mlsanityData to 14 Oct 2026

BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion

arXiv 2508.08241 ↗First posted 11 Aug 2025cs.ROcited by 165

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

Abstract (arXiv)

The human-like form of humanoid robots positions them uniquely to achieve the agility and versatility in motor skills that humans possess. Learning from human demonstrations offers a scalable approach to acquiring these capabilities. However, prior works either produce unnatural motions or rely on motion-specific tuning to achieve satisfactory naturalness. Furthermore, these methods are often motion- or goal-specific, lacking the versatility to compose diverse skills, especially when solving unseen tasks. We present BeyondMimic, a framework that scales to diverse motions and carries the versatility to compose them seamlessly in tackling unseen downstream tasks. At heart, a compact motion-tracking formulation enables mastering a wide range of radically agile behaviors, including aerial cartwheels, spin-kicks, flip-kicks, and sprinting, with a single setup and shared hyperparameters, all while achieving state-of-the-art human-like performance. Moving beyond the mere imitation of existing motions, we propose a unified latent diffusion model that empowers versatile goal specification, seamless task switching, and dynamic composition of these agile behaviors. Leveraging classifier guidance, a diffusion-specific technique for test-time optimization toward novel objectives, our model extends its capability to solve downstream tasks never encountered during training, including motion inpainting, joystick teleoperation, and obstacle avoidance, and transfers these skills zero-shot to real hardware. This work opens new frontiers for humanoid robots by pushing the limits of scalable human-like motor skill acquisition from human motion and advancing seamless motion synthesis that achieves generalization and versatility beyond training setups.

Key facts. Cited by 165 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 51 of its 68 references that are in the map. First posted on arXiv 11 Aug 2025.

Builds on

51 of 68 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025Flow Matching Policy Gradients28 Jul
  2. 2025Diffuse-CLoC: Guided Diffusion for Physics-based Character Look-ahead Control14 Mar
  3. 2024CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control4 Oct
  4. 2024BiRoDiff: Diffusion policies for bipedal robot locomotion on unseen terrains7 Jul
  5. 2024PDP: Physics-Based Character Animation via Diffusion Policy3 Jun
  6. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusion7 Mar
  7. 2022Is Conditional Generative Modeling all you need for Decision-Making?28 Nov

Other references · 44

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  4. 2023T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Modelscited by 1,351
  5. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  6. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  7. 2022Human Motion Diffusion Modelcited by 1,080
  8. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,061
  9. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 512
  10. 2019Learning agile and dynamic motor skills for legged robotscited by 504
  11. 2022EDGE: Editable Dance Generation From Musiccited by 287
  12. 2020Learning Agile Robotic Locomotion Skills by Imitating Animalscited by 251
32 more
  1. 2021Robust Motion In-betweeningcited by 229
  2. 2023Guided Motion Diffusion for Controllable Human Motion Synthesiscited by 223
  3. 2023Perpetual Humanoid Control for Real-time Simulated Avatarscited by 218
  4. 2024OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learningcited by 189
  5. 2023Real-World Humanoid Locomotion with Reinforcement Learningcited by 187
  6. 2024HumanPlus: Humanoid Shadowing and Imitation from Humanscited by 185
  7. 2018DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skillscited by 163
  8. 2024Expressive Whole-Body Control for Humanoid Robotscited by 139
  9. 2022Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behaviorcited by 138
  10. 2025ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skillscited by 130
  11. 2023Universal Humanoid Motion Representations for Physics-Based Controlcited by 116
  12. 2024MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpaintingcited by 116
  13. 2025TWIST: Teleoperated Whole-Body Imitation Systemcited by 101
  14. 2024Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Controlcited by 99
  15. 2025GMT: General Motion Tracking for Humanoid Whole-Body Controlcited by 83
  16. 2024Flexible Motion In-betweening with Diffusion Modelscited by 71
  17. 2025KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skillscited by 52
  18. 2025TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenizationcited by 51
  19. 2024DiffuseLoco: Real-Time Legged Locomotion Control with Diffusion from Offline Datasetscited by 49
  20. 2018Feedback Control For Cassie With Deep Reinforcement Learningcited by 45
  21. 2025Attention-Based Map Encoding for Learning Generalized Legged Locomotioncited by 40
  22. 2025CLONE: Closed-Loop Whole-Body Humanoid Teleoperation for Long-Horizon Taskscited by 38
  23. 2025UniTracker: Learning Universal Whole-Body Motion Tracker for Humanoid Robotscited by 37
  24. 2025PARC: Physics-based Augmentation with Reinforcement Learning for Character Controllerscited by 28
  25. 2025HuB: Learning Extreme Humanoid Balancecited by 28
  26. 2025SkillMimic-V2: Learning Robust and Generalizable Interaction Skills from Sparse and Noisy Demonstrationscited by 25
  27. 2022Creating a Dynamic Quadrupedal Robotic Goalkeeper with Reinforcement Learningcited by 23
  28. 2019Feedback MPC for Torque-Controlled Legged Robotscited by 21
  29. 2025Design and Control of a Bipedal Robotic Charactercited by 18
  30. 2025A Unified and General Humanoid Whole-Body Controller for Versatile Locomotioncited by 11
  31. 2024GLIM: 3D Range-Inertial Localization and Mapping with GPU-Accelerated Scan Matching Factorscited by 8
  32. 2014Momentum Control with Hierarchical Inverse Dynamics on a Torque-Controlled Humanoidcited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 32; 2026: 133.

165 papers.

