mlsanityData to 14 Oct 2026

Papers

New on arXiv

Sat 8 Feb 2025

173 papers

  1. Leveraging Constraint Violation Signals For Action-Constrained Reinforcement LearningDeep reinforcement learning methods → Safe and constrained RL
  2. Real Time Control of Tandem-Wing Experimental Platform Using Concerto Reinforcement LearningDeep reinforcement learning methods → RL for robot navigation and UAV control
  3. Refining Positive and Toxic Samples for Dual Safety Self-Alignment of LLMs with Minimal Human InterventionsLLM alignment / RLHF / preference optimisation → Safety alignment and jailbreak attacks +1
  4. CryptoX : Compositional Reasoning Evaluation of Large Language ModelsLLM reasoning → Reasoning benchmarks and evaluation
  5. Learning Conformal Abstention Policies for Adaptive Risk Management in Large Language and Vision-Language ModelsMultimodal LLMs / vision-language models → Hallucination mitigation in LVLMs
  6. Multi-Agent Simulator Drives Language Models for Legal Intensive InteractionLLM agents and tool use → Social simulation and multi-agent debate
  7. Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model MergingLLM alignment / RLHF / preference optimisation → LLM preference optimization methods
  8. Group Reasoning Emission Estimation NetworksLLM reasoning → Knowledge- and tool-augmented reasoning
  9. Multimodal Cognitive Reframing Therapy via Multi-hop Psychotherapeutic ReasoningLLM reasoning → Clinical and biomedical applications
  10. Towards Trustworthy Retrieval Augmented Generation for Large Language Models: A SurveyRetrieval-augmented generation → RAG pipeline design and evaluation
  11. FlavorDiffusion: Predicting Food Pairings and Chemical Interactions Using Diffusion ModelsDiffusion models → Flow matching, time series and science
  12. A Survey on Explainable Deep Reinforcement LearningDeep reinforcement learning methods → Interpretable and logic-guided RL
  13. Related Knowledge Perturbation Matters: Rethinking Multiple Pieces of Knowledge Editing in Same-SubjectLLM reasoning → Knowledge- and tool-augmented reasoning
  14. Forbidden Science: Dual-Use AI Challenge Benchmark and Scientific Refusal TestsLLM safety and security → Safety alignment, refusal and guardrails
  15. Knowledge Graph-Guided Retrieval Augmented GenerationRetrieval-augmented generation → Knowledge-graph and structured-knowledge RAG
  16. Design Considerations in Offline Preference-based RLLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF
  17. SSDD-GAN: Single-Step Denoising Diffusion GAN for Cochlear Implant Surgical Scene CompletionDiffusion models → Medical imaging and segmentation
  18. Convergence of TD(0) under Polynomial Mixing with Nonlinear Function ApproximationDeep reinforcement learning methods → RL theory and sample complexity
  19. Context information can be more important than reasoning for time series forecasting with a large language modelLLM reasoning → Time series reasoning
  20. Semantic-Aware Adaptive Video Streaming Using Latent Diffusion Models for Wireless NetworksDiffusion models → Diffusion for compression and wireless
  21. Machine Unlearning via Information Theoretic RegularizationLLM safety and security → Machine unlearning
  22. Surprise Potential as a Measure of Interactivity in Driving ScenariosEnd-to-end autonomous driving → Adversarial scenarios and safety testing
  23. Investigating the Shortcomings of LLMs in Step-by-Step Legal ReasoningLLM reasoning → Reasoning for agents, planning and code
  24. On the Convergence and Stability of Upside-Down Reinforcement Learning, Goal-Conditioned Supervised Learning, and Online Decision TransformersOffline RL and imitation learning from data → Offline RL algorithms +1
  25. CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and DebuggingLLM agents and tool use → Software engineering coding agents
  26. Evaluating Vision-Language Models for Emotion RecognitionLLM reasoning → Audio-language model reasoning +1
  27. Mol-MoE: Training Preference-Guided Routers for Molecule GenerationMixture-of-experts → MoE in reinforcement learning and robotics +1
  28. TrackDiffuser: Nearly Model-Free Bayesian Filtering with Diffusion ModelDiffusion models → Flow matching, time series and science
  29. Training-Free Constrained Generation With Stable Diffusion ModelsDiffusion models → Flow matching, time series and science
  30. Lossless Acceleration of Large Language Models with Hierarchical Drafting based on Temporal Locality in Speculative DecodingEfficient LLM inference and serving → Speculative decoding
  31. Evolving LLMs' Self-Refinement Capability via Synergistic Training-Inference OptimizationLLM reasoning → Test-time compute and efficient thinking
  32. UbiMoE: A Ubiquitous Mixture-of-Experts Vision Transformer Accelerator With Hybrid Computation Pattern on FPGAMixture-of-experts → Vision mixture-of-experts
