mlsanityData to 14 Oct 2026

Papers

New on arXiv

Tue 17 Mar 2026

485 papers

  1. Invisible Orchestrators Suppress Protective Behavior and Dissociate Power-Holders: Safety Risks in Multi-Agent LLM SystemsLLM agents and tool use → Agent threats, guardrails and governance
  2. AgriIR: A Scalable Framework for Domain-Specific Knowledge RetrievalRetrieval-augmented generation → Time series and agricultural RAG
  3. Caption First, VQA Second: Knowledge Density, Not Task Format, Drives Multimodal ScalingMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  4. The Consciousness Cluster: Emergent preferences of Models that Claim to be ConsciousLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  5. Medical Reasoning with Large Language Models: A Survey and MR-BenchLLM reasoning → Clinical and biomedical applications
  6. WAND: Windowed Attention and Knowledge Distillation for Efficient Autoregressive Text-to-Speech ModelsKnowledge distillation → Speech and audio distillation
  7. Re-Mask and Redirect: Exploiting Denoising Irreversibility in Diffusion Language ModelsDiffusion models → Discrete and text diffusion +2
  8. Agentic AI for Human Resources: LLM-Driven Candidate AssessmentLLM agents and tool use → General LLM agent frameworks and benchmarks
  9. PI-Mamba: Linear-Time Protein Backbone Generation via Spectrally Initialized Flow MatchingState-space sequence models (S4, Mamba) → Core SSM architectures for language
  10. From Heard to Lived Opinions: Simulating Opinion Dynamics with Grounded LLM Agents in Economic EnvironmentsLLM agents and tool use → Social simulation and multi-agent debate
  11. Mitigating Premature Discretization with Progressive Quantization for Robust Vector TokenizationMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  12. OpenResearcher: A Fully Open Pipeline for Long-Horizon Deep Research Trajectory SynthesisLLM agents and tool use → Web, search, and research agents
  13. Understanding Pruning Regimes in Vision-Language Models Through Domain-Aware Layer SelectionMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  14. DEAF: A Benchmark for Diagnostic Evaluation of Acoustic Faithfulness in Audio Language ModelsMultimodal LLMs / vision-language models → Video understanding with MLLMs
  15. TharuChat: Bootstrapping Large Language Models for a Low-Resource Language via Synthetic Data and Human ValidationSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  16. Alignment Makes Language Models Normative, Not DescriptiveLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  17. ML-AutoResearch: Training Machine Learning Research Agents with Automatically Generated EnvironmentsLLM agents and tool use → Web, search, and research agents
  18. CODMAS: A Dialectic Multi-Agent Collaborative Framework for Structured RTL OptimizationLLM agents and tool use → Software engineering coding agents
  19. Catching rationalization in the act: detecting motivated reasoning before and after CoT via activation probingLLM reasoning → Prompting and chain-of-thought reasoning
  20. MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the WildLLM agents and tool use → Agent skill learning and evolution
  21. Towards Unsupervised Adversarial Document Detection in Retrieval Augmented Generation SystemsRetrieval-augmented generation → Privacy and security of RAG
  22. Detecting Data Poisoning in Code Generation LLMs via Black-Box, Vulnerability-Oriented ScanningLLM safety and security → Jailbreaking
  23. Generalist Multimodal LLMs Gain Biometric Expertise via Human SalienceMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  24. How Clued up are LLMs? Evaluating Multi-Step Deductive Reasoning in a Text-Based Game EnvironmentLLM reasoning → Reasoning for agents, planning and code +1
  25. Shielded Reinforcement Learning Under Dynamic Temporal Logic ConstraintsDeep reinforcement learning methods → Safe and constrained RL
  26. Intent Formalization: A Grand Challenge for Reliable Coding in the Age of AI AgentsLLM agents and tool use → Software engineering coding agents
  27. MosaicMem: Hybrid Spatial Memory for Controllable Video World ModelsWorld models → Video-generation world models and simulators +1
  28. Hidden Clones: Exposing and Fixing Family Bias in Vision-Language Model EnsemblesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  29. LLM-Powered Flood Depth Estimation from Social Media Imagery: A Vision-Language Model Framework with Mechanistic Interpretability for Transportation ResilienceMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection
  30. When the Specification Emerges: Benchmarking Faithfulness Loss in Long-Horizon Coding AgentsLLM agents and tool use → Software engineering coding agents
  31. Knowledge Localization in Mixture-of-Experts LLMs Using Cross-Lingual InconsistencyMixture-of-experts → MoE large language models
  32. SLowRL: Safe Low-Rank Adaptation Reinforcement Learning for LocomotionDeep reinforcement learning methods → RL for robot locomotion and manipulation
  33. ACE-LoRA: Graph-Attentive Context Enhancement for Parameter-Efficient Adaptation of Medical Vision-Language ModelsMultimodal LLMs / vision-language models → Medical vision-language models
  34. CircuitBuilder: From Polynomials to Circuits via Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  35. Large Reasoning Models Struggle to Transfer Parametric Knowledge Across ScriptsLLM reasoning → Reasoning benchmarks and evaluation
  36. PaAgent: Portrait-Aware Image Restoration Agent via Subjective-Objective Reinforcement LearningMultimodal LLMs / vision-language models → Image editing and quality assessment +2
  37. Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video ModelsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  38. Do Understanding and Generation Fight? A Diagnostic Study of DPO for Unified Multimodal ModelsLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  39. OpenQlaw: An Agentic AI Assistant for Analysis of 2D Quantum MaterialsLLM reasoning → Clinical and biomedical applications +1
  40. HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language ReasoningLLM reasoning → Multimodal reasoning +2
  41. LLM NL2SQL Robustness: Surface Noise vs. Linguistic Variation in Traditional and Agentic SettingsLLM agents and tool use → Web, search, and research agents
  42. Empirical Recipes for Efficient and Compact Vision-Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  43. Rewarding DINO: Predicting Dense Rewards with Vision Foundation ModelsLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  44. DeepStage: Learning Autonomous Defense Policies Against Multi-Stage APT CampaignsDeep reinforcement learning methods → Adversarial robustness and RL in finance
  45. MSRAMIE: Multimodal Structured Reasoning Agent for Multi-instruction Image EditingLLM reasoning → Multimodal reasoning +1
  46. Adversarial attacks against Modern Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness
  47. PhysQuantAgent: An Inference Pipeline of Mass Estimation for Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  48. WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric RepresentationWorld models → Video-generation world models and simulators +1
