mlsanityData to 7 Oct 2026

One-Step Diffusion Policy: Fast Visuomotor Policies via Diffusion Distillation

arXiv 2410.21257 ↗First posted 28 Oct 2024cs.RO cs.LGcited by 83

On the map: Diffusion models → Diffusion and flow policies for robotics

Abstract (arXiv)

Diffusion models, praised for their success in generative tasks, are increasingly being applied to robotics, demonstrating exceptional performance in behavior cloning. However, their slow generation process stemming from iterative denoising steps poses a challenge for real-time applications in resource-constrained robotics setups and dynamically changing environments. In this paper, we introduce the One-Step Diffusion Policy (OneDP), a novel approach that distills knowledge from pre-trained diffusion policies into a single-step action generator, significantly accelerating response times for robotic control tasks. We ensure the distilled generator closely aligns with the original policy distribution by minimizing the Kullback-Leibler (KL) divergence along the diffusion chain, requiring only 2%-10% additional pre-training cost for convergence. We evaluated OneDP on 6 challenging simulation tasks as well as 4 self-designed real-world tasks using the Franka robot. The results demonstrate that OneDP not only achieves state-of-the-art success rates but also delivers an order-of-magnitude improvement in inference speed, boosting action prediction frequency from 1.5 Hz to 62 Hz, establishing its potential for dynamic and computationally constrained robotic applications. We share the project page at https://research.nvidia.com/labs/dir/onedp/.

Key facts. Cited by 83 papers in the map (data through 7 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 48 of its 50 references that are in the map. First posted on arXiv 28 Oct 2024.

Builds on

48 of 50 references.

Closest ancestors · 12

Same direction, newest first

  1. 2024Diffusion Policies creating a Trust Region for Offline Reinforcement Learning30 May
  2. 2024Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillation13 May
  3. 20243D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations6 Mar
  4. 20243D Diffuser Actor: Policy Diffusion with 3D Scene Representations16 Feb
  5. 2023Learning a Diffusion Model Policy from Rewards via Q-Score Matching18 Dec
  6. 2023Score Regularized Policy Optimization through Diffusion Behavior11 Oct
  7. 2023IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies20 Apr
  8. 2023Goal-Conditioned Imitation Learning using Score-based Diffusion Policies5 Apr
  9. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusion7 Mar
  10. 2022Is Conditional Generative Modeling all you need for Decision-Making?28 Nov
  11. 2022SE(3)-DiffusionFields: Learning smooth cost functions for joint grasp and motion optimization through diffusion8 Sep
  12. 2022Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning12 Aug

Other references · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  6. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,539
  8. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understandingcited by 6,322
  9. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  10. 2022DreamFusion: Text-to-3D using 2D Diffusioncited by 3,006
  11. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  12. 2022Video Diffusion Modelscited by 2,280
24 more
  1. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,961
  2. 2023Consistency Modelscited by 1,778
  3. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  4. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  5. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  6. 2023ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillationcited by 1,207
  7. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,023
  8. 2023One-step Diffusion with Distribution Matching Distillationcited by 978
  9. 2022eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoiserscited by 921
  10. 2024WorldSimBench: Towards Video Generation Models as World Simulatorscited by 867
  11. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 699
  12. 2022Pseudo Numerical Methods for Diffusion Models on Manifoldscited by 695
  13. 2023VideoCrafter1: Open Diffusion Models for High-Quality Video Generationcited by 530
  14. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANscited by 515
  15. 2023Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusioncited by 448
  16. 2021Grad-TTS: A Diffusion Probabilistic Model for Text-to-Speechcited by 445
  17. 2021Implicit Behavioral Cloningcited by 442
  18. 2021Knowledge Distillation in Iterative Generative Models for Improved Sampling Speedcited by 344
  19. 2023Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Modelscited by 232
  20. 2024Score identity Distillation: Exponentially Fast Distillation of Pretrained Diffusion Models for One-Step Generationcited by 211
  21. 2022Diffusion-GAN: Training GANs with Diffusioncited by 203
  22. 2018RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitationcited by 202
  23. 2022Fast Sampling of Diffusion Models via Operator Learningcited by 173
  24. 2023UFOGen: You Forward Once Large Scale Text-to-Image Generation via Diffusion GANscited by 165

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 28; 2026: 51.

83 papers.

Sort:

By area:

