{"total":91,"rows":[{"id":"2409.00588","title":"Diffusion Policy Policy Optimization","created":"2024-09-01","cited_by_count":280,"area":"diffusion"},{"id":"2405.16173","title":"Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization","created":"2024-05-25","cited_by_count":110,"area":"diffusion"},{"id":"2407.13734","title":"Understanding Reinforcement Learning-Based Fine-Tuning of Diffusion Models: A Tutorial and Review","created":"2024-07-18","cited_by_count":98,"area":"diffusion"},{"id":"2404.07771","title":"An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimization","created":"2024-04-11","cited_by_count":73,"area":"diffusion"},{"id":"2403.14613","title":"DreamReward: Text-to-3D Generation with Human Preference","created":"2024-03-21","cited_by_count":56,"area":null},{"id":"2406.00681","title":"Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient","created":"2024-06-02","cited_by_count":51,"area":"diffusion"},{"id":"2401.15443","title":"DiffuserLite: Towards Real-time Diffusion Planning","created":"2024-01-27","cited_by_count":42,"area":null},{"id":"2406.09509","title":"CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making","created":"2024-06-13","cited_by_count":39,"area":"diffusion"},{"id":"2503.00535","title":"What Makes a Good Diffusion Planner for Decision Making?","created":"2025-03-01","cited_by_count":38,"area":"diffusion"},{"id":"2312.08533","title":"World Models via Policy-Guided Trajectory Diffusion","created":"2023-12-13","cited_by_count":34,"area":"wm"},{"id":"2408.03400","title":"Attacks and Defenses for Generative Diffusion Models: A Comprehensive Survey","created":"2024-08-06","cited_by_count":32,"area":"diffusion"},{"id":"2402.04080","title":"Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning","created":"2024-02-06","cited_by_count":31,"area":"diffusion"},{"id":"2407.12381","title":"Flow Matching Imitation Learning for Multi-Support Manipulation","created":"2024-07-17","cited_by_count":29,"area":"offlinerl"},{"id":"2402.14795","title":"CyberDemo: Augmenting Simulated Human Demonstration for Real-World Dexterous Manipulation","created":"2024-02-22","cited_by_count":28,"area":"offlinerl"},{"id":"2410.11402","title":"M2Diffuser: Diffusion-based Trajectory Optimization for Mobile Manipulation in 3D Scenes","created":"2024-10-15","cited_by_count":27,"area":"diffusion"},{"id":"2312.03817","title":"Diffusion Illusions: Hiding Images in Plain Sight","created":"2023-12-06","cited_by_count":26,"area":null},{"id":"2504.10041","title":"Prior Does Matter: Visual Navigation via Denoising Diffusion Bridge Models","created":"2025-04-14","cited_by_count":25,"area":"diffusion"},{"id":"2402.13777","title":"Deep Generative Models for Offline Policy Learning: Tutorial, Survey, and Perspectives on Future Directions","created":"2024-02-21","cited_by_count":20,"area":"offlinerl"},{"id":"2407.01950","title":"LDP: A Local Diffusion Planner for Efficient Robot Navigation and Collision Avoidance","created":"2024-07-02","cited_by_count":18,"area":"diffusion"},{"id":"2406.05427","title":"Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL","created":"2024-06-08","cited_by_count":15,"area":"ssm"},{"id":"2502.17100","title":"Generative Models in Decision Making: A Survey","created":"2025-02-24","cited_by_count":15,"area":null},{"id":"2505.03432","title":"Wasserstein Convergence of Score-based Generative Models under Semiconvexity and Discontinuous Gradients","created":"2025-05-06","cited_by_count":15,"area":"diffusion"},{"id":"2410.18082","title":"Prioritized Generative Replay","created":"2024-10-23","cited_by_count":13,"area":"deeprl"},{"id":"2410.00051","title":"Generalizing Consistency Policy to Visual RL with Prioritized Proximal Experience Regularization","created":"2024-09-28","cited_by_count":11,"area":"diffusion"},{"id":"2502.19805","title":"Implicit