mlsanityData to 14 Oct 2026

3D FlowMatch Actor: Unified 3D Policy for Single- and Dual-Arm Manipulation

arXiv 2508.11002 ↗First posted 14 Aug 2025cs.ROcited by 20

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

also in 1 more
Abstract (arXiv)

We present 3D FlowMatch Actor (3DFA), a 3D policy architecture for robot manipulation that combines flow matching for trajectory prediction with 3D pretrained visual scene representations for learning from demonstration. 3DFA leverages 3D relative attention between action and visual tokens during action denoising, building on prior work in 3D diffusion-based single-arm policy learning. Through a combination of flow matching and targeted system-level and architectural optimizations, 3DFA achieves over 30x faster training and inference than previous 3D diffusion-based policies, without sacrificing performance. On the bimanual PerAct2 benchmark, it establishes a new state of the art, outperforming the next-best method by an absolute margin of 41.4%. In extensive real-world evaluations, it surpasses strong baselines with up to 1000x more parameters and significantly more pretraining. In unimanual settings, it sets a new state of the art on 74 RLBench tasks by directly predicting dense end-effector trajectories, eliminating the need for motion planning. Comprehensive ablation studies underscore the importance of our design choices for both policy effectiveness and efficiency.

Key facts. Cited by 20 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 49 of its 74 references that are in the map. First posted on arXiv 14 Aug 2025.

Builds on

49 of 74 references.

Closest ancestors · 14

Same direction, newest first

  1. 2025FlowRAM: Grounding Flow Matching Policy with Region-Aware Mamba Framework for Robotic Manipulation19 Jun
  2. 2025Spatial-Temporal Graph Diffusion Policy with Kinematic Modeling for Bimanual Robotic Manipulation13 Mar
  3. 2024Fast and Robust Visuomotor Riemannian Flow Matching Policy14 Dec
  4. 2024FlowPolicy: Enabling Fast and Robust 3D Flow-based Policy via Consistency Flow Matching for Robot Manipulation6 Dec
  5. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation10 Oct
  6. 2024Learning Robotic Manipulation Policies from Point Clouds with Conditional Flow Matching11 Sep
  7. 2024ActionFlow: Equivariant, Accurate, and Efficient Policies with Spatially Symmetric Flow Matching6 Sep
  8. 2024Affordance-based Robot Manipulation with Flow Matching2 Sep
  9. 2024Riemannian Flow Matching Policy for Robot Motion Learning15 Mar
  10. 20243D Diffuser Actor: Policy Diffusion with 3D Scene Representations16 Feb
  11. 2024Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following9 Feb
  12. 2023IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies20 Apr
2 more
  1. 2023Goal-Conditioned Imitation Learning using Score-based Diffusion Policies5 Apr
  2. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusion7 Mar

Other references · 35

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2022Flow Matching for Generative Modelingcited by 5,702
  6. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  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. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,568
  10. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  11. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,225
  12. 2021Perceiver: General Perception with Iterative Attentioncited by 1,104
23 more
  1. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 852
  2. 2019RLBench: The Robot Learning Benchmark & Learning Environmentcited by 689
  3. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 551
  4. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 519
  5. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 495
  6. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulationcited by 422
  7. 2024Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperationcited by 391
  8. 2023RVT: Robotic View Transformer for 3D Object Manipulationcited by 225
  9. 2023RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shotcited by 183
  10. 2022Offline Reinforcement Learning via High-Fidelity Generative Behavior Modelingcited by 182
  11. 2023Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulationcited by 138
  12. 2025RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twinscited by 121
  13. 2022Instruction-driven history-aware policies for robotic manipulationscited by 94
  14. 2021Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulationcited by 85
  15. 2023Stabilize to Act: Learning to Coordinate for Bimanual Manipulationcited by 39
  16. 2023Energy-based Models are Zero-Shot Planners for Compositional Scene Rearrangementcited by 30
  17. 2024ODIN: A Single Model for 2D and 3D Segmentationcited by 25
  18. 2024VoxAct-B: Voxel-Based Acting and Stabilizing Policy for Bimanual Manipulationcited by 21
  19. 2022Learning Bimanual Scooping Policies for Food Acquisitioncited by 20
  20. 2024AnyBimanual: Transferring Unimanual Policy for General Bimanual Manipulationcited by 16
  21. 2025Gripper Keypose and Object Pointflow as Interfaces for Bimanual Robotic Manipulationcited by 16
  22. 2025Rethinking Bimanual Robotic Manipulation: Learning with Decoupled Interaction Frameworkcited by 12
  23. 2025Learning Bimanual Manipulation via Action Chunking and Inter-Arm Coordination with Transformerscited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 20.

20 papers.

Sort:

By area:

  1. 2026Dex4D: Task-Agnostic Point Track Policy for Zero-Shot Dexterous Manipulationcited by 14
  2. 2026ST-VLA: Enabling 4D-Aware Spatiotemporal Understanding for General Robot Manipulationcited by 3
  3. 20263D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidancecited by 3
  4. 2026Instant-Fold: In-Context Imitation Learning for Deformable Object Manipulationcited by 2
  5. 2026Scaling Bimanual Household Manipulation from 1,500 hours of Demonstrations to On-Policy Correctionscited by 2
  6. 2026R3D: Revisiting 3D Policy Learningcited by 1
  7. 2026Bimanual Robot Manipulation via Multi-Agent In-Context Learningcited by 1
  8. 2026CUBic: Coordinated Unified Bimanual Perception and Control Frameworkcited by 1
  9. 2026High-Fidelity One-Step Generative Visuomotor Policy via Recursive Correction, Frequency Consistency, and Contrastive Flow Matchingcited by 1
  10. 2026See like a Robot: Robot-Centric Pointmaps for VLA Modelscited by 1
  11. 2026Robust Bimanual Vision-Language-Action Models via Embarrassingly Simple Modality Maskingcited by 1
  12. 2026Task-Prototype Guided Flow Matching for Few-Shot Generalization in Vision-Language Robot Manipulationcited by 1
8 more
  1. 2026KAN We Flow? Advancing Robotic Manipulation with 3D Flow Matching via KAN & RWKVcited by 0
  2. 2026RoTri-Diff: A Spatial Robot-Object Triadic Interaction-Guided Diffusion Model for Bimanual Manipulationcited by 0
  3. 2026PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulationcited by 0
  4. 2026Learning 3D Affordances for Blade Insertion in Cluttered Stowingcited by 0
  5. 2026GeomVLA: Unifying Scene, Motion, and Action in 3Dcited by 0
  6. 2026JAMB: Joint Action-Motion Diffusion for Bimanual Manipulationcited by 0
  7. 2026An Empirical Study on What Matters for Viewpoint-Generalizable Policies in Visual Imitation Learningcited by 0
  8. 2026Learning Conditional Source Distribution via Flow Reversal for Temporal Flow Matchingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 20253D Flow Diffusion Policy: Visuomotor Policy Learning via Generating Flow in 3D Space
  2. 2025ISS Policy : Scalable Diffusion Policy with Implicit Scene Supervision
  3. 2026RoboFlow4D: A Lightweight Flow World Model Toward Real-Time Flow-Guided Robotic Manipulation
  4. 20253DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model
  5. 2026Flowing With Purpose: Latent Action Guided Flow Matching Policies For Robotic Manipulation
  6. 20243D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations
  7. 2026FlowVLA: Enabling World Dynamics Understanding through Pluggable 3D Flow Learning
  8. 2026Bridge3D: Enabling Vision-Language-Action Models to See and Act in 3D