  49. Demystifying Video ReasoningLLM reasoning → Multimodal reasoning +1
  50. Efficient Reasoning on the EdgeLLM reasoning → Test-time compute and efficient thinking +2
  51. Chronos: Temporal-Aware Conversational Agents with Structured Event Retrieval for Long-Term MemoryLLM agents and tool use → Agent memory systems
  52. DreamPlan: Efficient Reinforcement Fine-Tuning of Vision-Language Planners via Video World ModelsWorld models → Embodied and robot world models +2
  53. Stochastic Resetting Accelerates Reinforcement Learning Beyond Random SearchDeep reinforcement learning methods → Deep RL algorithms and representations
  54. Learning to Present: Inverse Specification Rewards for Agentic Slide GenerationLLM agents and tool use → Multimodal and embodied agents
  55. Prompt Programming for Cultural Bias and Alignment of Large Language ModelsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment
  56. Deep Reinforcement Learning-driven Edge Offloading for Latency-constrained XR pipelinesDeep reinforcement learning methods → RL for energy, networks and operations
  57. Is Conformal Factuality for RAG-based LLMs Robust? Novel Metrics and Systematic InsightsRetrieval-augmented generation → RAG robustness and adaptive retrieval
  58. Adaptive Moments are Surprisingly Effective for Plug-and-Play Diffusion SamplingDiffusion models → Inverse problems and image restoration
  59. V-Co: A Closer Look at Visual Representation Alignment via Co-DenoisingDiffusion models → Diffusion foundations and sampling
  60. IOSVLM: A 3D Vision-Language Model for Unified Dental Diagnosis from Intraoral ScansMultimodal LLMs / vision-language models → Medical vision-language models
  61. Anticipatory Planning for Multimodal AI AgentsDeep reinforcement learning methods → RL training of language and agent models
  62. Semi-supervised Latent Disentangled Diffusion Model for Textile Pattern GenerationDiffusion models → 3D, point cloud and scene generation
  63. Nonstandard Errors in AI AgentsLLM agents and tool use → Social simulation and multi-agent debate
  64. SpecMoE: Spectral Mixture-of-Experts Foundation Model for Cross-Species EEG DecodingMixture-of-experts → Medical and biomedical MoE
  65. Retrieving Counterfactuals Improves Visual In-Context LearningLLM reasoning → Multimodal reasoning +1
  66. World Reconstruction From Inconsistent ViewsDiffusion models → 3D, point cloud and scene generation
  67. Differential Harm Propensity in Personalized LLM Agents: The Curious Case of Mental Health DisclosureLLM agents and tool use → Agent threats, guardrails and governance +1
  68. IQuest-Coder-V1 Technical ReportLLM agents and tool use → Software engineering coding agents
  69. The Cost of Reasoning: Chain-of-Thought Induces Overconfidence in Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  70. Predictive Statistics Shape Emergent World Representations of Grid WalkersWorld models → Latent predictive world models
  71. HMAR: Hierarchical Modality-Aware Expert and Dynamic Routing Medical Image Retrieval ArchitectureMixture-of-experts → Medical and biomedical MoE
  72. When Should a Robot Think? Resource-Aware Reasoning via Reinforcement Learning for Embodied Robotic Decision-MakingLLM reasoning → Spatial and embodied reasoning
  73. Kinema4D: Kinematic 4D World Modeling for Spatiotemporal Embodied SimulationWorld models → Embodied and robot world models
  74. Fast-WAM: Do World Action Models Need Test-time Future Imagination?World models → Embodied and robot world models +1
  75. Kestrel: Grounding Self-Refinement for LVLM Hallucination MitigationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  76. Self-Aware Markov Models for Discrete ReasoningDiffusion models → Discrete and text diffusion
  77. Omanic: Towards Step-wise Evaluation of Multi-hop Reasoning in Large Language ModelsLLM reasoning → Knowledge- and tool-augmented reasoning
  78. HeBA: Heterogeneous Bottleneck Adapters for Robust Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  79. What if Pinocchio Were a Reinforcement Learning Agent: A Normative End-to-End PipelineDeep reinforcement learning methods → RL training of language and agent models
  80. Mixture of Style Experts for Diverse Image StylizationMixture-of-experts → Vision mixture-of-experts
  81. Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM SycophancyLLM reasoning → Prompting and chain-of-thought reasoning
  82. MLLM-based Textual Explanations for Face ComparisonMultimodal LLMs / vision-language models → Social bias and fairness in VLMs
  83. Domain Mixture Design via Log-Likelihood Differences for Aligning Language Models with a Target ModelLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  84. Rationale Matters: Learning Transferable Rubrics via Proxy-Guided Critique for VLM Reward ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  85. Runtime Governance for AI Agents: Policies on PathsLLM agents and tool use → Agent threats, guardrails and governance
  86. V-DyKnow: A Dynamic Benchmark for Time-Sensitive Knowledge in Vision Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  87. When and Why Does Unsupervised RL Succeed in Mathematical Reasoning? A Manifold Envelopment PerspectiveLLM reasoning → Reinforcement learning for reasoning
  88. REFORGE: Multi-modal Attacks Reveal Vulnerable Concept Unlearning in Image Generation ModelsLLM safety and security → Vision-language and text-to-image safety
  89. VideoMatGen: PBR Materials through Joint Generative ModelingDiffusion models → 3D, point cloud and scene generation
  90. Segmentation-Based Attention Entropy: Detecting and Mitigating Object Hallucinations in Large Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  91. EmoLLM: Appraisal-Grounded Cognitive-Emotional Co-Reasoning in Large Language ModelsLLM reasoning → Audio-language model reasoning
  92. FleetOpt: Analytical Fleet Provisioning for LLM Inference with Compress-and-Route as Implementation MechanismEfficient LLM inference and serving → Serving systems and request scheduling
  93. VIEW2SPACE: Studying Multi-View Visual Reasoning from Sparse ObservationsLLM reasoning → Multimodal reasoning
  94. From the Inside Out: Progressive Distribution Refinement for Confidence CalibrationLLM alignment / RLHF / preference optimisation → Reward hacking and misspecification +1
  95. AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue AgentsLLM agents and tool use → Agent memory systems
  96. Unlearning for One-Step Generative Models via Unbalanced Optimal TransportLLM safety and security → Vision-language and text-to-image safety
  97. Breaking the Chain: A Causal Analysis of LLM Faithfulness to Intermediate StructuresLLM reasoning → Prompting and chain-of-thought reasoning
  98. Follow the Clues, Frame the Truth: Hybrid-evidential Deductive Reasoning in Open-Vocabulary Multimodal Emotion RecognitionLLM reasoning → Audio-language model reasoning
  99. GAP-MLLM: Geometry-Aligned Pre-training for Activating 3D Spatial Perception in Multimodal Large Language ModelsLLM reasoning → Spatial and embodied reasoning +1
