mlsanityData to 14 Oct 2026

Papers

New on arXiv

Wed 31 Dec 2025

216 papers

  1. SAC-NeRF: Adaptive Ray Sampling for Neural Radiance Fields via Soft Actor-Critic Reinforcement LearningDeep reinforcement learning methods → RL with diffusion and flow models
  2. Speculative Decoding: Performance or Illusion?Efficient LLM inference and serving → Speculative decoding
  3. From Detection to Diagnosis: Advancing Hallucination Analysis with Automated Data SynthesisSynthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data
  4. UR-Bench: A Benchmark for Multi-Hop Reasoning over Ultra-High-Resolution ImagesLLM reasoning → Multimodal reasoning +1
  5. AzeroS: Extending LLM to Speech with Self-Generated Instruction-Free TuningSynthetic data and self-improvement for LLMs → Code and instruction data synthesis
  6. Noise-Aware and Dynamically Adaptive Federated Defense Framework for SAR Image Target RecognitionLLM safety and security → Federated unlearning and poisoning
  7. Dichotomous Diffusion Policy OptimizationDiffusion models → Diffusion and flow policies for robotics
  8. Enhancing Retrieval-Augmented Generation with Topic-Enriched Embeddings: A Hybrid Approach Integrating Traditional NLP TechniquesRetrieval-augmented generation → Generation and context integration
  9. VideoCuRL: Video Curriculum Reinforcement Learning with Orthogonal Difficulty DecompositionLLM reasoning → Multimodal reasoning +1
  10. Counterfactual Self-Questioning for Stable Policy Optimization in Language ModelsSynthetic data and self-improvement for LLMs → Synthetic reasoning data and bootstrapping
  11. Explicit Abstention Knobs for Predictable Reliability in Video Question AnsweringMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  12. Ask, Clarify, Optimize: Human-LLM Agent Collaboration for Smarter Inventory ControlLLM agents and tool use → Social simulation and multi-agent debate
  13. GRL-SNAM: Geometric Reinforcement Learning with Path Differential Hamiltonians for Simultaneous Navigation and Mapping in Unknown EnvironmentsDeep reinforcement learning methods → RL for robot navigation and UAV control
  14. The Agentic Leash: Extracting Causal Feedback Fuzzy Cognitive Maps with LLMsLLM agents and tool use → Medical and scientific domain agents
  15. Spatial4D-Bench: A Versatile 4D Spatial Intelligence BenchmarkLLM reasoning → Spatial and embodied reasoning
  16. It's Never Too Late: Noise Optimization for Collapse Recovery in Trained Diffusion ModelsDiffusion models → Diffusion foundations and sampling
  17. Reinforcement learning with timed constraints for robotics motion planningDeep reinforcement learning methods → Interpretable and logic-guided RL
  18. RIMRULE: Improving Tool-Using Language Agents via MDL-Guided Rule LearningLLM agents and tool use → Tool learning and function calling
  19. TeleWorld: Towards Dynamic Multimodal Synthesis with a 4D World ModelWorld models → Video-generation world models and simulators
  20. Large Empirical Case Study: Go-Explore adapted for AI Red Team TestingLLM agents and tool use → Agent threats, guardrails and governance +1
  21. SpaceTimePilot: Generative Rendering of Dynamic Scenes Across Space and TimeDiffusion models → Video generation
  22. Scaling Open-Ended Reasoning to Predict the FutureLLM reasoning → Time series reasoning
  23. Context-aware LLM-based AI Agents for Human-centered Energy Management Systems in Smart BuildingsLLM agents and tool use → Financial trading and forecasting agents
  24. AdaGReS:Adaptive Greedy Context Selection via Redundancy-Aware Scoring for Token-Budgeted RAGRetrieval-augmented generation → RAG robustness and adaptive retrieval
  25. Modeling Language as a Sequence of ThoughtsLLM reasoning → Test-time compute and efficient thinking
  26. ResponseRank: Data-Efficient Reward Modeling through Preference Strength LearningLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  27. Diffusion Language Models are Provably Optimal Parallel SamplersDiffusion models → Discrete and text diffusion
