mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 25 Oct 2025

165 papers

  1. Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RLDeep reinforcement learning methods → RL theory and sample complexity
  2. Evaluating LLMs' Reasoning Over Ordered Procedural StepsLLM reasoning → Reasoning benchmarks and evaluation
  3. Evaluating Multimodal Large Language Models on Core Music Perception TasksMultimodal LLMs / vision-language models → Video understanding with MLLMs
  4. Benchmarking Egocentric Multimodal Goal Inference for Assistive Wearable AgentsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  5. PromptReverb: Multimodal Room Impulse Response Generation Through Latent Rectified Flow MatchingDiffusion models → Audio, speech and music
  6. Modeling Hierarchical Thinking in Large Reasoning ModelsLLM reasoning → Test-time compute and efficient thinking
  7. Group size effects and collective misalignment in LLM multi-agent systemsLLM agents and tool use → Social simulation and multi-agent debate
  8. A Novel Multi-Timescale Stability-Preserving Hierarchical Reinforcement Learning Controller Framework for Adaptive Control in High-Dimensional Dynamical SystemsDeep reinforcement learning methods → RL theory and sample complexity
  9. Top-Down Semantic Refinement for Image CaptioningMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  10. Can Small and Reasoning Large Language Models Score Journal Articles for Research Quality and Do Averaging and Few-shot Help?LLM reasoning → Reasoning benchmarks and evaluation
  11. Label Smoothing Improves Gradient Ascent in LLM UnlearningLLM safety and security → Machine unlearning
  12. Reasoning Models Reason Well, Until They Don'tLLM reasoning → Test-time compute and efficient thinking
  13. BLIP-FusePPO: A Vision-Language Deep Reinforcement Learning Framework for Lane Keeping in Autonomous VehiclesMultimodal LLMs / vision-language models → Driving VLMs and open-vocabulary detection +2
  14. T2SMark: Balancing Robustness and Diversity in Noise-as-Watermark for Diffusion ModelsDiffusion models → Robustness, privacy and adversarial aspects +1
  15. Mapping Faithful Reasoning in Language ModelsLLM reasoning → Prompting and chain-of-thought reasoning
  16. FAIR-RAG: Faithful Adaptive Iterative Refinement for Retrieval-Augmented GenerationRetrieval-augmented generation → Agentic RAG, agents and memory
  17. DynaSolidGeo: A Dynamic Benchmark for Genuine Spatial Mathematical Reasoning of VLMs in Solid GeometryLLM reasoning → Spatial and embodied reasoning
  18. Transformer Key-Value Memories Are Nearly as Interpretable as Sparse AutoencodersMechanistic interpretability → SAE features and their applications
  19. GRPO-Guard: Mitigating Implicit Over-Optimization in Flow Matching via Regulated ClippingLLM reasoning → Reinforcement learning for reasoning +1
  20. LacMaterial: Large Language Models as Analogical Chemists for Materials DiscoveryLLM reasoning → Clinical and biomedical applications
  21. CityRiSE: Reasoning Urban Socio-Economic Status in Large Vision-Language Models via Reinforcement LearningLLM reasoning → Spatial and embodied reasoning +1
  22. WAON: A Large-Scale Japanese Image-Text Dataset for Cultural Adaptation in Contrastive Vision-Language ModelsMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  23. SecureLearn -- An Attack-agnostic Defense for Multiclass Machine Learning Against Data Poisoning AttacksLLM safety and security → Backdoor and data poisoning attacks
  24. From Slides to Chatbots: Enhancing Large Language Models with University Course MaterialsRetrieval-augmented generation → Agentic RAG, agents and memory
  25. Actor-Critic Learning for Risk-Constrained Linear Quadratic RegulationDeep reinforcement learning methods → RL for games and combinatorial optimization
  26. SteerX: Disentangled Steering for LLM PersonalizationMechanistic interpretability → Activation steering methods
  27. PACR: Progressively Ascending Confidence Reward for LLM ReasoningLLM reasoning → Reinforcement learning for reasoning
