# Streaming Diffusion Policy: Fast Policy Synthesis with Variable Noise Diffusion Models

arXiv: https://arxiv.org/abs/2406.04806 · HTML: https://mlsanity.com/paper/2406.04806/

## Key facts

- Cited by 56 papers in the map (data through 14 Oct 2026).
- Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models.
- Builds on 31 of its 37 references that are in the map.
- First posted on arXiv 7 Jun 2024.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)
- Offline RL and imitation learning from data / [Robot manipulation imitation learning](https://mlsanity.com/offlinerl/robot-manipulation-imitation-learning/)

## Builds on (most cited first, 30 of 31)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware](https://mlsanity.com/paper/2304.13705/) (2023)
- [Planning with Diffusion for Flexible Behavior Synthesis](https://mlsanity.com/paper/2205.09991/) (2022)
- [What Matters in Learning from Offline Human Demonstrations for Robot Manipulation](https://mlsanity.com/paper/2108.03298/) (2021)
- [On Distillation of Guided Diffusion Models](https://mlsanity.com/paper/2210.03142/) (2022)
- [Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion](https://mlsanity.com/paper/2310.02279/) (2023)
- [Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robots](https://mlsanity.com/paper/2402.10329/) (2024)
- [Imitating Human Behaviour with Diffusion Models](https://mlsanity.com/paper/2301.10677/) (2023)
- [Diffusion-based Generation, Optimization, and Planning in 3D Scenes](https://mlsanity.com/paper/2301.06015/) (2023)
- [Goal-Conditioned Imitation Learning using Score-based Diffusion Policies](https://mlsanity.com/paper/2304.02532/) (2023)
- [Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMC](https://mlsanity.com/paper/2302.11552/) (2023)
- [Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillation](https://mlsanity.com/paper/2405.07503/) (2024)
- [Motion Planning Diffusion: Learning and Planning of Robot Motions with Diffusion Models](https://mlsanity.com/paper/2308.01557/) (2023)
- [Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition](https://mlsanity.com/paper/2307.14535/) (2023)
- [SE(3)-DiffusionFields: Learning smooth cost functions for joint grasp and motion optimization through diffusion](https://mlsanity.com/paper/2209.03855/) (2022)
- [AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation](https://mlsanity.com/paper/2305.09515/) (2023)
- [Rolling Diffusion Models](https://mlsanity.com/paper/2402.09470/) (2024)
- [PlayFusion: Skill Acquisition via Diffusion from Language-Annotated Play](https://mlsanity.com/paper/2312.04549/) (2023)
- [TEDi: Temporally-Entangled Diffusion for Long-Term Motion Synthesis](https://mlsanity.com/paper/2307.15042/) (2023)
- [EDMP: Ensemble-of-costs-guided Diffusion for Motion Planning](https://mlsanity.com/paper/2309.11414/) (2023)
- [PoCo: Policy Composition from and for Heterogeneous Robot Learning](https://mlsanity.com/paper/2402.02511/) (2024)
- [Crossway Diffusion: Improving Diffusion-based Visuomotor Policy via Self-supervised Learning](https://mlsanity.com/paper/2307.01849/) (2023)
- [Movement Primitive Diffusion: Learning Gentle Robotic Manipulation of Deformable Objects](https://mlsanity.com/paper/2312.10008/) (2023)
- [Adaptive Online Replanning with Diffusion Models](https://mlsanity.com/paper/2310.09629/) (2023)
- [Don't Start from Scratch: Behavioral Refinement via Interpolant-based Policy Diffusion](https://mlsanity.com/paper/2402.16075/) (2024)
- [Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks](https://mlsanity.com/paper/2210.15629/) (2022)