  28. DarkQA: Benchmarking Vision-Language Models on Visual-Primitive Question Answering in Low-Light Indoor ScenesMultimodal LLMs / vision-language models → VLM benchmarks and visual reasoning
  29. Attribution-Guided Distillation of Matryoshka Sparse AutoencodersMechanistic interpretability → Sparse autoencoder training and evaluation
  30. ShowUI-π: Flow-based Generative Models as GUI Dexterous HandsLLM agents and tool use → GUI and mobile agents
  31. AMAP Agentic Planning Technical ReportLLM agents and tool use → General LLM agent frameworks and benchmarks
  32. MSACL: Multi-Step Actor-Critic Learning with Lyapunov Certificates for Exponentially Stabilizing ControlDeep reinforcement learning methods → RL theory and sample complexity
  33. ProDM: Synthetic Reality-driven Property-aware Progressive Diffusion Model for Coronary Calcium Motion Correction in Non-gated Chest CTDiffusion models → Medical imaging and segmentation
  34. HaineiFRDM: Structure-Preserving Diffusion for Film Restoration under Fast Motion and Diverse DefectsDiffusion models → Inverse problems and image restoration
  35. Are First-Order Diffusion Samplers Really Slower? A Fast Forward-Value ApproachDiffusion models → Diffusion foundations and sampling
  36. FinMMDocR: Benchmarking Financial Multimodal Reasoning with Scenario Awareness, Document Understanding, and Multi-Step ComputationLLM reasoning → Reasoning for agents, planning and code +1
  37. Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning EcosystemLLM agents and tool use → Reinforcement learning for LLM agents
  38. VLN-MME: Diagnosing MLLMs as Language-guided Visual Navigation agentsMultimodal LLMs / vision-language models → Embodied and 3D vision-language models +1
  39. Triangulation as an Acceptance Rule for Multilingual Mechanistic InterpretabilityMechanistic interpretability → Knowledge and representations inside LLMs
  40. Unregularized Linear Convergence in Zero-Sum Game from Preference FeedbackLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  41. Learning Temporally Consistent Turbulence Between Sparse Snapshots via Diffusion ModelsDiffusion models → Flow matching, time series and science
  42. Compute-Accuracy Pareto Frontiers for Open-Source Reasoning Large Language ModelsLLM reasoning → Test-time compute and efficient thinking +1
  43. Sparse Offline Reinforcement Learning with Corruption RobustnessOffline RL and imitation learning from data → Offline RL algorithms
  44. AstroReview: An LLM-driven Multi-Agent Framework for Telescope Proposal Peer Review and RefinementLLM agents and tool use → Web, search, and research agents
  45. Control of Microrobots with Reinforcement Learning under On-Device Compute ConstraintsDeep reinforcement learning methods → Spiking and neuromorphic RL
  46. MDiffFR: Modality-Guided Diffusion Generation for Cold-start Items in Federated RecommendationDiffusion models → Diffusion recommenders
  47. LSRE: Latent Semantic Rule Encoding for Real-Time Semantic Risk Detection in Autonomous DrivingEnd-to-end autonomous driving → VLMs for autonomous driving
  48. MUSIC: MUlti-Step Instruction Contrast for Multi-Turn Reward ModelsLLM alignment / RLHF / preference optimisation → Preference alignment for recommenders and RAG
  49. R-Debater: Retrieval-Augmented Debate Generation through Argumentative MemoryRetrieval-augmented generation → RAG robustness and adaptive retrieval +1
  50. VLA-RAIL: A Real-Time Asynchronous Inference Linker for VLA Models and RobotsVision-language-action models → Efficient VLA inference and adaptation
  51. HeteroHBA: A Generative Structure-Manipulating Backdoor Attack on Heterogeneous GraphsLLM safety and security → Backdoor and data poisoning attacks
  52. RoboMIND 2.0: A Multimodal, Bimanual Mobile Manipulation Dataset for Generalizable Embodied IntelligenceOffline RL and imitation learning from data → Robot manipulation imitation learning
