mlsanityData to 7 Oct 2026

Diffusion Policy: Visuomotor Policy Learning via Action Diffusion

arXiv 2303.04137 ↗First posted 7 Mar 2023cs.ROcited by 2,730

On the map: World models → Embodied and robot world models

also in 1 more
Abstract (arXiv)

This paper introduces Diffusion Policy, a new way of generating robot behavior by representing a robot's visuomotor policy as a conditional denoising diffusion process. We benchmark Diffusion Policy across 12 different tasks from 4 different robot manipulation benchmarks and find that it consistently outperforms existing state-of-the-art robot learning methods with an average improvement of 46.9%. Diffusion Policy learns the gradient of the action-distribution score function and iteratively optimizes with respect to this gradient field during inference via a series of stochastic Langevin dynamics steps. We find that the diffusion formulation yields powerful advantages when used for robot policies, including gracefully handling multimodal action distributions, being suitable for high-dimensional action spaces, and exhibiting impressive training stability. To fully unlock the potential of diffusion models for visuomotor policy learning on physical robots, this paper presents a set of key technical contributions including the incorporation of receding horizon control, visual conditioning, and the time-series diffusion transformer. We hope this work will help motivate a new generation of policy learning techniques that are able to leverage the powerful generative modeling capabilities of diffusion models. Code, data, and training details is publicly available diffusion-policy.cs.columbia.edu

Key facts. Cited by 2,730 papers in the map (data through 7 Oct 2026). Placed in Embodied and robot world models, one of 11 directions in World models. Builds on 7 of its 66 references that are in the map. First posted on arXiv 7 Mar 2023.

Builds on

7 of 66 references.

References · 7

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  4. 2022Compositional Visual Generation with Composable Diffusion Modelscited by 619
  5. 2022Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learningcited by 543
  6. 2023Imitating Human Behaviour with Diffusion Modelscited by 260
  7. 2023On the Importance of Noise Scheduling for Diffusion Modelscited by 193

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 97; 2024: 422; 2025: 959; 2026: 1252.

2,730 papers.

Sort:

By area:

  1. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  2. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  3. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  4. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  5. 2023Training Diffusion Models with Reinforcement Learningcited by 939
  6. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 844
  7. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 670
  8. 2024Autoregressive Image Generation without Vector Quantizationcited by 644
  9. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 634
  10. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Roboticscited by 507
  11. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 502
  12. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 484
38 more
  1. 2025RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulationcited by 477
  2. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Modelscited by 440
  3. 2023DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Modelscited by 431
  4. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulationcited by 411
  5. 2024RoboCasa: Large-Scale Simulation of Everyday Tasks for Generalist Robotscited by 391
  6. 2025AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systemscited by 390
  7. 2025UniVLA: Learning to Act Anywhere with Task-centric Latent Actionscited by 386
  8. 2024Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperationcited by 377
  9. 2024One Step Diffusion via Shortcut Modelscited by 373
  10. 2024DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planningcited by 357
  11. 2023Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulationcited by 353
  12. 2025WorldVLA: Towards Autoregressive Action World Modelcited by 351
  13. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulationcited by 331
  14. 2024DiffusionDrive: Truncated Diffusion Model for End-to-End Autonomous Drivingcited by 324
  15. 2023MimicGen: A Data Generation System for Scalable Robot Learning using Human Demonstrationscited by 308
  16. 2023SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planningcited by 289
  17. 2026Causal World Modeling for Robot Controlcited by 289
  18. 2025X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Modelcited by 285
  19. 2023Aligning Text-to-Image Diffusion Models with Reward Backpropagationcited by 284
  20. 2024Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representationscited by 279
  21. 20243D Diffuser Actor: Policy Diffusion with 3D Scene Representationscited by 278
  22. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 274
  23. 2026Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planningcited by 274
  24. 2023Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Modelscited by 264
  25. 2024Diffusion Policy Policy Optimizationcited by 255
  26. 2023Using Human Feedback to Fine-tune Diffusion Models without Any Reward Modelcited by 246
  27. 2023NoMaD: Goal Masked Diffusion Policies for Navigation and Explorationcited by 234
  28. 2023Goal-Conditioned Imitation Learning using Score-based Diffusion Policiescited by 229
  29. 2023RVT: Robotic View Transformer for 3D Object Manipulationcited by 224
  30. 2025Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasetscited by 218
  31. 2024ManiSkill3: GPU Parallelized Robotics Simulation and Rendering for Generalizable Embodied AIcited by 216
  32. 2024OGBench: Benchmarking Offline Goal-Conditioned RLcited by 216
  33. 2025Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Modelscited by 216
  34. 2023Any-point Trajectory Modeling for Policy Learningcited by 207
  35. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledgecited by 203
  36. 2025Real-Time Execution of Action Chunking Flow Policiescited by 199
  37. 2025Unified Video Action Modelcited by 195
  38. 2025DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Controlcited by 191

50 most cited of 2,730 All 2,730 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025D3P: Dynamic Denoising Diffusion Policy via Reinforcement Learning
  2. 2026Immiscible Diffusion Policy: Preserving Multimodal Robot Actions through Label-Free Noise Assignment
  3. 2025Latent Policy Barrier: Learning Robust Visuomotor Policies by Staying In-Distribution
  4. 2023Score Regularized Policy Optimization through Diffusion Behavior
  5. 2025D2PPO: Diffusion Policy Policy Optimization with Dispersive Loss
  6. 2023Motion Planning Diffusion: Learning and Planning of Robot Motions with Diffusion Models
  7. 2026Learning Diffusion Policy from Primitive Skills for Robot Manipulation