  100. Evo-Retriever: LLM-Guided Curriculum Evolution with Viewpoint-Pathway Collaboration for Multimodal Document RetrievalMultimodal LLMs / vision-language models → Document understanding and multimodal RAG
All 485
  1. RetailBench: Evaluating Long-Horizon Autonomous Decision-Making and Strategy Stability of LLM Agents in Realistic Retail EnvironmentsLLM agents and tool use → Social simulation and multi-agent debate
  2. TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown SchemasDeep reinforcement learning methods → RL training of language and agent models
  3. Visual Distraction Undermines Moral Reasoning in Vision-Language ModelsLLM reasoning → Reasoning benchmarks and evaluation +1
  4. Fast-HaMeR: Boosting Hand Mesh Reconstruction using Knowledge DistillationKnowledge distillation → Detection and dense prediction distillation
  5. Capability-Guided Compression: Toward Interpretability-Aware Budget Allocation for Large Language ModelsMechanistic interpretability → SAE features and their applications
  6. CD-FKD: Cross-Domain Feature Knowledge Distillation for Robust Single-Domain Generalization in Object DetectionKnowledge distillation → Detection and dense prediction distillation
  7. SF-Mamba: Rethinking State Space Model for VisionState-space sequence models (S4, Mamba) → Vision Mamba backbones
  8. HGP-Mamba: Integrating Histology and Generated Protein Features for Mamba-based Multimodal Survival Risk PredictionState-space sequence models (S4, Mamba) → Mamba for medical image analysis
  9. Via Negativa for AI Alignment: Why Negative Constraints Are Structurally Superior to Positive PreferencesLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  10. IndexRAG: Bridging Facts for Cross-Document Reasoning at Index TimeLLM reasoning → Knowledge- and tool-augmented reasoning +1
  11. RECOVER: Robust Entity Correction via agentic Orchestration of hypothesis Variants for Evidence-based RecoveryLLM agents and tool use → General LLM agent frameworks and benchmarks
  12. PlotTwist: A Creative Plot Generation Framework with Small Language ModelsLLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment +1
  13. Deep Reinforcement Learning-Assisted Automated Operator Portfolio for Constrained Multi-objective OptimizationDeep reinforcement learning methods → RL for games and combinatorial optimization
  14. Robust Physics-Guided Diffusion for Full-Waveform InversionDiffusion models → Flow matching, time series and science
  15. DermaFlux: Synthetic Skin Lesion Generation with Rectified Flows for Enhanced Image ClassificationDiffusion models → Medical imaging and segmentation
  16. Controlling Fish Schools via Reinforcement Learning of Virtual Fish MovementDeep reinforcement learning methods → RL for robot navigation and UAV control
  17. Encoding Predictability and Legibility for Style-Conditioned Diffusion PolicyDiffusion models → Diffusion and flow policies for robotics
  18. DynamicGate MLP Conditional Computation via Learned Structural Dropout and Input Dependent Gating for Functional PlasticityMixture-of-experts → MoE theory and gating functions
  19. D3-RSMDE: 40× Faster and High-Fidelity Remote Sensing Monocular Depth EstimationDiffusion models → 3D, point cloud and scene generation
  20. Iris: Bringing Real-World Priors into Diffusion Model for Monocular Depth EstimationDiffusion models → 3D, point cloud and scene generation
  21. Behavioral Steering in a 35B MoE Language Model via SAE-Decoded Probe Vectors: One Agency Axis, Not Five TraitsLLM agents and tool use → General LLM agent frameworks and benchmarks +2
  22. Decoding the Critique Mechanism in Large Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  23. DriveFix: Spatio-Temporally Coherent Driving Scene RestorationDiffusion models → Diffusion and flow policies for robotics +1
  24. VisBrowse-Bench: Benchmarking Visual-Native Search for Multimodal Browsing AgentsMultimodal LLMs / vision-language models → Document understanding and multimodal RAG +1
  25. Locate-then-Sparsify: Attribution Guided Sparse Strategy for Visual Hallucination MitigationMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  26. Agile Interception of a Flying Target using Competitive Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  27. VIGOR: VIdeo Geometry-Oriented Reward for Temporal Generative AlignmentDiffusion models → 3D, point cloud and scene generation +1
  28. Adaptive Theory of Mind for LLM-based Multi-Agent CoordinationLLM agents and tool use → General LLM agent frameworks and benchmarks
  29. AW-MoE: All-Weather Mixture of Experts for Robust Multi-Modal 3D Object DetectionMixture-of-experts → Vision mixture-of-experts
  30. When Thinking Hurts: Mitigating Visual Forgetting in Video Reasoning via Frame RepetitionLLM reasoning → Multimodal reasoning +1
  31. Grounding the Score: Explicit Visual Premise Verification for Reliable Vision-Language Process Reward ModelsLLM reasoning → Multimodal reasoning +1
  32. Visual Prompt Discovery via Semantic ExplorationLLM reasoning → Multimodal reasoning
  33. Dual Consensus: Escaping from Spurious Majority in Unsupervised RLVR via Two-Stage Vote MechanismLLM reasoning → Reinforcement learning for reasoning
  34. SpecSteer: Synergizing Local Context and Global Reasoning for Efficient Personalized GenerationLLM reasoning → Test-time compute and efficient thinking
  35. Enabling Dynamic Tracking in Vision-Language-Action Models via Time-Discrete and Time-Continuous Velocity FeedforwardVision-language-action models → Efficient VLA inference and adaptation
  36. CoMAI: A Collaborative Multi-Agent Framework for Robust and Equitable Interview EvaluationLLM agents and tool use → General LLM agent frameworks and benchmarks
  37. Leveling3D: Leveling Up 3D Reconstruction with Feed-Forward 3D Gaussian Splatting and Geometry-Aware GenerationDiffusion models → 3D, point cloud and scene generation
  38. MOSAIC: Composable Safety Alignment with Modular Control TokensLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  39. Offline Exploration-Aware Fine-Tuning for Long-Chain Mathematical ReasoningLLM reasoning → Reinforcement learning for reasoning
  40. PanguMotion: Continuous Driving Motion Forecasting with Pangu TransformersEnd-to-end autonomous driving → Generative simulation for driving
  41. Structured Semantic Cloaking for Jailbreak Attacks on Large Language ModelsLLM safety and security → Jailbreaking
  42. Reliable Reasoning in SVG-LLMs via Multi-Task Multi-Reward Reinforcement LearningLLM reasoning → Multimodal reasoning +1
  43. ECHO: Edge-Cloud Humanoid Orchestration for Language-to-Motion ControlDiffusion models → Diffusion and flow policies for robotics
  44. KidsNanny: A Two-Stage Multimodal Content Moderation Pipeline Integrating Visual Classification, Object Detection, OCR, and Contextual Reasoning for Child SafetyLLM reasoning → Reasoning for agents, planning and code
  45. Task-Specified Compliance Bounds for Humanoids via Lipschitz-Constrained PoliciesDeep reinforcement learning methods → RL for robot locomotion and manipulation
