{"list":"other","total":71,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2303.04137","title":"Diffusion Policy: Visuomotor Policy Learning via Action Diffusion","created":"2023-03-07","cited_by_count":2838},{"id":"2209.14687","title":"Diffusion Posterior Sampling for General Noisy Inverse Problems","created":"2022-09-29","cited_by_count":1416},{"id":"2110.06169","title":"Offline Reinforcement Learning with Implicit Q-Learning","created":"2021-10-12","cited_by_count":1293},{"id":"2205.09991","title":"Planning with Diffusion for Flexible Behavior Synthesis","created":"2022-05-20","cited_by_count":1061},{"id":"2407.01392","title":"Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion","created":"2024-07-01","cited_by_count":681},{"id":"2208.06193","title":"Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning","created":"2022-08-12","cited_by_count":562},{"id":"2211.15657","title":"Is Conditional Generative Modeling all you need for Decision-Making?","created":"2022-11-28","cited_by_count":516},{"id":"1903.01973","title":"Learning Latent Plans from Play","created":"2019-03-05","cited_by_count":316},{"id":"2206.07568","title":"Contrastive Learning as Goal-Conditioned Reinforcement Learning","created":"2022-06-15","cited_by_count":253},{"id":"2410.20092","title":"OGBench: Benchmarking Offline Goal-Conditioned RL","created":"2024-10-26","cited_by_count":238},{"id":"2302.11552","title":"Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC","created":"2023-02-22","cited_by_count":220},{"id":"2502.02538","title":"Flow Q-Learning","created":"2025-02-04","cited_by_count":184},{"id":"2311.16424","title":"Manifold Preserving Guided Diffusion","created":"2023-11-28","cited_by_count":157},{"id":"2302.01877","title":"AdaptDiffuser: Diffusion Models as Adaptive Self-evolving Planners","created":"2023-02-03","cited_by_count":149},{"id":"2307.11949","title":"HIQL: Offline Goal-Conditioned RL with Latent States as Actions","created":"2023-07-22","cited_by_count":141},{"id":"2501.15564","title":"Diffusion-Based Planning for Autonomous Driving with Flexible Guidance","created":"2025-01-26","cited_by_count":141},{"id":"2304.01203","title":"Optimal Goal-Reaching Reinforcement Learning via Quasimetric Learning","created":"2023-04-03","cited_by_count":121},{"id":"2303.17076","title":"DiffCollage: Parallel Generation of Large Content with Diffusion Models","created":"2023-03-30","cited_by_count":103},{"id":"2402.15567","title":"Foundation Policies with Hilbert Representations","created":"2024-02-23","cited_by_count":94},{"id":"2401.03360","title":"Generative Skill Chaining: Long-Horizon Skill Planning with Diffusion Models","created":"2023-10-13","cited_by_count":91},{"id":"2305.17330","title":"MADiff: Offline Multi-agent Learning with Diffusion Models","created":"2023-05-27","cited_by_count":75},{"id":"2401.02644","title":"Simple Hierarchical Planning with Diffusion","created":"2024-01-05","cited_by_count":73},{"id":"2402.03201","title":"Guidance with Spherical Gaussian Constraint for Conditional Diffusion","created":"2024-02-05","cited_by_count":71},{"id":"2505.23458","title":"Diffusion Guidance Is a Controllable Policy Improvement Operator","created":"2025-05-29","cited_by_count":58},{"id":"2506.04168","title":"Horizon Reduction Makes RL Scalable","created":"2025-06-04","cited_by_count":57},{"id":"2401.15443","title":"DiffuserLite: Towards Real-time Diffusion Planning","created":"2024-01-27","cited_by_count":42},{"id":"2404.06356","title":"Policy-Guided Diffusion","created":"2024-04-09","cited_by_count":41},{"id":"2407.06169","title":"Potential Based Diffusion Motion Planning","created":"2024-07-08","cited_by_count":41},{"id":"2503.05153","title":"Generative Trajectory Stitching through Diffusion Composition","created":"2025-03-07","cited_by_count":41},{"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},{"id":"2410.03072","title":"Multi-Robot Motion Planning with Diffusion Models","created":"2024-10-04","cited_by_count":38},{"id":"2411.16627","title":"Inference-Time Policy Steering through Human Interactions","created":"2024-11-25","cited_by_count":38},{"id":"2502.03607","title":"Simultaneous Multi-Robot Motion Planning with Projected Diffusion Models","created":"2025-02-05","cited_by_count":38},{"id":"2503.00535","title":"What Makes a Good Diffusion Planner for Decision Making?","created":"2025-03-01","cited_by_count":38},{"id":"2402.02439","title":"DiffStitch: Boosting Offline Reinforcement Learning with Diffusion-based