AI RESEARCH
PhysMoDPO: Physically-Plausible Humanoid Motion with Preference Optimization
arXiv CS.AI
•
ArXi:2603.13228v1 Announce Type: cross 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.