  33. Data efficient Robotic Object Throwing with Model-Based Reinforcement LearningDeep reinforcement learning methods → RL for robot locomotion and manipulation
  34. On Memory Construction and Retrieval for Personalized Conversational AgentsRetrieval-augmented generation → Conversational and speech RAG
  35. Event Stream-based Visual Object Tracking: HDETrack V2 and A High-Definition BenchmarkKnowledge distillation → Detection and dense prediction distillation
  36. Large Multimodal Models for Low-Resource Languages: A SurveyMultimodal LLMs / vision-language models → MLLM training and visual instruction tuning
  37. Diffusion Model for Interest Refinement in Multi-Interest RecommendationDiffusion models → Diffusion recommenders
  38. Efficient Reinforcement Learning Through Adaptively Pretrained Visual EncoderDeep reinforcement learning methods → RL for robot locomotion and manipulation
  39. Sequential Stochastic Combinatorial Optimization Using Hierarchal Reinforcement LearningDeep reinforcement learning methods → RL for games and combinatorial optimization
  40. Differentially Private Synthetic Data via APIs 3: Using Simulators Instead of Foundation ModelSynthetic data and self-improvement for LLMs → Privacy-preserving tabular data synthesis
  41. Physics-Conditioned Diffusion Models for Lattice Gauge TheoryDiffusion models → Diffusion foundations and sampling
  42. DeepThink: Aligning Language Models with Domain-Specific User IntentsLLM reasoning → Test-time compute and efficient thinking +1
  43. Mechanistic Interpretability of Emotion Inference in Large Language ModelsMechanistic interpretability → Activation steering methods
  44. HAMSTER: Hierarchical Action Models For Open-World Robot ManipulationVision-language-action models → Generalist VLA models and benchmarks
  45. OntoTune: Ontology-Driven Self-training for Aligning Large Language ModelsLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
  46. LLM-Powered Decentralized Generative Agents with Adaptive Hierarchical Knowledge Graph for Cooperative PlanningLLM agents and tool use → General LLM agent frameworks and benchmarks
  47. ConRFT: A Reinforced Fine-tuning Method for VLA Models via Consistency PolicyVision-language-action models → Reinforcement learning and post-training
  48. Iterative Deepening Sampling as Efficient Test-Time ScalingLLM reasoning → Test-time compute and efficient thinking
  49. Stochastic Forward-Backward Deconvolution: Training Diffusion Models with Finite Noisy DatasetsDiffusion models → Diffusion foundations and sampling
  50. Diverse Image Generation with Diffusion Models and Cross Class Label Learning for Polyp ClassificationDiffusion models → Medical imaging and segmentation
  51. The Odyssey of the Fittest: Can Agents Survive and Still Be Good?LLM agents and tool use → General LLM agent frameworks and benchmarks
  52. Agentic AI Systems Applied to tasks in Financial Services: Modeling and model risk management crewsLLM agents and tool use → Financial trading and forecasting agents
  53. Sample-Efficient Reinforcement Learning from Human Feedback via Information-Directed SamplingLLM alignment / RLHF / preference optimisation → Reward modeling and RLHF +1
  54. UniCMs: A Unified Consistency Model For Efficient Multimodal Generation and UnderstandingDiffusion models → Image generation, text-to-image and editing
  55. Dynamic Noise Preference Optimization: Self-Improvement of Large Language Models with Self-Synthetic DataLLM alignment / RLHF / preference optimisation → LLM preference optimization methods +1
  56. Imitation Learning from a Single Temporally Misaligned VideoOffline RL and imitation learning from data → Robot manipulation imitation learning
  57. Beyond and Free from Diffusion: Invertible Guided Consistency TrainingDiffusion models → Diffusion foundations and sampling
  58. MDE: Modality Discrimination Enhancement for Multi-modal Recommendation
  59. Smart Sampling Strategies for Wireless Industrial Data Acquisition
  60. On the Effectiveness of Large Language Models in Automating Categorization of Scientific Texts
  61. Segmentation-free integration of nuclei morphology and spatial transcriptomics for retinal images
  62. Unpaired Image Dehazing via Kolmogorov-Arnold Transformation of Latent Features
  63. CrossVideoMAE: Self-Supervised Image-Video Representation Learning with Masked Autoencoders
  64. Topological derivative approach for deep neural network architecture adaptation
  65. CluStRE: Streaming Graph Clustering with Multi-Stage Refinement
  66. Deep Learning Meets Oversampling: A Learning Framework to Handle Imbalanced Classification
  67. WirelessGPT: A Generative Pre-trained Multi-task Learning Framework for Wireless Communication
