mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 4 Aug 2026

584 papers

  1. One Domain, Many Tongues: Composing Domain and Language LoRAs for Cross-Lingual Remote-Sensing MLLMs without Paired DataMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  2. RECAP: Relation Evidence Calibration for Detecting Spatial Relation Hallucinations in Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  3. SpecialEduBench: Benchmarking Vision-Language Models on Knowledge, Skill, and Attitude in Language Intervention for Autistic ChildrenMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  4. Selection-Invariant Communication Compilers for Privacy-Aware Multi-Agent LLM WorkflowsLLM agents and tool use → Agent threats, guardrails and governance
  5. JEPA-WAM: Connecting Generated Visual Instructions to World Action Models through JEPA Latent RepresentationsWorld models → Embodied and robot world models
  6. When Agentic Executions Fail: Detecting and Localizing Runtime Faults from TelemetryLLM agents and tool use → Software engineering coding agents
  7. Offline Ambient-Controlled Latent Diffusion: Architecture, Telemetry, and On-Device EvaluationDiffusion models → Diffusion foundations and sampling
  8. Local verification cannot detect non-transportability: a cohomological theory of context preservation in agentic reasoningLLM agents and tool use → General LLM agent frameworks and benchmarks
  9. AgonAlpha: Autonomous Alpha Discovery via Prompt Economy and Scalable Agentic SearchLLM agents and tool use → Web, search, and research agents
  10. BRACE: Taming Sharp Irregularities via Barycentric Rational Forecasting for Fast Diffusion Transformers InferenceDiffusion models → Diffusion foundations and sampling
  11. Learning to Predict Middle-Layer Attention in MLLMs for Visual Token PruningMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  12. Post-Hoc Trajectory-Risk Certification for Modular LLM-Based Security AgentsLLM agents and tool use → Agent threats, guardrails and governance
  13. OneDayAgent: Towards a Long-Horizon Harness for Autonomous AgentsLLM agents and tool use → Software engineering coding agents
  14. Eliciting Intrinsic Hallucinations in LLMs via Semantically Equivalent Adversarial AttacksRetrieval-augmented generation → Hallucination detection in RAG
  15. The RAIL Principles for Neurosymbolic AI: Reasoning, Assurances, Interfacing and LearningLLM reasoning → Reasoning benchmarks and evaluation
  16. EA-Graph: Artifact-Anchored Verification Memory for Coding Agents under Upstream DriftLLM agents and tool use → Agent memory systems
  17. CURATE: Leveraging LLM Agents to Compose, Catalog, and Deploy Reproducible WorkflowsLLM agents and tool use → Software engineering coding agents
  18. The Fairness Collapse Phenomenon: Bias Amplification in Language Models Trained on Synthetic DataSynthetic data and self-improvement for LLMs → Model collapse from synthetic data
  19. Strategic Evaluation of Planning Strategies for LLM Agents in Cyber-Physical SystemsLLM agents and tool use → Agent threats, guardrails and governance
  20. SIGNPOST-Bench: Benchmarking Text-Vision Conflict Resolution in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  21. MatrAIx: Simulating the World with 8.3 Billion Persona AgentsLLM agents and tool use → Social simulation and multi-agent debate
  22. Behavioral Skill Reconstruction: Reconstructing Hidden Functionality from LLM Agent SkillsLLM agents and tool use → Agent threats, guardrails and governance
  23. AgentForge: An Immersive Role-Playing Platform for Learning Agentic Software EngineeringLLM agents and tool use → Software engineering coding agents
  24. RUTA: Principled Visual Token Allocation via Rate-Utility OptimizationLLM reasoning → Multimodal reasoning +1
  25. Radar4D-VLM: Proposal-Grounded Temporal 4D Radar Reasoning Across Frozen Language ModelsLLM reasoning → Chain-of-thought reasoning for driving +1
  26. Teaching Foundation Models to Read mmWave: Pose-Guided Kinematic Representation for Human Behavior UnderstandingLLM agents and tool use → Multimodal and embodied agents
  27. Perception Before Reasoning: Dynamic Latent Reasoning for Video Understanding and Question AnsweringLLM reasoning → Multimodal reasoning
  28. FinPerMA: A Theory-Informed, Event-Grounded Personalized-Memory Benchmark for LLM AgentsLLM agents and tool use → Agent memory systems
  29. SpecDrop: Parameter-Free Category-Conditioned Routing for Modular SpecializationMixture-of-experts → Vision mixture-of-experts
  30. FinProBench: Evaluating Financial AI Agents with Role-Grounded Rubrics Derived from Professional DeliverablesLLM agents and tool use → Financial trading and forecasting agents
  31. Spend Bits Where Queries Look: KV Cache Vector Quantization with Attention-Preserving TransformsEfficient LLM inference and serving → KV cache quantization
  32. The LLM Proposes, the Executive Disposes: A Self-Verifying Agent Instrument that Dissociates Commitment Drift from Binding Drift in Long-Horizon AgentsLLM agents and tool use → Agent memory systems
  33. An Inline Control Architecture for Language Models in Intelligent Transportation SystemsLLM safety and security → Safety alignment, refusal and guardrails
  34. Learning Sexism Detection Using Multi-Agent Perspectivist Preference OptimizationLLM agents and tool use → Social simulation and multi-agent debate +1
  35. AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt InjectionLLM agents and tool use → Agent threats, guardrails and governance +1
  36. When Modalities Fail to Tango: Conformal Backdoor Detection in Multimodal Contrastive LearningLLM safety and security → Backdoor and data poisoning attacks
  37. Robust and Personalized Federated Learning for Aircraft-Engine Prognostics under Benign and Adversarial Client HeterogeneityLLM safety and security → Federated unlearning and poisoning
  38. An Explainable LLM Agent Layer for Open-World Anomaly Detection in Oil WellsLLM agents and tool use → Software engineering coding agents
  39. ParVL: Parallel Scaling and Expandable Compute Allocation for Multimodal LLMsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  40. TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated ReasoningLLM reasoning → Reinforcement learning for reasoning +2
  41. Test-Time Scaling in Reasoning LLMs: Inference Regimes, Evaluation, and ReproducibilityLLM reasoning → Test-time compute and efficient thinking
  42. Assessment of Conditional Diffusion Model for Synthetic Histopathology Image GenerationDiffusion models → Medical imaging and segmentation
  43. Video-DeepResearch: Towards the Next-Generation Multimodal Deepresearch AgentLLM agents and tool use → Multimodal and embodied agents
  44. ReflectRL: Learning from Golden Negative Trajectories via Reflective-to-Direct ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  45. Should We Type or Talk to LLM Agents? A Comprehensive Study of Voice and Keyboard Input PerturbationsLLM agents and tool use → General LLM agent frameworks and benchmarks
  46. Separating quantum circuits from classical LLMsDiffusion models → Diffusion foundations and sampling
  47. Interpretable Adaptive Sampling for LLM Test-Time ScalingLLM reasoning → Test-time compute and efficient thinking
  48. Muon Meets Mamba: Spectral Optimization for State Space ModelsState-space sequence models (S4, Mamba) → Core SSM architectures for language
  49. Bimanual Manipulation Within an 8 GB Budget: Zero-Copy Sensing and Quantized ACT on an Entry-Level JetsonDiffusion models → Diffusion and flow policies for robotics +1
  50. Progressive Learning of a Diffusion-based Inpainting Model for Separating Overlapped FingerprintsDiffusion models → 3D, point cloud and scene generation
  51. Latent Reward Registers for Diffusion Preference AlignmentDiffusion models → Diffusion and flow policies for robotics +2
  52. ETA: A New Agentic Paradigm for Embodied TasksLLM agents and tool use → Multimodal and embodied agents
  53. Sparse Weight Decomposition for Efficient Circuit ExtractionMechanistic interpretability → Circuits and mechanistic analysis
  54. UniEvo-RS: Omni-Prompt Unified Remote Sensing Segmentation with Representative Exemplar-Driven Prototype EvolutionMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  55. Socially Grounded Agentic AI: Coordinating Plural Perspectives through Social TheoryLLM agents and tool use → General LLM agent frameworks and benchmarks
  56. Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill ReuseEfficient LLM inference and serving → KV cache optimization