  28. You Don't Need Prompt Engineering Anymore: The Prompting InversionLLM reasoning → Prompting and chain-of-thought reasoning
  29. DiffusionLane: Diffusion Model for Lane DetectionDiffusion models → Diffusion and flow policies for robotics
  30. CGoT: A Novel Inference Mechanism for Embodied Multi-Agent Systems Using Composable Graphs of ThoughtsLLM reasoning → Chain-of-thought reasoning for driving +1
  31. Robust MIMO Channel Estimation Using Energy-Based Generative Diffusion ModelsDiffusion models → Diffusion for compression and wireless
  32. When Fewer Layers Break More Chains: Layer Pruning Harms Test-Time Scaling in LLMsLLM reasoning → Test-time compute and efficient thinking
  33. Right Place, Right Time: Market Simulation-based RL for Execution OptimisationDeep reinforcement learning methods → Adversarial robustness and RL in finance
  34. Human-Inspired Neuro-Symbolic World Modeling and Logic Reasoning for Interpretable Safe UAV Landing Site AssessmentWorld models → World models for navigation +1
  35. ACG: Action Coherence Guidance for Flow-based Vision-Language-Action modelsVision-language-action models → Efficient VLA inference and adaptation +1
  36. LongCat-Video Technical ReportWorld models → Video-generation world models and simulators
  37. OptiTree: Hierarchical Thoughts Generation with Tree Search for LLM Optimization ModelingLLM reasoning → Test-time compute and efficient thinking
  38. HARMONY: Hidden Activation Representations and Model Output-Aware Uncertainty Estimation for Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  39. Expert Validation of Synthetic Cervical Spine Radiographs Generated with a Denoising Diffusion Probabilistic ModelDiffusion models → Medical imaging and segmentation
  40. Solving Continuous Mean Field Games: Deep Reinforcement Learning for Non-Stationary DynamicsDeep reinforcement learning methods → RL for games and combinatorial optimization
  41. Attention Residual Fusion Network with Contrast for Source-free Domain AdaptationKnowledge distillation → General knowledge distillation methods
  42. LOC: A General Language-Guided Framework for Open-Set 3D Occupancy PredictionMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  43. Controllable Mathematical Reasoning via Self-Optimizing Thought VectorsLLM reasoning → Test-time compute and efficient thinking
  44. Mint: A Simple Test-Time Adaptation of Vision-Language Models against Common CorruptionsMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  45. Efficient Utility-Preserving Machine Unlearning with Implicit Gradient SurgeryLLM safety and security → Machine unlearning
  46. GRAID: Enhancing Spatial Reasoning of VLMs Through High-Fidelity Data GenerationLLM reasoning → Spatial and embodied reasoning +1
  47. Every Activation Boosted: Scaling General Reasoner to 1 Trillion Open Language FoundationLLM reasoning → Test-time compute and efficient thinking +1
  48. Mitigating Coordinate Prediction Bias from Positional Encoding FailuresMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  49. Generalization or Memorization: Dynamic Decoding for Mode SteeringMechanistic interpretability → Steering and interpreting LLM reasoning
  50. Embracing Trustworthy Brain-Agent Collaboration as Paradigm Extension for Intelligent Assistive TechnologiesLLM agents and tool use → Medical and scientific domain agents
  51. FPGA-based Lane Detection System incorporating Temperature and Light Control Units
  52. Cross-Enhanced Multimodal Fusion of Eye-Tracking and Facial Features for Alzheimer's Disease Diagnosis
  53. CFL-SparseMed: Communication-Efficient Federated Learning for Medical Imaging with Top-k Sparse Updates
  54. PANORAMA: A Dataset and Benchmarks Capturing Decision Trails and Rationales in Patent Examination
  55. Error Adjustment Based on Spatiotemporal Correlation Fusion for Traffic Forecasting
  56. The Structural Scalpel: Automated Contiguous Layer Pruning for Large Language Models
  57. Beyond Hidden-Layer Manipulation: Semantically-Aware Logit Interventions for Debiasing LLMs
  58. Efficient Low Rank Attention for Long-Context Inference in Large Language Models
