# SMP: Reusable Score-Matching Motion Priors for Physics-Based Character Control

arXiv: https://arxiv.org/abs/2512.03028 · HTML: https://mlsanity.com/paper/2512.03028/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Placed in Imitation learning methods, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 44 of its 88 references that are in the map.
- First posted on arXiv 2 Dec 2025.

## Placed in

- Offline RL and imitation learning from data / [Imitation learning methods](https://mlsanity.com/offlinerl/imitation-learning-methods/)

## Builds on (most cited first, 30 of 44)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Denoising Diffusion Implicit Models](https://mlsanity.com/paper/2010.02502/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [DreamFusion: Text-to-3D using 2D Diffusion](https://mlsanity.com/paper/2209.14988/) (2022)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [High-Dimensional Continuous Control Using Generalized Advantage Estimation](https://mlsanity.com/paper/1506.02438/) (2015)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Magic3D: High-Resolution Text-to-3D Content Creation](https://mlsanity.com/paper/2211.10440/) (2022)
- [ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation](https://mlsanity.com/paper/2305.16213/) (2023)
- [On the Continuity of Rotation Representations in Neural Networks](https://mlsanity.com/paper/1812.07035/) (2018)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [One-step Diffusion with Distribution Matching Distillation](https://mlsanity.com/paper/2311.18828/) (2023)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [MotionDiffuse: Text-Driven Human Motion Generation with Diffusion Model](https://mlsanity.com/paper/2208.15001/) (2022)
- [Sim-to-Real Transfer of Robotic Control with Dynamics Randomization](https://mlsanity.com/paper/1710.06537/) (2017)
- [Action2Motion: Conditioned Generation of 3D Human Motions](https://mlsanity.com/paper/2007.15240/) (2020)
- [Analyzing and Improving the Training Dynamics of Diffusion Models](https://mlsanity.com/paper/2312.02696/) (2023)
- [HuMoR: 3D Human Motion Model for Robust Pose Estimation](https://mlsanity.com/paper/2105.04668/) (2021)
- [LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching](https://mlsanity.com/paper/2311.11284/) (2023)
- [Asymmetric Actor Critic for Image-Based Robot Learning](https://mlsanity.com/paper/1710.06542/) (2017)
- [Robust Motion In-betweening](https://mlsanity.com/paper/2102.04942/) (2021)
- [Character Controllers Using Motion VAEs](https://mlsanity.com/paper/2103.14274/) (2021)
- [CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control](https://mlsanity.com/paper/2410.03441/) (2024)
- [Real-Time Style Modelling of Human Locomotion via Feature-Wise Transformations and Local Motion Phases](https://mlsanity.com/paper/2201.04439/) (2022)
- [MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations](https://mlsanity.com/paper/2310.10198/) (2023)
- [Interactive Character Control with Auto-Regressive Motion Diffusion Models](https://mlsanity.com/paper/2306.00416/) (2023)
- [TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization](https://mlsanity.com/paper/2503.19901/) (2025)

## Built on by (most cited first, 15 of 15)

- [SCRIPT: Scalable Diffusion Policy with Multi-stage Training for Language-driven Physics-Based Humanoid Control](https://mlsanity.com/paper/2605.22894/) (2026)
- [PAC-MAN: Perception-Aware CBF-RL for Whole-Body Safety in Humanoid Dodgeball](https://mlsanity.com/paper/2607.28623/) (2026)
- [PDF-HR: Pose Distance Fields for Humanoid Robots](https://mlsanity.com/paper/2602.04851/) (2026)
- [ExpertGen: Scalable Sim-to-Real Expert Policy Learning from Imperfect Behavior Priors](https://mlsanity.com/paper/2603.15956/) (2026)
- [MotionRFT: Unified Reinforcement Fine-Tuning for Text-to-Motion Generation](https://mlsanity.com/paper/2603.27185/) (2026)
- [MIND: Multi-Scale Intent Diffusion for Text-Driven Physics-Based Humanoid Control](https://mlsanity.com/paper/2605.26006/) (2026)
- [Sketch2Motion: Text-driven 2D Sketch to 3D Animation via Diffusion-guided Skeleton Optimization](https://mlsanity.com/paper/2605.28394/) (2026)
- [PFM-HR: Pose Flow Matching for Humanoid Robots](https://mlsanity.com/paper/2608.03227/) (2026)
- [Progressively Learning Heterogeneous Skills in a Unified Latent Space](https://mlsanity.com/paper/2608.23258/) (2026)
- [Flow-Matched Motion Priors: Online Optimal-Transport Rewards for Imitation Learning](https://mlsanity.com/paper/2609.15631/) (2026)
- [DSD: Learning Diverse and Reusable Motor Skills via Diffusion Skill Discovery](https://mlsanity.com/paper/2609.17682/) (2026)
- [LYRIC: Language-Driven Physics-Based Character Control for Contact-Rich Whole-Body Object Interaction](https://mlsanity.com/paper/2609.19688/) (2026)
- [OmniMimic: Dynamics-completed Motion Augmentation for Multi-style Omnidirectional Quadruped Locomotion](https://mlsanity.com/paper/2609.20566/) (2026)
- [World Motion Models: Flexible Sequence Modeling of SE(3) Trajectories](https://mlsanity.com/paper/2610.01742/) (2026)
- [Scalable Multi-Human Cooperative Manipulation via Commander-Executor Coordination](https://mlsanity.com/paper/2610.14911/) (2026)

## Abstract (arXiv)

Data-driven motion priors that can guide agents toward producing naturalistic behaviors play a pivotal role in creating life-like virtual characters. Adversarial imitation learning has been a highly effective method for learning motion priors from reference motion data. However, adversarial priors, with few exceptions, need to be retrained for each new controller, thereby limiting their reusability and necessitating the retention of the reference motion data when applied to downstream tasks. In this work, we present Score-Matching Motion Priors (SMP), which leverages pre-trained motion diffusion models and score distillation sampling (SDS) to create reusable task-agnostic motion priors. SMPs can be pre-trained on a motion dataset, independent of any control policy or task. Once trained, SMPs can be kept frozen and reused as general-purpose reward functions to train new policies to produce naturalistic behaviors for downstream tasks. We show that a general motion prior trained on large-scale datasets can be repurposed into a variety of style-specific priors. Furthermore, SMP can compose different styles to synthesize new styles not present in the original dataset. Our method can create reusable and modular motion priors that produce high-quality motions comparable to state-of-the-art adversarial imitation learning methods. In our experiments, we demonstrate the effectiveness of SMP across a diverse suite of control tasks with physically simulated humanoid characters. Video available at https://youtu.be/jBA2tWk6vzU