Humanoid Generative Pre-Training for Zero-Shot Motion Tracking
Zekun Qi, Xuchuan Chen, Jilong Wang, Chenghuai Lin, Yunrui Lian, Wenyao Zhang, Xinqiang Yu, He Wang
Abstract
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.
BibTeX
@inproceedings{cvpr2026_humanoidgenerati,
title = {Humanoid Generative Pre-Training for Zero-Shot Motion Tracking},
author = {Zekun Qi and Xuchuan Chen and Jilong Wang and Chenghuai Lin and Yunrui Lian and Wenyao Zhang and Xinqiang Yu and He Wang and Li Yi},
booktitle = {CVPR 2026},
year = {2026}
}