mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 30 Aug 2025

157 papers

  1. FinFlowRL: An Imitation-Reinforcement Learning Framework for Adaptive Stochastic Control in FinanceDeep reinforcement learning methods → Adversarial robustness and RL in finance
  2. Inducing State Anxiety in LLM Agents Reproduces Human-Like Biases in Consumer Decision-MakingLLM agents and tool use → Social simulation and multi-agent debate
  3. SABR: A Stable Adaptive Bitrate Framework Using Behavior Cloning Pretraining and Reinforcement Learning Fine-TuningDeep reinforcement learning methods → Deep RL algorithms and representations
  4. Attention of a Kiss: Exploring Attention Maps in Video Diffusion for XAIxArtsDiffusion models → Video generation
  5. Context-Aware Knowledge Distillation with Adaptive Weighting for Image ClassificationKnowledge distillation → General knowledge distillation methods
  6. Backdoor Samples Detection Based on Perturbation Discrepancy Consistency in Pre-trained Language ModelsLLM safety and security → Backdoor and data poisoning attacks
  7. Discrete Prompt Tuning via Recursive Utilization of Black-box Multimodal Large Language Model for Personalized Visual Emotion RecognitionMultimodal LLMs / vision-language models → Multimodal emotion understanding
  8. ParaThinker: Native Parallel Thinking as a New Paradigm to Scale LLM Test-time ComputeLLM reasoning → Test-time compute and efficient thinking
  9. Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time ScalingLLM reasoning → Test-time compute and efficient thinking +1
  10. Can Multi-turn Self-refined Single Agent LMs with Retrieval Solve Hard Coding Problems?LLM agents and tool use → Software engineering coding agents
  11. NetGent: Agent-Based Automation of Network Application WorkflowsLLM agents and tool use → Software engineering coding agents
  12. TimeCopilotLLM agents and tool use → Financial trading and forecasting agents
  13. DGL-RSIS: Decoupling Global Spatial Context and Local Class Semantics for Training-Free Remote Sensing Image SegmentationMultimodal LLMs / vision-language models → Embodied and 3D vision-language models
  14. SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error CorrectionLLM agents and tool use → Web, search, and research agents
  15. KVComp: A High-Performance, LLM-Aware, Lossy Compression Framework for KV CacheEfficient LLM inference and serving → KV cache optimization
  16. Galaxea Open-World Dataset and G0 Dual-System VLA ModelVision-language-action models → Generalist VLA models and benchmarks
  17. Learning Dolly-In Filming From Demonstration Using a Ground-Based RobotOffline RL and imitation learning from data → Imitation learning methods
  18. Gray-Box Computed Torque Control for Differential-Drive Mobile Robot TrackingDeep reinforcement learning methods → RL for robot locomotion and manipulation
  19. ConceptBot: Enhancing Robot's Autonomy through Task Decomposition with Large Language Models and Knowledge GraphLLM reasoning → Spatial and embodied reasoning
  20. Reinforcement Learning of Dolly-In Filming Using a Ground-Based RobotDeep reinforcement learning methods → RL for robot locomotion and manipulation
  21. Efficient Graph Knowledge Distillation from GNNs to Kolmogorov--Arnold Networks via Self-Attention Dynamic SamplingKnowledge distillation → Graph neural network distillation
  22. Social World ModelsWorld models → World models for language agents
  23. When Thinking Backfires: Mechanistic Insights Into Reasoning-Induced MisalignmentLLM reasoning → Reasoning benchmarks and evaluation
  24. LatentEdit: Adaptive Latent Control for Consistent Semantic EditingDiffusion models → Image generation, text-to-image and editing
  25. MobiAgent: A Systematic Framework for Customizable Mobile AgentsLLM agents and tool use → GUI and mobile agents
  26. Modeling Motivated Reasoning in Law: Evaluating Strategic Role Conditioning in LLM SummarizationLLM reasoning → Reasoning for agents, planning and code
  27. Learning Yourself: Class-Incremental Semantic Segmentation with Language-Inspired Bootstrapped DisentanglementSynthetic data and self-improvement for LLMs → Self-improving MLLMs and synthetic data
  28. ERank: Fusing Supervised Fine-Tuning and Reinforcement Learning for Effective and Efficient Text RerankingRetrieval-augmented generation → Generation and context integration +1
  29. VideoRewardBench: Comprehensive Evaluation of Multimodal Reward Models for Video UnderstandingMultimodal LLMs / vision-language models → Video understanding with MLLMs +1
  30. Talk Less, Call Right: Enhancing Role-Play LLM Agents with Automatic Prompt Optimization and Role PromptingLLM agents and tool use → Social simulation and multi-agent debate
  31. Multi-Agent Data Visualization and Narrative GenerationLLM agents and tool use → Multimodal and embodied agents
  32. Partially Functional Dynamic Backdoor Diffusion-based Causal ModelDiffusion models → Diffusion foundations and sampling
  33. Embodied Spatial Intelligence: from Implicit Scene Modeling to Spatial ReasoningLLM reasoning → Spatial and embodied reasoning
  34. CVPD at QIAS 2025 Shared Task: An Efficient Encoder-Based Approach for Islamic Inheritance ReasoningLLM reasoning → Reasoning for agents, planning and code
  35. GOSU: Retrieval-Augmented Generation with Global-Level Optimized Semantic Unit-Centric FrameworkRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  36. Benchmarking Agentic Newswriting via Journalistic WorkflowsLLM agents and tool use → Web, search, and research agents