  59. RoGBot: Relationship-Oblivious Graph-based Neural Network with Contextual Knowledge for Bot Detection
  60. Derivative-Free Sequential Quadratic Programming for Equality-Constrained Stochastic Optimization
  61. SemiETPicker: Fast and Label-Efficient Particle Picking for CryoET Tomography Using Semi-Supervised Learning
  62. Confidence Sets for Multidimensional Scaling
  63. GraphTOP: Graph Topology-Oriented Prompting for Graph Neural Networks
  64. SmartMixed: A Two-Phase Training Strategy for Adaptive Activation Function Learning in Neural Networks
  65. Low-Precision Streaming PCA
  66. 3D Roadway Scene Object Detection with LIDARs in Snowfall Conditions
  67. Hollywood Town: Long-Video Generation via Cross-Modal Multi-Agent Orchestration
  68. Reinforcement learning-guided optimization of critical current in high-temperature superconductors
  69. Extragradient Method for (L0, L1)-Lipschitz Root-finding Problems
  70. A PyTorch Framework for Scalable Non-Crossing Quantile Regression
  71. Knowledge-guided Continual Learning for Behavioral Analytics Systems
  72. NetBurst: Event-Centric Forecasting of Bursty, Intermittent Time Series
  73. Confabulations from ACL Publications (CAP): A Dataset for Scientific Hallucination Detection
  74. A Fully Interpretable Statistical Approach for Roadside LiDAR Background Subtraction
  75. Privacy-Aware Federated nnU-Net for ECG Page Digitization
  76. Dynamic Dropout: Leveraging Conway's Game of Life for Neural Networks Regularization
  77. Efficient Large-Deformation Medical Image Registration via Recurrent Dynamic Correlation
  78. TraceTrans: Translation and Spatial Tracing for Surgical Prediction
  79. Conformalized Polynomial Chaos Expansion for Uncertainty-aware Surrogate Modeling
  80. VisJudge-Bench: Aesthetics and Quality Assessment of Visualizations
  81. GigaEmbeddings: Efficient Russian Language Embedding Model
  82. Bias Begins with Data: The FairGround Corpus for Robust and Reproducible Research on Algorithmic Fairness
  83. EndoSfM3D: Learning to 3D Reconstruct Any Endoscopic Surgery Scene using Self-supervised Foundation Model
  84. Irony Detection in Urdu Text: A Comparative Study Using Machine Learning Models and Large Language Models
  85. Design Stability in Adaptive Experiments: Implications for Treatment Effect Estimation
  86. Uncertainty quantification in model discovery by distilling interpretable material constitutive models from Gaussian process posteriors
  87. GeoDiffusion: A Training-Free Framework for Accurate 3D Geometric Conditioning in Image Generation
  88. Toward Humanoid Brain-Body Co-design: Joint Optimization of Control and Morphology for Fall Recovery
  89. Moving Beyond Diffusion: Hierarchy-to-Hierarchy Autoregression for fMRI-to-Image Reconstruction
  90. Multilingual Target-Stance Extraction
  91. LIFT: Interpretable truck driving risk prediction with literature-informed fine-tuned LLMs
  92. Graph-Coarsening Approach for the Capacitated Vehicle Routing Problem with Time Windows
  93. Monitoring State Transitions in Markovian Systems with Sampling Cost
  94. Beyond Augmentation: Leveraging Inter-Instance Relation in Self-Supervised Representation Learning
  95. Harnessing the Power of Large Language Models for Software Testing Education: A Focus on ISTQB Syllabus
  96. Memory-based Language Models: An Efficient, Explainable, and Eco-friendly Approach to Large Language Modeling
  97. AnyECG-Lab: An Exploration Study of Fine-tuning an ECG Foundation Model to Estimate Laboratory Values from Single-Lead ECG Signals
  98. T2I-RiskyPrompt: A Benchmark for Safety Evaluation, Attack, and Defense on Text-to-Image Model
  99. Stable neural networks and connections to continuous dynamical systems
  100. MetaCaDI: A Meta-Learning Framework for Causal Discovery from Multiple Environments with Unknown Interventions
All 165
  1. VietLyrics: A Large-Scale Dataset and Models for Vietnamese Automatic Lyrics Transcription
  2. Predicting Metabolic Dysfunction-Associated Steatotic Liver Disease using Machine Learning Methods: A Retrospective Cohort Study