  68. Beyond Vision: How Large Language Models Interpret Facial Expressions from Valence-Arousal Values
  69. Bridging Traffic State and Trajectory for Dynamic Road Network and Trajectory Representation Learning
  70. Global Ease of Living Index: a machine learning framework for longitudinal analysis of major economies
  71. Deep Ritz method with Fourier feature mapping: A deep learning approach for solving variational models of microstructure
  72. BF-GAN: Development of an AI-driven Bubbly Flow Image Generation Model Using Generative Adversarial Networks
  73. Poincar'e Inequality for Local Log-Polyak-Lojasiewicz Measures : Non-asymptotic Analysis in Low-temperature Regime
  74. Improving Environment Novelty Quantification for Effective Unsupervised Environment Design
  75. Predictive Coresets
  76. Rethinking Link Prediction for Directed Graphs
  77. Explainable and Class-Revealing Signal Feature Extraction via Scattering Transform and Constrained Zeroth-Order Optimization
  78. Pareto-Optimality, Smoothness, and Stochasticity in Learning-Augmented One-Max-Search
  79. Extended Histogram-based Outlier Score (EHBOS)
  80. Using agent-based models and EXplainable Artificial Intelligence (XAI) to simulate social behaviors and policy intervention scenarios: A case study of private well users in Ireland
  81. Proving the Coding Interview: A Benchmark for Formally Verified Code Generation
  82. 4D VQ-GAN: Synthesising Medical Scans at Any Time Point for Personalised Disease Progression Modelling of Idiopathic Pulmonary Fibrosis
  83. Flow-based Conformal Prediction for Multi-dimensional Time Series
  84. Generalizable Radio-Frequency Radiance Fields for Spatial Spectrum Synthesis
  85. Rethinking Word Similarity: Semantic Similarity through Classification Confusion
  86. TOKON: TOKenization-Optimized Normalization for time series analysis with a large language model
  87. Zero-Shot End-to-End Relation Extraction in Chinese: A Comparative Study of Gemini, LLaMA and ChatGPT
  88. Managing Geological Uncertainty in Critical Mineral Supply Chains: A POMDP Approach with Application to U.S. Lithium Resources
  89. Mobile Application Threats and Security
  90. Federated Learning with Reservoir State Analysis for Time Series Anomaly Detection
  91. Generalized Venn and Venn-Abers Calibration with Applications in Conformal Prediction
  92. The Evolution of Dataset Distillation: Toward Scalable and Generalizable Solutions
  93. Language Models Largely Exhibit Human-like Constituent Ordering Preferences
  94. Rigid Body Adversarial Attacks
  95. The late-stage training dynamics of (stochastic) subgradient descent on homogeneous neural networks
  96. Flowing Through Layers: A Continuous Dynamical Systems Perspective on Transformers
  97. An inpainting approach to manipulate asymmetry in pre-operative breast images
  98. KMI: A Dataset of Korean Motivational Interviewing Dialogues for Psychotherapy
  99. Incongruence Identification in Eyewitness Testimony
  100. Gender Bias in Instruction-Guided Speech Synthesis Models
All 173
  1. Generating Physically Realistic and Directable Human Motions from Multi-Modal Inputs
  2. ETHEREAL: Energy-efficient and High-throughput Inference using Compressed Tsetlin Machine
  3. ELMTEX: Fine-Tuning Large Language Models for Structured Clinical Information Extraction. A Case Study on Clinical Reports
  4. Adversarial Machine Learning: Attacks, Defenses, and Open Challenges
  5. Amorphous Fortress Online: Collaboratively Designing Open-Ended Multi-Agent AI and Game Environments
  6. AnyEdit: Edit Any Knowledge Encoded in Language Models
  7. Mixing Time of the Proximal Sampler in Relative Fisher Information via Strong Data Processing Inequality
  8. dynoGP: Deep Gaussian Processes for dynamic system identification
  9. XiHeFusion: Harnessing Large Language Models for Science Communication in Nuclear Fusion
  10. Towards Sustainable NLP: Insights from Benchmarking Inference Energy in Large Language Models
  11. Closing the Responsibility Gap in AI-based Network Management: An Intelligent Audit System Approach
  12. FreeBlend: Advancing Concept Blending with Staged Feedback-Driven Interpolation Diffusion
  13. Online Bidding Algorithms with Strict Return on Spend (ROS) Constraint
  14. Semantic Data Augmentation Enhanced Invariant Risk Minimization for Medical Image Domain Generalization
  15. Low-Rank Agent-Specific Adaptation (LoRASA) for Multi-Agent Policy Learning
  16. ATLAS: Autoformalizing Theorems through Lifting, Augmentation, and Synthesis of Data
  17. TabICL: A Tabular Foundation Model for In-Context Learning on Large Data
  18. MMHMER:Multi-viewer and Multi-task for Handwritten Mathematical Expression Recognition