  37. Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face GenerationDiffusion models → Image generation, text-to-image and editing
  38. The Gold Medals in an Empty Room: Diagnosing Metalinguistic Reasoning in LLMs with CamlangLLM reasoning → Reasoning benchmarks and evaluation
  39. LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache CompressionMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  40. Double-Constraint Diffusion Model with Nuclear Regularization for Ultra-low-dose PET ReconstructionDiffusion models → Medical imaging and segmentation
  41. The Resurgence of GCG Adversarial Attacks on Large Language ModelsLLM safety and security → Jailbreaking
  42. Beyond Negative Transfer: Disentangled Preference-Guided Diffusion for Cross-Domain Sequential RecommendationDiffusion models → Diffusion recommenders
  43. GraphKV: Breaking the Static Selection Paradigm with Graph-Based KV Cache EvictionEfficient LLM inference and serving → KV cache optimization
  44. Domain Adaptation-Based Crossmodal Knowledge Distillation for 3D Semantic SegmentationKnowledge distillation → Detection and dense prediction distillation
  45. NoiseCutMix: A Novel Data Augmentation Approach by Mixing Estimated Noise in Diffusion ModelsDiffusion models → Image generation, text-to-image and editing
  46. Open Data Synthesis For Deep ResearchSynthetic data and self-improvement for LLMs → LLM synthetic data generation
  47. Activation Steering Meets Preference Optimization: Defense Against Jailbreaks in Vision Language ModelsMultimodal LLMs / vision-language models → MLLM jailbreaks and adversarial robustness +3
  48. Two Causes, Not One: Rethinking Omission and Fabrication Hallucinations in MLLMsLLM reasoning → Hallucination detection and mitigation +1
  49. KG-RAG: Enhancing GUI Agent Decision-Making via Knowledge Graph-Driven Retrieval-Augmented GenerationRetrieval-augmented generation → Agentic RAG, agents and memory +1
  50. SurgLLM: A Versatile Large Multimodal Model with Spatial Focus and Temporal Awareness for Surgical Video UnderstandingMultimodal LLMs / vision-language models → Medical vision-language models
  51. LLM-Driven Policy Diffusion: Enhancing Generalization in Offline Reinforcement LearningOffline RL and imitation learning from data → Decision transformers and sequence modeling
  52. Scalable Option Learning in High-Throughput EnvironmentsDeep reinforcement learning methods → Deep RL algorithms and representations
  53. Are We Really Learning the Score Function? Reinterpreting Diffusion Models Through Wasserstein Gradient Flow MatchingDiffusion models → Diffusion foundations and sampling
  54. Jacobian Exploratory Dual-Phase Reinforcement Learning for Dynamic Endoluminal Navigation of Deformable Continuum RobotsDeep reinforcement learning methods → RL for robot locomotion and manipulation
  55. Mechanistic interpretability for steering vision-language-action modelsVision-language-action models → Generalist VLA models and benchmarks +1
  56. TrimTokenator: Towards Adaptive Visual Token Pruning for Large Multimodal ModelsMultimodal LLMs / vision-language models → Visual token pruning and efficiency +1
  57. Continuously Tempered Diffusion SamplersDiffusion models → Diffusion foundations and sampling
  58. Balanced Actor Initialization: Stable RLHF Training of Distillation-Based Reasoning ModelsLLM reasoning → Reinforcement learning for reasoning +1
  59. Language-Aware Information Maximization for Transductive Few-Shot CLIPMultimodal LLMs / vision-language models → Prompt learning and adaptation of CLIP
  60. FlexLink: Boosting your NVLink Bandwidth by 27% without accuracy concern
  61. A Cost-Benefit Analysis of On-Premise Large Language Model Deployment: Breaking Even with Commercial LLM Services
  62. DarwinWafer: A Wafer-Scale Neuromorphic Chip
  63. Dual Actor DDPG for Airborne STAR-RIS Assisted Communications
  64. ProteuS: A Generative Approach for Simulating Concept Drift in Financial Markets
  65. Deep opacity and AI: A threat to XAI and to privacy protection mechanisms
  66. A Kriging-HDMR-based surrogate model with sample pool-free active learning strategy for reliability analysis
  67. Zero-Knowledge Proofs in Sublinear Space
  68. SynDelay: A Synthetic Dataset for Delivery Delay Prediction
  69. Perception Graph for Cognitive Attack Reasoning in Augmented Reality
  70. Application of discrete Ricci curvature in pruning randomly wired neural networks: A case study with chest x-ray classification of COVID-19
  71. A Dataset Generation Scheme Based on Video2EEG-SPGN-Diffusion for SEED-VD
  72. Privacy-Preserving Offloading for Large Language Models in 6G Vehicular Networks
  73. No Clustering, No Routing: How Transformers Actually Process Rare Tokens
  74. An End-to-End System for Culturally-Attuned Driving Feedback using a Dual-Component NLG Engine
  75. Universal Representation of Generalized Convex Functions and their Gradients
  76. Training Text-to-Molecule Models with Context-Aware Tokenization
  77. Is Synthetic Image Augmentation Useful for Imbalanced Classification Problems? Case-Study on the MIDOG2025 Atypical Cell Detection Competition
  78. Resilient Biosecurity in the Era of AI-Enabled Bioweapons
  79. Contrastive clustering based on regular equivalence for influential node identification in complex networks
  80. Towards Digital Twins for Optimal Radioembolization
  81. NMR-Solver: Automated Structure Elucidation via Large-Scale Spectral Matching and Physics-Guided Fragment Optimization
