mlsanityData to 7 Oct 2026

ManiCM: Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulation

arXiv 2406.01586 ↗First posted 3 Jun 2024cs.RO cs.AIcited by 57

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

Abstract (arXiv)

Diffusion models have been verified to be effective in generating complex distributions from natural images to motion trajectories. Recent diffusion-based methods show impressive performance in 3D robotic manipulation tasks, whereas they suffer from severe runtime inefficiency due to multiple denoising steps, especially with high-dimensional observations. To this end, we propose a real-time robotic manipulation model named ManiCM that imposes the consistency constraint to the diffusion process, so that the model can generate robot actions in only one-step inference. Specifically, we formulate a consistent diffusion process in the robot action space conditioned on the point cloud input, where the original action is required to be directly denoised from any point along the ODE trajectory. To model this process, we design a consistency distillation technique to predict the action sample directly instead of predicting the noise within the vision community for fast convergence in the low-dimensional action manifold. We evaluate ManiCM on 31 robotic manipulation tasks from Adroit and Metaworld, and the results demonstrate that our approach accelerates the state-of-the-art method by 10 times in average inference speed while maintaining competitive average success rate.

Key facts. Cited by 57 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 46 of its 49 references that are in the map. First posted on arXiv 3 Jun 2024.

Builds on

46 of 49 references.

Closest ancestors · 13

Same direction, newest first

  1. 2024Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillation13 May
  2. 2024Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation6 Mar
  3. 20243D Diffuser Actor: Policy Diffusion with 3D Scene Representations16 Feb
  4. 2023Boosting Continuous Control with Consistency Policy10 Oct
  5. 2023AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model3 Oct
  6. 2023Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning29 Sep
  7. 2023MetaDiffuser: Diffusion Model as Conditional Planner for Offline Meta-RL31 May
  8. 2023Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning29 May
  9. 2023Goal-Conditioned Imitation Learning using Score-based Diffusion Policies5 Apr
  10. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusion7 Mar
  11. 2023Imitating Human Behaviour with Diffusion Models25 Jan
  12. 2022Is Conditional Generative Modeling all you need for Decision-Making?28 Nov
1 more
  1. 2022Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning12 Aug

Other references · 33

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  4. 2020Denoising Diffusion Implicit Modelscited by 9,655
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  6. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  7. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  8. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  9. 2023Consistency Modelscited by 1,778
  10. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,168
  11. 2021Variational Diffusion Modelscited by 1,145
  12. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,023
21 more
  1. 2023Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inferencecited by 826
  2. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 699
  3. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 685
  4. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 669
  5. 2021CLIPort: What and Where Pathways for Robotic Manipulationcited by 617
  6. 2023Learning Universal Policies via Text-Guided Video Generationcited by 506
  7. 2023LCM-LoRA: A Universal Stable-Diffusion Acceleration Modulecited by 211
  8. 2023Scaling Robot Learning with Semantically Imagined Experiencecited by 175
  9. 2022Masked World Models for Visual Controlcited by 169
  10. 2024MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Modelcited by 164
  11. 2024PIXART-δ: Fast and Controllable Image Generation with Latent Consistency Modelscited by 139
  12. 2021Coarse-to-Fine Q-attention: Efficient Learning for Visual Robotic Manipulation via Discretisationcited by 120
  13. 2024ManiGaussian: Dynamic Gaussian Splatting for Multi-task Robotic Manipulationcited by 106
  14. 2023Synthetic Experience Replaycited by 100
  15. 2023GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fieldscited by 99
  16. 2023VideoLCM: Video Latent Consistency Modelcited by 90
  17. 2022VRL3: A Data-Driven Framework for Visual Deep Reinforcement Learningcited by 51
  18. 2024DiffuserLite: Towards Real-time Diffusion Planningcited by 40
  19. 2023ConsistencyTTA: Accelerating Diffusion-Based Text-to-Audio Generation with Consistency Distillationcited by 22
  20. 2024DNAct: Diffusion Guided Multi-Task 3D Policy Learningcited by 22
  21. 2023CCM: Adding Conditional Controls to Text-to-Image Consistency Modelscited by 9

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 21; 2026: 28.

57 papers.

Sort:

By area:

  1. 2025RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twinscited by 117
  2. 2024FlowPolicy: Enabling Fast and Robust 3D Flow-based Policy via Consistency Flow Matching for Robot Manipulationcited by 99
  3. 2025ManiFlow: A General Robot Manipulation Policy via Consistency Flow Trainingcited by 43
  4. 2026RMBench: Memory-Dependent Robotic Manipulation Benchmark with Insights into Policy Designcited by 40
  5. 2025CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decodingcited by 38
  6. 2024G3Flow: Generative 3D Semantic Flow for Pose-aware and Generalizable Object Manipulationcited by 35
  7. 2024CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Predictioncited by 26
  8. 2026FASTER: Rethinking Real-Time Flow VLAscited by 20
  9. 2024Fast and Robust Visuomotor Riemannian Flow Matching Policycited by 18
  10. 2025CordViP: Correspondence-based Visuomotor Policy for Dexterous Manipulation in Real-Worldcited by 16
  11. 2025Falcon: Fast Visuomotor Policies via Partial Denoisingcited by 14
  12. 2025H3DP: Triply-Hierarchical Diffusion Policy for Visuomotor Learningcited by 13
38 more
  1. 2025FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistencycited by 13
  2. 2024Score and Distribution Matching Policy: Advanced Accelerated Visuomotor Policies via Matched Distillationcited by 12
  3. 2024Hierarchical Memory for Long Video QAcited by 9
  4. 2025Demystifying Diffusion Policies: Action Memorization and Simple Lookup Table Alternativescited by 9
  5. 2025VFP: Variational Flow-Matching Policy for Multi-Modal Robot Manipulationcited by 9
  6. 2025SafeBimanual: Diffusion-based Trajectory Optimization for Safe Bimanual Manipulationcited by 9
  7. 2025Fast Flow-based Visuomotor Policies via Conditional Optimal Transport Couplingscited by 8
  8. 2025Benchmarking Generalizable Bimanual Manipulation: RoboTwin Dual-Arm Collaboration Challenge at CVPR 2025 MEIS Workshopcited by 8
  9. 2026GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specializationcited by 7
  10. 2026Efficient Video Diffusion Models: Advancements and Challengescited by 6
  11. 2024BiKC: Keypose-Conditioned Consistency Policy for Bimanual Robotic Manipulationcited by 5
  12. 2025Time-Unified Diffusion Policy with Action Discrimination for Robotic Manipulationcited by 5
  13. 2026One-Step Flow Policy: Self-Distillation for Fast Visuomotor Policiescited by 5
  14. 2025FieldGen: From Teleoperated Pre-Manipulation Trajectories to Field-Guided Data Generationcited by 4
  15. 2025OMP: One-step Meanflow Policy with Directional Alignmentcited by 4
  16. 2026WarmPrior: Straightening Flow-Matching Policies with Temporal Priorscited by 4
  17. 2025Accelerating Diffusion Planners in Offline RL via Reward-Aware Consistency Trajectory Distillationcited by 3
  18. 2026InfBaGel: Human-Object-Scene Interaction Generation with Dynamic Perception and Iterative Refinementcited by 3
  19. 2025A Continuous-Time Consistency Model for 3D Point Cloud Generationcited by 2
  20. 2025Language-Conditioned Representations and Mixture-of-Experts Policy for Robust Multi-Task Robotic Manipulationcited by 2
  21. 2026FAR-Dex: Few-shot Data Augmentation and Adaptive Residual Policy Refinement for Dexterous Manipulationcited by 2
  22. 2026Ada3Drift: Adaptive Training-Time Drifting for One-Step 3D Visuomotor Robotic Manipulationcited by 2
  23. 2026HiFlow: Tokenization-Free Scale-Wise Autoregressive Policy Learning via Flow Matchingcited by 2
  24. 2026FA-RDP: A Frequency-Adaptive Reactive Diffusion Policy for Contact-Rich Manipulationcited by 2
  25. 2025FRMD: Fast Robot Motion Diffusion with Consistency-Distilled Movement Primitives for Smooth Action Generationcited by 1
  26. 2026ForeDiffusion: Foresight-Conditioned Diffusion Policy via Future View Construction for Robot Manipulationcited by 1
  27. 2026PRISM: Performer RS-IMLE for Single-pass Multisensory Imitation Learningcited by 1
  28. 2026CMP: Robust Whole-Body Tracking for Loco-Manipulation via Competence Manifold Projectioncited by 1
  29. 2026BORA: Bridging Offline Reinforcement Learning and Online Residual Adaptation for Real-World Dexterous VLA Modelscited by 1
  30. 2026Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometrycited by 1
  31. 2026High-Fidelity One-Step Generative Visuomotor Policy via Recursive Correction, Frequency Consistency, and Contrastive Flow Matchingcited by 1
  32. 2024Learning Generalizable 3D Manipulation With 10 Demonstrationscited by 0
  33. 2025Fine-Tuning Flow Matching via Maximum Likelihood Estimation of Reconstructionscited by 0
  34. 2025Kinematics-Aware Diffusion Policy with Consistent 3D Observation and Action Space for Whole-Arm Robotic Manipulationcited by 0
  35. 2026KAN We Flow? Advancing Robotic Manipulation with 3D Flow Matching via KAN & RWKVcited by 0
  36. 2026HybridFlow: A 2-NFE Generative Policy for Real-Time Robotic Manipulationcited by 0
  37. 2026FODMP: Fast One-Step Diffusion of Movement Primitives Generation for Time-Dependent Robot Actionscited by 0
  38. 2026Trajectory-Consistent Flow Matching for Robust Visuomotor Policy Learningcited by 0

50 most cited of 57 All 57 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Real-Time Iteration Scheme for Diffusion Policy
  2. 2025ADPro: a Test-time Adaptive Diffusion Policy via Manifold-constrained Denoising and Task-aware Initialization for Robotic Manipulation
  3. 2025Two-Steps Diffusion Policy for Robotic Manipulation via Genetic Denoising
  4. 2025Diffusion Models for Robotic Manipulation: A Survey
  5. 2026JAMB: Joint Action-Motion Diffusion for Bimanual Manipulation
  6. 2025Hybrid Consistency Policy: Decoupling Multi-Modal Diversity and Real-Time Efficiency in Robotic Manipulation
  7. 2024Hierarchical Diffusion Policy: manipulation trajectory generation via contact guidance
  8. 2025ISS Policy : Scalable Diffusion Policy with Implicit Scene Supervision