Search via Discrete Diffusion: A Study on Chess","created":"2025-02-27","cited_by_count":11,"area":"diffusion"},{"id":"2512.09929","title":"Closing the Train-Test Gap in World Models for Gradient-Based Planning","created":"2025-12-10","cited_by_count":11,"area":"wm"},{"id":"2407.14653","title":"OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning","created":"2024-07-19","cited_by_count":10,"area":"offlinerl"},{"id":"2409.07569","title":"A Comprehensive Survey on Inverse Constrained Reinforcement Learning: Definitions, Progress and Challenges","created":"2024-09-11","cited_by_count":10,"area":"deeprl"},{"id":"2511.17150","title":"DiffRefiner: Coarse to Fine Trajectory Planning via Diffusion Refinement with Semantic Interaction for End to End Autonomous Driving","created":"2025-11-21","cited_by_count":10,"area":"diffusion"},{"id":"2505.09144","title":"Latent Theory of Mind: A Decentralized Diffusion Architecture for Cooperative Manipulation","created":"2025-05-14","cited_by_count":9,"area":"diffusion"},{"id":"2602.13810","title":"Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action Generation","created":"2026-02-14","cited_by_count":9,"area":"deeprl"},{"id":"2403.10794","title":"Diffusion-Reinforcement Learning Hierarchical Motion Planning in Multi-agent Adversarial Games","created":"2024-03-16","cited_by_count":7,"area":null},{"id":"2410.13586","title":"Preference Aligned Diffusion Planner for Quadrupedal Locomotion Control","created":"2024-10-17","cited_by_count":7,"area":"diffusion"},{"id":"2411.10809","title":"Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replay","created":"2024-11-16","cited_by_count":7,"area":"diffusion"},{"id":"2501.05819","title":"Diffusion Models for Smarter UAVs: Decision-Making and Modeling","created":"2025-01-10","cited_by_count":7,"area":"diffusion"},{"id":"2505.07261","title":"CHD: Coupled Hierarchical Diffusion for Long-Horizon Tasks","created":"2025-05-12","cited_by_count":6,"area":null},{"id":"2407.16134","title":"Diffusion Transformer Captures Spatial-Temporal Dependencies: A Theory for Gaussian Process Data","created":"2024-07-23","cited_by_count":5,"area":"diffusion"},{"id":"2502.07279","title":"Exploratory Diffusion Model for Unsupervised Reinforcement Learning","created":"2025-02-11","cited_by_count":5,"area":"diffusion"},{"id":"2312.04326","title":"iDesigner: A High-Resolution and Complex-Prompt Following Text-to-Image Diffusion Model for Interior Design","created":"2023-12-07","cited_by_count":4,"area":"diffusion"},{"id":"2405.14790","title":"DIDI: Diffusion-Guided Diversity for Offline Behavioral Generation","created":"2024-05-23","cited_by_count":4,"area":null},{"id":"2408.15501","title":"MODULI: Unlocking Preference Generalization via Diffusion Models for Offline Multi-Objective Reinforcement Learning","created":"2024-08-28","cited_by_count":4,"area":"diffusion"},{"id":"2511.01374","title":"Learning Intractable Multimodal Policies with Reparameterization and Diversity Regularization","created":"2025-11-03","cited_by_count":3,"area":"deeprl"},{"id":"2603.27450","title":"FlowRL: A Taxonomy and Modular Framework for Reinforcement Learning with Diffusion Policies","created":"2026-03-29","cited_by_count":3,"area":"diffusion"},{"id":"2404.11416","title":"Neural Shr\\\"odinger Bridge Matching for Pansharpening","created":"2024-04-17","cited_by_count":2,"area":"diffusion"},{"id":"2405.19189","title":"DyDiff: Long-Horizon Rollout via Dynamics Diffusion for Offline Reinforcement Learning","created":"2024-05-29","cited_by_count":2,"area":"diffusion"},{"id":"2407.18597","title":"Reinforcement Learning for Sustainable Energy: A Survey","created":"2024-07-26","cited_by_count":2,"area":"deeprl"},{"id":"2409.02512","title":"Continual Diffuser (CoD): Mastering Continual Offline Reinforcement