  82. Disentangling Slow and Fast Temporal Dynamics in Degradation Inference with Hierarchical Differential Models
  83. Quantum Circuits for Quantum Convolutions: A Quantum Convolutional Autoencoder
  84. Enabling Trustworthy Federated Learning via Remote Attestation for Mitigating Byzantine Threats
  85. Forecasting the Ionosphere from Sparse GNSS Data with Temporal-Fusion Transformers
  86. Towards Methane Detection Onboard Satellites
  87. A Multi-Strategy Approach for AI-Generated Text Detection
  88. BALM-TSF: Balanced Multimodal Alignment for LLM-Based Time Series Forecasting
  89. Federated Survival Analysis with Node-Level Differential Privacy: Private Kaplan-Meier Curves
  90. RoFt-Mol: Benchmarking Robust Fine-Tuning with Molecular Graph Foundation Models
  91. Promptable Longitudinal Lesion Segmentation in Whole-Body CT
  92. Gated Associative Memory: A Parallel O(N) Architecture for Efficient Sequence Modeling
  93. TranCIT: Transient Causal Interaction Toolbox
  94. Probe-Rewrite-Evaluate: A Workflow for Reliable Benchmarks and Quantifying Evaluation Awareness
  95. C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Car Damage Detection
  96. Can AI be Auditable?
  97. Integrated Multivariate Segmentation Tree for Heterogeneous Credit Data Analysis in Small- and Medium-Sized Enterprises
  98. A Modality-agnostic Multi-task Foundation Model for Human Brain Imaging
  99. Advanced spectral clustering for heterogeneous data in credit risk monitoring systems
  100. Text-to-Layout: A Generative Workflow for Drafting Architectural Floor Plans Using LLMs
All 157
  1. FedThief: Harming Others to Benefit Oneself in Self-Centered Federated Learning
  2. Identifying Causal Direction via Dense Functional Classes
  3. Game Theoretic Resilience Recommendation Framework for CyberPhysical Microgrids Using Hypergraph MetaLearning
  4. Biological Pathway Informed Models with Graph Attention Networks (GATs)
  5. Graph Convolutional Network With Pattern-Spatial Interactive and Regional Awareness for Traffic Forecasting
  6. LLM-Assisted Iterative Evolution with Swarm Intelligence Toward SuperBrain
  7. Make me an Expert: Distilling from Generalist Black-Box Models into Specialized Models for Semantic Segmentation
  8. TRUST: Token-dRiven Ultrasound Style Transfer for Cross-Device Adaptation
  9. Artificial Intelligence-Based Analysis of Ice Cream Melting Behavior Under Various Ingredients
  10. Entropy-based Coarse and Compressed Semantic Speech Representation Learning
  11. NeuralSVCD for Efficient Swept Volume Collision Detection
  12. FLUID: A Fine-Grained Lightweight Urban Signalized-Intersection Dataset of Dense Conflict Trajectories
  13. ResearchQA: Evaluating Scholarly Question Answering at Scale Across 75 Fields with Survey-Mined Questions and Rubrics
  14. Multi-Focused Video Group Activities Hashing
  15. Localizing and Mitigating Memorization in Image Autoregressive Models
  16. Exploring Decision-Making Capabilities of LLM Agents: An Experimental Study on Jump-Jump Game
  17. A Novel Method to Determine Total Oxidant Concentration Produced by Non-Thermal Plasma Based on Image Processing and Machine Learning
  18. Cross-Domain Malware Detection via Probability-Level Fusion of Lightweight Gradient Boosting Models
  19. TECP: Token-Entropy Conformal Prediction for LLMs
