Biometric Identity Framework
  450. STAP: A Shuffle-Tokenized App Predictor with Ultra Long Context for Vocabulary-Free Mobile App Prediction
  451. Mitigating Stethoscope-Induced Shortcuts in Respiratory Sound Classification under Federated Domain Generalization with Causality-Inspired Interventions
  452. MELD: Mel-Spectrogram-Based Speech Language Modeling with Discrete Latent Variables
  453. Feedback-to-Rubrics: Can We Learn Expert Criteria from Inline Comments?
  454. Building and Road Recognition in Dense Urban Informal Settlements: A Dataset and Benchmark
  455. Parameter-Efficient Subspace Decoupling ViT for Mitigating Multi-Task Negative Transfer in Histological Scoring
  456. MIRAGE: Adaptive Multimodal Gating for Whole-Brain fMRI Encoding
  457. BuilDyn: Excitation-Driven Data Generation for Building Thermal Dynamics Modeling and Control
  458. HARP: Hadamard-Preconditioned Adaptive Rotation Processor for Extreme LLM Quantization
  459. The Topological Stability Index: A Variance-Based Measure for Persistence Barcodes
  460. CB-SLICE: Concept-Based Interpretable Error Slice Discovery
  461. Open World Autoencoding Drift Detection with Novel Class Recognition in Tabular Non-stationary Data Streams
  462. OptSkills: Learning Generalizable Optimization Skills from Problem Archetypes via Cluster-Based Distillation
  463. When Do Graph Foundation Models Transfer? A Data-Centric Theory
  464. Fairness Beyond Demographics: Optimizing Performance Across Appearance-Based Hidden Cohorts in Medical Imaging
  465. Quantifying and Optimizing Simplicity via Polynomial Representations
  466. Inferring Code Correctness from Specification
  467. The Interplay Between Interpolation and Aggregation in Regression: Optimal Sample Complexity
  468. Harnessing non-adversarial robustness in large language models
  469. PRAIB: Peer Review AI Benchmark of Behaviour of LLM-Assisted Reviewing
  470. Not All Inputs Are Valid: Towards Open-Set Video Moment Retrieval Using Language
  471. Data filtering methods for training language models
  472. Gated Graph Attention Networks with Learnable Temperature
  473. Nine Judges, Two Effective Votes: Correlated Errors Undermine LLM Evaluation Panels
  474. Low-Magnification SEM May Suffice: Interpretable Deep Learning for Multi-Scale Fracture-Cause Classification in Zirconia-Toughened Alumina
  475. Metric-Dependent Annotation Saturation for Learning from Label Distributions
  476. MEMENTO: Leveraging Web as a Learning Signal for Low-Data Domains
  477. Fewer Steps, Better Performance: Efficient Cross-Modal Clip Trimming for Video Moment Retrieval Using Language
  478. ActTraitBench: Quantifying the Knowledge-Decision Gap in Large Language Models via Human-Grounded Behavioral Validation
  479. Certified Policy Optimisation for Nested Causal Bandits via PAC-Bayes Risk
  480. Croissant Tasks: A Metadata Format for Reproducible Machine Learning Evaluations
  481. Hista and Numca: Estimate State Value Effectively for LLM Reinforcement Learning
  482. Energy-Aware NECO for Single-Pass Pixel-wise Out-of-Distribution Detection in Semantic Segmentation
  483. From XXLTraffic to EvoXXLTraffic: Scaling Traffic Forecasting to Sensor-Evolving Networks
  484. MMTM: Tri-Modal Topic Modeling for Long-Form Video via Similarity-Gated Fusion
  485. GeoMag: Geometric-Aware Video Motion Magnification via State Space Model
  486. S2MDF: A Plug-And-Play Layer for Intersection-Free Multi-Object Signed Distance Fields
  487. LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMs
  488. Benchmarking Positional Encoding Strategies for Transformer-Based EEG Foundation Models
  489. A unified deeplearning framework for contrast-phase-specific virtual monochromatic imaging
  490. DySem: Uncovering Dynamic Semantic Components of Large Language Models for Calculating Semantic Textual Similarity
  491. Instance-dependent Stochastic Lipschitz bandit
  492. Citation-Closure Retrieval and Per-Rule Attribution for Real-World Regulatory Compliance Question Answering
  493. AfriScience-MT: Towards Decolonizing Science in Africa through Text Translation
  494. Minimal Prompt Perturbations Lead to Code Vulnerabilities: Prompt Fragility and Hidden-State Signals in Coding LLMs
  495. HTAM: Hierarchical Transition-Attended Memory for Operator Optimization