  57. Intertemporal Preference Steering in Qwen3 via Contrastive Activation AdditionLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  58. MuRA: Multi-Rank Adaptation for Efficient and Effective Test-Time Vision-Language GeneralizationMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  59. BanglaWild: An In-the-Wild Bengali Scene Text Recognition Benchmark for OCR and Vision-Language ModelsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
  60. MultiGlobeQA: A Multilingual and Globally Diverse Benchmark for Geospatial ReasoningLLM reasoning → Spatial and embodied reasoning
  61. Enhancing VLM Reward Models Through Structure-Aware Fine-TuningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  62. ContinualSkillBench: Can LLM Agents Truly Evolve Their Capabilities?LLM agents and tool use → Agent skill learning and evolution
  63. EvoHIL: Self-Evolving Reward and Flow-Matched Policy Optimization for Robust Human-in-the-Loop Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  64. SciRet: A Compute-Aware Empirical Study of Retrieval and Reranking for Scientific RAGRetrieval-augmented generation → Agentic RAG, agents and memory
  65. LiteMVS: Efficient Multi-View Stereo with Foundation Distillation and Expert AggregationMixture-of-experts → Vision mixture-of-experts
  66. MAFIA: Query-Only Memory Attacks via Probing and Factual Injection against Audited LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  67. Oilbird: Training-Free Speculative Decoding with Keys the Verifier Already ComputesEfficient LLM inference and serving → Speculative decoding
  68. LatentGuard: Efficient and Inspectable Latent Reasoning for LLM SafeguardsLLM reasoning → Reasoning for agents, planning and code
  69. UHP Detection: LVLMs have their Unique Hallucination Pattern in the Consistency SpaceLLM reasoning → Hallucination detection and mitigation
  70. OmniPack: Unified Token Compression for Efficient Omni-modal Large Language ModelsEfficient LLM inference and serving → Audio and omni-modal token compression
  71. Autoreflection: How Agentic Strange Loops Turn Human Culture into AI InfrastructureLLM agents and tool use → General LLM agent frameworks and benchmarks
  72. Efficient Knowledge Distillation for LLMs: Offline Top-K Logits and a Fused Chunked KL LossKnowledge distillation → Knowledge distillation for LLMs
  73. Does Forgetting Transfer Across Modalities? A Real-World Benchmark for Cross-Modal Knowledge Unlearning EvaluationMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +1
  74. KnowHal: A Knowledge-Driven Benchmark for Comprehensive Multimodal Hallucination EvaluationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  75. MDLMPE: Distribution Aware Positional Encoding for Masked Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  76. TDVR: Joint Text Disambiguation and Viewpoint Reasoning for Zero-Shot 3D Visual GroundingLLM reasoning → Spatial and embodied reasoning
  77. GORDON: Graph-based Object-centric Rewards for Decomposition of Long-Horizon ManipulationDeep reinforcement learning methods → RL for robot locomotion and manipulation
  78. Risky Business: Measuring The Faithfulness-Safety TensionLLM reasoning → Prompting and chain-of-thought reasoning
  79. Agents Catching Agents: Shortcut Cascades and Benchmark Gaming in Clinical Multi-Agent SystemsLLM agents and tool use → Medical and scientific domain agents
  80. An Actionable Diagnosis of Multilingual, Multi-Agent Planning FailuresLLM agents and tool use → General LLM agent frameworks and benchmarks
  81. Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-ImprovementMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning +1
  82. Track4Action: Distilling World-Centric 3D Tracker into Vision-Language-Action PoliciesVision-language-action models → 3D and spatial-aware VLA
  83. On the Geometry of Music Bandwidth Extension in Latent Spaces of Audio CodecsDiffusion models → Audio, speech and music
  84. MultiCompose: Multi-Concept Personalized Composition with Per-Subject Attribute BindingDiffusion models → Image generation, text-to-image and editing
  85. LiLa-WAM: Lightweight Latent Reasoning World-Action Model for Robotic ManipulationWorld models → Embodied and robot world models
  86. Pattern over Pixels: Measuring Pattern Completion Bias in Multimodal Code GenerationMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  87. PhyAI: Real-Time Physical AI at the Edge, Scalable Rollouts in the CloudDeep reinforcement learning methods → RL training of language and agent models
  88. Keep the Needle, Prune the Haystack: Defect-Preserving Token Pruning for Efficient Zero-Shot Anomaly DetectionEfficient LLM inference and serving → Token pruning and merging for ViTs
  89. TAOT: Topology-Aware Optimal Transport for Dynamic Expert Replica Placement in MoE TrainingMixture-of-experts → Efficient MoE training and inference systems
  90. CausalOPD: First-Wrong-Step Supervision for Distilling Causal Chain ReasoningLLM reasoning → Prompting and chain-of-thought reasoning
  91. Group Perspective Matters: Regulating Debate Relationships Can Mitigate Blind Conformity in Multi-Agent DebateLLM reasoning → Reasoning for agents, planning and code +1
  92. When Teachers Mislead: Spurious-Signal-Aware On-Policy DistillationKnowledge distillation → On-policy and self-distillation for LLMs
  93. Cross-Layer Interaction under Weight-Space Ablation: A Closed-Form Attention Jacobian Bound and a Test on a Real Pretrained ModelMechanistic interpretability → Circuits and mechanistic analysis
  94. A Theory of Conditional Collapse under Low-Rank Weight-Space Ablations: I. The Single-Block Theory and Synthetic ValidationMechanistic interpretability → Circuits and mechanistic analysis
  95. Language-Specialized Multi-Teacher On-Policy Distillation for Multilingual LLM-Based ASRKnowledge distillation → On-policy and self-distillation for LLMs
  96. Formal Verification of Agentic Systems over Operational DataLLM agents and tool use → Software engineering coding agents
  97. Learning Clinical-Trial Strategy: Offline Policy Training for Decision AgentsLLM agents and tool use → Medical and scientific domain agents +1
  98. DiagChain: A Diagnostic Benchmark for Evaluating LLM Agents on Evidence-Grounded Attack Chain ReconstructionLLM agents and tool use → Agent threats, guardrails and governance
  99. GenOS: Compositional Certificates for Semantic Robustness in AI Code GenerationLLM agents and tool use → Software engineering coding agents
  100. From Social Coding to Agentic Coding: Productivity and Relational Reconfiguration in Open-Source CommunitiesLLM agents and tool use → Software engineering coding agents
All 584
  1. SlimVLM: Sensitivity-aware Dynamic Structured Pruning with Adaptive Visual Token Selection for Efficient Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  2. SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of Multi-Task Learning for LLMsLLM reasoning → Reinforcement learning for reasoning
  3. Divide-and-Conquer: Towards Generalizable Amortized Bayesian Inference for the Drift Diffusion ModelDiffusion models → Diffusion foundations and sampling
  4. Unified Visuomotor Targets: Supervising VLAs Beyond Physical ActionsVision-language-action models → Generalist VLA models and benchmarks
  5. Robust General Utility for Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  6. Heterogeneous LLM Serving with General-Purpose Processing-Near-Memory for Retrieval-Based Sparse AttentionEfficient LLM inference and serving → KV cache optimization
  7. Soft Guidance Starts to Outperform CoT Prompting as LLMs ImproveLLM reasoning → Prompting and chain-of-thought reasoning
  8. Hi-TTRL: Regulating Consensus with Hints for Test-Time Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning +1
  9. S3-Diff: Structural Semantic Synergy Diffusion Model for High Fidelity Super Resolution of Pathological ImagesDiffusion models → Medical imaging and segmentation
  10. IRIS: Visual-Semantic Binding for Forgery-Resistant Watermarking of Diffusion ImagesLLM safety and security → Watermarking generated content and models
  11. Cross-Lingual Bias in Large Language Models: A Comparative Analysis of English and SwahiliLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  12. Training Documents Reranker with Search Rubrics for Deep Research AgentLLM agents and tool use → Web, search, and research agents
  13. SkillJack: Persistent Skill Backdoors in Self-Evolving AgentsLLM safety and security → Prompt injection and agent security
  14. When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMsLLM reasoning → Test-time compute and efficient thinking