Trajectory Stitching","created":"2024-02-04","cited_by_count":36},{"id":"2502.07202","title":"Monte Carlo Tree Diffusion for System 2 Planning","created":"2025-02-11","cited_by_count":33},{"id":"2403.12404","title":"Understanding and Improving Training-free Loss-based Diffusion Guidance","created":"2024-03-19","cited_by_count":32},{"id":"2310.19427","title":"Refining Diffusion Planner for Reliable Behavior Synthesis by Automatic Detection of Infeasible Plans","created":"2023-10-30","cited_by_count":27},{"id":"2401.11237","title":"Closing the Gap between TD Learning and Supervised Learning -- A Generalisation Point of View","created":"2024-01-20","cited_by_count":27},{"id":"2504.16925","title":"Latent Diffusion Planning for Imitation Learning","created":"2025-04-23","cited_by_count":26},{"id":"2503.09817","title":"Temporal Difference Flows","created":"2025-03-12","cited_by_count":24},{"id":"2505.12737","title":"Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning","created":"2025-05-19","cited_by_count":23},{"id":"2509.21655","title":"DriftLite: Lightweight Drift Control for Inference-Time Scaling of Diffusion Models","created":"2025-09-25","cited_by_count":23},{"id":"2405.16907","title":"GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning","created":"2024-05-27","cited_by_count":22},{"id":"2509.06863","title":"floq: Training Critics via Flow-Matching for Scaling Compute in Value-Based RL","created":"2025-09-08","cited_by_count":22},{"id":"2512.10926","title":"Decoupled Q-Chunking","created":"2025-12-11","cited_by_count":20},{"id":"2510.06714","title":"Dual Goal Representations","created":"2025-10-08","cited_by_count":16},{"id":"2512.03520","title":"FloodDiffusion: Tailored Diffusion Forcing for Streaming Motion Generation","created":"2025-12-03","cited_by_count":16},{"id":"2211.11603","title":"Model-based Trajectory Stitching for Improved Offline Reinforcement Learning","created":"2022-11-21","cited_by_count":15},{"id":"2505.10881","title":"Prior-Guided Diffusion Planning for Offline Reinforcement Learning","created":"2025-05-16","cited_by_count":14},{"id":"2310.19308","title":"Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning","created":"2023-10-30","cited_by_count":13},{"id":"2405.17879","title":"Resisting Stochastic Risks in Diffusion Planners with the Trajectory Aggregation Tree","created":"2024-05-28","cited_by_count":13},{"id":"2506.00895","title":"State-Covering Trajectory Stitching for Diffusion Planners","created":"2025-06-01","cited_by_count":13},{"id":"2512.08108","title":"Scalable Offline Model-Based RL with Action Chunks","created":"2025-12-08","cited_by_count":13},{"id":"2506.07744","title":"Graph-Assisted Stitching for Offline Hierarchical Reinforcement Learning","created":"2025-06-09","cited_by_count":12},{"id":"2510.22512","title":"Transitive RL: Value Learning via Divide and Conquer","created":"2025-10-26","cited_by_count":12},{"id":"2204.12026","title":"BATS: Best Action Trajectory Stitching","created":"2022-04-26","cited_by_count":10},{"id":"2510.07730","title":"DEAS: DEtached value learning with Action Sequence for Scalable Offline RL","created":"2025-10-09","cited_by_count":10},{"id":"2506.00867","title":"Local Manifold Approximation and Projection for Manifold-Aware Diffusion Planning","created":"2025-06-01","cited_by_count":9},{"id":"2510.07257","title":"Test-Time Graph Search for Goal-Conditioned Reinforcement Learning","created":"2025-10-08","cited_by_count":8},{"id":"2601.00126","title":"Compositional Diffusion with Guided Search for Long-Horizon Planning","created":"2025-12-31","cited_by_count":8},{"id":"2602.02722","title":"Hierarchical Entity-centric Reinforcement Learning with Factored Subgoal Diffusion","created":"2026-02-02","cited_by_count":7},{"id":"2506.09498","title":"Fast Monte Carlo Tree Diffusion: 100x Speedup via Parallel Sparse Planning","created":"2025-06-11","cited_by_count":6},{"id":"2508.21800","title":"Tree-Guided Diffusion Planner","created":"2025-08-29","cited_by_count":4},{"id":"2603.02646","title":"Compositional Visual Planning via Inference-Time Diffusion Scaling","created":"2026-03-03","cited_by_count":2},{"id":"2602.07441","title":"Proximal Action Replacement for Behavior Cloning Actor-Critic in Offline Reinforcement Learning","created":"2026-02-07","cited_by_count":1},{"id":"2603.02650","title":"Improving Diffusion Planners by Self-Supervised Action Gating with Energies","created":"2026-03-03","cited_by_count":1}],"next_cursor":null}