Sort:

By area:

  1. 2025SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Controlcited by 101
  2. 2025OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interactioncited by 71
  3. 2025TWIST2: Scalable, Portable, and Holistic Humanoid Data Collection Systemcited by 44
  4. 2025ResMimic: From General Motion Tracking to Humanoid Whole-body Loco-Manipulation via Residual Learningcited by 41
  5. 2025WholeBodyVLA: Towards Unified Latent VLA for Whole-Body Loco-Manipulation Controlcited by 36
  6. 2025SPIDER: Scalable Physics-Informed Dexterous Retargetingcited by 32
  7. 2026Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matchingcited by 19
  8. 2025PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction Systemcited by 18
  9. 2025CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functionscited by 17
  10. 2025Learning Sim-to-Real Humanoid Locomotion in 15 Minutescited by 16
  11. 2026Flow Policy Gradients for Robot Controlcited by 16
  12. 2025DreamControl: Human-Inspired Whole-Body Humanoid Control for Scene Interaction via Guided Diffusioncited by 15
38 more
  1. 2025Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfercited by 15
  2. 2025SoftMimic: Learning Compliant Whole-body Control from Examplescited by 14
  3. 2026HumanX: Toward Agile and Generalizable Humanoid Interaction Skills from Human Videoscited by 14
  4. 2026TextOp: Real-time Interactive Text-Driven Humanoid Robot Motion Generation and Controlcited by 14
  5. 2025KungfuBot2: Learning Versatile Motion Skills for Humanoid Whole-Body Controlcited by 13
  6. 2026Hiking in the Wild: A Scalable Perceptive Parkour Framework for Humanoidscited by 13
  7. 2026Humanoid Manipulation Interface: Humanoid Whole-Body Manipulation from Robot-Free Demonstrationscited by 12
  8. 2026ZEST: Zero-shot Embodied Skill Transfer for Athletic Robot Controlcited by 11
  9. 2025OXE-AugE: A Large-Scale Robot Augmentation of OXE for Scaling Cross-Embodiment Policy Learningcited by 10
  10. 2026FRoM-W1: Towards General Humanoid Whole-Body Control with Language Instructionscited by 10
  11. 2026HEX: Humanoid-Aligned Experts for Cross-Embodiment Whole-Body Manipulationcited by 10
  12. 2026MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulationcited by 10
  13. 2025Humanoid Goalkeeper: Learning from Position Conditioned Task-Motion Constraintscited by 9
  14. 2026ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulationcited by 9
  15. 2025Towards Adaptable Humanoid Control via Adaptive Motion Trackingcited by 8
  16. 2026ZeroWBC: Learning Natural Whole-Body Humanoid Interaction from Human Egocentric Datacited by 8
  17. 2025GentleHumanoid: Learning Upper-body Compliance for Contact-rich Human and Object Interactioncited by 7
  18. 2025SENTINEL: A Fully End-to-End Language-Action Model for Humanoid Whole Body Controlcited by 7
  19. 2025RoboMirror: Understand Before You Imitate for Video to Humanoid Locomotioncited by 7
  20. 2026ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generationcited by 7
  21. 2025From Generated Human Videos to Physically Plausible Robot Trajectoriescited by 6
  22. 2026Deep Whole-body Parkourcited by 6
  23. 2026MeshMimic: Geometry-Aware Humanoid Motion Learning through 3D Scene Reconstructioncited by 6
  24. 2026Learning Dexterous Manipulation Using Contact Wrench Guidance From Human Demonstrationcited by 6
  25. 2025CHIP: Adaptive Compliance for Humanoid Control through Hindsight Perturbationcited by 5
  26. 2025UniAct: Unified Motion Generation and Action Streaming for Humanoid Robotscited by 5
  27. 2026Heracles: Bridging Precise Tracking and Generative Synthesis for General Humanoid Controlcited by 5
  28. 2026FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Controlcited by 5
  29. 2026SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Controlcited by 5
  30. 2026Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Trackingcited by 5
  31. 2026OpenHLM: An Empirical Recipe for Whole-Body Humanoid Loco-Manipulationcited by 5
  32. 2025Chasing Stability: Humanoid Running via Control Lyapunov Function Guided Reinforcement Learningcited by 4
  33. 2025Robot Crash Course: Learning Soft and Stylized Fallingcited by 4
  34. 2025Coordinated Humanoid Manipulation with Choice Policiescited by 4
  35. 2026TTT-Parkour: Rapid Test-Time Training for Perceptive Robot Parkourcited by 4
  36. 2026HAIC: Humanoid Agile Object Interaction Control via Dynamics-Aware World Modelcited by 4
  37. 2026CLOT: Closed-Loop Global Motion Tracking for Whole-Body Humanoid Teleoperationcited by 4
  38. 2026AGILE: A Comprehensive Workflow for Humanoid Loco-Manipulation Learningcited by 4

50 most cited of 165 All 165 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026OmniXtreme: Breaking the Generality Barrier in High-Dynamic Humanoid Control
  2. 2026InterMimicGen: Scaling Humanoid Loco-Manipulation through Self-Evolving Motion Imitation
  3. 2025Think on your feet: Seamless Transition between Human-like Locomotion in Response to Changing Commands
  4. 2026DreamControl-v2: Simpler and Scalable Autonomous Humanoid Skills via Trainable Guided Diffusion Priors
  5. 2026CHOREO: Every Humanoid Skill as a Trajectory
  6. 2026MotionDisco: Motion Discovery for Extreme Humanoid Loco-Manipulation
  7. 2026Being-M0.7: A Latent World-Action Model for Humanoid Robots
  8. 2026PASSAGE: Scaling Scene-Aligned Motion Learning for Perceptive Humanoid Traversal in Cluttered Environments ↗