  15. Hybrid LLM-Augmented Reinforcement Learning Agents for Complex Sequential Decision TasksLLM agents and tool use → Reinforcement learning for LLM agents
  16. Lightweight 3D Object Detection via Mamba-Based Knowledge DistillationState-space sequence models (S4, Mamba) → Point clouds, detection and remote sensing +1
  17. RAG-Stack: Co-Optimizing RAG Serving Performance and QualityRetrieval-augmented generation → RAG pipeline design and evaluation
  18. SkillSentry: Adaptive Honey Worlds for Dynamic Safety Testing of Agent SkillsLLM agents and tool use → Agent threats, guardrails and governance
  19. Continue or Replan? Bernoulli-Continuation Policy Learning for Adaptive Horizon ExecutionVision-language-action models → Reasoning and chain-of-thought in VLA
  20. MT-Web2Code: Benchmarking Coding Agents on Multi-Turn Regional Reconstruction and Localized ModificationMultimodal LLMs / vision-language models → Chart understanding and anomaly detection +1
  21. Hi-Token: Hierarchical Coordinate Tokenization for Generative Visual GroundingMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  22. When Correct Solutions Repeat: Rarity-Aware Credit Redistribution for GRPOLLM reasoning → Reinforcement learning for reasoning
  23. ChartAnno: Benchmarking Multimodal Large Language Models for Chart Annotation GenerationMultimodal LLMs / vision-language models → Chart understanding and anomaly detection
  24. LeanMem: Simple and Efficient Long-Term Memory for LLM AgentsLLM agents and tool use → Agent memory systems
  25. LLaDA MoE v2: Scaling Mixture-of-Experts Diffusion Language ModelsDiffusion models → Discrete and text diffusion +1
  26. Balancing Efficiency and Efficacy: Training-Free Attention-Guided Switching Between Explicit and Latent Thoughts for MLLMsLLM reasoning → Multimodal reasoning +1
  27. Approximate Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  28. OliveGemma: A 3 Billion Visual Language Model for Recognising the Mediterranean & European DietMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  29. When Truth Is Distributed: Misinformation Derails Collective Fact Recovery in LLM-Based Multi-Agent SystemsLLM agents and tool use → Social simulation and multi-agent debate
  30. Towards Improving Sequential Decision-Making in LLM Agents via Experience MemoryLLM agents and tool use → Reinforcement learning for LLM agents
  31. Shorter Reasoning, Earlier Answers? An Evaluation of Reasoning InterfacesLLM reasoning → Test-time compute and efficient thinking
  32. Self-Evolving Coding AgentsLLM agents and tool use → Software engineering coding agents +1
  33. Don't Let Me Ask for It: LLMs Show Deficiencies in Active Multi-Turn Information Acquisition for Abductive InferenceLLM reasoning → Reasoning benchmarks and evaluation
  34. Residual Flow Matching with Dynamic Cross-Interaction for 3D Multi-Person Motion PredictionDiffusion models → Video generation
  35. The Evolutionary Origin of Values: implications for AI alignment, sentience and existential riskLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  36. ArtECulture: Benchmarking Culture-Conditioned Visual Emotion Understanding in Multimodal Large Language ModelsMultimodal LLMs / vision-language models → Multimodal emotion understanding
  37. SPADE: An Input-Adaptive Sparse Attention Engine for Fast Video Diffusion Models InferenceDiffusion models → Video generation
  38. Screenshots or Tools? Eliciting Tool Use and Managing Multimodal Context in Hybrid GUI-MCP Computer-Use AgentsLLM agents and tool use → GUI and mobile agents
  39. Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space BridgingDiffusion models → Diffusion and flow policies for robotics +1
  40. SeaSlides: Semantic Abstraction Layer for Agentic Slide GenerationLLM agents and tool use → Multimodal and embodied agents
  41. Distractor-Aware Truncation: Disentangling Context-Length Effects from Signal Loss in Long-Context LLM BenchmarksRetrieval-augmented generation → Generation and context integration
  42. DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph ReasoningLLM reasoning → Multimodal reasoning +1
  43. The Tell-Tale Trace: Detecting Reasoning Failures in LLMs Using Chain-of-Thought DynamicsLLM reasoning → Prompting and chain-of-thought reasoning
  44. Test-Time Scaling for Safe Text-Guided Image Generation via Intermediate Clean EstimatesLLM reasoning → Diffusion reasoning and test-time scaling +2
  45. TaskPress: Query-Agnostic KV Cache Compression via Task-Guided PruningEfficient LLM inference and serving → KV cache optimization
  46. MoEGen: Mixture-of-Experts for Instance-Adaptive LoRA GenerationMixture-of-experts → Mixture of LoRA experts
  47. Attacking and Defending Multi-Agent Collaborative Filtering Systems Through ConnectivityLLM agents and tool use → Agentic recommender systems
  48. The Ignition Is Real, and It Lives at the Readout: Latent composition, difficulty-clocked ignition, and the interface-constituted commit in a recurrent-depth reasonerLLM reasoning → Test-time compute and efficient thinking
  49. ED-DiT: Physics-Guided Diffusion Pretraining for Transferable Molecular Representations from Electron DensityDiffusion models → Flow matching, time series and science
  50. UniNav: A Unified World-Action Diffusion Model for Visual NavigationWorld models → World models for navigation +1
  51. Relational Priors as Convergence Pressure in LLM-Based Multi-Agent SystemsLLM agents and tool use → Social simulation and multi-agent debate
  52. Structure-Aware Robust Fine-Tuning: Defending Vision-Language-Action Robots Against Physical Attention HijackingVision-language-action models → Safety and adversarial attacks
  53. SAKI: Score-Aware Low-Rank Key Indexing with Random-Matrix Noise Correction for KV RetrievalEfficient LLM inference and serving → KV cache optimization
  54. PFM-HR: Pose Flow Matching for Humanoid RobotsDiffusion models → Diffusion and flow policies for robotics
  55. Agentic Reinforcement Learning with Self-Distilled Reward ShapingLLM agents and tool use → Reinforcement learning for LLM agents
  56. Fail-Fast, Restart-Smart: Early Failure Prediction and Restart for SWE Agentic TasksLLM agents and tool use → Software engineering coding agents
  57. GROW: Group-Relative Advantage-Weighted On-Policy Reinforcement Learning of Autoregressive-Diffusion Text-to-Speech modelDiffusion models → Audio, speech and music +1
  58. The Agent Operating System (AOS): A Reference Operating Architecture for Distributed Agentic SystemsLLM agents and tool use → General LLM agent frameworks and benchmarks
  59. CrossScope: A Role-Asymmetric World Model for Joint Dual-Scope Surgical Video PredictionWorld models → Medical and surgical world models
  60. ICO: Enhancing Semantic-Shift Jailbreaks via Iterative Context OptimizationLLM safety and security → Jailbreaking
  61. DRIFT: Derailing Denoising Trajectories of Flow-Matching VLAs with Adversarial Patch AttackVision-language-action models → Efficient VLA inference and adaptation +1
  62. EduClaw-Bench: A Long-Horizon Benchmark for Pedagogical LLM Agents with Simulated LearnersLLM agents and tool use → Educational agents and math problem solving
  63. Aligning Large Vision-Language Models at Test Time: A Trajectory-Guided Structured Sampling ApproachLLM reasoning → Multimodal reasoning +1
  64. When Refusal Looks Safe: The Refusal-Cue Shortcut in Safety Guard ModelsLLM safety and security → Safety alignment, refusal and guardrails
  65. NeuroMosaic: Anatomically Grounded Multimodal Large Language Modeling for Molecularly Aware Glioma Reasoning from 3D MRI and Clinical NarrativesLLM reasoning → Clinical and biomedical applications
  66. Attribute-based Undetectable Watermarking for Generative AI ModelsLLM safety and security → Watermarking generated content and models
  67. Test-time reasoning effort and unauthorized tool use in language-model agents: a prespecified equivalence studyLLM reasoning → Reasoning for agents, planning and code +1
  68. Adversarial Stress Testing of Role-Playing Language Agents using Multi-Agent EvaluationLLM agents and tool use → Social simulation and multi-agent debate
  69. Evidence-Grounded Multimodal Knowledge Graph Construction for Multi-Lecture Educational ReasoningLLM reasoning → Multimodal reasoning
  70. Accelerating Human-Aware Robot Trajectory Generation via Diffusion and Consistency DistillationDiffusion models → Diffusion and flow policies for robotics
  71. ANCHOR-RE: An Agentic Neuro-Symbolic Framework for Grounded Biomedical Relation ExtractionLLM agents and tool use → Medical and scientific domain agents