  53. Hybrid Motion Planning with Deep Reinforcement Learning for Mobile Robot NavigationDeep reinforcement learning methods → RL for robot navigation and UAV control
  54. How Do Agentic AI Systems Deal With Software Energy Concerns? A Pull Request-Based StudyLLM agents and tool use → Software engineering coding agents
  55. How Do Agentic AI Systems Address Performance Optimizations? A BERTopic-Based Analysis of Pull RequestsLLM agents and tool use → Software engineering coding agents
  56. Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language ModelsLLM agents and tool use → General LLM agent frameworks and benchmarks
  57. Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic SpaceLLM reasoning → Test-time compute and efficient thinking
  58. Youtu-Agent: Scaling Agent Productivity with Automated Generation and Hybrid Policy OptimizationLLM agents and tool use → General LLM agent frameworks and benchmarks
  59. Group Deliberation Oriented Multi-Agent Conversational Model for Complex ReasoningLLM reasoning → Reasoning for agents, planning and code +1
  60. Reinforcement Learning-Augmented LLM Agents for Collaborative Decision Making and Performance OptimizationLLM agents and tool use → Reinforcement learning for LLM agents
  61. Recursive Language ModelsLLM reasoning → Test-time compute and efficient thinking
  62. Robust Bayesian Dynamic Programming for On-policy Risk-sensitive Reinforcement LearningDeep reinforcement learning methods → RL theory and sample complexity
  63. Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-TimeLLM reasoning → Test-time compute and efficient thinking
  64. Korean Canonical Legal Benchmark: Toward Knowledge-Independent Evaluation of LLMs' Legal Reasoning CapabilitiesLLM reasoning → Reasoning for agents, planning and code
  65. MCPAgentBench: A Real-world Task Benchmark for Evaluating LLM Agent MCP Tool UseLLM agents and tool use → Tool learning and function calling
  66. Safe in the Future, Dangerous in the Past: Dissecting Temporal and Linguistic Vulnerabilities in LLMsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  67. From Perception to Punchline: Empowering VLM with the Art of In-the-wild MemeLLM reasoning → Multimodal reasoning
  68. PhyGDPO: Physics-Aware Groupwise Direct Preference Optimization for Physically Consistent Text-to-Video GenerationLLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment
  69. From Building Blocks to Planning: Multi-Step Spatial Reasoning in LLMs with Reinforcement LearningLLM reasoning → Spatial and embodied reasoning
  70. SEGB: Self-Evolved Generative Bidding with Local Autoregressive Diffusion
  71. Developmental trajectories of decision making and affective dynamics in large language models
  72. From Chaos to Clarity: Schema-Constrained AI for Auditable Biomedical Evidence Extraction from Full-Text PDFs
  73. GenAITEd Ghana: A First-of-Its-Kind Context-Aware and Curriculum-Aligned Conversational AI Agent for Teacher Education
  74. Islamic Chatbots in the Age of Large Language Models
  75. PriceSeer: Evaluating Large Language Models in Real-Time Stock Prediction
  76. Defense Against Synthetic Speech: Real-Time Detection of RVC Voice Conversion Attacks
  77. PCEval: A Benchmark for Evaluating Physical Computing Capabilities of Large Language Models
  78. Spiking Heterogeneous Graph Attention Networks
  79. Placenta Accreta Spectrum Detection using Multimodal Deep Learning
  80. Evaluating Contextual Intelligence in Recyclability: A Comprehensive Study of Image-Based Reasoning Systems
  81. Deep Deterministic Nonlinear ICA via Total Correlation Minimization with Matrix-Based Entropy Functional
  82. CornViT: A Multi-Stage Convolutional Vision Transformer Framework for Hierarchical Corn Kernel Analysis
  83. Investigation into U.S. Citizen and Non-Citizen Worker Health Insurance and Employment
  84. Deep Learning Framework for RNA Inverse Folding with Geometric Structure Potentials
