mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sun 2 Nov 2025

153 papers

  1. Clustering-Based Weight Orthogonalization for Stabilizing Deep Reinforcement LearningDeep reinforcement learning methods → Deep RL algorithms and representations
  2. Spectral Neuro-Symbolic Reasoning II: Semantic Node Merging, Entailment Filtering, and Knowledge Graph AlignmentLLM reasoning → Knowledge- and tool-augmented reasoning
  3. Empirical Characterization of Temporal Constraint Processing in LLMsLLM agents and tool use → General LLM agent frameworks and benchmarks
  4. AGRAG: Advanced Graph-based Retrieval-Augmented Generation for LLMsLLM reasoning → Knowledge- and tool-augmented reasoning +1
  5. Shorter but not Worse: Frugal Reasoning via Easy Samples as Length Regularizers in Math RLVRLLM reasoning → Test-time compute and efficient thinking
  6. Tool Zero: Training Tool-Augmented LLMs via Pure RL from ScratchLLM agents and tool use → Reinforcement learning for LLM agents
  7. Dynamic Population Distribution Aware Human Trajectory Generation with Diffusion ModelDiffusion models → Diffusion and flow policies for robotics
  8. HarnessLLM: Automatic Testing Harness Generation via Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  9. Continual Learning, Not Training: Online Adaptation For AgentsLLM agents and tool use → Agent memory systems
  10. Efficient Test-Time Retrieval Augmented GenerationRetrieval-augmented generation → RAG pipeline design and evaluation
  11. HAFixAgent: History-Aware Program Repair AgentLLM agents and tool use → Software engineering coding agents
  12. Prompt-R1: Collaborative Automatic Prompting Framework via End-to-end Reinforcement LearningDeep reinforcement learning methods → RL training of language and agent models
  13. MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQLLLM agents and tool use → Web, search, and research agents
  14. GauDP: Reinventing Multi-Agent Collaboration through Gaussian-Image Synergy in Diffusion PoliciesDiffusion models → Diffusion and flow policies for robotics
  15. Aligning LLM agents with human learning and adjustment behavior: a dual agent approachLLM agents and tool use → Multimodal and embodied agents
  16. The Riddle of Reflection: Evaluating Reasoning and Self-Awareness in Multilingual LLMs using Indian RiddlesLLM reasoning → Reasoning benchmarks and evaluation
  17. Sighted by Default: Addressing Implicit Vision Assumptions in Real-Time VLM Assistance for BLV UsersMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  18. URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language ModelWorld models → Embodied and robot world models +1
  19. Fast-SmartWay: Panoramic-Free End-to-End Zero-Shot Vision-and-Language NavigationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  20. Maestro: Orchestrating Robotics Modules with Vision-Language Models for Zero-Shot Generalist RobotsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  21. Fleming-VL: Towards Universal Medical Visual Reasoning with Multimodal LLMsLLM reasoning → Clinical and biomedical applications +1
  22. GraphGeo: Multi-Agent Debate Framework for Visual Geo-localization with Heterogeneous Graph Neural NetworksLLM agents and tool use → Multimodal and embodied agents
  23. ColMate: Contrastive Late Interaction and Masked Text for Multimodal Document RetrievalRetrieval-augmented generation → Multimodal RAG
  24. Deep Generative Models for Enhanced Vitreous OCT ImagingDiffusion models → Medical imaging and segmentation
  25. KFCPO: Kronecker-Factored Approximated Constrained Policy OptimizationDeep reinforcement learning methods → Safe and constrained RL
  26. Assessing LLM Reasoning Steps via Principal Knowledge GroundingLLM reasoning → Reasoning benchmarks and evaluation
  27. A Comprehensive Empirical Evaluation of Agent Frameworks on Code-centric Software Engineering TasksLLM agents and tool use → Software engineering coding agents
  28. FlexiCache: Leveraging Temporal Stability of Attention Heads for Efficient KV Cache ManagementEfficient LLM inference and serving → KV cache optimization