Learning with Experience Rehearsal","created":"2024-09-04","cited_by_count":2,"area":"offlinerl"},{"id":"2503.20102","title":"Extendable Planning via Multiscale Diffusion","created":"2025-03-25","cited_by_count":2,"area":null},{"id":"2505.18344","title":"Improved Sample Complexity For Diffusion Model Training Without Empirical Risk Minimizer Access","created":"2025-05-23","cited_by_count":2,"area":"diffusion"},{"id":"2505.20781","title":"STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation","created":"2025-05-27","cited_by_count":2,"area":"diffusion"},{"id":"2506.03234","title":"BadReward: Clean-Label Poisoning of Reward Models in Text-to-Image RLHF","created":"2025-06-03","cited_by_count":2,"area":"alignment"},{"id":"2506.07083","title":"Inverse Design of Metamaterials with Manufacturing-Guiding Spectrum-to-Structure Conditional Diffusion Model","created":"2025-06-08","cited_by_count":2,"area":"diffusion"},{"id":"2508.08687","title":"Expert-Guided Diffusion Planner for Auto-Bidding","created":"2025-08-12","cited_by_count":2,"area":"diffusion"},{"id":"2510.12253","title":"Diffusion Models for Reinforcement Learning: Foundations, Taxonomy, and Development","created":"2025-10-14","cited_by_count":2,"area":"diffusion"},{"id":"2511.11592","title":"Mind Your Entropy: From Maximum Entropy to Trajectory Entropy-Constrained RL","created":"2025-10-25","cited_by_count":2,"area":"deeprl"},{"id":"2606.10613","title":"Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstrapped Flow Q-Learning","created":"2026-06-09","cited_by_count":2,"area":"offlinerl"},{"id":"2409.01427","title":"Enhancing Sample Efficiency and Exploration in Reinforcement Learning through the Integration of Diffusion Models and Proximal Policy Optimization","created":"2024-09-02","cited_by_count":1,"area":"diffusion"},{"id":"2503.01274","title":"DnD Filter: Differentiable State Estimation for Dynamic Systems using Diffusion Models","created":"2025-03-03","cited_by_count":1,"area":"diffusion"},{"id":"2504.14477","title":"ExFace: Expressive Facial Control for Humanoid Robots with Diffusion Transformers and Bootstrap Training","created":"2025-04-20","cited_by_count":1,"area":"diffusion"},{"id":"2509.03658","title":"Efficient Virtuoso: A Latent Diffusion Transformer Model for Goal-Conditioned Trajectory Planning","created":"2025-09-03","cited_by_count":1,"area":"diffusion"},{"id":"2509.15927","title":"Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search","created":"2025-09-19","cited_by_count":1,"area":null},{"id":"2510.12815","title":"Energy-Guided Diffusion Sampling for Long-Term User Behavior Prediction in Reinforcement Learning-based Recommendation","created":"2025-10-09","cited_by_count":1,"area":"diffusion"},{"id":"2510.14000","title":"A Diffusion-Refined Planner with Reinforcement Learning Priors for Confined-Space Parking","created":"2025-10-15","cited_by_count":1,"area":"deeprl"},{"id":"2511.03100","title":"Scaling Multi-Agent Environment Co-Design with Diffusion Models","created":"2025-11-05","cited_by_count":1,"area":"diffusion"},{"id":"2601.13416","title":"Diffusion Representations for Fine-Grained Image Classification: A Marine Plankton Case Study","created":"2026-01-19","cited_by_count":1,"area":"diffusion"},{"id":"2601.18069","title":"Diffusion Model-based Reinforcement Learning for Version Age of Information Scheduling: Average and Tail-Risk-Sensitive Control","created":"2026-01-26","cited_by_count":1,"area":"diffusion"},{"id":"2603.02650","title":"Improving Diffusion Planners by Self-Supervised Action Gating with Energies","created":"2026-03-03","cited_by_count":1,"area":"offlinerl"},{"id":"2604.05112","title":"Vintix II: Decision Pre-Trained Transformer is a Scalable In-Context Reinforcement Learner","created":"2026-04-06","cited_by_count":1,"area":"deeprl"},{"id":"2604.05673","title":"Rectified