mlsanityData to 14 Oct 2026

NaP-Control: Navigating Diffusion Prior for Versatile and Fast Character Control

arXiv 2605.20209 ↗First posted 15 Apr 2026cs.GR cs.LG cs.ROcited by 0

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

Abstract (arXiv)

Achieving precise, versatile whole-body character control in physics-based animation remains challenging. Recent diffusion-based policies generate rich and expressive motions but typically rely on gradient-based test-time guidance to satisfy task objectives, which is slow and can reduce robustness. We introduce NaP-Control (Navigating Diffusion Prior for Versatile and Fast Character Control), abbreviated as NaP. Our method uses reinforcement learning to manipulate the latent noise of a task-agnostic diffusion policy prior, steering it toward task-specific behaviors for fast, robust control with high motion fidelity. In contrast to methods that rely solely on offline training, NaP interacts with the environment during training to correct motions and optimize task rewards, improving success rates and enabling adaptation to challenging scenarios. By directly predicting task-optimized diffusion noise, NaP eliminates iterative guidance during denoising and enables efficient inference. Experiments show that NaP attains higher success rates and faster inference while preserving natural motion across diverse tasks.

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 55 of its 63 references that are in the map. First posted on arXiv 15 Apr 2026.

Builds on

55 of 63 references.

Closest ancestors · 10

Same direction, newest first

  1. 2025BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion11 Aug
  2. 2025Steering Your Diffusion Policy with Latent Space Reinforcement Learning18 Jun
  3. 2025Diffuse-CLoC: Guided Diffusion for Physics-based Character Look-ahead Control14 Mar
  4. 2024CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control4 Oct
  5. 2024Diffusion Policy Policy Optimization1 Sep
  6. 2024PDP: Physics-Based Character Animation via Diffusion Policy3 Jun
  7. 2024Large-scale Reinforcement Learning for Diffusion Models20 Jan
  8. 2023DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models25 May
  9. 2023Training Diffusion Models with Reinforcement Learning22 May
  10. 2023IDQL: Implicit Q-Learning as an Actor-Critic Method with Diffusion Policies20 Apr

Other references · 45

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2020Denoising Diffusion Implicit Modelscited by 9,781
  3. 2017Deep reinforcement learning from human preferencescited by 3,912
  4. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,720
  5. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  6. 2019AMASS: Archive of Motion Capture as Surface Shapescited by 1,236
  7. 2022Human Motion Diffusion Modelcited by 1,080
  8. 2022MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Modelcited by 780
  9. 2022PhysDiff: Physics-Guided Human Motion Diffusion Modelcited by 368
  10. 2023OmniControl: Control Any Joint at Any Time for Human Motion Generationcited by 238
  11. 2023Guided Motion Diffusion for Controllable Human Motion Synthesiscited by 223
  12. 2023Perpetual Humanoid Control for Real-time Simulated Avatarscited by 218
33 more
  1. 2024MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Modelcited by 168
  2. 2023Chain of Hindsight Aligns Language Models with Feedbackcited by 148
  3. 2021URLB: Unsupervised Reinforcement Learning Benchmarkcited by 139
  4. 2023MMM: Generative Masked Motion Modelcited by 131
  5. 2024InitNO: Boosting Text-to-Image Diffusion Models via Initial Noise Optimizationcited by 123
  6. 2024ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimizationcited by 119
  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. 2021Learning One Representation to Optimize All Rewardscited by 115
  10. 2023Optimizing Diffusion Noise Can Serve As Universal Motion Priorscited by 98
  11. 2023CALM: Conditional Adversarial Latent Models for Directable Virtual Characterscited by 94
  12. 2023Unified Human-Scene Interaction via Prompted Chain-of-Contactscited by 94
  13. 2023TLControl: Trajectory and Language Control for Human Motion Synthesiscited by 94
  14. 2018GPU-Accelerated Robotic Simulation for Distributed Reinforcement Learningcited by 90
  15. 2025MotionStreamer: Streaming Motion Generation via Diffusion-based Autoregressive Model in Causal Latent Spacecited by 86
  16. 2024DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Controlcited by 84
  17. 2023Optimizing DDPM Sampling with Shortcut Fine-Tuningcited by 81
  18. 2024CoMo: Controllable Motion Generation through Language Guided Pose Code Editingcited by 67
  19. 2023MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representationscited by 60
  20. 2023Interactive Character Control with Auto-Regressive Motion Diffusion Modelscited by 55
  21. 2025TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenizationcited by 51
  22. 2025GENMO: A GENeralist Model for Human MOtioncited by 49
  23. 2025AnyTop: Character Animation Diffusion with Any Topologycited by 41
  24. 2024MaskControl: Spatio-Temporal Control for Masked Motion Synthesiscited by 38
  25. 2023Composite Motion Learning with Task Controlcited by 28
  26. 2025SimMotionEdit: Text-Based Human Motion Editing with Motion Similarity Predictioncited by 27
  27. 2025UniPhys: Unified Planner and Controller with Diffusion for Flexible Physics-Based Character Controlcited by 25
  28. 2024PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarioscited by 24
  29. 2025Fg-T2M++: LLMs-Augmented Fine-Grained Text Driven Human Motion Generationcited by 21
  30. 2024UniMuMo: Unified Text, Music and Motion Generationcited by 19
  31. 2023AdaptNet: Policy Adaptation for Physics-Based Character Controlcited by 16
  32. 2025SENTINEL: A Fully End-to-End Language-Action Model for Humanoid Whole Body Controlcited by 7
  33. 2025UniMoGen: Universal Motion Generationcited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Taming Diffusion Probabilistic Models for Character Control
  2. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
  3. 2025Pixel Motion Diffusion is What We Need for Robot Control
  4. 2025Scalable Motion In-betweening via Diffusion and Physics-Based Character Adaptation
  5. 2025D3P: Dynamic Denoising Diffusion Policy via Reinforcement Learning
  6. 2025Responsive Noise-Relaying Diffusion Policy: Responsive and Efficient Visuomotor Control
  7. 2026Immiscible Diffusion Policy: Preserving Multimodal Robot Actions through Label-Free Noise Assignment
  8. 2026STEP: Warm-Started Visuomotor Policies with Spatiotemporal Consistency Prediction