  46. 360deg Image Perception with MLLMs: A Comprehensive Benchmark and a Training-Free MethodMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  47. The Finetuner's Fallacy: When to Pretrain with Your Finetuning DataWorld models → World models for language agents
  48. Open-Source Reproduction and Explainability Analysis of Corrective Retrieval Augmented GenerationRetrieval-augmented generation → RAG robustness and adaptive retrieval
  49. SQL-ASTRA: Alleviating Sparse Feedback in Agentic SQL via Column-Set Matching and Trajectory AggregationLLM agents and tool use → Reinforcement learning for LLM agents
  50. Execution-Grounded Credit Assignment for GRPO in Code GenerationLLM reasoning → Reinforcement learning for reasoning
  51. DyJR: Preserving Diversity in Reinforcement Learning with Verifiable Rewards via Dynamic Jensen-Shannon ReplayLLM reasoning → Reinforcement learning for reasoning
  52. HIPO: Instruction Hierarchy via Constrained Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  53. EFF-Grasp: Energy-Field Flow Matching for Physics-Aware Dexterous Grasp GenerationDiffusion models → Diffusion and flow policies for robotics
  54. NeuronSpark: A Spiking Neural Network Language Model with Selective State Space DynamicsState-space sequence models (S4, Mamba) → Core SSM architectures for language
  55. When Generative Augmentation Hurts: A Benchmark Study of GAN and Diffusion Models for Bias Correction in AI Classification SystemsDiffusion models → Image generation, text-to-image and editing
  56. Social Simulacra in the Wild: AI Agent Communities on MoltbookLLM agents and tool use → Social simulation and multi-agent debate
  57. SWE-QA-Pro: A Representative Benchmark and Scalable Training Recipe for Repository-Level Code UnderstandingLLM agents and tool use → Software engineering coding agents
  58. PathGLS: Evaluating Pathology Vision-Language Models without Ground Truth through Multi-Dimensional ConsistencyMultimodal LLMs / vision-language models → Medical vision-language models
  59. ASDA: Automated Skill Distillation and Adaptation for Financial ReasoningLLM reasoning → Reasoning for agents, planning and code
  60. VIGIL: Towards Edge-Extended Agentic AI for Enterprise IT SupportLLM agents and tool use → General LLM agent frameworks and benchmarks
  61. Efficient LLM Serving for Agentic Workflows: A Data Systems PerspectiveLLM agents and tool use → Software engineering coding agents +1
  62. Diffusion Models for Joint Audio-Video GenerationDiffusion models → Audio, speech and music
  63. Parallel In-context Learning for Large Vision Language ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency
  64. Towards the Vision-Sound-Language-Action Paradigm: The HEAR Framework for Sound-Centric ManipulationVision-language-action models → Reasoning and chain-of-thought in VLA
  65. MDM-Prime-v2: Binary Encoding and Index Shuffling Enable Scaling of Diffusion Language ModelsDiffusion models → Discrete and text diffusion
  66. Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language ModelsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  67. ARISE: Agent Reasoning with Intrinsic Skill Evolution in Hierarchical Reinforcement LearningLLM reasoning → Reasoning for agents, planning and code +1
  68. Toward Reliable Scientific Visualization Pipeline Construction with Structure-Aware Retrieval-Augmented LLMsRetrieval-augmented generation → RAG for code
  69. The Era of End-to-End Autonomy: Transitioning from Rule-Based Driving to Large Driving ModelsEnd-to-end autonomous driving → End-to-end system architecture
  70. Enhancing Linguistic Generalization of VLA: Fine-Tuning OpenVLA via Synthetic Instruction AugmentationSynthetic data and self-improvement for LLMs → Self-evolving LLM agents
  71. Collaborative Temporal Feature Generation via Critic-Free Reinforcement Learning for Cross-User Sensor-Based Activity RecognitionDeep reinforcement learning methods → RL for robot locomotion and manipulation
  72. Geometry-Aligned LLM Fine-Tuning for Sequential Narrow-Opening PlanningLLM reasoning → Spatial and embodied reasoning
  73. Interpretable Context Methodology: Folder Structure as Agentic ArchitectureLLM agents and tool use → Software engineering coding agents
  74. Operationalising Artificial Intelligence Bills of Materials (AIBOMs) for Verifiable AI Provenance and Lifecycle Assurance
  75. A Multi-Model Approach to English-Bangla Sentiment Classification of Government Mobile Banking App Reviews
  76. Text-as-Signal: Quantitative Semantic Scoring with Embeddings, Logprobs, and Noise Reduction
  77. WorkRB: A Community-Driven Evaluation Framework for AI in the Work Domain
  78. Form Without Function: Agent Social Behavior in the Moltbook Network
  79. Exploring Urban Land Use Patterns by Pattern Mining and Unsupervised Learning
  80. Assessing the Pedagogical Readiness of Large Language Models as AI Tutors in Low-Resource Contexts: A Case Study of Nepal's K-10 Curriculum
  81. Neural networks for Text-to-Speech evaluation
  82. A Representation-Level Assessment of Bias Mitigation in Foundation Models
  83. Uncertainty Estimation for the Open-Set Text Classification systems
  84. EMA Is Not All You Need: Mapping the Boundary Between Structure and Content in Recurrent Context
  85. Blending Human and LLM Expertise to Detect Hallucinations and Omissions in Mental Health Chatbot Responses
  86. When GPUs Fail Quietly: Observability-Aware Early Warning Beyond Numeric Telemetry
  87. Byzantine-Robust and Communication-Efficient Distributed Training: Compressive and Cyclic Gradient Coding
  88. On the Carbon Footprint of Economic Research in the Age of Generative AI
  89. The Cognitive Divergence: AI Context Windows, Human Attention Decline, and the Delegation Feedback Loop
  90. Deep Learning Multi-Horizon Irradiance Nowcasting: A Comparative Evaluation of Three Methods for Leveraging Sky Images
  91. EMPD: An Event-based Multimodal Physiological Dataset for Remote Pulse Wave Detection
  92. Sample Transform Cost-Based Training-Free Hallucination Detector for Large Language Models
  93. Research on Individual Trait Clustering and Development Pathway Adaptation Based on the K-means Algorithm
  94. Latent Semantic Manifolds in Large Language Models
  95. Scaling Attention via Feature Sparsity
  96. Between the Layers Lies the Truth: Uncertainty Estimation in LLMs Using Intra-Layer Local Information Scores
  97. Mix-and-Match Pruning: Globally Guided Layer-Wise Sparsification of DNNs
  98. Learning Communication Between Heterogeneous Agents in Multi-Agent Reinforcement Learning for Autonomous Cyber Defence
  99. Me, Myself, and π : Evaluating and Explaining LLM Introspection
  100. Solomonoff induction
  101. Efficient AI-Driven Multi-Section Whole Slide Image Analysis for Biochemical Recurrence Prediction in Prostate Cancer
  102. Target Concept Tuning Improves Extreme Weather Forecasting
  103. A General Deep Learning Framework for Wireless Resource Allocation under Discrete Constraints
  104. Prompt-tuning with Attribute Guidance for Low-resource Entity Matching
  105. An FPGA-Based SoC Architecture with a RISC-V Controller for Energy-Efficient Temporal-Coding Spiking Neural Networks
