{"ID":3004627,"CreatedAt":"2026-06-03T03:09:48.883664427Z","UpdatedAt":"2026-06-07T03:54:17.966829144Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.03985","arxiv_id":"2606.03985","title":"Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking","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.","short_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 maj...","url_abs":"https://arxiv.org/abs/2606.03985","url_pdf":"https://arxiv.org/pdf/2606.03985v1","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\"]","published":"2026-06-02T17:59:05Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\",\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false}