mlsanityData to 7 Oct 2026

Papers

New on arXiv

Sat 13 Dec 2025

151 papers

  1. Emergence: Overcoming Privileged Information Bias in Asymmetric Embodied Agents via Active QueryingLLM reasoning → Reasoning for agents, planning and code +1
  2. TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy AccelerationDiffusion models → Diffusion and flow policies for robotics +1
  3. Composite Classifier-Free Guidance for Multi-Modal Conditioning in Wind Dynamics Super-ResolutionDiffusion models → Diffusion foundations and sampling
  4. RAST-MoE-RL: A Regime-Aware Spatio-Temporal MoE Framework for Deep Reinforcement Learning in Ride-HailingMixture-of-experts → MoE in reinforcement learning and robotics
  5. Compressed Causal Reasoning: Quantization and GraphRAG Effects on Interventional and Counterfactual AccuracyLLM reasoning → Causal reasoning in LLMs
  6. More Than the Final Answer: Improving Visual Extraction and Logical Consistency in Vision-Language ModelsLLM reasoning → Multimodal reasoning +1
  7. Exploring the Design Space of Transition MatchingDiffusion models → Flow matching, time series and science
  8. Breaking the Curse of Dimensionality: On the Stability of Modern Vector RetrievalRetrieval-augmented generation → Vector search and ANN indexes
  9. Anchoring Values in Temporal and Group Dimensions for Flow Matching Model AlignmentLLM reasoning → Reinforcement learning for reasoning +2
  10. Speedrunning ImageNet DiffusionDiffusion models → Diffusion foundations and sampling
  11. V-Warper: Appearance-Consistent Video Diffusion Personalization via Value WarpingDiffusion models → Video generation
  12. VideoARM: Agentic Reasoning over Hierarchical Memory for Long-Form Video UnderstandingLLM reasoning → Multimodal reasoning +1
  13. Unified Control for Inference-Time Guidance of Denoising Diffusion ModelsDiffusion models → Diffusion and flow policies for robotics
  14. From Human Intention to Action Prediction: Intention-Driven End-to-End Autonomous DrivingEnd-to-end autonomous driving → Reasoning VLA and VLM driving policies
  15. V-Rex: Real-Time Streaming Video LLM Acceleration via Dynamic KV Cache RetrievalEfficient LLM inference and serving → KV cache optimization
  16. MetaTPT: Meta Test-time Prompt Tuning for Vision-Language ModelsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  17. Journey Before Destination: On the importance of Visual Faithfulness in Slow ThinkingLLM reasoning → Multimodal reasoning +1
  18. Training Versatile Coding Agents in Synthetic EnvironmentsLLM agents and tool use → Software engineering coding agents
  19. Measuring What Matters: Scenario-Driven Evaluation for Trajectory Predictors in Autonomous DrivingEnd-to-end autonomous driving → End-to-end system architecture
  20. MolGuidance: Advanced Guidance Strategies for Conditional Molecular Generation with Flow MatchingDiffusion models → Flow matching, time series and science
  21. HydroDiffusion: Diffusion-Based Probabilistic Streamflow Forecasting with a State Space BackboneDiffusion models → Flow matching, time series and science
  22. Rethinking Label Consistency of In-Context Learning: An Implicit Transductive Label Propagation PerspectiveLLM reasoning → Reasoning benchmarks and evaluation
  23. Diffusion Language Model Inference with Monte Carlo Tree SearchDiffusion models → Discrete and text diffusion
  24. MixtureKit: A General Framework for Composing, Training, and Visualizing Mixture-of-Experts ModelsMixture-of-experts → MoE theory and gating functions
  25. EchoVLM: Measurement-Grounded Multimodal Learning for EchocardiographyMultimodal LLMs / vision-language models → Medical vision-language models
  26. Screen, Cache, and Match: A Training-Free Causality-Consistent Reference Frame Framework for Human Animation
