mlsanityData to 14 Oct 2026

ManiFlow: A General Robot Manipulation Policy via Consistency Flow Training

arXiv 2509.01819 ↗First posted 1 Sep 2025cs.ROcited by 49

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

also in 1 more
Abstract (arXiv)

This paper introduces ManiFlow, a visuomotor imitation learning policy for general robot manipulation that generates precise, high-dimensional actions conditioned on diverse visual, language and proprioceptive inputs. We leverage flow matching with consistency training to enable high-quality dexterous action generation in just 1-2 inference steps. To handle diverse input modalities efficiently, we propose DiT-X, a diffusion transformer architecture with adaptive cross-attention and AdaLN-Zero conditioning that enables fine-grained feature interactions between action tokens and multi-modal observations. ManiFlow demonstrates consistent improvements across diverse simulation benchmarks and nearly doubles success rates on real-world tasks across single-arm, bimanual, and humanoid robot setups with increasing dexterity. The extensive evaluation further demonstrates the strong robustness and generalizability of ManiFlow to novel objects and background changes, and highlights its strong scaling capability with larger-scale datasets. Our website: maniflow-policy.github.io.

Key facts. Cited by 49 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 40 of its 48 references that are in the map. First posted on arXiv 1 Sep 2025.

Builds on

40 of 48 references.

Closest ancestors · 11

Same direction, newest first

  1. 2024The Ingredients for Robotic Diffusion Transformers14 Oct
  2. 2024Learning Robotic Manipulation Policies from Point Clouds with Conditional Flow Matching11 Sep
  3. 2024Affordance-based Robot Manipulation with Flow Matching2 Sep
  4. 2024Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goals8 Jul
  5. 2024ManiCM: Real-time 3D Diffusion Policy via Consistency Model for Robotic Manipulation3 Jun
  6. 2024Consistency Policy: Accelerated Visuomotor Policies via Consistency Distillation13 May
  7. 2024Riemannian Flow Matching Policy for Robot Motion Learning15 Mar
  8. 20243D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations6 Mar
  9. 20243D Diffuser Actor: Policy Diffusion with 3D Scene Representations16 Feb
  10. 2023Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models16 Oct
  11. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusion7 Mar

Other references · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2022Scalable Diffusion Models with Transformerscited by 6,054
  4. 2022Flow Matching for Generative Modelingcited by 5,702
  5. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  6. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  7. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  8. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  9. 2023Consistency Modelscited by 1,822
  10. 2025VGGT: Visual Geometry Grounded Transformercited by 1,539
  11. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
  12. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 551
17 more
  1. 2025RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulationcited by 518
  2. 2024Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robotscited by 394
  3. 2024One Step Diffusion via Shortcut Modelscited by 391
  4. 2023Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulationcited by 364
  5. 2023Vision-Language Foundation Models as Effective Robot Imitatorscited by 349
  6. 2023Uni3D: Exploring Unified 3D Representation at Scalecited by 237
  7. 2023RVT: Robotic View Transformer for 3D Object Manipulationcited by 225
  8. 2024Open-TeleVision: Teleoperation with Immersive Active Visual Feedbackcited by 145
  9. 2024RVT-2: Learning Precise Manipulation from Few Demonstrationscited by 137
  10. 2024Consistency Flow Matching: Defining Straight Flows with Velocity Consistencycited by 104
  11. 2023GNFactor: Multi-Task Real Robot Learning with Generalizable Neural Feature Fieldscited by 99
  12. 2024Bunny-VisionPro: Real-Time Bimanual Dexterous Teleoperation for Imitation Learningcited by 77
  13. 2024RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins (early version)cited by 69
  14. 2023DexArt: Benchmarking Generalizable Dexterous Manipulation with Articulated Objectscited by 66
  15. 2024DNAct: Diffusion Guided Multi-Task 3D Policy Learningcited by 23
  16. 2024Score and Distribution Matching Policy: Advanced Accelerated Visuomotor Policies via Matched Distillationcited by 13
  17. 2025Integrating LMM Planners and 3D Skill Policies for Generalizable Manipulationcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 7; 2026: 42.

49 papers.

Sort:

By area:

  1. 2025VLA-0: Building State-of-the-Art VLAs with Zero Modificationcited by 49
  2. 2026ABPolicy: Asynchronous B-Spline Flow Policy for Real-Time and Smooth Robotic Manipulationcited by 10
  3. 2025Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Compositioncited by 9
  4. 2026Shallow-π: Knowledge Distillation for Flow-based VLAscited by 8
  5. 2026FlowCorrect: Efficient Interactive Correction of Generative Flow Policies for Robotic Manipulationcited by 7
  6. 2026Drift-Based Policy Optimization: Native One-Step Policy Learning for Online Robot Controlcited by 5
  7. 2025OMP: One-step Meanflow Policy with Directional Alignmentcited by 4
  8. 2026Neuro-Symbolic Safety Guidance for Vision-Language-Action Models via Constrained Flow Matchingcited by 4
  9. 2026πR2: Reactive Real-time Flow Policiescited by 4
  10. 2025RoboManipBaselines: A Unified Framework for Imitation Learning in Robotic Manipulation across Real and Simulation Environmentscited by 3
  11. 2026HiFlow: Tokenization-Free Scale-Wise Autoregressive Policy Learning via Flow Matchingcited by 2
  12. 2026LAFP: Preserving Latent Action Structure in Latent Policy Learning via Flow Matchingcited by 2
37 more
  1. 2026Where Should Action Generation Begin? A Learnable Source Prior for Generative Robot Policiescited by 2
  2. 2026DriftingVLA: Native One-Step Vision-Language-Action Generation via Per-Dimension Temporal Driftingcited by 2
  3. 2025Improving Robustness to Out-of-Distribution States in Imitation Learning via Deep Koopman-Boosted Diffusion Policycited by 1
  4. 2026Habilis-β: A Fast-Motion and Long-Lasting On-Device Vision-Language-Action Modelcited by 1
  5. 2026Human-Robot Copilot for Data-Efficient Imitation Learningcited by 1
  6. 2026R3D: Revisiting 3D Policy Learningcited by 1
  7. 2026DEFLECT: Temporal Counterfactual Preference Learning for Delay-Robust Asynchronous VLAscited by 1
  8. 2026Set-Supervised Diffusion Policy: Learning Action-Chunking Diffusion through Correctionscited by 1
  9. 2026Invertible Neural Network Adapter for One-Step Flow Matching in Robot Manipulationcited by 1
  10. 2026Support-Constrained RL Enables Real-World Policy Improvement without Real-World Experiencecited by 1
  11. 2026High-Fidelity One-Step Generative Visuomotor Policy via Recursive Correction, Frequency Consistency, and Contrastive Flow Matchingcited by 1
  12. 2026SUN: Agentic Robot Policy Learning with Persistent Task Programscited by 1
  13. 2025RAMAC: Multimodal Risk-Aware Offline Reinforcement Learning and the Role of Behavior Regularizationcited by 0
  14. 2025Multi-Robot Motion Planning from Vision and Language using Heat-Inspired Diffusioncited by 0
  15. 2026Hierarchical Audio-Visual-Proprioceptive Fusion for Precise Robotic Manipulationcited by 0
  16. 2026Structural Action Transformer for 3D Dexterous Manipulationcited by 0
  17. 2026Expanding Spatial and Temporal Context for Robotic Imitation Learning With Scene Graphscited by 0
  18. 2026Let the Dynamics Flow: Stable Flow Matching Dynamical Systemscited by 0
  19. 2026Action Map Policy: Learning 3D Closed-loop Manipulation via Pixel Classificationcited by 0
  20. 2026Pix2Act: Image-Space Manipulation Policies with Equivariant Augmentationcited by 0
  21. 2026Temporal Policy: History-Initialized Action Generation for Robotic Learning from Demonstrationcited by 0
  22. 2026A Hierarchical Approach to Imitation Learning for Manipulation Tasks Requiring Time Varying Forcescited by 0
  23. 2026Toward Unified Robot Learning: Bridging Representation, Vision-Language-Action, and World Modelscited by 0
  24. 2026Bi-MoDe: Bilateral Control-based Imitation Learning via Modifier-Conditioned Decoding for Modulation of Execution Speed and Contact Intensitycited by 0
  25. 2026ProxiDex: Learning Dynamics-Guided Proximity Policy for Dexterous Manipulationcited by 0
  26. 2026EgoSpeedUp: Transferring Human Manipulation Tempo to Robot Policiescited by 0
  27. 2026RoboFFT: Finetuning generative robot policy via online reinforcement learning with forward processcited by 0
  28. 2026AnyStep-WAM: Budget-Aligned Distillation and Adaptive Inference for World Action Modelscited by 0
  29. 2026Manifold-Stable Flow Matchingcited by 0
  30. 2026Sample Complexity of Equivariant Reinforcement Learningcited by 0
  31. 2026BIND: Binding 3D Robot Actions to 2D Image Featurescited by 0
  32. 2026Kinematic MeanFlow: One-Step Action Generation Policy for Robotic Foundation Modelscited by 0
  33. 2026FastOPD: On-Policy Distillation for Lightweight VLA Deploymentcited by 0
  34. 2026Encoded but Not in Control: Revealing the Grounding Gap in Vision-Language Robot Policiescited by 0
  35. 2026DexFLEX: Contact-Aware Foundation Controller for Command-Guided Dexteritycited by 0
  36. 2026MultiFlow: Vision-Driven Multimodal fMRI Encoding via Stimulus-Informed Source Flow Matchingcited by 0
  37. 2026Steertuning Policies from a Few Human Videoscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024FlowPolicy: Enabling Fast and Robust 3D Flow-based Policy via Consistency Flow Matching for Robot Manipulation
  2. 2026ContextFlow: In-Context Flow Matching for Robot Manipulation
  3. 2025SeFA-Policy: Fast and Accurate Visuomotor Policy Learning with Selective Flow Alignment
  4. 2025Learning Robust Visuomotor Policies via Dynamics Alignment
  5. 2026CoLA-Flow Policy: Temporally Coherent Imitation Learning via Continuous Latent Action Flow Matching for Robotic Manipulation
  6. 2025DM1: MeanFlow with Dispersive Regularization for 1-Step Robotic Manipulation
  7. 2025EC-Flow: Enabling Versatile Robotic Manipulation from Action-Unlabeled Videos via Embodiment-Centric Flow
  8. 2026ForceFlow: Learning to Feel and Act via Contact-Driven Flow Matching