Schr\\\"odinger Bridge Matching for Few-Step Visual Navigation","created":"2026-04-07","cited_by_count":1,"area":"diffusion"},{"id":"2604.18210","title":"TacticGen: Grounding Adaptable and Scalable Generation of Football Tactics","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2605.12416","title":"Aligning Flow Map Policies with Optimal Q-Guidance","created":"2026-05-12","cited_by_count":1,"area":"diffusion"},{"id":"2605.16054","title":"Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making","created":"2026-05-15","cited_by_count":1,"area":"diffusion"},{"id":"2606.27766","title":"RS-Diffuser: Risk-Sensitive Diffusion Planning with Distributional Value Guidance","created":"2026-06-26","cited_by_count":1,"area":"offlinerl"},{"id":"2502.11386","title":"Intelligent Mobile AI-Generated Content Services via Interactive Prompt Engineering and Dynamic Service Provisioning","created":"2025-02-17","cited_by_count":0,"area":null},{"id":"2504.00952","title":"Personalized Federated Training of Diffusion Models with Privacy Guarantees","created":"2025-04-01","cited_by_count":0,"area":"diffusion"},{"id":"2506.07880","title":"Generative Resource Allocation for 6G O-RAN with Diffusion Policies","created":"2025-06-09","cited_by_count":0,"area":"diffusion"},{"id":"2508.12356","title":"Synthetic Data is Sufficient for Zero-Shot Visual Generalization from Offline Data","created":"2025-08-17","cited_by_count":0,"area":"offlinerl"},{"id":"2511.07260","title":"PADiff: Predictive and Adaptive Diffusion Policies for Ad Hoc Teamwork","created":"2025-11-10","cited_by_count":0,"area":"diffusion"},{"id":"2511.09044","title":"Advancing Autonomous Emergency Response Systems: A Generative AI Perspective","created":"2025-11-12","cited_by_count":0,"area":null},{"id":"2512.01987","title":"Forecasting in Offline Reinforcement Learning for Non-stationary Environments","created":"2025-12-01","cited_by_count":0,"area":"offlinerl"},{"id":"2602.09726","title":"ExO-PPO: an Extended Off-policy Proximal Policy Optimization Algorithm","created":"2026-02-10","cited_by_count":0,"area":"deeprl"},{"id":"2603.01771","title":"Hyperparameter Trajectory Inference with Conditional Lagrangian Optimal Transport","created":"2026-03-02","cited_by_count":0,"area":"deeprl"},{"id":"2605.09999","title":"Muninn: Your Trajectory Diffusion Model But Faster","created":"2026-05-11","cited_by_count":0,"area":"diffusion"},{"id":"2605.25531","title":"From Denoising to Decision Making: A Survey on Diffusion Model-Enabled Deep Reinforcement Learning for Wireless Networks","created":"2026-05-25","cited_by_count":0,"area":"diffusion"},{"id":"2606.00336","title":"From Noise to Control: Parameterized Diffusion Policies","created":"2026-05-29","cited_by_count":0,"area":"diffusion"},{"id":"2607.10369","title":"VINE: Taming Generative Control Policies for Reinforcement Learning","created":"2026-07-11","cited_by_count":0,"area":"diffusion"},{"id":"2607.17572","title":"JAGG: Jacobian-Aggregated Group Gradient for Efficient GRPO Training of Diffusion Models","created":"2026-07-20","cited_by_count":0,"area":"lr"},{"id":"2610.04285","title":"Amortized Score-Hamiltonian Policy Iteration: A Grid-Free Scheme for Relaxed Stochastic Control Problems","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.12468","title":"DreamTrue: Action-Faithful Robot World Model with Counterfactual Post-Training","created":"2026-10-08","cited_by_count":0,"area":"wm"},{"id":"2610.13690","title":"Transformer-based In-Context Score Operator Learning for Diffusion Models","created":"2026-10-09","cited_by_count":0,"area":"diffusion"},{"id":"2610.14941","title":"Compositional Average Velocity Modeling for Efficient Diffusion Offline Reinforcement Learning","created":"2026-10-10","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}