  27. On Harnessing Idle Compute at the Edge for Foundation Model Training
  28. Bidirectional human-AI collaboration in brain tumour assessments improves both expert human and AI agent performance
  29. NystagmusNet: Explainable Deep Learning for Photosensitivity Risk Prediction
  30. Accelerated Digital Twin Learning for Edge AI: A Comparison of FPGA and Mobile GPU
  31. Enhanced Web User Interface Design Via Cross-Device Responsiveness Assessment Using An Improved HCI-INTEGRATED DL Schemes
  32. Two-Step Data Augmentation for Masked Face Detection and Recognition: Turning Fake Masks to Real
  33. Solving PDEs With Deep Neural Nets under General Boundary Conditions
  34. Multiscale Cross-Modal Mapping of Molecular, Pathologic, and Radiologic Phenotypes in Lipid-Deficient Clear Cell Renal CellCarcinoma
  35. Compute the edge p-Laplacian centrality for air traffic network
  36. CurvaDion: Curvature-Adaptive Distributed Orthonormalization
  37. Time-Constrained Recommendations: Reinforcement Learning Strategies for E-Commerce
  38. Graph AI generates neurological hypotheses validated in molecular, organoid, and clinical systems
  39. Made-in China, Thinking in America:U.S. Values Persist in Chinese LLMs
  40. Advancing Cache-Based Few-Shot Classification via Patch-Driven Relational Gated Graph Attention
  41. Policy Optimization for Dynamic Heart Transplant Allocation
  42. AI-Driven Early Warning Systems for Student Success: Discovering Static Feature Dominance in Temporal Prediction Models
  43. Adaptive Detector-Verifier Framework for Zero-Shot Polyp Detection in Open-World Settings
  44. GoMS: Graph of Molecule Substructure Network for Molecule Property Prediction
  45. The American Ghost in the Machine: How language models align culturally and the effects of cultural prompting
  46. Mage: Cracking Elliptic Curve Cryptography with Cross-Axis Transformers
  47. DualHNIE: Dual-Channel Hypergraph Learning for Node Importance Estimation in Heterogeneous Knowledge Graphs
  48. AI-Driven Real-Time Kick Classification in Olympic Taekwondo Using Sensor Fusion
  49. Sparse Concept Anchoring for Interpretable and Controllable Neural Representations
  50. Understanding Overparametrization in Survival Models through Interpolation
  51. Dynamical modeling of nonlinear latent factors in multiscale neural activity with real-time inference
  52. Cross-Modal Representational Knowledge Distillation for Enhanced Spike-Informed LFP Modeling
  53. From Particles to Fields: Reframing Photon Mapping with Continuous Gaussian Photon Fields
  54. Optimized Architectures for Kolmogorov-Arnold Networks
  55. Large language models have learned to use language
  56. Knowledge-Guided Masked Autoencoder with Linear Spectral Mixing and Spectral-Angle-Aware Reconstruction
  57. Can GPT replace human raters? Validity and reliability of machine-generated norms for metaphors
  58. AI Transparency Atlas: Framework, Scoring, and Real-Time Model Card Evaluation Pipeline
  59. Efficient Level-Crossing Probability Calculation for Gaussian Process Modeled Data
  60. Sim2Real Reinforcement Learning for Soccer skills
  61. Rough Sets for Explainability of Spectral Graph Clustering
  62. Co-Hub Node Based Multiview Graph Learning with Theoretical Guarantees
  63. Data-driven modelling of autonomous and forced dynamical systems
  64. Endless World: Real-Time 3D-Aware Long Video Generation
  65. Learning Dynamics in Memristor-Based Equilibrium Propagation
  66. Boosting Monocular Metric Depth Estimation via Bokeh Rendering
  67. ViInfographicVQA: A Benchmark for Single and Multi-image Visual Question Answering on Vietnamese Infographics
  68. Understanding Critical Thinking in Generative Artificial Intelligence Use: Development, Validation, and Correlates of the Critical Thinking in AI Use Scale