  72. Process-Knowledge-Embedded Safe DRL for Real-Time Dispatch of Process Loads in Industrial MicrogridsDeep reinforcement learning methods → RL for energy, networks and operations
  73. Lightweight Chunk Selection for Mobile Retrieval-Augmented GenerationRetrieval-augmented generation → Generation and context integration +1
  74. Verifiable Memory: Learning Unified Memory Management with Local and Global Verifiers for Large Language Model AgentsLLM agents and tool use → Agent memory systems
  75. Rectify Then Diffuse: Disentangling Concepts Before Denoising Trajectory UnfoldsDiffusion models → Robustness, privacy and adversarial aspects
  76. CLEAR: Causal Context-Based Agentic Reasoning for Vulnerability DetectionLLM reasoning → Reasoning for agents, planning and code +1
  77. DP-MemView: A Memory Interface for Attribute-Level Transcript Privacy in Long-Term LLM AgentsLLM agents and tool use → Agent threats, guardrails and governance
  78. Trajectory-Guided Forget-Recover Network for Continual LLM UnlearningLLM safety and security → Machine unlearning
  79. Don't Peek at the Answer: Outcome-Masked Group Relative Policy Optimization for Label-Free RLVRLLM reasoning → Reinforcement learning for reasoning
  80. Simulation-free and finite-time diffusion modelDiffusion models → Diffusion foundations and sampling
  81. Shooting for Contact: Contact-Implicit Multiple Shooting for Dynamic Motion RetargetingDeep reinforcement learning methods → RL for robot locomotion and manipulation
  82. Adaptive Two-Stage Visual Token Pruning for Efficient Inference in Video-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  83. Convex-Hull-Neighborhood Smooth Dual Generalization: Controlling Local Correction Propagation in Offline RLOffline RL and imitation learning from data → Offline RL algorithms
  84. A Hierarchical Approach to Imitation Learning for Manipulation Tasks Requiring Time Varying ForcesDiffusion models → Diffusion and flow policies for robotics +1
  85. Channel-wise Dynamic Knowledge Distillation via Adaptive Sample Generation for Action RecognitionKnowledge distillation → General knowledge distillation methods
  86. What Language Does and What the Evidence Supports: A Functional Role Taxonomy and Evidence Audit of Language Grounding in Embodied AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  87. DHMark: Public-Key Watermarking for LLM-Generated Text via Diffie-Hellman-Guided Rejection SamplingLLM safety and security → Watermarking generated content and models
  88. SMOPD: Multi-Reward Reinforcement Learning via Specialize-and-Merge Online Policy DistillationLLM alignment / RLHF / preference optimisation → Process reward models for reasoning +1
  89. SynEnergy: Anomaly Semantic-Guided Diffusion for Synthetic Energy Data GenerationDiffusion models → Flow matching, time series and science
  90. SUV: Future Scene Understanding as Video Generation for End-to-End DrivingEnd-to-end autonomous driving → Generative simulation for driving
  91. GSTEP: Global Spatio-Temporal Density-Driven Visual Token Pruning for Efficient Video Large Language ModelsEfficient LLM inference and serving → Visual token pruning in multimodal models
  92. DiverseDiT++: Quantifying, Analyzing, and Promoting Representation Diversity in Diffusion TransformersDiffusion models → Diffusion foundations and sampling
  93. PAMT: Process-Aligned Reinforcement Learning for Multi-Domain Machine TranslationDeep reinforcement learning methods → RL training of language and agent models
  94. Getting the Parameters Right: A Difficulty-Graded Benchmark and Probe-Guided Training for LLM Tool CallsLLM agents and tool use → Tool learning and function calling
  95. Revisiting TD Target Aggregation under Uncertainty in Q-LearningDeep reinforcement learning methods → RL theory and sample complexity
  96. CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum LearningLLM reasoning → Reinforcement learning for reasoning
  97. TraceCAD: Trace-Guided Repair for Agentic CAD GenerationLLM agents and tool use → Multimodal and embodied agents
  98. TASQ: Temporal-Adaptive Bit Sparsification Quantization for Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  99. How Should Vision-Language-Action Models Use Proprioceptive State?Vision-language-action models → Generalist VLA models and benchmarks
  100. PI-Mem: Pushing Long-Context Reasoning to 3.6M Tokens with Parallel-Iterative MemoryLLM reasoning → Test-time compute and efficient thinking
  101. CAPE-T2V: Captioner-Anchored Prompt Enhancement toward Two-Sided Conditioning Alignment in Text-to-Video GenerationDiffusion models → Video generation
  102. PLAN: Parallel Liquid-Inspired Approximation Network for Efficient Representation Learning in Flexible Job Shop SchedulingDeep reinforcement learning methods → RL for energy, networks and operations
  103. Beyond Accuracy: A Multidimensional Evaluation of Statistical Reasoning in Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  104. LLM Serving in the Wild: An Empirical Study of Frameworks, Methods, and System DesignsEfficient LLM inference and serving → Serving systems and request scheduling
  105. PACE: Adaptive Budget Allocation for Time-Efficient Embodied PlanningLLM reasoning → Spatial and embodied reasoning
  106. DDSynth-RL: Audio Synthesizer Inversion via Discrete Diffusion with Reinforcement LearningDiffusion models → Audio, speech and music
  107. CastFSR: A Fast--Slow--Reflect Agentic Reasoning Framework for Context-Aware Time Series ForecastingLLM reasoning → Time series reasoning +1
  108. Evaluating Counterfactual Sensitivity to Patient Information in Medication-Safety ReasoningLLM reasoning → Clinical and biomedical applications
  109. DiffImaginE: Imagine to Verify Entity Types with DiffusionDiffusion models → Image generation, text-to-image and editing
  110. UrbanAgent: A Tool-Augmented Agent for Cross-System Urban TasksLLM agents and tool use → Multimodal and embodied agents
  111. Towards Real-world Environment-aware Zero-shot Text-to-speech Synthesis via Disentangled Audio InfillingDiffusion models → Audio, speech and music
  112. Tiny Enough to Break In: Agentic Remote Access Trojans Powered by Small Language ModelsLLM agents and tool use → Agent threats, guardrails and governance
  113. SparSEEty: Extracting Tokens from Sparsity-Exploiting LLM Serving Systems via Deterministic Side ChannelsEfficient LLM inference and serving → Early exit and edge inference
  114. Neurosymbolic Reasoning with Incremental Knowledge for Sample Efficient Hierarchical Reinforcement LearningLLM reasoning → Reinforcement learning for reasoning
  115. EmbodiedVAE: Disentangled Video VAE for Efficient and Controllable Embodied ManipulationWorld models → Embodied and robot world models +1
  116. AcceptMoE: Commitment-Weighted Self-Sizing Verifier Expert Sets for Efficient MoE Speculative DecodingMixture-of-experts → Efficient MoE training and inference systems +1
  117. Qwen-3D: A Generalist 3D Vision-Language Model for Spatial UnderstandingMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  118. TQLite: Multi-LLM Jury Guided Distillation for Real-time MQM Translation Quality EvaluationLLM reasoning → Reasoning benchmarks and evaluation
  119. ConFL: Explainable Concurrent Fault Localization via Hierarchy-Guided LLM ReasoningLLM reasoning → Reasoning for agents, planning and code
  120. EmAvatar: Multimodal Empathetic Response Generation via Conflict Resolution and Expressive Guidance
  121. Large Language Models are Approximate Survival Estimators
  122. CrossScale-GLIO: Topology-Preserving Vision-Language Alignment of MRI and Whole-Slide Histopathology for Diffuse Glioma
  123. BDSLI: A hybrid CNN-Transformer model for Bengali Sign Language interpretation
  124. Fast Matrix Multiplication in fp8: Certified Coefficient Optimization and Measured Error
  125. FuncCode: Compressing Kolmogorov--Arnold Networks in Function Space with Hardware-Aware Quantization
  126. VISPATH: Visual-Intent-Guided Path Reasoning for Multimodal Knowledge Graph Question Answering
  127. COAL-SQL: Coverage-Guided Augmentation and Failure-Driven Learning for Text-to-SQL Post-Training
  128. Counterexamples and Sufficient Conditions: Comments on "Optimally-Transported Generalized Method of Moments"
  129. A Two-Stage Multi-Scale Attention-Based Network for Weakly Supervised Cataract Fundus Image Enhancement
  130. ZetaDial: dialing net charge of protein binders at inference time for therapeutic developability
