mlsanityData to 14 Oct 2026

PFM-HR: Pose Flow Matching for Humanoid Robots

arXiv 2608.03227 ↗First posted 4 Aug 2026cs.ROcited by 0

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

Abstract (arXiv)

Motion priors improve reinforcement learning for physics-based humanoid tracking, but temporal priors require ordered motion clips, while pose priors provide limited guidance for policy-induced pose transitions. We present Pose Flow Matching for Humanoid Robots (PFM-HR), a reusable flow matching prior trained directly on large scale unordered pose data. PFM-HR introduces the Pose Geometry Score (PGS), which quantifies how joint coordinate changes during rollouts align with the local geometry of pose variation captured by the prior. Using PGS to modulate the tracking reward guides policy exploration toward structured pose changes while keeping the prior frozen across tracking tasks. Experiments demonstrate that PFM-HR improves both single motion and general motion tracking, especially for highly dynamic motions.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 32 of its 40 references that are in the map. First posted on arXiv 4 Aug 2026.

Builds on

32 of 40 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion11 Aug

Other references · 31

  1. 2022Scalable Diffusion Models with Transformerscited by 6,054
  2. 2022Flow Matching for Generative Modelingcited by 5,702
  3. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  4. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  5. 2021Robust Motion In-betweeningcited by 229
  6. 2023Perpetual Humanoid Control for Real-time Simulated Avatarscited by 218
  7. 2023Universal Humanoid Motion Representations for Physics-Based Controlcited by 116
  8. 2024MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpaintingcited by 116
  9. 2025SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Controlcited by 101
  10. 2023CALM: Conditional Adversarial Latent Models for Directable Virtual Characterscited by 94
  11. 2022Adversarial Motion Priors Make Good Substitutes for Complex Reward Functionscited by 89
  12. 2022Pose-NDF: Modeling Human Pose Manifolds with Neural Distance Fieldscited by 85
19 more
  1. 2025GMT: General Motion Tracking for Humanoid Whole-Body Controlcited by 83
  2. 2025Visual Imitation Enables Contextual Humanoid Controlcited by 68
  3. 2023MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representationscited by 60
  4. 2025ResMimic: From General Motion Tracking to Humanoid Whole-body Loco-Manipulation via Residual Learningcited by 41
  5. 2023Neural Categorical Priors for Physics-Based Character Controlcited by 38
  6. 2024Text-to-Image Rectified Flow as Plug-and-Play Priorscited by 38
  7. 2023On the Posterior Distribution in Denoising: Application to Uncertainty Quantificationcited by 33
  8. 2024NRDF: Neural Riemannian Distance Fields for Learning Articulated Pose Priorscited by 27
  9. 2025VisualMimic: Visual Humanoid Loco-Manipulation via Motion Tracking and Generationcited by 26
  10. 2023DPoser: Diffusion Model as Robust 3D Human Pose Priorcited by 17
  11. 2025SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Controlcited by 15
  12. 2025DPoser-X: Diffusion Model as Robust 3D Whole-body Human Pose Priorcited by 13
  13. 2025Physics-Based Motion Imitation with Adversarial Differential Discriminatorscited by 12
  14. 2025MimicKit: A Reinforcement Learning Framework for Motion Imitation and Controlcited by 10
  15. 2026ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulationcited by 9
  16. 2025Score Distillation of Flow Matching Modelscited by 8
  17. 2025Geometric Neural Distance Fields for Learning Human Motion Priorscited by 6
  18. 2026Heracles: Bridging Precise Tracking and Generative Synthesis for General Humanoid Controlcited by 5
  19. 2026PDF-HR: Pose Distance Fields for Humanoid Robotscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Flow Policy Gradients for Robot Control
  2. 2026PASSAGE: Scaling Scene-Aligned Motion Learning for Perceptive Humanoid Traversal in Cluttered Environments ↗
  3. 2026Let the Dynamics Flow: Stable Flow Matching Dynamical Systems
  4. 2024Riemannian Flow Matching Policy for Robot Motion Learning
  5. 2026RFM-Pose:Reinforcement-Guided Flow Matching for Fast Category-Level 6D Pose Estimation
  6. 2026Learning Reusable Hybrid Motion Priors for Humanoid Locomotion from Motion Imitation
  7. 2025Extremum Flow Matching for Offline Goal Conditioned Reinforcement Learning
  8. 2025RobotDancing: Residual-Action Reinforcement Learning Enables Robust Long-Horizon Humanoid Motion Tracking