  85. When to Ponder: Adaptive Compute Allocation for Code Generation via Test-Time Training
  86. Towards eco friendly cybersecurity: machine learning based anomaly detection with carbon and energy metrics
  87. Hierarchical topological clustering
  88. FANoS-v2: Feedback-Controlled Momentum with Thermostat Damping for Lightweight Neural Optimization
  89. Comparative Evaluation of CNN Architectures for Neural Style Transfer in Indonesian Batik Motif Generation: A Comprehensive Study
  90. Outlier Detection Using Vector Cosine Similarity by Adding a Dimension
  91. Universal Conditional Logic: A Formal Language for Prompt Engineering
  92. VL-OrdinalFormer: Vision Language Guided Ordinal Transformers for Interpretable Knee Osteoarthritis Grading
  93. Compressed Map Priors for 3D Perception
  94. Democratizing Electronic-Photonic AI Systems: An Open-Source AI-Infused Cross-Layer Co-Design and Design Automation Toolflow
  95. Toward Large-Scale Photonics-Empowered AI Systems: From Physical Design Automation to System-Algorithm Co-Exploration
  96. Constructing a Neuro-Symbolic Mathematician from First Principles
  97. A Spatially Masked Adaptive Gated Network for multimodal post-flood water extent mapping using SAR and incomplete multispectral data
  98. Mortar: Evolving Mechanics for Automatic Game Design
  99. Learning Speech Representations with Variational Predictive Coding
  100. Adaptive Constraint Propagation: Scaling Structured Inference for Large Language Models via Meta-Reinforcement Learning
All 216
  1. Dynamic Bayesian Optimization Framework for Instruction Tuning in Partial Differential Equation Discovery
  2. Exploration in the Limit
  3. Cuffless, calibration-free hemodynamic monitoring with physics-informed machine learning models
  4. IMBWatch -- a Spatio-Temporal Graph Neural Network approach to detect Illicit Massage Business
  5. Automated electrostatic characterization of quantum dot devices in single- and bilayer heterostructures
  6. When the Same Coefficients Reach Different Places: Asymmetric Realizability in Transplanting Tokenizers across Large Language Models
  7. Group Cross-Correlations with Faintly Constrained Filters
  8. Deep Learning Approach for the Diagnosis of Pediatric Pneumonia Using Chest X-ray Imaging
  9. GaMO: Geometry-aware Multi-view Diffusion Outpainting for Sparse-View 3D Reconstruction
  10. Coordinated Humanoid Manipulation with Choice Policies
  11. Edit3r: Instant 3D Scene Editing from Sparse Unposed Images
  12. FineTec: Fine-Grained Action Recognition Under Temporal Corruption via Skeleton Decomposition and Sequence Completion
  13. From Inpainting to Editing: Unlocking Robust Mask-Free Visual Dubbing via Generative Bootstrapping
  14. Vulcan: Instance-specialized, Verifiable Systems Heuristics Through LLM-driven Search
  15. Many Minds from One Model: Bayesian-Inspired Transformers for Population Diversity
  16. On the geometry and topology of representations: the manifolds of modular addition
  17. Reliable and Resilient Collective Communication Library for LLM Training and Serving
  18. Generative Classifiers Avoid Shortcut Solutions
  19. Convergence of the generalization error for deep gradient flow methods for PDEs
  20. MAMA-Memeia! Multi-Aspect Multi-Agent Collaboration for Depressive Symptoms Identification in Memes
  21. FoundationSLAM: Unleashing the Power of Depth Foundation Models for End-to-End Dense Visual SLAM
  22. Bi-C2R: Bidirectional Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification
  23. Basic Inequalities for First-Order Optimization with Applications to Statistical Risk Analysis
  24. Classifying long legal documents using short random chunks
  25. Efficiently Estimating Data Efficiency for Language Model Fine-tuning
  26. PhysTalk: Language-driven Real-time Physics in 3D Gaussian Scenes
  27. A Modal Logic for Possibilistic Reasoning with Fuzzy Formal Contexts