  106. Auditing the Auditors: Does Community-based Moderation Get It Right?
  107. NanoZK: Privacy-Preserving Verifiable Inference for Large Language Models via Layerwise Zero-Knowledge Proofs
  108. SA-CycleGAN-2.5D: Self-Attention CycleGAN with Tri-Planar Context for Multi-Site MRI Harmonization
  109. Anonymous-by-Construction: An LLM-Driven Framework for Privacy-Preserving Text
  110. Adaptive Contracts for Cost-Effective AI Delegation
  111. A scalable neural bundle map for multiphysics prediction in lithium-ion battery across varying configurations
  112. SYMDIREC: A Neuro-Symbolic Divide-Retrieve-Conquer Framework for Enhanced RTL Synthesis and Summarization
  113. OPERA: Online Data Pruning for Efficient Retrieval Model Adaptation
  114. Structural Abstraction as an Inductive Bias for Non-Stationary Language Model Training
  115. Self-Conditioned Denoising for Atomistic Representation Learning
  116. Tabular LLMs for Interpretable Few-Shot Alzheimer's Disease Prediction with Multimodal Biomedical Data
  117. Visual Product Search Benchmark
  118. Patient4D: Temporally Consistent Patient Body Mesh Recovery from Monocular Operating Room Video
  119. Domain-informed explainable boosting machines for trustworthy lateral spread predictions
  120. Noise-Response Calibration: A Causal Intervention Protocol for LLM-Judges
  121. Exploiting the English Grammar Profile for L2 grammatical analysis with LLMs
  122. Beyond OAuth: Task-Scoped Authorization for AI Agents via Natural Language Slices
  123. SLAM Adversarial Lab: An Extensible Framework for Visual SLAM Robustness Evaluation under Adverse Conditions
  124. GazeOnce360: Fisheye-Based 360deg Multi-Person Gaze Estimation with Global-Local Feature Fusion
  125. Self-Regularized Learning Methods
  126. BEV-SLD: Self-Supervised Scene Landmark Detection for Global Localization with LiDAR Bird's-Eye View Images
  127. A Lensless Polarization Camera
  128. Shallow Representation of Option Implied Information
  129. Personalized Fall Detection by Balancing Data with Selective Feedback Using Contrastive Learning
  130. Multilingual Reference Need Assessment System for Wikipedia
  131. REAL: Regression-Aware Reinforcement Learning for LLM-as-a-Judge
  132. Contextual Preference Distribution Learning
  133. SMAL-pets: SMAL Based Avatars of Pets from Single Image
  134. Topology-Preserving Deep Joint Source-Channel Coding for Semantic Communication
  135. Security Assessment and Mitigation Strategies for Large Language Models: A Comprehensive Defensive Framework
  136. Cascade-Aware Multi-Agent Routing: Spatio-Temporal Sidecars and Geometry-Switching
  137. Pixel-level Counterfactual Contrastive Learning for Medical Image Segmentation
  138. SENSE: Efficient EEG-to-Text via Privacy-Preserving Semantic Retrieval
  139. An End-to-End Framework for Functionality-Embedded Provenance Graph Construction and Threat Interpretation
  140. Accurate Shift Invariant Convolutional Neural Networks Using Gaussian-Hermite Moments
  141. Evaluating LLM-Simulated Conversations in Modeling Inconsistent and Uncollaborative Behaviors in Human Social Interaction
  142. Ensemble Self-Training for Unsupervised Machine Translation
  143. PRISM: Demystifying Retention and Interaction in Mid-Training
  144. Edge-Efficient Two-Stream Multimodal Architecture for Non-Intrusive Bathroom Fall Detection
  145. TrackDeform3D: Markerless and Autonomous 3D Keypoint Tracking and Dataset Collection for Deformable Objects
  146. Evaluating Ill-Defined Tasks in Large Language Models
  147. Transformers are Bayesian Networks
  148. Optimization-Embedded Active Multi-Fidelity Surrogate Learning for Multi-Condition Airfoil Shape Optimization
  149. DesertFormer: Transformer-Based Semantic Segmentation for Off-Road Desert Terrain Classification in Autonomous Navigation Systems
  150. Early Quantization Shrinks Codebook: A Simple Fix for Diversity-Preserving Tokenization
  151. SCE-LITE-HQ: Smooth visual counterfactual explanations with generative foundation models
  152. When Marginals Match but Structure Fails: Covariance Fidelity in Generative Models
  153. Shared Representation Learning for Reference-Guided Targeted Sound Detection
  154. Generative AI-assisted Participatory Modeling in Socio-Environmental Planning under Deep Uncertainty
  155. Transformers Can Learn Rules They've Never Seen: Proof of Computation Beyond Interpolation
  156. Integrating Inductive Biases in Transformers via Distillation for Financial Time Series Forecasting
  157. Formal verification of tree-based machine learning models for lateral spreading
  158. Interpretable AI-Assisted Early Reliability Prediction for a Two-Parameter Parallel Root-Finding Scheme
  159. Implementation of tangent linear and adjoint models for neural networks based on a compiler library tool
  160. The State of Generative AI in Software Development: Insights from Literature and a Developer Survey
  161. Are a Thousand Words Better Than a Single Picture? Beyond Images -- A Framework for Multi-Modal Knowledge Graph Dataset Enrichment
  162. Hybrid Classical-Quantum Transfer Learning with Noisy Quantum Circuits
  163. Over-the-air White-box Attack on the Wav2Vec Speech Recognition Neural Network
  164. MAND: Modality-Aware Novelty Detection for Open-World Egocentric Activity Recognition
  165. CineSRD: Leveraging Visual, Acoustic, and Linguistic Cues for Open-World Visual Media Speaker Diarization
  166. Behavior-Centric Extraction of Scenarios from Highway Traffic Data and their Domain-Knowledge-Guided Clustering using CVQ-VAE
  167. Topology-Guided Biomechanical Profiling: A White-Box Framework for Opportunistic Screening of Spinal Instability on Routine CT
  168. Data-knowledge dual-driven intelligent framework for full-chain, experiment-efficient synthesis of 2D dendrites
  169. SegviGen: Repurposing 3D Generative Model for Part Segmentation
  170. MessyKitchens: Contact-rich object-level 3D scene reconstruction
  171. ManiTwin: Scaling Data-Generation-Ready Digital Object Dataset to 100K
  172. SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation
  173. SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models
  174. SOMA: Unifying Parametric Human Body Models
  175. Long-Horizon Traffic Forecasting via Incident-Aware Conformal Spatio-Temporal Transformers
  176. Online Experiential Learning for Language Models
  177. Unifying Optimization and Dynamics to Parallelize Sequential Computation: A Guide to Parallel Newton Methods for Breaking Sequential Bottlenecks
  178. GIST: Gauge-Invariant Spectral Transformers for Scalable Graph Neural Operators
  179. Mediocrity is the key for LLM as a Judge Anchor Selection
  180. Dynamic Meta-Layer Aggregation for Byzantine-Robust Federated Learning
  181. M^3: Dense Matching Meets Multi-View Foundation Models for Monocular Gaussian Splatting SLAM
  182. Internalizing Agency from Reflective Experience