  69. Detecting the Disturbance: A Nuanced View of Introspective Abilities in LLMs
  70. A Graph Attention Network-Based Framework for Reconstructing Missing LiDAR Beams
  71. Can Graphs Improve Tabular Foundation Models?
  72. DeepVekua: Geometric-Spectral Representation Learning for Physics-Informed Fields
  73. ArtGen: Conditional Generative Modeling of Articulated Objects in Arbitrary Part-Level States
  74. The Morphemic Origin of Zipf's Law: A Factorized Combinatorial Framework
  75. The Data Efficiency Frontier of Financial Foundation Models: Scaling Laws from Continued Pretraining
  76. Entropy Collapse: A Universal Failure Mode of Intelligent Systems
  77. M4Human: A Large-Scale Multimodal mmWave Radar Benchmark for Human Mesh Reconstruction
  78. STAGE: Storyboard-Anchored Generation for Cinematic Multi-shot Narrative
  79. JPEG-Inspired Cloud-Edge Holography
  80. ElasticVR: Elastic Task Computing in Multi-User Multi-Connectivity Wireless Virtual Reality (VR) Systems
  81. Synthetic Swarm Mosquito Dataset for Acoustic Classification: A Proof of Concept
  82. Towards a pretrained deep learning estimator of the Linfoot informational correlation
  83. TCLeaf-Net: a transformer-convolution framework with global-local attention for robust in-field lesion-level plant leaf disease detection
  84. Uncertainty Quantification for Machine Learning: One Size Does Not Fit All
  85. SCIR: A Self-Correcting Iterative Refinement Framework for Enhanced Information Extraction Based on Schema
  86. Extending the application of dynamic Bayesian networks in calculating market risk: Standard and stressed expected shortfall
  87. Dynamic Homophily with Imperfect Recall: Modeling Resilience in Adversarial Networks
  88. Eventually LIL Regret: Almost Sure lnln T Regret for a sub-Gaussian Mixture on Unbounded Data
  89. UniMark: Artificial Intelligence Generated Content Identification Toolkit
  90. WeDetect: Fast Open-Vocabulary Object Detection as Retrieval
  91. MRD: Using Physically Based Differentiable Rendering to Probe Vision Models for 3D Scene Understanding
  92. OMUDA: Omni-level Masking for Unsupervised Domain Adaptation in Semantic Segmentation
  93. TwinFormer: A Dual-Level Transformer for Long-Sequence Time-Series Forecasting
  94. F5-TTS-RO: Extending F5-TTS to Romanian TTS via Lightweight Input Adaptation
  95. GrowTAS: Progressive Expansion from Small to Large Subnets for Efficient ViT Architecture Search
  96. Near-Zero-Overhead Freshness for Recommendation Systems via Inference-Side Model Updates
  97. Robust Outlier Detection and Low-Latency Concept Drift Adaptation for Data Stream Regression: A Dual-Channel Architecture
  98. Quantum-Aware Generative AI for Materials Discovery: A Framework for Robust Exploration Beyond DFT Biases
  99. RealDrag: The First Dragging Benchmark with Real Target Image
  100. Fractional Differential Equation Physics-Informed Neural Network and Its Application in Battery State Estimation
All 151
  1. Cognitive-YOLO: LLM-Driven Architecture Synthesis from First Principles of Data for Object Detection
  2. Feature Aggregation for Efficient Continual Learning of Complex Facial Expressions
  3. Balancing Accuracy and Speed: A Multi-Fidelity Ensemble Kalman Filter with a Machine Learning Surrogate Model
  4. GRC-Net: Gram Residual Co-attention Net for epilepsy prediction
  5. Accurate de novo sequencing of the modified proteome with OmniNovo
  6. Hellinger loss function for Generative Adversarial Networks
  7. Market-Bench: Evaluating Large Language Models on Introductory Quantitative Trading and Market Dynamics
  8. A Multi-Axial Mindset for Ontology Design Lessons from Wikidata's Polyhierarchical Structure
  9. Optimized Learned Count-Min Sketch
  10. Stochastic Volatility Modelling with LSTM Networks: A Hybrid Approach for S&P 500 Index Volatility Forecasting