  131. EXAONE Finance 1.0: An Attention-free Time Series Foundation Model for Financial Time Series
  132. Enabling Proactive Spoken Turns via a Generalized Style-Aware Full-Duplex Framework
  133. Data Driven Equation Discovery for Phase-Ordering Dynamics : From Allen Cahn to the Ising Model
  134. Triangular Fuzzy Rescaling Distance
  135. Active Spiking Perception: The Membrane Potential as a Belief State for Anytime 3D Point Cloud Recognition
  136. TorchDCM: A Unified PyTorch-Native Package for Discrete Choice Modeling
  137. Wrong Operator or Blind Design? A Post-Training Diagnostic for Physics-Informed Coefficient Learning
  138. WIP: LLM Odyssey: A Game-Based Platform for Teaching LLM Engineering Concepts
  139. Network Denoising Revisited: A Ricci-Flow-Inspired Graph Diffusion Method
  140. Information-Theoretic Causal Modelling of Semiconductor Process Dynamics
  141. Phase-Aware CNN for Real-Time 5G/6G Channel Estimation with Hardware-in-the-loop Validation
  142. Variable Selection in the Context of AI Fairness
  143. Diffuse to Compress: Leveraging Diffusion LMs for Lossless Compression
  144. Real-time physics inversion for retrieval of sub-pixel wildfire temperatures from VSWIR imaging spectroscopy
  145. Geometry Beats Estimated Depth: RGB-Only Multi-Camera 3D Tracking under Sim2Real
  146. Open-World Hierarchical Perception: Taxonomic Abstraction over Class-Agnostic Proposals for the Safe Handling of Out-of-Vocabulary Road Objects
  147. Beyond Isotropic Assumptions: Continuity-Constrained Segmentation and GPU Morphometry for Nanoscale GBM Analysis
  148. Multimodal Skin Lesion Classification with Swin Transformer and Clinical Metadata Fusion
  149. A Review of Vision-Based Vehicle Detection for UAV-Based Traffic Monitoring: Experimental Insights and Future Directions
  150. COMEX: A Composition-Grounded Benchmark and Learning Framework for Explainable Aesthetic Image Cropping
  151. Latent-Frequency Validity: Fast Spectral Editing with Screened Video-VAE Transfer Operators
  152. MS-MLB: An Open Machine Learning Benchmark for Blood-Based MS Classification
  153. Binding Biometrics with AI Agent Identifiers for Delegation of Authority
  154. SafeCommit: Certifying When Memory-Grounded Agents May Safely Act
  155. Sample Complexity of Multicalibration for Multilevel Properties
  156. Compass: Continuously Aligning Social Media Feeds via In-Situ Reflections
  157. LLM-based Vulnerability Discovery in Business Process Documentation
  158. Towards End-to-End Multilingual Metaphor Processing: Integrating Detection, Translation, and Evaluation
  159. Geometry-Informed Parameter-Efficient Fine-Tuning of Pre-trained Molecular GNNs for Blood-Brain Barrier Permeability Prediction
  160. PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration
  161. When Is a Conformal Guarantee Fair? Auditing Silent Subgroup Under-Coverage in Alzheimer's Disease Longitudinal Prediction
  162. Dynamical Lie Algebras Cannot Describe Shallow QAOA: Cragged Terrains, Barren Plateaus, and Empirical Hardness Models
  163. SAFECAST: Robust Failure Detection for VLA Policies with Contrast-Set Training and Calibration
  164. Attention-based representations for multi-task computation
  165. Hallucinations on the Board: Tool-Augmented Evaluation of LLM Chess Commentary
  166. Physics-informed reduced-order modelling with equivariant spectral submanifolds
  167. Multimodal Alignment Through Joint Kernel Entropic Gromov--Wasserstein Optimal Transport
  168. Interoceptive Attention as Dynamic Homeostatic Prioritization in a Foraging Agent
  169. Transferable Dual-Stream Representations for Mesoscale-Preserving Sea Surface Temperature Downscaling
  170. Random features for Grassmannian kernel approximation with bounded rank-one projections
  171. OmniVR: Audio-Video Conditional Generation for Archival Footage Restoration
  172. TIDE: A Physically Diverse 3D Turbulence Benchmark Dataset for Advancing Scientific Machine Learning
  173. A Unified Model for Cross-Domain Clone Detection via Model Merging
  174. Attention-Only White-Box Transformer via LeJEPA-Based Self-Supervised Pretraining
  175. PADFormer: Pose-agnostic Anomaly Detection from Sparse View Images
  176. From Non-Convex Self-Concordant Regularization to Scalable Quasi-Newton Training of PINNs
  177. Unscented KalmanNet: Structure-Preserving Deep Learning with Calibrated Posterior Uncertainty under Incomplete Physics and Unknown Noise
  178. From Financial Sentiment Classification to Return Predictability: A QLoRA Benchmark of Large Language Models
  179. SiMDex: Mining Similar Egocentric Videos for Cross-Embodiment Dexterous Manipulation
  180. Patients-like-me: A Variational LM--GNN Framework for Explainable Clinical Prediction
  181. Adversarially Robust Abductive Fusion of Pre-trained Transformer-based Perception Models
  182. Large Language Models for Low-Resource Languages: A Conceptual Framework for an Electronic Explanatory Dictionary of the Tajik Language
  183. Test, then Route: How Language Models Execute In-Context Conditional Rules Across Models and Languages
  184. A Comparative Study of Feature Selection Methods for EHR Diagnosis Codes in Opioid Use Disorder Prediction
  185. TriCLE: Tri-Modal Vision-Language Reasoning for Edge-Deployed Fine-Grained Clustering
  186. TS2TabPFN: Time Series Classification and Extrinsic Regression through Feature Extraction and a Tabular Foundation Model
  187. Understanding Fault Tolerance of Adversarially Robust Pruned Models
  188. Visualizing Graph-to-Answer Mechanism Recovery in Materials-Science Hypothesis Generation
  189. Mind the Cap: Output-Budget Regimes Change the Measured Multilingual Reasoning Gap
  190. MINT: Tensor Decomposition on Stacked Recurrence Matrices for Time Series Data Mining
  191. BrainBench: Benchmarking Large Language Models for Comprehensive EEG Understanding
  192. TRNet: Learning with Topographic Priors for VHR Paddy Rice Mapping
  193. Sublogarithmic Swap Regret in Multiplayer General-Sum Games via Hybrid Regularization
  194. LiNC: Lightweight Noise Correction via Per-Sample Trust and Gaussian Mixture Modeling
  195. Neighborhood-Aware Dual Biomedical Entity Linking
  196. InvFlowFD: Reference-Free and Background-Set-Free Perceptual Music Quality Metric with Flow Matching Inversion
  197. Interpretable Fuzzy Inference for UAV Target Tracking Using Bounding-Box Geometry
  198. Out-Of-The-Loop Multi-Fidelity Bayesian Optimization
  199. GEB-Bench: Abstract Structures Told in Many Voices
  200. LoRetta: A Foundation Model and Extensive Dataset for Global-Scale Remote Sensing Dense Image Matching
  201. Spatiotemporal Graph Transformer for Traffic Intelligence in Edge Computing
  202. FBID: Adaptive Personalized Federated Learning for Robust Out-of-Distribution Attack Detection in IoT Networks
  203. Monte Carlo Tree Search for Table-to-Multimodal Report Generation
  204. Advancing Utility Pole and Sign Detection Through Deep Learning
  205. SJEPA: Learning Elegant Latent Dynamics with Hybrid Symbolic-Neural Predictors
  206. LaPrune: Controllable Differentiable Sparsity at Million Scale
  207. Unifying quantum measurement constructions via a relative-entropy minimum change principle
  208. Modality Agreement- and Conflict-Aware Prototype Hypergraph Learning for Multimodal Intent Understanding
  209. CAMP: A Cycle-Aware Multi-Scale Patch Mixer for Time Series Forecasting
  210. FM4WiFi: Flow Matching for Multi-AP Coordination in Dense Deployments of Beyond Wi-Fi 8 Networks
  211. Statistical learning theory and Occam's razor: Regularization
  212. Recurrent Residual Quantization: A Progressive Multi-Precision Representation for LLMs
  213. Beyond the QBER Threshold: A Temporal QBER Based Machine Learning Framework for Multi Attack Detection in BB84 QKD
  214. The Cost of Binarizing Survival Outcomes in Clinical Prognostic Modeling
  215. Tactus: Open-Vocabulary Object Recognition from Low-Cost Pressure Arrays
  216. SocietyBench: Forecasting Counterfactual Social-World Evolution
  217. WorldCup Arena: Prospective, Leakage-Free Evaluation of Frontier LLMs on a Live Tournament
  218. PAST-Bench: Benchmarking the Foundations of Recursive Self-Improvement in Personal Agents
  219. Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generation
  220. When Attention Goes Blind: Numerical Failure in ALiBi Positional Encodings
  221. Perceptual Anchoring: Prototype-Guided Text Calibration for Training-free Open-Vocabulary Semantic Segmentation
  222. string2string Studio: An Interactive, In-Browser Platform for String-to-String Algorithms