  29. Occlusion-Aware Diffusion Model for Pedestrian Intention PredictionDiffusion models → Diffusion and flow policies for robotics
  30. All-in-one Graph-based Indexing for Hybrid Search on GPUsRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  31. OmniBrainBench: A Comprehensive Multimodal Benchmark for Brain Imaging Analysis Across Multi-stage Clinical TasksMultimodal LLMs / vision-language models → Medical vision-language models
  32. Portal UX Agent -- A Plug-and-Play Engine for Rendering UIs from Natural Language SpecificationsLLM agents and tool use → GUI and mobile agents
  33. OMEGA: Optimized Multimodal Position Encoding Index Derivation with Global Adaptive Scaling for Vision-Language ModelsMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  34. Equilibrium Policy Generalization: A Reinforcement Learning Framework for Cross-Graph Zero-Shot Generalization in Pursuit-Evasion GamesDeep reinforcement learning methods → Adversarial robustness and RL in finance
  35. GUI-AIMA: Aligning Intrinsic Multimodal Attention with a Context Anchor for GUI GroundingLLM agents and tool use → GUI and mobile agents
  36. Do Math Reasoning LLMs Help Predict the Impact of Public Transit Events?LLM reasoning → Reinforcement learning for reasoning
  37. Logic-informed reinforcement learning for cross-domain optimization of large-scale cyber-physical systemsDeep reinforcement learning methods → Safe and constrained RL
  38. EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven AlignmentLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  39. GrowthHacker: Automated Off-Policy Evaluation Optimization Using Code-Modifying LLM AgentsLLM agents and tool use → General LLM agent frameworks and benchmarks
  40. Efficient Reinforcement Learning for Large Language Models with Intrinsic ExplorationLLM reasoning → Reinforcement learning for reasoning
  41. Active Thinking Model: A Goal-Directed Self-Improving Framework for Real-World Adaptive IntelligenceLLM reasoning → Test-time compute and efficient thinking
  42. Self-Consistency Is Losing Its Edge: Diminishing Returns and Rising Costs in Modern LLMsLLM reasoning → Test-time compute and efficient thinking
  43. Malliavin Calculus as Stochastic Backpropogation
  44. The Impact of LLM-Generated Reviews on Recommender Systems: Textual Shifts, Performance Effects, and Strategic Platform Control
  45. Video Models Start to Solve Chess, Maze, Sudoku, Mental Rotation, and Raven' Matrices
  46. Hybrid Quantum Transformer for Language Generation
  47. Evaluating DisCoCirc in Translation Tasks & its Limitations: A Comparative Study Between Bengali & English
  48. Two Datasets Are Better Than One: Method of Double Moments for 3-D Reconstruction in Cryo-EM
  49. Deep one-gate per layer networks with skip connections are universal classifiers
  50. In-Context-Learning-Assisted Quality Assessment Vision-Language Models for Metal Additive Manufacturing
  51. Assessing Factual Music Comprehension in Large Audio Language Models
  52. Communication-Constrained Private Decentralized Online Personalized Mean Estimation
  53. A Dynamic Recurrent Adjacency Memory Network for Mixed-Generation Power System Stability Forecasting
  54. AI-driven Large-scale Electron Microscopy enables Whole-tissue Subcellular Digitization
  55. The Geometry of Grokking: Norm Minimization on the Zero-Loss Manifold
  56. Q-Sat AI: Machine Learning-Based Decision Support for Data Saturation in Qualitative Studies
  57. Deciphering Personalization: Towards Fine-Grained Explainability in Natural Language for Personalized Image Generation Models
  58. A Unified Model for Human Mobility Generation in Natural Disasters
  59. Learning-Guided Integration Contours Construction for Fast Large-Scale Generalized Eigensolvers
  60. Neural Green's Functions
  61. Generative Machine Learning Models for the Deconvolution of Charge Carrier Dynamics in Organic Photovoltaic Cells
  62. S2Doc -- Spatial-Semantic Document Format
  63. Anatomically Constrained Transformers for Echocardiogram Analysis