  11. Moment and Highlight Detection via MLLM Frame Segmentation
  12. Adversarially Probing Cross-Family Sound Symbolism in 27 Languages
  13. Semantic Distance Measurement based on Multi-Kernel Gaussian Processes
  14. Resolution-Agnostic Neural Operators for Multi-Rate Sparse-View CT
  15. Learning to Get Up Across Morphologies: Zero-Shot Recovery with a Unified Humanoid Policy
  16. Ultra-Low Bitrate Perceptual Image Compression with Shallow Encoder
  17. A Geometric Theory of Cognition for Machine Intelligence
  18. Comparison of different segmentation algorithms on brain volume and fractal dimension in infant brain MRIs
  19. Scalable branch-and-bound model selection with non-monotonic criteria including AIC, BIC and Mallows's mathitCp
  20. TechImage-Bench: Rubric-Based Evaluation for Technical Image Generation
  21. Fine-Grained Zero-Shot Learning with Attribute-Centric Representations
  22. EEG-DLite: Dataset Distillation for Efficient Large EEG Model Training
  23. CineLOG: A Training Free Approach for Cinematic Long Video Generation
  24. A Hybrid Deep Learning Framework for Emotion Recognition in Children with Autism During NAO Robot-Mediated Interaction
  25. Not All Transparency Is Equal: Source Presentation Effects on Attention, Interaction, and Persuasion in Conversational Search
  26. ALERT Open Dataset and Input-Size-Agnostic Vision Transformer for Driver Activity Recognition using IR-UWB
  27. A Multi-Year Urban Streetlight Imagery Dataset for Visual Monitoring and Spatio-Temporal Drift Detection
  28. Navigation Around Unknown Space Objects Using Visible-Thermal Image Fusion
  29. Epistemoverse: Toward an AI-Driven Knowledge Metaverse for Intellectual Heritage Preservation
  30. Thermal RGB Fusion for Micro-UAV Wildfire Perimeter Tracking with Minimal Comms
  31. AutoMV: An Automatic Multi-Agent System for Music Video Generation
  32. SMRABooth: Subject and Motion Representation Alignment for Customized Video Generation
  33. TA-KAND: Two-stage Attention Triple Enhancement and U-KAN based Diffusion For Few-shot Knowledge Graph Completion
  34. A Sensing Dataset Protocol for Benchmarking and Multi-Task Wireless Sensing
  35. Floorplan2Guide: LLM-Guided Floorplan Parsing for BLV Indoor Navigation
  36. Extending the Context of Pretrained LLMs by Dropping Their Positional Embeddings
  37. Audio-Visual Camera Pose Estimation with Passive Scene Sounds and In-the-Wild Video
  38. Keep the Lights On, Keep the Lengths in Check: Plug-In Adversarial Detection for Time-Series LLMs in Energy Forecasting
  39. Open Horizons: Evaluating Deep Models in the Wild
  40. MeltwaterBench: Deep learning for spatiotemporal downscaling of surface meltwater
  41. BaRISTA: Brain Scale Informed Spatiotemporal Representation of Human Intracranial Neural Activity
  42. Modeling Dabrafenib Response Using Multi-Omics Modality Fusion and Protein Network Embeddings Based on Graph Convolutional Networks
  43. Approximation with SiLU Networks: Constant Depth and Exponential Rates for Basic Operations
  44. BOOST: BOttleneck-Optimized Scalable Training Framework for Low-Rank Large Language Models
  45. A Benchmark Dataset for Spatially Aligned Road Damage Assessment in Small Uncrewed Aerial Systems Disaster Imagery
  46. High-Dimensional Tensor Discriminant Analysis: Low-Rank Discriminant Structure, Representation Synergy, and Theoretical Guarantees
  47. Citation-Grounded Code Comprehension: Preventing LLM Hallucination Through Hybrid Retrieval and Graph-Augmented Context
  48. Neural CDEs as Correctors for Learned Time Series Models
  49. A Neuro-Symbolic Framework for Accountability in Public-Sector AI
  50. A Novel Patch-Based TDA Approach for Computed Tomography Imaging
  51. AI-Augmented Pollen Recognition in Optical and Holographic Microscopy for Veterinary Imaging