# MaskAdapt: Learning Flexible Motion Adaptation via Mask-Invariant Prior for Physics-Based Characters

arXiv: https://arxiv.org/abs/2603.29272 · HTML: https://mlsanity.com/paper/2603.29272/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 34 references that are in the map.
- First posted on arXiv 31 Mar 2026.

## Builds on (most cited first, 29 of 29)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [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)
- [Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learning](https://mlsanity.com/paper/2108.10470/) (2021)
- [Executing your Commands via Motion Diffusion in Latent Space](https://mlsanity.com/paper/2212.04048/) (2022)
- [BABEL: Bodies, Action and Behavior with English Labels](https://mlsanity.com/paper/2106.09696/) (2021)
- [Perpetual Humanoid Control for Real-time Simulated Avatars](https://mlsanity.com/paper/2305.06456/) (2023)
- [FLAME: Free-form Language-based Motion Synthesis & Editing](https://mlsanity.com/paper/2209.00349/) (2022)
- [MMM: Generative Masked Motion Model](https://mlsanity.com/paper/2312.03596/) (2023)
- [MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting](https://mlsanity.com/paper/2409.14393/) (2024)
- [CLoSD: Closing the Loop between Simulation and Diffusion for multi-task character control](https://mlsanity.com/paper/2410.03441/) (2024)
- [CALM: Conditional Adversarial Latent Models for Directable Virtual Characters](https://mlsanity.com/paper/2305.02195/) (2023)
- [HOVER: Versatile Neural Whole-Body Controller for Humanoid Robots](https://mlsanity.com/paper/2410.21229/) (2024)
- [Learning values across many orders of magnitude](https://mlsanity.com/paper/1602.07714/) (2016)
- [DartControl: A Diffusion-Based Autoregressive Motion Model for Real-Time Text-Driven Motion Control](https://mlsanity.com/paper/2410.05260/) (2024)
- [SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generation](https://mlsanity.com/paper/2304.10417/) (2023)
- [MotionFix: Text-Driven 3D Human Motion Editing](https://mlsanity.com/paper/2408.00712/) (2024)
- [TokenHSI: Unified Synthesis of Physical Human-Scene Interactions through Task Tokenization](https://mlsanity.com/paper/2503.19901/) (2025)
- [PMP: Learning to Physically Interact with Environments using Part-wise Motion Priors](https://mlsanity.com/paper/2305.03249/) (2023)
- [Neural Categorical Priors for Physics-Based Character Control](https://mlsanity.com/paper/2308.07200/) (2023)
- [Composite Motion Learning with Task Control](https://mlsanity.com/paper/2305.03286/) (2023)
- [SimMotionEdit: Text-Based Human Motion Editing with Motion Similarity Prediction](https://mlsanity.com/paper/2503.18211/) (2025)
- [AdaptNet: Policy Adaptation for Physics-Based Character Control](https://mlsanity.com/paper/2310.00239/) (2023)
- [Dynamic Motion Blending for Versatile Motion Editing](https://mlsanity.com/paper/2503.20724/) (2025)
- [Synchronize Dual Hands for Physics-Based Dexterous Guitar Playing](https://mlsanity.com/paper/2409.16629/) (2024)

## Abstract (arXiv)

We present MaskAdapt, a framework for flexible motion adaptation in physics-based humanoid control. The framework follows a two-stage residual learning paradigm. In the first stage, we train a mask-invariant base policy using stochastic body-part masking and a regularization term that enforces consistent action distributions across masking conditions. This yields a robust motion prior that remains stable under missing observations, anticipating later adaptation in those regions. In the second stage, a residual policy is trained atop the frozen base controller to modify only the targeted body parts while preserving the original behaviors elsewhere. We demonstrate the versatility of this design through two applications: (i) motion composition, where varying masks enable multi-part adaptation within a single sequence, and (ii) text-driven partial goal tracking, where designated body parts follow kinematic targets provided by a pre-trained text-conditioned autoregressive motion generator. Through experiments, MaskAdapt demonstrates strong robustness and adaptability, producing diverse behaviors under masked observations and delivering superior targeted motion adaptation compared to prior work.