  183. What DINO saw: ALiBi positional encoding reduces positional bias in Vision Transformers
  184. An assessment of data-centric methods for label noise identification in remote sensing data sets
  185. Conditional Distributional Treatment Effects: Doubly Robust Estimation and Testing
  186. Real-Time Decoding of Movement Onset and Offset for Brain-Controlled Rehabilitation Exoskeleton
  187. SurgSigma: A Spectrum of Large-Scale Multimodal Data and Foundation Models for Surgical Intelligence
  188. WildDepth: A Multimodal Dataset for 3D Wildlife Perception and Depth Estimation
  189. Beyond Accuracy: Evaluating Forecasting Models by Multi-Echelon Inventory Cost
  190. ODIN-Based CPU-GPU Architecture with Replay-Driven Simulation and Emulation
  191. CABTO: Context-Aware Behavior Tree Grounding for Robot Manipulation
  192. DexGrasp-Zero: A Morphology-Aligned Policy for Zero-Shot Cross-Embodiment Dexterous Grasping
  193. RaDAR: Relation-aware Diffusion-Asymmetric Graph Contrastive Learning for Recommendation
  194. High-Dimensional Gaussian Mean Estimation under Realizable Contamination
  195. InCoder-32B: Code Foundation Model for Industrial Scenarios
  196. Conservative Continuous-Time Treatment Optimization
  197. SpokenUS: A Spoken User Simulator for Task-Oriented Dialogue
  198. SOMP: Scalable Gradient Inversion for Large Language Models via Subspace-Guided Orthogonal Matching Pursuit
  199. Dual Stream Independence Decoupling for True Emotion Recognition under Masked Expressions
  200. TurnWise: The Gap between Single- and Multi-turn Language Model Capabilities
  201. SuCor: Susceptibility Distortion Correction via Parameter-Free and Self-Regularized Optimal Transport
  202. pADAM: A Plug-and-Play All-in-One Diffusion Architecture for Multi-Physics Learning
  203. A Practical Algorithm for Feature-Rich, Non-Stationary Bandit Problems
  204. Finding Common Ground in a Sea of Alternatives
  205. Probing Cultural Signals in Large Language Models through Author Profiling
  206. Data-driven forced response analysis with min-max representations of nonlinear restoring forces
  207. When the City Teaches the Car: Label-Free 3D Perception from Infrastructure
  208. Bayesian Inference of Psychometric Variables From Brain and Behavior in Implicit Association Tests
  209. MedCL-Bench: Benchmarking stability-efficiency trade-offs and scaling in biomedical continual learning
  210. Understanding Quantization of Optimizer States in LLM Pre-training: Dynamics of State Staleness and Effectiveness of State Resets
  211. GeMA: Learning Latent Manifold Frontiers for Benchmarking Complex Systems
  212. Federated Learning with Multi-Partner OneFlorida+ Consortium Data for Predicting Major Postoperative Complications
  213. Emotion-Aware Classroom Quality Assessment Leveraging IoT-Based Real-Time Student Monitoring
  214. Arabic Morphosyntactic Tagging and Dependency Parsing with Large Language Models
  215. Novelty-Driven Target-Space Discovery in Automated Electron and Scanning Probe Microscopy
  216. High-dimensional estimation with missing data: Statistical and computational limits
  217. Search2Motion: Training-Free Object-Level Motion Control via Attention-Consensus Search
  218. Learning Lineage-guided Geodesics with Finsler Geometry
  219. Cost Trade-offs in Matrix Inversion Updates for Streaming Outlier Detection
  220. vAccSOL: Efficient and Transparent AI Vision Offloading for Mobile Robots
  221. CritiSense: Critical Digital Literacy and Resilience Against Misinformation
  222. x2-Fusion: Cross-Modality and Cross-Dimension Flow Estimation in Event Edge Space
  223. When AI Agents Learn from Each Other: Insights from Emergent AI Agent Communities on OpenClaw for Human-AI Partnership in Education
  224. Spectral Property-Driven Data Augmentation for Hyperspectral Single-Source Domain Generalization
  225. Can Linguistically Related Languages Guide LLM Translation in Low-Resource Settings?
  226. LLMs learn scientific taste from institutional traces across the social sciences
  227. Efficient Brood Cell Detection in Layer Trap Nests for Bees and Wasps: Balancing Labeling Effort and Species Coverage
  228. Domain-Independent Dynamic Programming with Constraint Propagation
  229. BUSSARD: Normalizing Flows for Bijective Universal Scene-Specific Anomalous Relationship Detection
  230. When AI Navigates the Fog of War
  231. FlowComposer: Composable Flows for Compositional Zero-Shot Learning
  232. Simplex-to-Euclidean Bijection for Conjugate and Calibrated Multiclass Gaussian Process Classification
  233. TCATSeg: A Tooth Center-Wise Attention Network for 3D Dental Model Semantic Segmentation
  234. ACPV-Net: All-Class Polygonal Vectorization for Seamless Vector Map Generation from Aerial Imagery
  235. Omnilingual SONAR: Cross-Lingual and Cross-Modal Sentence Embeddings Bridging Massively Multilingual Text and Speech
  236. Tarab: A Multi-Dialect Corpus of Arabic Lyrics and Poetry
  237. Data-driven generalized perimeter control: Z"urich case study
  238. FSMC-Pose: Frequency and Spatial Fusion with Multiscale Self-calibration for Cattle Mounting Pose Estimation
  239. On the Transfer of Collinearity to Computer Vision
  240. BATQuant: Outlier-resilient MXFP4 Quantization via Learnable Block-wise Optimization
  241. HistoAtlas: A Pan-Cancer Morphology Atlas Linking Histomics to Molecular Programs and Clinical Outcomes
  242. Trajectory-Optimized Time Reparameterization for Learning-Compatible Reduced-Order Modeling of Stiff Dynamical Systems
  243. Diverging Transformer Predictions for Human Sentence Processing: A Comprehensive Analysis of Agreement Attraction Effects
  244. Context Matters: Repository-Aware Security Analysis of the Agent Skill Ecosystem
  245. Face2Scene: Using Facial Degradation as an Oracle for Diffusion-Based Scene Restoration
  246. Deep Tabular Representation Corrector
  247. Manifold-Matching Autoencoders
  248. Characterizing Delusional Spirals through Human-LLM Chat Logs
  249. Deep Learning-Driven Black-Box Doherty Power Amplifier with Pixelated Output Combiner and Extended Efficiency Range
  250. Understanding Cell Fate Decisions with Temporal Attention
  251. BenchPreS: A Benchmark for Context-Aware Personalized Preference Selectivity of Persistent-Memory LLMs
  252. CompDiff enables fair and zero shot medical image generation across demographic intersections through compositional diffusion
  253. Bridging the Simulation-to-Reality Gap in Electron Microscope Calibration via VAE-EM Estimation
  254. SAMSEM -- A Generic and Scalable Approach for IC Metal Line Segmentation
  255. DanceHA: A Multi-Agent Framework for Document-Level Aspect-Based Sentiment Analysis
  256. How often do Answers Change? Estimating Recency Requirements in Question Answering
  257. Rethinking Pose Refinement in 3D Gaussian Splatting under Pose Prior and Geometric Uncertainty
  258. Designing for Disagreement: Front-End Guardrails for Assistance Allocation in LLM-Enabled Robots