  1. 2025Cosmos World Foundation Model Platform for Physical AIcited by 833
  2. 2025Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policycited by 73
  3. 2024Diffusion-VLA: Generalizable and Interpretable Robot Foundation Model via Self-Generated Reasoningcited by 57
  4. 2025RL-100: Performant Robotic Manipulation with Real-World Reinforcement Learningcited by 47
  5. 2025NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidancecited by 46
  6. 2025BEHAVIOR Robot Suite: Streamlining Real-World Whole-Body Manipulation for Everyday Household Activitiescited by 29
  7. 2026RDT2: Exploring the Scaling Limit of UMI Data Towards Zero-Shot Cross-Embodiment Generalizationcited by 29
  8. 2025Diffuse-CLoC: Guided Diffusion for Physics-based Character Look-ahead Controlcited by 27
  9. 2026FASTER: Rethinking Real-Time Flow VLAscited by 20
  10. 2024Fast and Robust Visuomotor Riemannian Flow Matching Policycited by 18
  11. 2025Falcon: Fast Visuomotor Policies via Partial Denoisingcited by 14
  12. 2026VLA-Corrector: Lightweight Detect-and-Correct Inference for Adaptive Action Horizoncited by 14
38 more
  1. 2025H3DP: Triply-Hierarchical Diffusion Policy for Visuomotor Learningcited by 13
  2. 2025FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistencycited by 13
  3. 2024Score and Distribution Matching Policy: Advanced Accelerated Visuomotor Policies via Matched Distillationcited by 12
  4. 2025D3P: Dynamic Denoising Diffusion Policy via Reinforcement Learningcited by 10
  5. 2025VFP: Variational Flow-Matching Policy for Multi-Modal Robot Manipulationcited by 9
  6. 2026Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action Generationcited by 9
  7. 2025Fast Flow-based Visuomotor Policies via Conditional Optimal Transport Couplingscited by 8
  8. 2025Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action Policycited by 8
  9. 2025DM1: MeanFlow with Dispersive Regularization for 1-Step Robotic Manipulationcited by 8
  10. 2026Realtime-VLA FLASH: Speculative Inference Framework for Diffusion-based VLAscited by 8
  11. 2026STEP: Warm-Started Visuomotor Policies with Spatiotemporal Consistency Predictioncited by 7
  12. 2025Dynamic Rank Adjustment in Diffusion Policies for Efficient and Flexible Trainingcited by 6
  13. 2025TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Accelerationcited by 6
  14. 2026Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategiescited by 6
  15. 2026Sparse ActionGen: Accelerating Diffusion Policy with Real-time Pruningcited by 5
  16. 2026One-Step Flow Policy: Self-Distillation for Fast Visuomotor Policiescited by 5
  17. 2026You've Got a Golden Ticket: Improving Generative Robot Policies With A Single Noise Vectorcited by 5
  18. 2026Vesta: A Generalist Embodied Reasoning Modelcited by 5
  19. 2025R2RGEN: Real-to-Real 3D Data Generation for Spatially Generalized Manipulationcited by 4
  20. 2025From Demonstrations to Safe Deployment: Path-Consistent Safety Filtering for Diffusion Policiescited by 4
  21. 2025OMP: One-step Meanflow Policy with Directional Alignmentcited by 4
  22. 2026From Flow to One Step: Real-Time Multi-Modal Trajectory Policies via Implicit Maximum Likelihood Estimation-based Distribution Distillationcited by 4
  23. 2026Drift-Based Policy Optimization: Native One-Step Policy Learning for Online Robot Controlcited by 4
  24. 2026FASTER: Value-Guided Sampling for Fast RLcited by 4
  25. 2026WarmPrior: Straightening Flow-Matching Policies with Temporal Priorscited by 4
  26. 2026SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Controlcited by 4
  27. 2026Foresight Without Seeing: Latent Futures for World Action Modelscited by 4
  28. 2025Efficient Task-specific Conditional Diffusion Policies: Shortcut Model Acceleration and SO(3) Optimizationcited by 3
  29. 2025Robot Motion Planning using One-Step Diffusion with Noise-Optimized Approximate Motionscited by 3
  30. 2025Accelerating Diffusion Planners in Offline RL via Reward-Aware Consistency Trajectory Distillationcited by 3
  31. 2025Fast Visuomotor Policy for Robotic Manipulationcited by 3
  32. 2026Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Controlcited by 3
  33. 2024Subconscious Robotic Imitation Learningcited by 2
  34. 2026Ada3Drift: Adaptive Training-Time Drifting for One-Step 3D Visuomotor Robotic Manipulationcited by 2
  35. 2026CofactVLA: Deconfounding Vision-Language-Action Models via Counterfactual Interventioncited by 2
  36. 2026DriftingVLA: Native One-Step Vision-Language-Action Generation via Per-Dimension Temporal Driftingcited by 2
  37. 2025ImitDiff: Transferring Foundation-Model Priors for Distraction Robust Visuomotor Policycited by 1
  38. 2025Retrieve-Augmented Generation for Speeding up Diffusion Policy without Additional Trainingcited by 1

50 most cited of 83 All 83 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2024Streaming Diffusion Policy: Fast Policy Synthesis with Variable Noise Diffusion Models
  2. 2025Real-Time Iteration Scheme for Diffusion Policy
  3. 2025Two-Steps Diffusion Policy for Robotic Manipulation via Genetic Denoising
  4. 2023Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised Learning
  5. 2025Time-Unified Diffusion Policy with Action Discrimination for Robotic Manipulation
  6. 2025Responsive Noise-Relaying Diffusion Policy: Responsive and Efficient Visuomotor Control
  7. 2025CDP: Towards Robust Autoregressive Visuomotor Policy Learning via Causal Diffusion
  8. 2024Unpacking the Individual Components of Diffusion Policy