  64. SLAP: Shortcut Learning for Abstract Planning
  65. TSVer: A Benchmark for Fact Verification Against Time-Series Evidence
  66. Epanechnikov nonparametric kernel density estimation based feature-learning in respiratory disease chest X-ray images
  67. Hyper Hawkes Processes: Interpretable Models of Marked Temporal Point Processes
  68. Improving Romanian LLM Pretraining Data using Diversity and Quality Filtering
  69. SliceVision-F2I: A Synthetic Feature-to-Image Dataset for Visual Pattern Representation on Network Slices
  70. GeoToken: Hierarchical Geolocalization of Images via Next Token Prediction
  71. T-MLA: A targeted multiscale log-exponential attack framework for neural image compression
  72. AI Progress Should Be Measured by Capability-Per-Resource, Not Scale Alone: A Framework for Gradient-Guided Resource Allocation in LLMs
  73. Happiness as a Measure of Fairness
  74. HPLT 3.0: Very Large-Scale Multilingual Resources for LLMs and MT. Mono- and Bi-lingual Data, Multilingual Evaluation, and Pre-Trained Models
  75. Generalized Guarantees for Variational Inference in the Presence of Even and Elliptical Symmetry
  76. Energy-Efficient Deep Learning Without Backpropagation: A Rigorous Hardware-Validated Benchmarking Study of Forward-Only Algorithms
  77. Window-Based Feature Engineering for Cognitive Workload Detection
  78. MedEqualizer: A Framework Investigating Bias in Synthetic Medical Data and Mitigation via Augmentation
  79. Building a Silver-Standard Dataset from NICE Guidelines for Clinical LLMs
  80. Knowledge Elicitation with Large Language Models for Interpretable Cancer Stage Identification from Pathology Reports
  81. VayuChat: An LLM-Powered Conversational Interface for Air Quality Data Analytics
  82. Binary perceptron computational gap -- a parametric fl RDT view
  83. On the Emergence of Induction Heads for In-Context Learning
  84. FastBoost: Progressive Attention with Dynamic Scaling for Efficient Deep Learning
  85. Seed-Induced Uniqueness in Transformer Models: Subspace Alignment Governs Subliminal Transfer
  86. OceanAI: A Conversational Platform for Accurate, Transparent, Near-Real-Time Oceanographic Insights
  87. AI for pRedicting Exacerbations in KIDs with aSthma (AIRE-KIDS)
  88. SARIMAX-Based Power Outage Prediction During Extreme Weather Events
  89. What's the next frontier for Data-centric AI? Data Savvy Agents
  90. IF-CRITIC: Towards a Fine-Grained LLM Critic for Instruction-Following Evaluation
  91. HyFormer-Net: A Synergistic CNN-Transformer with Interpretable Multi-Scale Fusion for Breast Lesion Segmentation and Classification in Ultrasound Images
  92. Equality Graph Assisted Symbolic Regression
  93. None To Optima in Few Shots: Bayesian Optimization with MDP Priors
  94. Integrating Visual and X-Ray Machine Learning Features in the Study of Paintings by Goya
  95. Transformer-Based Decoding in Concatenated Coding Schemes Under Synchronization Errors
  96. MID: A Self-supervised Multimodal Iterative Denoising Framework
  97. Hydra: Dual Exponentiated Memory for Multivariate Time Series Analysis
  98. Advancing Machine-Generated Text Detection from an Easy to Hard Supervision Perspective
  99. Balanced Multimodal Learning via Mutual Information
  100. ORANGE: An Online Reflection ANd GEneration framework with Domain Knowledge for Text-to-SQL
All 153
  1. VesSAM: Efficient Multi-Prompting for Segmenting Complex Vessel
  2. Modeling Microenvironment Trajectories on Spatial Transcriptomics with NicheFlow
  3. Keys in the Weights: Transformer Authentication Using Model-Bound Latent Representations
  4. Using Synthetic Data to estimate the True Error is theoretically and practically doable
  5. A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis
  6. The Hidden Power of Normalization Layers in Neural Networks: Exponential Capacity Control
  7. RefTon: Reference person shot assist virtual Try-on
  8. Motion-Robust Multimodal Fusion of PPG and Accelerometer Signals for Three-Class Heart Rhythm Classification