  259. SympFormer: Accelerated attention blocks via Inertial Dynamics on Density Manifolds
  260. Exploring different approaches to customize language models for domain-specific text-to-code generation
  261. An Approximate Graph Elicits Detonation Lattice
  262. FEAT: A Linear-Complexity Foundation Model for Extremely Large Structured Data
  263. msData: A Millisecond-Resolution Network Dataset for Advancing Time Series Foundation Models
  264. ExpressMind: A Multimodal Pretrained Large Language Model for Expressway Operation
  265. On the Emotion Understanding of Synthesized Speech
  266. DST-Net: A Dual-Stream Transformer with Illumination-Independent Feature Guidance and Multi-Scale Spatial Convolution for Low-Light Image Enhancement
  267. Optimal uncertainty bounds for multivariate kernel regression under bounded noise: A Gaussian process-based dual function
  268. Multi-Agent Reinforcement Learning Counteracts Delayed CSI in Multi-Satellite Systems
  269. DynHD: Hallucination Detection for Diffusion Large Language Models via Denoising Dynamics Deviation Learning
  270. TinyGLASS: Real-Time Self-Supervised In-Sensor Anomaly Detection
  271. ProgressiveAvatars: Progressive Animatable 3D Gaussian Avatars
  272. Unified Removal of Raindrops and Reflections: A New Benchmark and A Novel Pipeline
  273. DISCOVER: A Solver for Distributional Counterfactual Explanations
  274. VQKV: High-Fidelity and High-Ratio Cache Compression via Vector-Quantization
  275. From Natural Language to Executable Option Strategies via Large Language Models
  276. IRIS: A Real-World Benchmark for Inverse Recovery and Identification of Physical Dynamic Systems from Monocular Video
  277. EngGPT2: Sovereign, Efficient and Open Intelligence
  278. LenghuSky-8: An 8-Year All-Sky Cloud Dataset with Star-Aware Masks and Alt-Az Calibration for Segmentation and Nowcasting
  279. An Efficient Heterogeneous Co-Design for Fine-Tuning on a Single GPU
  280. Cross-modal learning for plankton recognition
  281. 3D Fourier-based Global Feature Extraction for Hyperspectral Image Classification
  282. Trained Persistent Memory for Frozen Encoder--Decoder LLMs: Six Architectural Methods
  283. Who Benchmarks the Benchmarks? A Case Study of LLM Evaluation in Icelandic
  284. Near-light Photometric Stereo with Symmetric Lights
  285. Fanar 2.0: Arabic Generative AI Stack
  286. Unpaired Cross-Domain Calibration of DMSP to VIIRS Nighttime Light Data Based on CUT Network
  287. Age Predictors Through the Lens of Generalization, Bias Mitigation, and Interpretability: Reflections on Causal Implications
  288. Prior-Informed Neural Network Initialization: A Spectral Approach for Function Parameterizing Architectures
  289. Semantic One-Dimensional Tokenizer for Image Reconstruction and Generation
  290. InViC: Intent-aware Visual Cues for Medical Visual Question Answering
  291. FederatedFactory: Generative One-Shot Learning for Extremely Non-IID Distributed Scenarios
  292. FactorEngine: A Program-level Knowledge-Infused Factor Mining Framework for Quantitative Investment
  293. Advancing Visual Reliability: Color-Accurate Underwater Image Enhancement for Real-Time Underwater Missions
  294. Toward Experimentation-as-a-Service in 5G/6G: The Plaza6G Prototype for AI-Assisted Trials
  295. PashtoCorp: A 1.25-Billion-Word Corpus, Evaluation Suite, and Reproducible Pipeline for Low-Resource Language Development
  296. Automated identification of Ichneumonoidea wasps via YOLO-based deep learning: Integrating HiresCam for Explainable AI
  297. Explainable machine learning workflows for radio astronomical data processing
  298. Learning Human-Object Interaction for 3D Human Pose Estimation from LiDAR Point Clouds
  299. Deep learning based intelligent IDS for Large-scale IoT networks
  300. PKINet-v2: Towards Powerful and Efficient Poly-Kernel Remote Sensing Object Detection
  301. SpikeCLR: Contrastive Self-Supervised Learning for Few-Shot Event-Based Vision using Spiking Neural Networks
  302. An Interpretable Machine Learning Framework for Non-Small Cell Lung Cancer Drug Response Analysis
  303. A Human-Centred Architecture for Large Language Models-Cognitive Assistants in Manufacturing within Quality Management Systems
  304. Learning to Predict, Discover, and Reason in High-Dimensional Event Sequences
  305. Omnilingual MT: Machine Translation for 1,600 Languages
  306. NeSy-Route: A Neuro-Symbolic Benchmark for Constrained Route Planning in Remote Sensing
  307. Micro-AU CLIP: Fine-Grained Contrastive Learning from Local Independence to Global Dependency for Micro-Expression Action Unit Detection
  308. PyPhonPlan: Simulating phonetic planning with dynamic neural fields and task dynamics
  309. Attention-guided Evidence Grounding for Spoken Question Answering
  310. Surrogate-Assisted Genetic Programming with Rank-Based Phenotypic Characterisation for Dynamic Multi-Mode Project Scheduling
  311. EvoTale: Continual Character Customization for Expanding Story Worlds
  312. Laya: A LeJEPA Approach to EEG via Latent Prediction over Reconstruction
  313. Physics-integrated neural differentiable modeling for immersed boundary systems
  314. FG-SGL: Fine-Grained Semantic Guidance Learning via Motion Process Decomposition for Micro-Gesture Recognition
  315. Human/AI Collective Intelligence for Deliberative Democracy: A Human-Centred Design Approach
  316. Is Semi-Automatic Transcription Useful in Corpus Creation? Preliminary Considerations on the KIParla Corpus
  317. Point-to-Mask: From Arbitrary Point Annotations to Mask-Level Infrared Small Target Detection
  318. Synergizing Deep Learning and Biological Heuristics for Extreme Long-Tail White Blood Cell Classification
  319. How to Utilize Complementary Vision-Text Information for 2D Structure Understanding
  320. More Rounds, More Noise: Why Multi-Turn Review Fails to Improve Cross-Context Verification
  321. RASLF: Representation-Aware State Space Model for Light Field Super-Resolution
  322. Exclusivity-Guided Mask Learning for Semi-Supervised Crowd Instance Segmentation and Counting
  323. Neural Pushforward Samplers for the Fokker-Planck Equation on Embedded Riemannian Manifolds
  324. PureCLIP-Depth: Prompt-Free and Decoder-Free Monocular Depth Estimation within CLIP Embedding Space
  325. ReFORM: Review-aggregated Profile Generation via LLM with Multi-Factor Attention for Restaurant Recommendation
  326. Ground Reaction Inertial Poser: Physics-based Human Motion Capture from Sparse IMUs and Insole Pressure Sensors
  327. Generative AI for Quantum Circuits and Quantum Code: A Technical Review and Taxonomy
  328. Proactive Rejection and Grounded Execution: A Dual-Stage Intent Analysis Paradigm for Safe and Efficient AIoT Smart Homes
  329. A Scoping Review of AI-Driven Digital Interventions in Mental Health Care: Mapping Applications Across Screening, Support, Monitoring, Prevention, and Clinical Education