  496. Uncertainty-Aware Transfer Learning for Cross-Building Energy Forecasting: Toward Robust and Scalable District-Level Energy Management
  497. EMAG: Differentiable 4D Gaussian Mixture Splatting for EEG Spatial Super-Resolution
  498. Realistic honeypot evaluations for scheming propensity
  499. Efficient, Validation-Free Intrinsic Quality Estimation for Large-Scale Face Recognition Datasets
  500. NaRA: Noise-Aware LoRA for Parameter-Efficient Fine-Tuning of Diffusion LLMs
  501. The Little Book of Generative AI Foundations: An Intuitive Mathematical Primer
  502. Personalized Turn-Level User Conversation Satisfaction Benchmark
  503. BitTP: The Lightweight Trajectory Prediction Model with BitLLM for Edge-Devices
  504. Subcortical Shape Variations and Their Associations with Cognition Across the 8th Decade of Life. A Study in the Lothian Birth Cohort 1936
  505. A Systematic Evaluation of Molecular Mixture Behavior Prediction
  506. FHRFormer: A Self-Supervised Masked Transformer Framework for Fetal Heart Rate Time-Series Inpainting and Forecasting
  507. Momentum Based Reward Design for Low Emission Traffic Signal Control
  508. Unsupervised Semantic Segmentation Facilitates Model Understanding
  509. A Novel Tensor Product-Based Neural Network for Solving Partial Differential Equations
  510. NICE: A Theory-Grounded Diagnostic Benchmark for Social Intelligence of LLMs
  511. Kernel Renormalization in Bayesian Deep Neural Networks: the Equivalent Wishart Ansatz in the Proportional Regime
  512. Scaling Laws for Agent Harnesses via Effective Feedback Compute
  513. Spurious Prompts: Can Irrelevant Prompts Steer Large Language Models?
  514. From Prompts to Context: An Ontology-Driven Framework for Human-Generative AI Collaboration
  515. A Geometric View of SRC: Learning Representations for Stable Residual Inference
  516. EviLink: Multi-Path Schema Linking with Uncertainty-Guided Evidence Acquisition for Large-Scale Text-to-SQL
  517. Eigen-Spike Emergence and Quadratic Equivalents for Conjugate Kernels on Nonlinearly Separable Data
  518. AMDP: Asynchronous Multi-Directional Pipeline Parallelism for Large-Scale Models Training
  519. Geometry-Guided Modeling of Foundation Features Enables Generalizable Object Shape Deformation Learning
  520. LLM-Evolved Domain-Independent Heuristics for Symbolic AI Planning
  521. MARTIAN: A Rendering Framework for Aerial Mars Imagery from HiRISE Orbital Data
  522. The Sample Complexity of Multiclass and Sparse Contextual Bandits
  523. VikingMem: A Memory Base Management System for Stateful LLM-based Applications
  524. Classification of non-analyzable word types in web documents to implement an effective Korean e-learning system
  525. Evaluating Cross-lingual Knowledge Consistency in Code-Mixed vis-a-vis Indian Languages using IndicKLAR
  526. MoSSP: A Momentum-Based Single-Loop Stochastic Penalty Method for Nonconvex Constrained DC-Regularized Optimization
  527. Relational Rank Geometry in Transformers: Detecting and Steering Hidden-State Relation Frames
  528. Predicting Causal Effects from Natural Language Queries using Structured Representations
  529. Entity-Collision: A Stratified Protocol for Attributing Retrieval Lift in Agent Memory
  530. COMET: Concept Space Dissection of the Modality Gap in Audio-Text Multimodal Contrastive Embeddings
  531. M=oLe-Lambda: Learning the Coupled-Cluster Response State for Energies, Gradients, and Properties
  532. Learning Context-Conditioned Predicate Semantics via Prototype Feedback
  533. Training Deliberative Monitors for Black-Box Scheming Detection
  534. How to Relieve Distribution Shifts in Semantic Segmentation for Off-Road Environments
  535. Non-Forgetting Knowledge Allocation with Bi-level Competition for Class-Incremental Learning
  536. Brain-IT-VQA: From Brain Signals to Answers
  537. FPLIER: Federated Pathway-Level Information Extractor
  538. FinVerBench: Benchmark Validity and Calibration in Large Language Model Financial Statement Verification
  539. BitC-3DGS: High-Capacity 3D Gaussian Splatting Watermarking via Bit Compression
  540. On the Construction and Implications of Low-Loss Valleys in LoRA-based Bayesian Inference
  541. GPS-Enhanced Tourist Mobility Modeling with Seasonal Spatial Priors and LLM-Based Activity Chain Generation
  542. Optimizing Latent Representations for Robust Building Damage Assessment Onboard Earth Observation Satellites