  3. Does Homophily Help in Robust Test-time Node Classification?
  4. Machine Learning Enabled Early Warning System For Financial Distress Using Real-Time Digital Signals
  5. Supervised Fine-Tuning or In-Context Learning? Evaluating LLMs for Clinical NER
  6. Adapting Noise-Driven PUF and AI for Secure WBG ICS: A Proof-of-Concept Study
  7. GSAlign: Geometric and Semantic Alignment Network for Aerial-Ground Person Re-Identification
  8. A Multi-level Analysis of Factors Associated with Student Performance: A Machine Learning Approach to the SAEB Microdata
  9. PatenTEB: A Comprehensive Benchmark and Model Family for Patent Text Embedding
  10. Epistemic Deep Learning: Enabling Machine Learning Models to Know When They Do Not Know
  11. Accident Anticipation via Temporal Occurrence Prediction
  12. LUNA: Efficient and Topology-Agnostic Foundation Model for EEG Signal Analysis
  13. Real-Time Semantic Segmentation on FPGA for Autonomous Vehicles Using LMIINet with the CGRA4ML Framework
  14. PaperAsk: A Benchmark for Reliability Evaluation of LLMs in Paper Search and Reading
  15. Synthetic-to-Real Transfer Learning for Chromatin-Sensitive PWS Microscopy
  16. Bridging the Perceptual-Statistical Gap in Dysarthria Assessment: Why Machine Learning Still Falls Short
  17. Rational Adversaries and the Maintenance of Fragility: A Game-Theoretic Theory of Rational Stagnation
  18. Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation
  19. Audio Frequency-Time Dual Domain Evaluation on Depression Diagnosis
  20. Taming Silent Failures: A Framework for Verifiable AI Reliability
  21. HPC-Driven Modeling with ML-Based Surrogates for Magnon-Photon Dynamics in Hybrid Quantum Systems
  22. Evolution of the lexicon: a probabilistic point of view
  23. Estimating the Error of Large Language Models at Pairwise Text Comparison
  24. Enpowering Your Pansharpening Models with Generalizability: Unified Distribution is All You Need
  25. Hybrid-Vector Retrieval for Visually Rich Documents: Combining Single-Vector Efficiency and Multi-Vector Accuracy
  26. GALA: A GlobAl-LocAl Approach for Multi-Source Active Domain Adaptation
  27. DynamicTree: Interactive Real Tree Animation via Sparse Voxel Spectrum
  28. DETECT: Determining Ease and Textual Clarity of German Text Simplifications
  29. LSPRAG: LSP-Guided RAG for Language-Agnostic Real-Time Unit Test Generation
  30. Visual Model Selection using Feature Importance Clusters in Fairness-Performance Similarity Optimized Space
  31. Simplifying Knowledge Transfer in Pretrained Models
  32. The Lossy Horizon: Error-Bounded Predictive Coding for Lossy Text Compression (Episode I)
  33. TrajGATFormer: A Graph-Based Transformer Approach for Worker and Obstacle Trajectory Prediction in Off-site Construction Environments
  34. Causal Effect Estimation with TMLE: Handling Missing Data and Near-Violations of Positivity
  35. MOGRAS: Human Motion with Grasping in 3D Scenes
  36. MMbeddings: Parameter-Efficient, Low-Overfitting Probabilistic Embeddings Inspired by Nonlinear Mixed Models
  37. Multi-dataset Joint Pre-training of Emotional EEG Enables Generalizable Affective Computing
  38. Scaling Non-Parametric Sampling with Representation
  39. RGC: a radio AGN classifier based on deep learning. I. A semi-supervised multiclass model for VLA images
  40. Quantitative Bounds for Sorting-Based Permutation-Invariant Embeddings
  41. Dopamine-driven synaptic credit assignment in neural networks
  42. M-CIF: Multi-Scale Alignment For CIF-Based Non-Autoregressive ASR
  43. Measure what Matters: Psychometric Evaluation of AI with Situational Judgment Tests
  44. LT-Exosense: A Vision-centric Multi-session Mapping System for Lifelong Safe Navigation of Exoskeletons
  45. Surface Reading LLMs: Synthetic Text and its Styles
  46. I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media Interactions
  47. SentiMaithili: A Benchmark Dataset for Sentiment and Reason Generation for the Low-Resource Maithili Language
  48. Frequency-Spatial Interaction Driven Network for Low-Light Image Enhancement
  49. Power to the Clients: Federated Learning in a Dictatorship Setting
  50. Benchmarking and Learning Real-World Customer Service Dialogue
  51. STG-Avatar: Animatable Human Avatars via Spacetime Gaussian
  52. Edit Less, Achieve More: Dynamic Sparse Neuron Masking for Lifelong Knowledge Editing in LLMs
  53. Tractable Shapley Values and Interactions via Tensor Networks
  54. HandPass: A Wi-Fi CSI Palm Authentication Approach for Access Control
  55. Probing Neural Combinatorial Optimization Models
  56. egoEMOTION: Egocentric Vision and Physiological Signals for Emotion and Personality Recognition in Real-World Tasks
  57. Learning 3D Anisotropic Noise Distributions Improves Molecular Force Field Modeling
  58. CogStereo: Neural Stereo Matching with Implicit Spatial Cognition Embedding
  59. When UAV Swarm Meets IRS: Collaborative Secure Communications in Low-altitude Wireless Networks
  60. Gradual Forgetting: Logarithmic Compression for Extending Transformer Context Windows
  61. STAR-RIS-assisted Collaborative Beamforming for Low-altitude Wireless Networks
  62. Discovering Latent Graphs with GFlowNets for Diverse Conditional Image Generation
  63. Scaling Up Efficient Small Language Models Serving and Deployment for Semantic Job Search
  64. Dynamic Graph Neural Networks for Physiological Based Pharmacokinetic Modeling: A Novel Data Driven Approach to Drug Concentration Prediction
  65. Hierarchical Graph Networks for Accurate Weather Forecasting via Lightweight Training