  28. SymSeqBench: a unified framework for the generation and analysis of rule-based symbolic sequences and datasets
  29. Evaluating the Impact of Compression Techniques on the Robustness of CNNs under Natural Corruptions
  30. Large language models and the entropy of English
  31. Strategic Response of News Publishers to Generative AI
  32. Semi-overlapping Multi-bandit Best Arm Identification for Sequential Support Network Learning
  33. Beyond the Last Frame: Process-aware Evaluation for Generative Video Reasoning
  34. CPJ: Explainable Agricultural Pest Diagnosis via Caption-Prompt-Judge with LLM-Judged Refinement
  35. RAIR: A Rule-Aware Benchmark Uniting Challenging Long-Tail and Visual Salience Subset for E-commerce Relevance Assessment
  36. Iterative Deployment Improves Planning Skills in LLMs
  37. Vibe Coding, Interface Flattening
  38. ADOPT: Adaptive Dependency-Guided Joint Prompt Optimization for Multi-Step LLM Pipelines
  39. Semi-Supervised Diversity-Aware Domain Adaptation for 3D Object detection
  40. Frequent subgraph-based persistent homology for graph classification
  41. AI-Driven Cloud Resource Optimization for Multi-Cluster Environments
  42. Spectral Graph Neural Networks for Cognitive Task Classification in fMRI Connectomes
  43. PRISM: A hierarchical multiscale approach for time series forecasting
  44. Semi-Automated Data Annotation in Multisensor Datasets for Autonomous Vehicle Testing
  45. Towards autonomous time-calibration of large quantum-dot devices: Detection, real-time feedback, and noise spectroscopy
  46. BEDA: Belief Estimation as Probabilistic Constraints for Performing Strategic Dialogue Acts
  47. mHC: Manifold-Constrained Hyper-Connections
  48. Encyclo-K: Evaluating LLMs with Dynamically Composed Knowledge Statements
  49. Characterization of Transfer Using Multi-task Learning Curves
  50. Big AI is accelerating the metacrisis: What can we do?
  51. OFL-SAM2: Prompt SAM2 with Online Few-shot Learner for Efficient Medical Image Segmentation
  52. A study on constraint extraction and exception exclusion in care worker scheduling
  53. PrivacyBench: A Conversational Benchmark for Evaluating Privacy in Personalized AI
  54. AODDiff: Probabilistic Reconstruction of Aerosol Optical Depth via Diffusion-based Bayesian Inference
  55. CropTrack: A Tracking with Re-Identification Framework for Precision Agriculture
  56. GenZ: Foundational models as latent variable generators within traditional statistical models
  57. Explaining Why Things Go Where They Go: Interpretable Constructs of Human Organizational Preferences
  58. Inter-Agent Relative Representations for Multi-Agent Option Discovery
  59. Video and Language Alignment in 2D Systems for 3D Multi-object Scenes with Multi-Information Derivative-Free Control
  60. Practising responsibility: Ethics in NLP as a hands-on course
  61. DTI-GP: Bayesian operations for drug-target interactions using deep kernel Gaussian processes
  62. Limits of quantum generative models with classical sampling hardness
  63. LeanCat: A Benchmark Suite for Formal Category Theory in Lean (Part I: 1-Categories)
  64. Nonlinear Noise2Noise for Efficient Monte Carlo Denoiser Training
  65. Self-Supervised Neural Architecture Search for Multimodal Deep Neural Networks
  66. Projection-based Adversarial Attack using Physics-in-the-Loop Optimization for Monocular Depth Estimation
  67. HiGR: Industrial-Scale Hierarchical Generative Slate Recommendation Framework in Tencent
  68. Gradient Descent as Implicit EM in Distance-Based Neural Models
  69. Uncertainty-aware Semi-supervised Ensemble Teacher Framework for Multilingual Depression Detection
  70. From Trial to Deployment: A SEM Analysis of Traveler Adoptions to Fully Operational Autonomous Taxis
  71. Dream2Flow: Bridging Video Generation and Open-World Manipulation with 3D Object Flow
  72. UniC-Lift: Unified 3D Instance Segmentation via Contrastive Learning
  73. Fairness-Aware Insurance Pricing: A Multi-Objective Optimization Approach