  543. DefSynUS: Real-time Patient-specific Intrahepatic Vessel Identification via Deformation-Aware CT-US Domain Adaptation
  544. From General Vision to Reliable Traversability Estimation: Adapting Vision Foundation Models for Unstructured Outdoor Environments
  545. Planning with the Views
  546. LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents
  547. TAE: Target-aware enhancer for nighttime UAV tracking
  548. Opt-Verifier: Unleashing the Power of LLMs for Optimization Modeling via Dual-Side Verification
  549. From Blind Guess to Informed Judgment: Teaching LLMs to Evaluate Materials by Building Knowledge-Augmented Preference Signals
  550. Learning Representations from 3D Gaussian Splats
  551. Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention
  552. Singularity-aware Optimization via Randomized Geometric Probing: Towards Stable Non-smooth Optimization
  553. SCOPE: A Lightweight-training LLM Framework for Air Traffic Control Readback Monitoring
  554. RadioFormer3D: Weakly Supervised 3D Radio Map Estimation in Low-Altitude Airspace via Generative Modeling
  555. The Complexity of Verifying Feedforward Neural Networks in Quantised Settings
  556. Half-Truth Audio Detection and Localisation: A Lightweight Cross-Attentive Architecture and a Cross-Corpus Diagnostic Study
  557. Temporal Motif-aware Graph Test-time Adaptation for OOD Blockchain Anomaly Detection
  558. Learning to Perturb Hidden Representations for Generalizable Deep Learning
  559. KBF: Knowledge Boundary as Fingerprint for Language Model and Black-Box API Auditing
  560. DeepSurvey: Agent-Oriented Automated Survey Generation with Analytical Depth and Citation Reliability
  561. Network Optimization Aspects of Autonomous Vehicles: Challenges and Future Directions
  562. DynaGraph: Lightweight Multi-Model Interaction Framework via Dynamic Topological Reconfiguration
  563. Xetrieval: Mechanistically Explaining Dense Retrieval
  564. ESAM++: Efficient Online 3D Perception on the Edge
  565. Source-Grounded Semantic Reinforcement Learning for Low-Resource Target-Language Generation
  566. Quotient DAGs for Off-Policy Evaluation:Forward-Flow Importance Sampling and Exact Slate Propensities
  567. Mask the Target: A Plug-and-Play Regularizer Against LoRA Forgetting
  568. Convex Basins in Single-Index Model Loss Landscapes: Applications to Robust Recovery under Strong Adversarial Corruption
  569. Gradient Perturbation: Learning to Perturb Gradients for Adaptive Training
  570. The New Pro Se: Generative AI and the Surge in Federal Civil Self-Representation
  571. Access Sets Matter: Budgeting Expert Reads for Scalable Weight-Space Model Merging
  572. AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling
  573. PhoneWorld: From Real-App Trajectories to Dynamic and Verifiable Environments for Phone-Use Agents
  574. VitalAgent: A Tool-Augmented Agent for Reactive and Proactive Physiological Monitoring over Wearable Health Data
  575. Evolutionary Rule Extraction from Corporate Default Prediction Models
  576. Comparative Evaluation of Machine Translation Systems on Images with Text
  577. MOOSE-Copilot: A Web-Based Interactive Assistant for Unified Exploratory and Fine-Grained Scientific Hypothesis Discovery
  578. Inform, Coach, Relate, Listen: Auditing LLM Caregiving Support Roles
  579. SciIntBench: Measuring LLM Compliance with Research Integrity Norms Under Adversarial Framing
  580. Composing Non-Conjugate Factor Graphs with Closed-Form Variational Inference
  581. Deep Optimal Individualized Treatment Rules for Bivariate Survival Outcomes via Adaptive Prediction-Powered Learning
  582. Honest Lying: Understanding Memory Confabulation in Reflexive Agents
  583. FlowSeg: Dynamic Semantic Guidance for LLM-Conditioned Segmentation
  584. FedSmoothLoRA: Toward Smoother and Faster Convergence in Federated Low-Rank Adaptation
  585. Kronecker Embeddings: Byte-Level Structured Token Representations for Parameter-Efficient Language Models
  586. Uni-RCM: Unified Reference-guided Cross-modal Mapping for Multi-Class Anomaly Detection
  587. Forget Less, Generalize More: Unifying Temporal and Structural Adaptation for Dynamic Graphs
  588. Comparative evaluation of photogrammetric reconstruction methods and 3D Gaussian Splatting for road surface roughness analysis
