Optimizes diffusion models via Direct Preference Optimization (DPO) to generate human motion that is inherently executable by real humanoid robots.
March 16, 2026
Original Paper
PhysMoDPO: Physically-Plausible Humanoid Motion with Preference Optimization
arXiv · 2603.13228
The Takeaway
It closes the gap between 'pretty' generated animations and physically valid robotics, enabling zero-shot motion transfer to hardware like the G1 humanoid without post-hoc correction distortion.
From the abstract
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 a