Sign up to save your podcasts
Or
Share Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking
Share to email
Share to Facebook
Share to X
Share to email
Share to Facebook
Share to X
Or
Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking
🤗 Upvotes: 33 | cs.RO, cs.AI, cs.CV
Authors:
Zekun Qi, Xuchuan Chen, Dairu Liu, Chenghuai Lin, Yunrui Lian, Sikai Liang, Zhikai Zhang, Yu Guan, Jilong Wang, Wenyao Zhang, Xinqiang Yu, He Wang, Li Yi
Title:
Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking
Arxiv:
http://arxiv.org/abs/2606.03985v1
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.
View all episodes
By Jingwen Liang, Gengyu Wang🤗 Upvotes: 33 | cs.RO, cs.AI, cs.CV
Authors:
Zekun Qi, Xuchuan Chen, Dairu Liu, Chenghuai Lin, Yunrui Lian, Sikai Liang, Zhikai Zhang, Yu Guan, Jilong Wang, Wenyao Zhang, Xinqiang Yu, He Wang, Li Yi
Title:
Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking
Arxiv:
http://arxiv.org/abs/2606.03985v1
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.