  223. Can Large Language Models Recover Semantic Optimization Opportunities That Compilers Miss?
  224. JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion
  225. UniWorld-Design: From Pixel Generation to Layer-Native Design
  226. Information-Geometric Forward Policy Training in GFlowNets
  227. HalluTruthQA-4K: A Fine-Grained Corpus and Annotation Process for Arabic Hallucination Detection and Truth Verification
  228. A game theory for foundation models shows new paths to rational cooperation through similarity inference
  229. TACT: Taxonomy-Aligned Post-Training for Pedagogically Adaptive English Tutoring
  230. Logic Before Language: Pre-pretraining on Formal Derivations Fosters Skill Acquisition and Compressibility
  231. Robust Low-Tubal-Rank Tensor Completion under Cross-Concentrated Sampling
  232. A Physics-Flavored Transformer Network for Parametrizing Contraction Dynamics of Engineered Skeletal Muscle Tissues
  233. PRISM: Powerful Time Series to Image (TS2I) Representations for Multivariate Anomaly Detection
  234. GeoMAR: Unleashing Geometrically Aligned Features for Masked Autoregressive Blind Face Restoration
  235. The Transformer Revolution, Part 1: Dynamic Processing through Output-Weight Interconnections
  236. Equivariant Music Transformer
  237. Low-Dimensional High-Leverage Subspace Optimization: Beyond Full-Parameter Coupled Training for Neural Network Quantization
  238. When and Where to Look: Adaptive Visual Evidence Scheduling for Efficient Long Video Understanding
  239. Implementing Causal Perception: Competing SCMs and Situated Fairness
  240. Trajectory inference via Acceleration Matching
  241. StreamDAM: Presence-Aware Memory for Real-Time Streaming Video Object Segmentation
  242. When Efficiency Becomes Fragility: Exploiting Dynamic Routing Vulnerabilities in Adaptive UAV Tracking
  243. ANNOTARES: A Dataset for Extracting Logical Structures from German Statutory Texts
  244. NCGR: Noise-Conditional Gated Rectification for Camera Extrinsic Perturbations in BEV 3D Object Detection
  245. CARE-X: Towards Clinically Useful Radiology VLMs with Auxiliary Supervision, Reward-Aligned Learning, and Tool-Augmented Measurement
  246. Confidence Horizons
  247. Omega-S: A Functional Resilience Index for LLM Fine-Tuning
  248. DS@GT-ARC at eRisk 2026 Task 3: Sparse, Semantic, and LLM Reranking for ADHD Symptom Sentences
  249. Operationally Feasible Synthetic Power-Grid Scenarios via Learning the AC-Operable Joint Distribution
  250. GENESIS: Towards Explainable Causal Discovery
  251. ADMITBench: A Safety-Governed Reference Framework for Evaluating the Admissibility of Industrial LLM Advisories
  252. CPrefix: A Combinatorial Tensor Framework for Structured Discrete Color Mappings
  253. CRS-Triage: Confidence- and Reliability-Aware Selective Triage under Incomplete Clinical Evidence
  254. Beyond Representational Similarity: Source-Conditioned Description-Length Gain for Generative Plagiarism Detection and Candidate Source Reranking
  255. Bi-semantic Chemical Embedder for Joint Representation Learning of SMILES and Natural Language
  256. When Calibration Depends on the Scoring Rule: Quantized Biomedical LLM Classification
  257. FedCritic-MIMO: Communication-Efficient Serverless Federated Critic Learning for Massive-MIMO Resource Control in Open and Disaggregated 6G RANs
  258. Sensitivity, Causality, and Repair Dissociate: A Layer-Wise Analysis of Perturbation Robustness and Its Scaling
  259. Resume Means Resume: A Machine-Checked Conformance Contract for Checkpoint, Interrupt, and Resume Semantics in Workflow Persistence Layers
  260. Geo-Embed: Towards Unified Multimodal Embeddings for Urban Understanding
  261. FlowForm: Synergizing Fluid Physics with Topological Consistency for Satellite Flood Synthesis
  262. UNVaMP: Neural Knowledge Tracing with Variational Regularization of Latent Knowledge Dynamics
  263. VIBE: A VAD-Informed Benchmark for Entity-Centered Affective Profiling of Large Language Model Outputs
  264. M-GATE: Multilingual Grammar, Accuracy in Translation, and Efficiency Benchmark for Large Language Models
  265. Evaluating LLMs in Database Scenarios: A Lifecycle Benchmark for Assessing Their Potential in Core Database Tasks
  266. AgenticVAU: Multi-Agent Explore-Verify Reasoning for Video Anomaly Understanding
  267. Computing Actual Causes for Neural Network Predictions under Structured Causal Inputs
  268. GDPevo: Evaluating Agent Self-Evolution on Real Business Tasks
  269. Unsupervised Adversarial Domain Adaptation for Uterine layer Segmentation: From Labeled Cine to Unlabeled Dynamic EPI MRI