  589. How Much Is a Dataset Worth? Scaling Laws, the Vendi Score, and Matrix Spectral Functions
  590. CrystalXRD-Bench: Benchmarking Vision-Language Models for XRD Peak Indexing Across Diverse Crystalline Materials
  591. One Click per Cell Type Suffices: Training-free Group Interaction for Cell Instance Segmentation
  592. DELOS: Contrastive Deep Learning for Low-SNR Blind Transit Searches in Kepler Photometry
  593. FinGuard: Detecting Financial Regulatory Non-Compliance in LLM Interactions
  594. Learning Design Skills as Memory Policies for Agentic Photonic Inverse Design
  595. When Does Persona Prompting Actually Help? A Retrieval and Metric Analysis of Expert Role Injection in LLMs
  596. ParCo-SDF: Learning Prior-Free Partial-to-Complete Signed Distance Fields of Deformable Objects
  597. Constructing efficient channels for ideal observers using the conjugate gradient method
  598. Beyond Bilingual Transfer: Multilingual Code-Switching in Instruction Tuning
  599. Real-Time Retargeting Using Controllability Boundary for Chandrayaan-3 Lunar Landing
  600. The Good, the Bad, and the Ugly of Markov Boundary for Tabular Prediction
  601. Architecture-Sensitive Supervised Fine-Tuning for Screen-Conditioned Action Prediction: A PiSAR Benchmark
  602. Low Rank for Rank: Uncertainty-Aware Task-Specific LLM Ranking under Sparse Pairwise Comparisons
  603. Offloading Score: Measuring AI Reliance Through Counterfactual Workflows
  604. Orthogonal Negative Guidance in Attention Feature Space for Text-to-Image Generation
  605. On the Optimizer Dependence of Neural Scaling Laws
  606. Latent Terms: Dense Retrievers Contain Trivially Extractable BM25-ready Zipfian Vocabularies
  607. TRACER: Persistent Regularization for Robust Multimodal Finetuning
  608. BrahmicTokenizer-131K: An Indic-Capable Drop-In Replacement for o200k_base
  609. Deep Adaptive Dimension Reduction for Bayesian Inference in Inverse Problems
  610. Kernel-based potential mean-field games with unbiased random Fourier U-statistics
  611. Attention Asymmetry in AI Layoff Discourse on X: A Computational Analysis of Capital vs Labour Amplification
  612. Solving Integer Linear Programming with Parallel Tempering
  613. Casual as an Anchor: Resolving Supervision Misalignment in Formality Transfer Dataset
  614. Does Distributed Training Undermine Compute Governance?
  615. PassNet: Scaling Large Language Models for Graph Compiler Pass Generation
  616. Neural-Behavioral Representation of Natural Whole-body Movement in Monkeys
  617. DeepFake Forensics AI: A Multi-Modal Detection and Blockchain-Anchored Evidence Management Platform
  618. Attention as In-Context Empirical Bayes: A Two-Stage View via Particle Dynamics
  619. A Study on Question-Answer Dataset for LLM Safety Evaluation with a Focus on Illegal Activities
  620. Enhancing Factuality through Consensus and Consistency in Summarization Using Minimum Bayes Risk Decoding
  621. Rethinking FID Through the Geometry of the Reference Dataset
  622. EarthShift: a benchmark for measuring robustness to real-world distribution shifts in Earth observation
  623. Mixing Vector Model for Copolymer Inference via Mixed Integer Linear Programming
  624. NeuroEdge: Real-Time Hand Gesture Recognition with High-Density EMG Using Deep Learning at the Edge
