# PhysMoDPO: Physically-Plausible Humanoid Motion with Preference Optimization

arXiv: https://arxiv.org/abs/2603.13228 · HTML: https://mlsanity.com/paper/2603.13228/

## Key facts

- Cited by 2 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 53 of its 58 references that are in the map.
- First posted on arXiv 13 Mar 2026.

## Placed in

- Diffusion models / [Diffusion and flow policies for robotics](https://mlsanity.com/diffusion/diffusion-and-flow-policies-for-robotics/)
- LLM alignment / RLHF / preference optimisation / [Diffusion and multimodal model alignment](https://mlsanity.com/alignment/diffusion-and-multimodal-model-alignment/)

## Builds on (most cited first, 30 of 53)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [Diffusion Model Alignment Using Direct Preference Optimization](https://mlsanity.com/paper/2311.12908/) (2023)
- [T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations](https://mlsanity.com/paper/2301.06052/) (2023)
- [Action-Conditioned 3D Human Motion Synthesis with Transformer VAE](https://mlsanity.com/paper/2104.05670/) (2021)
- [TEMOS: Generating diverse human motions from textual descriptions](https://mlsanity.com/paper/2204.14109/) (2022)
- [MoMask: Generative Masked Modeling of 3D Human Motions](https://mlsanity.com/paper/2312.00063/) (2023)
- [PhysDiff: Physics-Guided Human Motion Diffusion Model](https://mlsanity.com/paper/2212.02500/) (2022)
- [EDGE: Editable Dance Generation From Music](https://mlsanity.com/paper/2211.10658/) (2022)
- [BABEL: Bodies, Action and Behavior with English Labels](https://mlsanity.com/paper/2106.09696/) (2021)
- [OmniControl: Control Any Joint at Any Time for Human Motion Generation](https://mlsanity.com/paper/2310.08580/) (2023)
- [Guided Motion Diffusion for Controllable Human Motion Synthesis](https://mlsanity.com/paper/2305.12577/) (2023)
- [Perpetual Humanoid Control for Real-time Simulated Avatars](https://mlsanity.com/paper/2305.06456/) (2023)
- [Object Motion Guided Human Motion Synthesis](https://mlsanity.com/paper/2309.16237/) (2023)
- [TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis](https://mlsanity.com/paper/2305.00976/) (2023)
- [OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning](https://mlsanity.com/paper/2406.08858/) (2024)
- [TEACH: Temporal Action Composition for 3D Humans](https://mlsanity.com/paper/2209.04066/) (2022)
- [MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model](https://mlsanity.com/paper/2404.19759/) (2024)
- [BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusion](https://mlsanity.com/paper/2508.08241/) (2025)
- [HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes](https://mlsanity.com/paper/2210.09729/) (2022)
- [Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation](https://mlsanity.com/paper/2403.04436/) (2024)
- [ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills](https://mlsanity.com/paper/2502.01143/) (2025)
- [Taming Diffusion Models for Audio-Driven Co-Speech Gesture Generation](https://mlsanity.com/paper/2303.09119/) (2023)
- [Universal Humanoid Motion Representations for Physics-Based Control](https://mlsanity.com/paper/2310.04582/) (2023)
- [MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting](https://mlsanity.com/paper/2409.14393/) (2024)
- [DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformer](https://mlsanity.com/paper/2103.10206/) (2021)
- [Audio2Gestures: Generating Diverse Gestures from Speech Audio with Conditional Variational Autoencoders](https://mlsanity.com/paper/2108.06720/) (2021)

## Built on by (most cited first, 2 of 2)

- [FlowHMR: Physically Plausible Motion Capture from Video](https://mlsanity.com/paper/2610.03691/) (2026)
- [From Digital Human Interactions to Physics-Based Humanoid Skills: Physics-Grounded Post-Training of Interaction Generators](https://mlsanity.com/paper/2610.10322/) (2026)

## Abstract (arXiv)

Recent progress in text-conditioned human motion generation has been largely driven by diffusion models trained on large-scale human motion data. Building on this progress, recent methods attempt to transfer such models for character animation and real robot control by applying a Whole-Body Controller (WBC) that converts diffusion-generated motions into executable trajectories. While WBC trajectories become compliant with physics, they may expose substantial deviations from original motion. To address this issue, we here propose PhysMoDPO, a Direct Preference Optimization framework. Unlike prior work that relies on hand-crafted physics-aware heuristics such as foot-sliding penalties, we integrate WBC into our training pipeline and optimize diffusion model such that the output of WBC becomes compliant both with physics and original text instructions. To train PhysMoDPO we deploy physics-based and task-specific rewards and use them to assign preference to synthesized trajectories. Our extensive experiments on text-to-motion and spatial control tasks demonstrate consistent improvements of PhysMoDPO in both physical realism and task-related metrics on simulated robots. Moreover, we demonstrate that PhysMoDPO results in significant improvements when applied to zero-shot motion transfer in simulation and for real-world deployment on a G1 humanoid robot.