Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking
This work addresses the agility-generalization trade-off in humanoid motion tracking by scaling data and model capacity, enabling robust zero-shot performance for robotics and animation applications.
Humanoid-GPT introduces a GPT-style Transformer pre-trained on a 2B-frame motion corpus for whole-body control, achieving zero-shot generalization to unseen motions and tasks, outperforming prior methods in tracking dynamic behaviors.
We introduce Humanoid-GPT, a GPT-style Transformer with causal attention trained on a billion-scale motion corpus for whole-body control. Unlike prior shallow MLP trackers constrained by scarce data and an agility-generalization trade-off, Humanoid-GPT is pre-trained on a 2B-frame retargeted corpus that unifies all major mocap datasets with large-scale in-house recordings. Scaling both data and model capacity yields a single generative Transformer that tracks highly dynamic behaviors while achieving unprecedented zero-shot generalization to unseen motions and control tasks. Extensive experiments and scaling analyses show that our model establishes a new performance frontier, demonstrating robust zero-shot generalization to unseen tasks while simultaneously tracking highly dynamic and complex motions.