  330. Robust Generative Audio Quality Assessment: Disentangling Quality from Spurious Correlations
  331. Online Semi-infinite Linear Programming: Efficient Algorithms via Function Approximation
  332. Are Large Language Models Truly Smarter Than Humans?
  333. S-VAM: Shortcut Video-Action Model by Self-Distilling Geometric and Semantic Foresight
  334. Sample-Efficient Adaptation of Drug-Response Models to Patient Tumors under Strong Biological Domain Shift
  335. Polyglot-Lion: Efficient Multilingual ASR for Singapore via Balanced Fine-Tuning of Qwen3-ASR
  336. MemX: A Local-First Long-Term Memory System for AI Assistants
  337. SignNav: Leveraging Signage for Semantic Visual Navigation in Large-Scale Indoor Environments
  338. Homogeneous and Heterogeneous Consistency progressive Re-ranking for Visible-Infrared Person Re-identification
  339. STARK: Spatio-Temporal Attention for Representation of Keypoints for Continuous Sign Language Recognition
  340. Segmentation-before-Staining Improves Structural Fidelity in Virtual IHC-to-Multiplex IF Translation
  341. AI-Generated Figures in Academic Publishing: Policies, Tools, and Practical Guidelines
  342. GATS: Gaussian Aware Temporal Scaling Transformer for Invariant 4D Spatio-Temporal Point Cloud Representation
  343. Deep Adaptive Model-Based Design of Experiments
  344. Structure-Aware Multimodal LLM Framework for Trustworthy Near-Field Beam Prediction
  345. Parametric Social Identity Injection and Diversification in Public Opinion Simulation
  346. Communication-Aware Multi-Agent Reinforcement Learning for Decentralized Cooperative UAV Deployment
  347. Noisy Data is Destructive to Reinforcement Learning with Verifiable Rewards
  348. Rethinking UMM Visual Generation: Masked Modeling for Efficient Image-Only Pre-training
  349. Answer Bubbles: Information Exposure in AI-Mediated Search
  350. SIA: A Synthesize-Inject-Align Framework for Knowledge-Grounded and Secure E-commerce Search LLMs with Industrial Deployment
  351. DualPrim: Compact 3D Reconstruction with Positive and Negative Primitives
  352. SciZoom: A Large-scale Benchmark for Hierarchical Scientific Summarization across the LLM Era
  353. EPOFusion: Exposure aware Progressive Optimization Method for Infrared and Visible Image Fusion
  354. Boosting Quantitive and Spatial Awareness for Zero-Shot Object Counting
  355. Pre-training LLM without Learning Rate Decay Enhances Supervised Fine-Tuning
  356. Functorial Neural Architectures from Higher Inductive Types
  357. Out-of-Distribution Object Detection in Street Scenes via Synthetic Outlier Exposure and Transfer Learning
  358. Language Models Don't Know What You Want: Evaluating Personalization in Deep Research Needs Real Users
  359. RepoReviewer: A Local-First Multi-Agent Architecture for Repository-Level Code Review
  360. Frequency Matters: Fast Model-Agnostic Data Curation for Pruning and Quantization
  361. NanoGS: Training-Free Gaussian Splat Simplification
  362. Reevaluating the Intra-Modal Misalignment Hypothesis in CLIP
  363. OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder
  364. LICA: Layered Image Composition Annotations for Graphic Design Research
  365. CounterRefine: Answer-Conditioned Counterevidence Retrieval for Inference-Time Knowledge Repair in Factual Question Answering
  366. RecBundle: A Next-Generation Geometric Paradigm for Explainable Recommender Systems
  367. Interact3D: Compositional 3D Generation of Interactive Objects
  368. Structured prototype regularization for synthetic-to-real driving scene parsing
  369. A Depth-Aware Comparative Study of Euclidean and Hyperbolic Graph Neural Networks on Bitcoin Transaction Systems
  370. Volumetrically Consistent Implicit Atlas Learning via Neural Diffeomorphic Flow for Placenta MRI
  371. ClaimFlow: Tracing the Evolution of Scientific Claims in NLP
  372. SEAHateCheck: Functional Tests for Detecting Hate Speech in Low-Resource Languages of Southeast Asia
  373. Resource Consumption Threats in Large Language Models
  374. Attribution Upsampling should Redistribute, Not Interpolate
  375. Adaptive regularization parameter selection for high-dimensional inverse problems: A Bayesian approach with Tucker low-rank constraints
  376. ViT-AdaLA: Adapting Vision Transformers with Linear Attention
  377. Safe Distributionally Robust Feature Selection under Covariate Shift
  378. Population Annealing as a Discrete-Time Schr"odinger Bridge
  379. A Context Alignment Pre-processor for Enhancing the Coherence of Human-LLM Dialog
  380. POaaS: Minimal-Edit Prompt Optimization as a Service to Lift Accuracy and Cut Hallucinations on On-Device sLLMs
  381. Shuffling the Stochastic Mirror Descent via Dual Lipschitz Continuity and Kernel Conditioning
  382. Power Analysis for Prediction-Powered Inference
  383. Residual Stream Duality in Modern Transformer Architectures
  384. 3D tomography of exchange phase in a Si/SiGe quantum dot device
  385. Speak, Segment, Track, Navigate: An Interactive System for Video-Guided Skull-Base Surgery