  270. LegalPincite: Multi-level Legal Information Retrieval Dataset
  271. Can LLMs Test Terminal User Interfaces?
  272. AI-Based Sound Effect Generation: A Narrative Review of Generative Models Across Input Modalities
  273. MissClick: Execution-Aware Adversarial Attacks on Coordinate Generation in GUI Grounding Models
  274. AgenticECO: An Agentic Framework for ECO on 3D Integrated Circuits
  275. CARE-Bench: Benchmarking Patient-Facing LLM Triage
  276. Constructing Disambiguated Knowledge Bases from Large Language Models at Scale
  277. SAT-Edge-Agent: Hardware-in-the-Loop Edge-Agent Orchestration for Onboard Satellite Intelligence
  278. Towards Reliable and Reproducible Fetal Brain Biometry: A Deep Learning Approach Using MRI
  279. When Outputs Disperse, Does Epistemic Revision Follow? A Black-Box Diagnostic for Machine Collectives
  280. Detecting Hallucinations and Recovering Verified Answers in Arabic Islamic Question Answering
  281. Amortized Interventional Forecasting for Multivariate CIR Processes
  282. Attention is Case-Sensitive
  283. Predicting Deep Neural Network Training Outcomes from Early Training Telemetry
  284. To Describe or Construct Statistical Learning Models Using the Category-theoretical Language
  285. Less Traffic, Better Outcomes: Competition-Aware Request Dispatch in Real-Time Ad Exchanges
  286. When Agents Learn to Be You: Benchmarking Privacy Leakage, Impersonation Risk, and Defenses in Persona Skills
  287. TARL: Transaction-Aware Reliable Ledgers for Executable Memory Management in Long-Term Agents
  288. Learning and Clustering on Temporal Graphs: Principles, Primitives, and Pooling
  289. Accelerating Dynamic Graph Clustering on GPU Architectures with cuGraph
  290. LAEF: A Lead-Agnostic ECG Foundation Model Towards Point-of-Care Diagnostics
  291. LiveEvalBench: Toward Open-World Evaluation for Web Generation
  292. VetScore: Risk-Weighted Fact Verification for Veterinary Long-Form QA with Citations
  293. DiagLoop: A Counterfactual Data Flywheel with Stage-Localized Reinforcement for Diagnostic LLMs
  294. XiDepth: a Lightweight and Efficient Network for Self-supervised Monocular Depth Estimation
  295. Morphology-Aware Implicit Super-Resolution Network for Pathological Images
  296. Shielding for Higher-Order Safety
  297. Taming the Implicit: Dual-Channel Risk-Aware Reinforcement Fine-Tuning for Continual Multimodal Post-Training
  298. How Closely Do LLM Reviews Align with Human Peer Review?
  299. Decoupling Generation and Selection for Budget-Constrained Faithful Summarization
  300. AutoSND: From Execution Evidence to Structural Policies for Automated Network Dismantling Heuristic Discovery
  301. When Do Fewer Visual Tokens Accelerate Multimodal Inference? A Break-Even Study Across Decision Locations and Hardware
  302. Conditionally Identifiable Latent-Environment Modeling for Out-of-Distribution Recommendation
  303. Is Inter-Seed Cross-Play Enough? Evaluating the Robustness of Zero-Shot Coordination Algorithms to Implementation Details
  304. Learning Biomechanically Plausible Human Motion from Sparse Radar Point Clouds
  305. MuEvo: LLM-Driven Evolution of Multi-Heuristic Ensemble
  306. SEER: A Self-Grounded Evidence Interface for Controlled Spatial Relation Classification
  307. POEM: Phase-Aware SO(2) Feature Rotation for Time Series Forecasting Under Periodicity Drift
  308. ConformalShift: Targeted Event Reordering Against Adaptive ECG Monitoring
  309. Unequal Verdicts: Investigating Gender Bias in LLM-Based Fake News Detection
  310. A Security-Oriented Lifecycle Model for Large Language Model Systems
  311. LoopMTP: A looped transformer guided by latent multi-token prediction
  312. Geospatial-Prior Guidance for 3D Semantic Scene Completion
  313. A machine-readable catalogue of the Tsiolkovsky papers (fond 555, Archive of the Russian Academy of Sciences), and a way to measure how well its handwriting can be read
  314. Predictive Enhancement Calibration for Latent Breast MRI Virtual Contrast Enhancement
  315. Rethinking Modality Reliability in Multimodal Sentiment Analysis with Incomplete Observations
  316. FraQ: Efficient Coordinate-Space Recompression for Federated Low-Rank Adaptation
  317. Large language models for partial differential equation workflows
  318. Disentangling Language Modeling and Boundaries
  319. FOUND-AF: Benchmarking ECG Foundation Models for Atrial Fibrillation Detection
  320. Design-Time Optimization of Deep Neural Networks for Intermittent Learning on Microcontrollers
  321. Policy Fragmentation or Institutional Alignment? Institutional Governance of AI in Universities and Business Schools
  322. AI-Assisted Peer Review Across Research Communities: From Reviewer AI Policies to LLM Review Quality
  323. Pin Once, Swap Light: Subspace-Aligned Centroid-Residual Training for Efficient Ultra-LoRA Serving
  324. Looking under the Wrong Lamppost: On the Limitations of Automated Translation Quality Estimation
  325. Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning
  326. Adversarial Fast-Moving Real-World Domains as Test Beds for Benchmarking AI Scientist Capabilities
  327. Enhancing Tabular Learners with Context-Aware Semantic Embeddings
  328. Compass: Degradation-Simulated Reciprocal Learning with Lightweight Needle RWKV for Multimodal Crack Segmentation under Missing Modalities
  329. Test-Time Augmentation for Tabular-to-Image Classifiers under Distribution Shifts
  330. Behaviorally Adaptive Visual Diversion for Inclusive and Resilient Digital Assessment Delivery
  331. Consensus Measures for Unstructured Biomedical Text Annotations
  332. MinerU.Chem: A High-Precision System for Optical Chemical Structure and Reaction Recognition
  333. Dr. AGENTONOMICS: A Didactic Experiment of AGENTONOMICS
  334. Pivot-Centric Trajectory Prediction: Bridging Long Horizons via Dynamical Guidance
  335. AI Forensics Across White-, Grey-, and Black-Box Access: A Process Model and Research Agenda for Post-Incident Investigation of AI Systems
  336. GVCCTurbo: Rate-Compute Quality Scheduling for Codebook Driven Generative Compression
  337. Detecting Pose Estimation Failures via Keypoint Self-Consistency
  338. Reversing Arrows in Large Language Models
  339. How Many Labels Are Enough? ALDA: Active Learning Deployment Advisor for Medical Image Classification
  340. From Multi-Resolution Cells to Gigapixel Whole Slide Images Foundation Model for Computational Pathology
  341. ChronoLens: Measuring Language Change Across Time, Languages, and Linguistic Levels
  342. ConlangBench: Exploring Language Knowledge and Learning in LLMs through Diverse Constructed Languages
  343. Can LLM design high-quality experiments? A Comprehensive and Systematic Benchmark on Autonomous Experimental Design
  344. WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks
  345. FedCARE: A Multi-Objective Personalised Federated Learning Framework for Smart Healthcare
  346. Principles of Robot Autonomy
  347. Beyond Initialization Loss: A Systematic Study of Token Embedding Initialization Strategies for LLM Vocabulary Extension
  348. Leveraging System-Level Observations to Inform Bayesian Learning of Model Parameters for Quantitative Verification
  349. A fully nonlinear structural vector autoregressive model identified via independent innovation analysis
  350. Beyond the Gegenbauer Paradigm: q-Orthogonal Kernels for Machine Learning
  351. Efficient Multilingual Neural Machine Translation via Corpus-Driven Vocabulary Pruning: An English-Arabic Case Study
  352. Adaptive Modality Reliability Diagnosis and Restoration for Robust Multimodal Intent Recognition
  353. Should the Boundary Term Be Learned in Reflected Diffusion? Conormal Trace and Reflection Masking
  354. ToolLIFT: Lifting Tool-Specific Trajectories into Function-Level Graphs for Generalizable Tool Planning
  355. Solver-Aware Decompositions for Programming-by-Example: When Dividing Requires Knowing how to Conquer
  356. Probing Character-level Transformers for the Spanish L-shaped Morphome
  357. DataSpace: Benchmarking Data Agents for Verifiable Analytics over Heterogeneous Workspaces
  358. Predicting Multilingual Classification and Translation Performance of LLMs with Cross-Lingual Alignment -- Is English Enough?
  359. A Low-Cost Hybrid Reservoir Computing Model for Isolated Sign Language Video Recognition
  360. Quality Control Algorithms for Pattern Counting
  361. Dynamically Allocating Evaluation Effort for Model Ranking
  362. FedRings: A Scalable and Topology-Aware Federated Learning Framework for LEO Satellite Constellations
  363. Stop Replacing Noise with Noise: Two-Source Reliability Assessment for Label Correction and Sample Reweighting in Label-Noise Learning