  20. Universal Properties of Activation Sparsity in Modern Large Language Models
  21. Encoder-Only Image Registration
  22. Stage-wise Adaptive Label Distribution for Facial Age Estimation
  23. SemaMIL: Semantic-Aware Multiple Instance Learning with Retrieval-Guided State Space Modeling for Whole Slide Images
  24. Memory Limitations of Prompt Tuning in Transformers
  25. Lagrangian Relaxation for Multi-Action Partially Observable Restless Bandits: Heuristic Policies and Indexability
  26. MedSEBA: Synthesizing Evidence-Based Answers Grounded in Evolving Medical Literature
  27. Metis: Training LLMs with FP4 Quantization
  28. DevilSight: Augmenting Monocular Human Avatar Reconstruction through a Virtual Perspective
  29. Curriculum Guided Personalized Subgraph Federated Learning
  30. A Study on the Framework for Evaluating the Ethics and Trustworthiness of Generative AI
  31. DAOVI: Distortion-Aware Omnidirectional Video Inpainting
  32. Unifying Adversarial Perturbation for Graph Neural Networks
  33. HERO-VQL: Hierarchical, Egocentric and Robust Visual Query Localization
  34. Visually Grounded Narratives: Reducing Cognitive Burden in Researcher-Participant Interaction
  35. Adaptive Point-Prompt Tuning: Fine-Tuning Heterogeneous Foundation Models for 3D Point Cloud Analysis
  36. A Multimodal and Multi-centric Head and Neck Cancer Dataset for Segmentation, Diagnosis and Outcome Prediction
  37. Optimized Weight Initialization on the Stiefel Manifold for Deep ReLU Neural Networks
  38. Iterative Low-rank Network for Hyperspectral Image Denoising
  39. AQFusionNet: Multimodal Deep Learning for Air Quality Index Prediction with Imagery and Sensor Data
  40. Target-Oriented Single Domain Generalization
  41. Theory Foundation of Physics-Enhanced Residual Learning
  42. LUT-Fuse: Towards Extremely Fast Infrared and Visible Image Fusion via Distillation to Learnable Look-Up Tables
  43. Solving Conic Programs over Sparse Graphs using a Variational Quantum Approach: The Case of the AC Optimal Power Flow
  44. Counterfactual Risk Minimization with IPS-Weighted BPR and Self-Normalized Evaluation in Recommender Systems
  45. CryptoFace: End-to-End Encrypted Face Recognition
  46. Chunked TabPFN: Exact Training-Free In-Context Learning for Long-Context Tabular Data
  47. GIER: Gap-Driven Self-Refinement for Large Language Models
  48. Contact-Aided Navigation of Flexible Robotic Endoscope Using Deep Reinforcement Learning in Dynamic Stomach
  49. A Framework for Task and Motion Planning based on Expanding AND/OR Graphs
  50. MorphGen: Morphology-Guided Representation Learning for Robust Single-Domain Generalization in Histopathological Cancer Classification
  51. TReF-6: Inferring Task-Relevant Frames from a Single Demonstration for One-Shot Skill Generalization
  52. Access Paths for Efficient Ordering with Large Language Models
  53. Illuminating Patterns of Divergence: DataDios SmartDiff for Large-Scale Data Difference Analysis
  54. Wage Sentiment Indices Derived from Survey Comments via Large Language Models
  55. SIGMUS: Semantic Integration for Knowledge Graphs in Multimodal Urban Spaces
  56. Intelligent Spectrum Management in Satellite Communications
  57. OpinioRAG: Towards Generating User-Centric Opinion Highlights from Large-scale Online Reviews