  74. Splatwizard: A Benchmark Toolkit for 3D Gaussian Splatting Compression
  75. BIOME-Bench: A Benchmark for Biomolecular Interaction Inference and Multi-Omics Pathway Mechanism Elucidation from Scientific Literature
  76. EchoFoley: Event-Centric Hierarchical Control for Video Grounded Creative Sound Generation
  77. FlowBlending: Stage-Aware Multi-Model Sampling for Fast and High-Fidelity Video Generation
  78. FPGA Co-Design for Efficient N:M Sparse and Quantized Model Inference
  79. BandiK: Efficient Multi-Task Decomposition Using a Multi-Bandit Framework
  80. Evolving, Not Training: Zero-Shot Reasoning Segmentation via Evolutionary Prompting
  81. Causal Discovery with Mixed Latent Confounding via Precision Decomposition
  82. Nested Learning: The Illusion of Deep Learning Architectures
  83. Mobility-Assisted Decentralized Federated Learning: Convergence Analysis and A Data-Driven Approach
  84. Quantum Visual Word Sense Disambiguation: Unraveling Ambiguities Through Quantum Inference Model
  85. BatteryAgent: Synergizing Physics-Informed Interpretation with LLM Reasoning for Intelligent Battery Fault Diagnosis
  86. Multi-modal cross-domain mixed fusion model with dual disentanglement for fault diagnosis under unseen working conditions
  87. A New Decomposition Paradigm for Graph-structured Nonlinear Programs via Message Passing
  88. An Adaptive, Disentangled Representation for Multidimensional MRI Reconstruction
  89. Renormalization Group Guided Tensor Network Structure Search
  90. Do Large Language Models Know What They Are Capable Of?
  91. Diagnosing Heteroskedasticity and Resolving Multicollinearity Paradoxes in Physicochemical Property Prediction
  92. From Sequential to Spatial: Reordering Autoregression for Efficient Visual Generation
  93. DynaFix: Iterative Automated Program Repair Driven by Execution-Level Dynamic Information
  94. Soliton profiles: Classical Numerical Schemes vs. Neural Network - Based Solvers
  95. AI-Driven Acoustic Voice Biomarker-Based Hierarchical Classification of Benign Laryngeal Voice Disorders from Sustained Vowels
  96. AutoFed: Personalized Federated Traffic Prediction via Adaptive Prompt
  97. FireRescue: A UAV-Based Dataset and Enhanced YOLO Model for Object Detection in Fire Rescue Scenes
  98. LLHA-Net: A Hierarchical Attention Network for Two-View Correspondence Learning
  99. Chat-Driven Optimal Management for Virtual Network Services
  100. MoniRefer: A Real-world Large-scale Multi-modal Dataset based on Roadside Infrastructure for 3D Visual Grounding
  101. Collaborative Low-Rank Adaptation for Pre-Trained Vision Transformers
  102. 3D Semantic Segmentation for Post-Disaster Assessment
  103. GH-ESD: Grounded Hypothesis-Driven Error Slice Discovery for Instance-Level Vision Tasks
  104. Improving Few-Shot Change Detection Visual Question Answering via Decision-Ambiguity-guided Reinforcement Fine-Tuning
  105. MultiRisk: Multiple Risk Control via Iterative Score Thresholding
  106. SynRAG: A Large Language Model Framework for Executable Query Generation in Heterogeneous SIEM System
  107. CPR: Causal Physiological Representation Learning for Robust ECG Analysis under Distribution Shifts
  108. HaluNet: Learning Hallucination Risk from Internal Signals in LLM Question Answering
  109. RGBT-GroundBench: Visual Grounding Beyond RGB in Complex Real-World Scenarios
  110. Localized Calibrated Uncertainty in Code Language Models
  111. Probabilistic Computers for Neural Quantum States
  112. OCP-GN: A Scalable Second-order Optimizer for Stochastic Optimization
  113. Hierarchical Vector-Quantized Latents for Perceptual Low-Resolution Video Compression
  114. More Than Bits: Multi-Envelope Double Binary Factorization for Extreme Quantization
  115. A Graph Neural Network with Auxiliary Task Learning for Missing PMU Data Reconstruction
  116. Generative AI-enhanced Sector-based Investment Portfolio Construction