  9. LLMs Position Themselves as More Rational Than Humans: Emergence of AI Self-Awareness Measured Through Game Theory
  10. Dynamic Multi-level Weighted Alignment Network for Zero-shot Sketch-based Image Retrieval
  11. The Biased Oracle: Assessing LLMs' Understandability and Empathy in Medical Diagnoses
  12. Towards Channel Charting Enhancement with Non-Reconfigurable Intelligent Surfaces
  13. Transformers as Intrinsic Optimizers: Forward Inference through the Energy Principle
  14. Random Spiking Neural Networks are Stable and Spectrally Simple
  15. Learning with Category-Equivariant Representations for Human Activity Recognition
  16. Dynamic Logic of Trust-Based Beliefs
  17. Android Malware Detection: A Machine Leaning Approach
  18. HEATNETs: Explainable Random Feature Neural Networks for High-Dimensional Parabolic PDEs
  19. SpEx: A Spectral Approach to Explainable Clustering
  20. Controlling Gender Bias in Retrieval via a Backpack Architecture
  21. Training with Fewer Bits: Unlocking Edge LLMs Training with Stochastic Rounding
  22. Fast Stochastic Greedy Algorithm for k-Submodular Cover Problem
  23. Layer-Wise Modality Decomposition for Interpretable Multimodal Sensor Fusion
  24. TriCon-Fair: Triplet Contrastive Learning for Mitigating Social Bias in Pre-trained Language Models
  25. Identifying Slug Formation in Oil Well Pipelines: A Use Case from Industrial Analytics
  26. MULTI-Bench: A Multi-Turn Interactive Benchmark for Assessing Emotional Intelligence ability of Spoken Dialogue Models
  27. Perturbations in the Orthogonal Complement Subspace for Efficient Out-of-Distribution Detection
  28. Pay for The Second-Best Service: A Game-Theoretic Approach Against Dishonest LLM Providers
  29. CodeClash: Benchmarking Goal-Oriented Software Engineering
  30. Parameter Interpolation Adversarial Training for Robust Image Classification
  31. Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials
  32. Enhancing Adversarial Transferability in Visual-Language Pre-training Models via Local Shuffle and Sample-based Attack
  33. Towards Ultra-Low Latency: Binarized Neural Network Architectures for In-Vehicle Network Intrusion Detection
  34. Optimizing Native Sparse Attention with Latent Attention and Local Global Alternating Strategies
  35. TA-LSDiff:Topology-Aware Diffusion Guided by a Level Set Energy for Pancreas Segmentation
  36. Real-Time Learning of Predictive Dynamic Obstacle Models for Robotic Motion Planning
  37. LL-ViT: Edge Deployable Vision Transformers with Look Up Table Neurons
  38. Med-Banana: Learning Quality-Controlled Medical Image Editing from Success-and-Failure Trajectories
  39. Attention Saturation and Gradient Suppression at Inflection Layers: Diagnosing and Mitigating Bottlenecks in Transformer Adaptation
  40. AReaL-Hex: Accommodating Asynchronous RL Training over Heterogeneous GPUs
  41. FedOnco-Bench: A Reproducible Benchmark for Privacy-Aware Federated Tumor Segmentation with Synthetic CT Data
  42. Fast PINN Eigensolvers via Biconvex Reformulation
  43. Class-agnostic 3D Segmentation by Granularity-Consistent Automatic 2D Mask Tracking
  44. Count-Based Approaches Remain Strong: A Benchmark Against Transformer and LLM Pipelines on Structured EHR
  45. A Hybrid YOLOv5-SSD IoT-Based Animal Detection System for Durian Plantation Protection
  46. Quantifying truth and authenticity in AI-assisted candidate evaluation: A multi-domain pilot analysis
  47. Reliable Curation of EHR Dataset via Large Language Models under Environmental Constraints
  48. A Framework Based on Graph Cellular Automata for Similarity Evaluation in Urban Spatial Networks
  49. A Quantitative Study of Sustained Focus in Large Language Models via Repetitive Deterministic Prediction Tasks
  50. Trust Region-Based Bayesian Optimisation to Discover Diverse Solutions
  51. Erasing 'Ugly' from the Internet: Propagation of the Beauty Myth in Text-Image Models
  52. Effective Series Decomposition and Components Learning for Time Series Generation
  53. Correspondence Between Ising Machines and Neural Networks