  19. Knowledge is Power: Harnessing Large Language Models for Enhanced Cognitive Diagnosis
  20. Latent Structure Modulation in Large Language Models Through Stochastic Concept Embedding Transitions
  21. FRAME: Boosting LLMs with A Four-Quadrant Multi-Stage Pretraining Strategy
  22. 4DR P2T: 4D Radar Tensor Synthesis with Point Clouds
  23. Dual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learning
  24. Democratic Training Against Universal Adversarial Perturbations
  25. Demystifying Catastrophic Forgetting in Two-Stage Incremental Object Detector
  26. SSH: Sparse Spectrum Adaptation via Discrete Hartley Transformation
  27. Fg-T2M++: LLMs-Augmented Fine-Grained Text Driven Human Motion Generation
  28. Towards Learning Scalable Agile Dynamic Motion Planning for Robosoccer Teams with Policy Optimization
  29. Evaluation of Vision Transformers for Multimodal Image Classification: A Case Study on Brain, Lung, and Kidney Tumors
  30. IndexTTS: An Industrial-Level Controllable and Efficient Zero-Shot Text-To-Speech System
  31. Do Spikes Protect Privacy? Investigating Black-Box Model Inversion Attacks in Spiking Neural Networks
  32. A Physical Coherence Benchmark for Evaluating Video Generation Models via Optical Flow-guided Frame Prediction
  33. Vision-Ultrasound Robotic System based on Deep Learning for Gas and Arc Hazard Detection in Manufacturing
  34. Riemannian Manifold Learning for Stackelberg Games with Neural Flow Representations
  35. Feature Explosion: a generic optimization strategy for outlier detection algorithms
  36. Multi-scale Masked Autoencoder for Electrocardiogram Anomaly Detection
  37. Modeling of Core Loss Based on Machine Learning and Deep Learning
  38. Robustifying Fourier Features Embeddings for Implicit Neural Representations
  39. Convolutional Neural Network Segmentation for Satellite Imagery Data to Identify Landforms Using U-Net Architecture
  40. You Are What You Eat -- AI Alignment Requires Understanding How Data Shapes Structure and Generalisation
  41. LMS-Net: A Learned Mumford-Shah Network For Few-Shot Medical Image Segmentation
  42. Gen-DFL: Decision-Focused Generative Learning for Robust Decision Making
  43. Position: LLMs Can be Good Tutors in English Education
  44. Learning Memory and Material Dependent Constitutive Laws
  45. False Discovery Rate Control via Frequentist-assisted Horseshoe
  46. DCENWCNet: A Deep CNN Ensemble Network for White Blood Cell Classification with LIME-Based Explainability
  47. Block Graph Neural Networks for tumor heterogeneity prediction
  48. Content-based Video Retrieval in Traffic Videos using Latent Dirichlet Allocation Topic Model
  49. Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following
  50. Inversion of Magnetic Data using Learned Dictionaries and Scale Space
  51. Unsupervised Self-Prior Embedding Neural Representation for Iterative Sparse-View CT Reconstruction
  52. Approximating the total variation distance between spin systems
  53. Unbiased Sliced Wasserstein Kernels for High-Quality Audio Captioning
  54. AdaFlow: Efficient Long Video Editing via Adaptive Attention Slimming And Keyframe Selection
  55. MoFM: A Large-Scale Human Motion Foundation Model
  56. APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding
  57. Toward Copyright Integrity and Verifiability via Multi-Bit Watermarking for Intelligent Transportation Systems
  58. SAMGPT: Text-free Graph Foundation Model for Multi-domain Pre-training and Cross-domain Adaptation
  59. LRA-GNN: Latent Relation-Aware Graph Neural Network with Initial and Dynamic Residual for Facial Age Estimation
  60. Deep Generative Models with Hard Linear Equality Constraints
  61. Graph-based Molecular In-context Learning Grounded on Morgan Fingerprints
  62. Machine learning-guided construction of an analytic kinetic energy functional for orbital free density functional theory
  63. Vision-in-the-loop Simulation for Deep Monocular Pose Estimation of UAV in Ocean Environment
  64. Dictionary Learning: The Complexity of Learning Sparse Superposed Features with Feedback
  65. Analyzing public sentiment to gauge key stock events and determine volatility in conjunction with time and options premiums
  66. Convolutional Deep Colorization for Image Compression: A Color Grid Based Approach
  67. Probabilistic Foundations for Metacognition via Hybrid-AI
  68. A Novel Convolutional-Free Method for 3D Medical Imaging Segmentation
  69. Hierarchical Lexical Manifold Projection in Large Language Models: A Novel Mechanism for Multi-Scale Semantic Representation
  70. Open Challenges in Time Series Anomaly Detection: An Industry Perspective
  71. Learning Task Representations from In-Context Learning
  72. The Role of Prosody in Spoken Question Answering
  73. Coarse-to-Fine Structure-Aware Artistic Style Transfer