  364. Dual-domain U-Nets with embedded back projection operators for motion-resolved 4D CBCT reconstruction
  365. SLAMFormer-∞: Infinite SLAM Transformer for Unbounded Frontend and Backend Processing
  366. State Propagation Also Satisfies: A Complex-Valued State-Space Model for Deterministic State Tracking
  367. SGFormer: Structure-Guided Transformer for Robust Local Feature Matching
  368. HyperbolicDiffusion: Sharp & Scalable Tiled Generation on the Hyperbolic Plane
  369. Multi-Task Multi-Frame Visual Piano Transcription
  370. AI World Cup 2026: Benchmarking Large Language Models for End-to-End Football Tournament Prediction
  371. Enactive Artificial Intelligence: A Decision-Centric Architecture for Complex Systems
  372. DUD: Decoupled Update Dynamics for Reliable Uncertainty Quantification in Large Language Models
  373. Earth Embeddings
  374. Distilled Roads: Generalisable Road Network Extraction Across Sensors, Resolutions, and Region
  375. Towards Robust Tool Use in Agents via Experience-Driven Adaptive Guidance
  376. MMLongBench-Doc-V2: A Corrected-Annotation, Semantics-Aware Revision of MMLongBench-Doc
  377. SRAP: SVD-Refined Adversarial Perturbations for Imperceptible Face-Swap Defense
  378. TimeRLM: Recursive Language Models Enable Precise Anomaly Localization in Long-Context Time-Series
  379. Benign interpolation and Occam's razor
  380. FreqAdapt: Frequency-Adaptive Processing for RAW Object Detection
  381. LLM-Derived Priors for Thompson Sampling in Cold-Start Comment Recommendation
  382. Shaping Wind-Tunnel Airflow for Unmanned Aerial Vehicles using Online Learning
  383. FACTWASH: Catching AI Rewrites That Wash Hearsay into Fact
  384. DRPFNet: Dual-domain Residual Progressive Fusion Network for RGB-Thermal Object Detection
  385. Tight Worst-Case Bounds for the Smallest Eigenvalue of ReLU NTK Gram Matrices
  386. Conformal risk control for model-form uncertainty in parametric non-intrusive reduced-order models
  387. Can Text-to-Image Models Draw from the Right Frame of Reference?
  388. A Direct Route to Markov Chain Convergence via Asymptotic Equivalence with the Target
  389. When Oracle Conditioning Misleads Deployment: Conditioning-Availability Bias in Echocardiographic Segmentation
  390. Route-Align-Verify for Functional Correctness in Code Generation
  391. Benchmarking the Benchmarks: Testing the Predictive Validity of Commonsense Benchmarks
  392. Traceable Multi-Agent System for Knowledge-Based Forecasting
  393. Long-term Traffic Scene Prediction via Polynomial Representations in Autonomous Driving
  394. AS-FedBridge: Pseudo-Spike Bridge Distillation for Heterogeneous ANN-SNN Federated Learning
  395. PolyLayout: Multi-room Manhattan Layout Estimation
  396. LocAnyMed: Vision-Language Grounding for Multimodal Medical Images
  397. Task-Oriented Candidate-Latent Feedback for Coarse-to-Fine Sensing in Distributed OFDM-ISAC Networks
  398. Evaluating LLM Trade-offs for Enterprise Automation: Lessons from Workflow Generation in a Production Enterprise Platform
  399. Recurrent Contrastive Learning for Imbalanced Medical Image Classification
  400. PLS-Calib: A Partial Least Squares Framework for Event Camera and Odometry Calibration under Ground Motion Constraints
  401. Provably Learning Multi-Head Attention with Queries
  402. AgentPanel: Toward a New Paradigm for Human--AI Collaboration in Exploring Scientific Questions
  403. 3DGSI-Assessor: A Large-Scale Dataset and An LMM-based Method for 3D Gaussian Splatting Image Quality Assessment
  404. Noise-Aware Shrinkage for Differentially Private Zeroth-Order Fine-Tuning of Large Language Models
  405. GUI-Lens: Coarse-to-Fine Cropping for GUI Grounding with General-Purpose VLMs
  406. Efficient Video Dataset Distillation via Cluster-Guided Prototype Blending
  407. Hear to See: Discerning Stateful Listening for Audio-Visual Instance Segmentation
  408. FinVerse: Financial Time-Series Benchmark
  409. NanoMorph-3D: An End-to-End Physics-Driven Unrolling Framework for Nanomaterial Reconstruction
  410. Clarity Contrast and Similarity Selection for Multi-Focus Image Fusion
  411. From Wearable Data to Personalized and Actionable Health Insights
  412. ShielDroid: A Hybrid Approach Integrating Machine and Deep Learning for Android Malware Detection
  413. One Knob to Rule Them All: A Unified Optimal Transport View of Cold-Start Active Learning
  414. CIGTSurv: Clinical Information Guided Tri-modal Survival Prediction with Local Prototype Association and Global Feature Alignment
  415. On the Diversity of Analogy Making in Large Language Models
  416. Open-Linguistic Concept Unified Learning for Cross-Site Interpretable Dermatology Image Diagnosis
  417. Reachability Is Not Realization: Tracing the Sources of LLM Benchmark Gains
  418. Self-Supervised Representation-Guided Generative Dataset Distillation
  419. iFAN: Inference-Aware Learning for Plain Mask Transformers
  420. Bridging Online and Offline Handwriting via Differentiable Physical Rendering
  421. On the Implicit Flatness Bias of Sharpness-Aware Minimization: A Linear Stability Analysis with Quantitative Hyperparameter Bounds
  422. TumorBoard: Evidence-Grounded Multi-Agent Decision Support for Longitudinal Neuro-Oncology
  423. CRIL-U-Net: Compact Ratio-Interaction Learning for Focal Cortical Dysplasia Segmentation from T1w and FLAIR MRI
  424. EditFlow3D: Automated Local Editing of 3D Assets with Trajectory Preservation
  425. Diversity is Not Ambiguity: Toward Accurate and Efficient Ambiguity Detection for Open-Domain QA
  426. Frequency-Decorrelated Temporal Ensembles for EEG--fNIRS Imagined-Handwriting Decoding
  427. Surrogate Substitution Preserves PHI Detectability: A Multi-Detector Equivalence Study
  428. EFX Allocation In (Multi)Hypergraphs
  429. SpreadMark: Robust Image Watermarking via Spread-Spectrum Embedding
  430. Caved or Convinced: Temporal Sampling Gates Claim Deference in Video Large Language Models
  431. Surface Keypoint Representation for Multi-Object and Articulated Human-Object Interaction Generation
  432. UniGD: A Unified Generative-Discriminative Framework for Industrial Retrieval
  433. CROSS: Cascaded Distillation and Dual-Constraint Grounding for Remote Sensing Referring Segmentation
  434. Spatial proteomics guided by H&E-based AI reveals recurrence-risk niches in triple-negative breast cancer
  435. From Routes to Steps: Separating Semantic Progress from Local Execution in Vision-and-Language Navigation
  436. Minimax-Optimal Semiparametric Contextual Dynamic Pricing with Multimodal Revenue
  437. Internalizing Academic Writing Workflows for Introduction Generation via Struct-Aware Policy Learning
  438. Frozen High-Resolution Inference for Cross-City Object Detection: An AI City Challenge 2026 Study
  439. Beyond Average Performance: Dynamic Instance Clustering and Specialized Algorithm Design in LLM-Assisted Evolutionary Search
  440. DigitCode: Symbolic Tokenization of Hand Motion by Anatomical Units
  441. SeCo-SBIR: Semantically Consistent Prompt Learning for Zero-Shot Sketch-Based Image Retrieval
  442. From SQL Errors to Concept Gaps: An AI-Powered Knowledge Graph Analytics Platform for Personalized Feedback
  443. Optimal Liability Design for Medical AI
  444. Non-Destructive Quantification of Urea Adulteration in Bovine Milk Using Transmittance Multispectral Imaging
  445. Double Descent in Gradient Boosting Decision Trees via Split-Candidate Scaling
  446. Multimodal Plant Root Phenotyping with Integration of 3D Skeleton Extraction and Language Analysis
  447. A Unified Resolution-Conditioned Framework for Orthogonal Line-Scanning Image Fusion
  448. FaithIR: Rethinking Infrared Image Super-Resolution from Perceptual Sharpness to Task Relevant Fidelity
  449. HomoEnsNER: Does Language Alignment Outperform Architectural Complexity in Gujarati Named Entity Recognition?
  450. Double Down on Defense: Strengthening Deep Perceptual Hashes against Evasion Attacks without Retraining
  451. FakeI2V-Bench: Benchmarking the Applicability of Image-level Deepfake Detectors for Deepfake Video Detection
  452. VIVID: A Culturally Grounded Benchmark Exposing the Figurative Language Gap in Vietnamese NLP
  453. Scalable Frequency- and Length-Aware Subdocument Deduplication for Large Language Model Pretraining
  454. Automatic Patient-Specific Microwave Ablation Planning Accelerated by a Physics-Guided Deep Learning Model
  455. Causal Inference with Unstructured Outcomes
  456. CorePath: A Breast-Specialized Pathology Foundation Model for Core Needle Biopsy Diagnosis and Risk-Controlled Report Generation
  457. LDU-Bench: Multimodal LLM Evaluation for Lithography Defect Understanding under Layout-Varying Circuit Backgrounds
  458. AI Agent Economics: Can Autonomous Economic Behavior Emerge among AI Agents under Minimal External Conditions?
  459. AI Security Leaderboard: Methodology, Results and Minimal Standard
  460. Activation-Guided Neuron Intervention to Induce Alzheimer's-Related Computational Language Phenotypes in a Large Language Model
  461. Global Graph-Validated Optimization for VLM-based 3D Indoor Scene Generation
  462. SeqLLM: Augmenting LLMs with Behavioral-Sequence Modeling for High-Stakes Decisions at WeChat Pay
  463. RIDGE: Re-Noising with Internal Dynamic Guidance for Image Editing
  464. PDD-RRG: Posterior Diagnostic Decision for Study-level Radiology Report Generation
  465. Learning Music Style for Piano Arrangement Through Cross-Modal Bootstrapping
  466. AIDE: Automated Instruction via Distilled Expertise for Reference-Free Motor Skill Coaching
  467. Exploiting Separability in Multi-Scale Grey-Box Bayesian Optimization
  468. Emulate or Estimate? The Divergent Strengths of Base and Post-Trained Language Models for Opinion Simulation
  469. Language Models Encode the Contextual Truth of Propositions
  470. Standalone DINOv3 for Training-Free Open-Vocabulary Semantic Segmentation in Remote Sensing
  471. LoCA: Forward-Only LLM Tuning after One-Shot Calibration with Local Credit Assignment
  472. Paired Recipient-based Evaluation of Survival Prediction for Deceased Donor Kidney Transplants
  473. Clinically-Grounded Hierarchical Classification for Consistent Chest X-ray Interpretation
  474. A Graph Signal Processing Perspective on Numerical Sequence Representations in LLM In-Context Learning
  475. V-FIND: Revealing the Intrinsic Forgery Knowledge Encoded in Video Forgery Detectors
  476. ProPRL: Property-Aware Prerequisite Relation Learning in Educational Knowledge Graphs
  477. Stochastic Saddle Avoidance Beyond Unit Excitation and Smoothness: A Pathwise Lyapunov-Perron Framework
  478. On the Non-Specificity of Statistical Measures Used in Script Decipherment
  479. On the missing benchmarks layer and a potential solution
  480. Control Allocation in Neural Network Optimization: Joint Affine Control of Weight and Bias Updates
  481. Internalising the Identity Primitive: Cryptographic Individuality for an Autonomous Agent on a Public Blockchain
  482. Temporal Leakage in LLM Backtesting: Measurement, Validation, and Adjusted Scores
  483. Mapping the City Through the Lens of Language Models
  484. HyperFL: Query-Adaptive Representation Learning for Software Fault Localization