## Built on by (most cited first, 30 of 56)

- [Real-Time Execution of Action Chunking Flow Policies](https://mlsanity.com/paper/2506.07339/) (2025)
- [Stable Video Infinity: Infinite-Length Video Generation with Error Recycling](https://mlsanity.com/paper/2510.09212/) (2025)
- [Leave No Observation Behind: Real-time Correction for VLA Action Chunks](https://mlsanity.com/paper/2509.23224/) (2025)
- [Streaming Flow Policy: Simplifying diffusion/flow-matching policies by treating action trajectories as flow trajectories](https://mlsanity.com/paper/2505.21851/) (2025)
- [Diffuse-CLoC: Guided Diffusion for Physics-based Character Look-ahead Control](https://mlsanity.com/paper/2503.11801/) (2025)
- [FASTER: Rethinking Real-Time Flow VLAs](https://mlsanity.com/paper/2603.19199/) (2026)
- [Learning Native Continuation for Action Chunking Flow Policies](https://mlsanity.com/paper/2602.12978/) (2026)
- [SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies](https://mlsanity.com/paper/2506.11948/) (2025)
- [Falcon: Fast Visuomotor Policies via Partial Denoising](https://mlsanity.com/paper/2503.00339/) (2025)
- [Score and Distribution Matching Policy: Advanced Accelerated Visuomotor Policies via Matched Distillation](https://mlsanity.com/paper/2412.09265/) (2024)
- [IMLE Policy: Fast and Sample Efficient Visuomotor Policy Learning via Implicit Maximum Likelihood Estimation](https://mlsanity.com/paper/2502.12371/) (2025)
- [Responsive Noise-Relaying Diffusion Policy: Responsive and Efficient Visuomotor Control](https://mlsanity.com/paper/2502.12724/) (2025)
- [FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistency](https://mlsanity.com/paper/2506.08822/) (2025)
- [D3P: Dynamic Denoising Diffusion Policy via Reinforcement Learning](https://mlsanity.com/paper/2508.06804/) (2025)
- [Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition](https://mlsanity.com/paper/2510.01068/) (2025)
- [Real-Time Iteration Scheme for Diffusion Policy](https://mlsanity.com/paper/2508.05396/) (2025)
- [Vid-CamEdit: Video Camera Trajectory Editing with Generative Rendering from Estimated Geometry](https://mlsanity.com/paper/2506.13697/) (2025)
- [STEP: Warm-Started Visuomotor Policies with Spatiotemporal Consistency Prediction](https://mlsanity.com/paper/2602.08245/) (2026)
- [One-Step Flow Policy: Self-Distillation for Fast Visuomotor Policies](https://mlsanity.com/paper/2603.12480/) (2026)
- [Efficient Video Diffusion Models: Advancements and Challenges](https://mlsanity.com/paper/2604.15911/) (2026)
- [RA-DP: Rapid Adaptive Diffusion Policy for Training-Free High-frequency Robotics Replanning](https://mlsanity.com/paper/2503.04051/) (2025)
- [Delay-Aware Diffusion Policy: Bridging the Observation-Execution Gap in Dynamic Tasks](https://mlsanity.com/paper/2512.07697/) (2025)
- [Sparse ActionGen: Accelerating Diffusion Policy with Real-time Pruning](https://mlsanity.com/paper/2601.12894/) (2026)
- [TIDAL: Temporally Interleaved Diffusion and Action Loop for High-Frequency VLA Control](https://mlsanity.com/paper/2601.14945/) (2026)
- [πR2: Reactive Real-time Flow Policies](https://mlsanity.com/paper/2607.26055/) (2026)
- [Real-Time Diffusion Policies for Games: Enhancing Consistency Policies with Q-Ensembles](https://mlsanity.com/paper/2503.16978/) (2025)
- [Smoother Action Chunking Flow Policy via Prior-Corrected Orthogonal Trust-Region Guidance](https://mlsanity.com/paper/2605.24433/) (2026)
- [ActionCache: Training-Free Acceleration for Vision-Language-Action Models with Action Caching and Refinement](https://mlsanity.com/paper/2607.06370/) (2026)
- [TacForcing: Streaming Action Generation with Execution-Time Tactile Feedback](https://mlsanity.com/paper/2608.25798/) (2026)
- [3D-CovDiffusion: 3D-Aware Diffusion Policy for Coverage Path Planning](https://mlsanity.com/paper/2510.03011/) (2025)

## Abstract (arXiv)

Diffusion models have seen rapid adoption in robotic imitation learning, enabling autonomous execution of complex dexterous tasks. However, action synthesis is often slow, requiring many steps of iterative denoising, limiting the extent to which models can be used in tasks that require fast reactive policies. To sidestep this, recent works have explored how the distillation of the diffusion process can be used to accelerate policy synthesis. However, distillation is computationally expensive and can hurt both the accuracy and diversity of synthesized actions. We propose SDP (Streaming Diffusion Policy), an alternative method to accelerate policy synthesis, leveraging the insight that generating a partially denoised action trajectory is substantially faster than a full output action trajectory. At each observation, our approach outputs a partially denoised action trajectory with variable levels of noise corruption, where the immediate action to execute is noise-free, with subsequent actions having increasing levels of noise and uncertainty. The partially denoised action trajectory for a new observation can then be quickly generated by applying a few steps of denoising to the previously predicted noisy action trajectory (rolled over by one timestep). We illustrate the efficacy of this approach, dramatically speeding up policy synthesis while preserving performance across both simulated and real-world settings.