Humanoid-GPT：擴展數據與結構以實現零樣本動作追蹤

Humanoid-GPT: Scaling Data and Structure for Zero-Shot Motion Tracking

June 2, 2026

作者: 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

cs.AI

摘要

我們提出 Humanoid-GPT，這是一個採用因果注意力的 GPT 風格 Transformer，在十億級動作語料庫上進行訓練，用於全身控制。不同於先前受限於數據稀缺及敏捷性-泛化權衡的淺層 MLP 追蹤器，Humanoid-GPT 在一個包含 20 億幀的重定向語料庫上進行預訓練，該語料庫統一了所有主要動作捕捉數據集與大規模內部錄製數據。透過擴展數據與模型容量，我們獲得了一個單一的生成式 Transformer，既能追蹤高度動態的行為，又能對未見過的動作與控制任務展現前所未有的零樣本泛化能力。廣泛的實驗與規模分析表明，我們的模型樹立了新的性能標竿，在追蹤高度動態且複雜動作的同時，展現出對未見過任務的強健零樣本泛化能力。

English

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.