  625. Multi-Stage VLM Pipeline for Zero-Shot Traffic Accident Understanding
  626. FreeForm: Reduced-Order Deformable Simulation from Particle-Based Skinning Eigenmodes
  627. FoRA: Fisher-orthogonal Rank Adaptation for Parameter-Efficient Fine-Tuning
  628. CapTalk: Text-Guided Stylization and Speech-Driven 3D Head Animation
  629. Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of Large Language Models
  630. ViASNet: A Video Ad Saliency Network for Predicting Dynamic Saliency and Viewer Engagement
  631. MusTBench: Benchmarking and Advancing Temporal Grounding in Music LLMs
  632. Turbulence-Robust Dynamic Object Segmentation with Multi-Signal Priors and SAM2 Refinement
  633. UniNote: A Unified Embedding Model for Multimodal Representation and Ranking
  634. Do Physics Foundation Models Learn Generalizable Physics? A Bias-Aware Benchmark Across Physical Regimes and Distribution Shifts
  635. Accommodation Goes Both Ways: Studying Linguistic Convergence Between Humans and Language Models
  636. Learnable Assessment Skills for LLM-based Automated Scoring: Rubric Construction via Iterative Optimization
  637. A Theoretical and Experimental Study of a Novel Adaptive Learning Algorithm
  638. Causal Label Recovery in Payment Networks
  639. When and How Human Curation Backfires: Preference Alignment under Multi-Model Self-Consuming Loop
  640. Prior-Guided Frequency-Calibrated Virtual EEG Channel Inference from Four Frontal Electrodes for Wearable EEG Augmentation
  641. Deep Psychovisual Image Representations
  642. KLAS: Using Similarity to Stitch Neural Networks for Improved Accuracy-Efficiency Tradeoffs
  643. Extreme dynamic symmetry enables omnidirectional and multifunctional robots
  644. OpenClawBench: Benchmarking Process-side Anomalies in Real-world Agent Execution Trajectories
  645. OmniRetrieval: Unified Retrieval across Heterogeneous Knowledge Sources
  646. Prediction-Powered Inference Across Many Tasks for AI Evaluation & Social Science Research
  647. Wait! There's a Way Out: A Decision Mechanism for Forecasting Conversational Derailment
  648. Surfacing Isolated Learners with Outcome-Independent Mediation of Feedback between Teachers and Students Using AI
  649. SigmaMedStat: Temporal Signal Modeling for ICU False Alarm Reduction
  650. Toward a More Ethical Facial Age Estimation: A Generalized Zero-Shot Benchmark Without Training on Children's Data
  651. Traditional machine learning vs. deep learning from dynamic graph representations of proteins' 3D folds in the task of protein structure classification
  652. Inferring the Size of Large Language Models From Popular Text Memorization
  653. An Approach for Thyroid Nodule Analysis Using Thermographic Images
  654. Motion-guided sparse correction enables expert-quality point tracking across diverse microscopy regimes
  655. SalsaAgent: A multimodal embodied language model for interactive dance generation
  656. Towards the automated segmentation of epicardial and mediastinal fats: A multi-manufacturer approach using intersubject registration and random forest
  657. MetaRanker: Human-in-the-loop Active Ranking for Metalens Image Quality
  658. libhmm: A Modern C++20 Library for Hidden Markov Models with Correct MLE Emission M-Steps
  659. Stochastic Lifting for Generating Trajectories of Stochastic Physical Systems