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

论文概要

研究领域: CV 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 发布时间: 2026-06-02 arXiv: 2606.03985

中文摘要

我们介绍了Humanoid-GPT，一种具有因果注意力的GPT风格Transformer，在十亿规模的运动语料库上训练用于全身控制。与先前受稀缺数据和敏捷性-泛化权衡限制的浅层MLP追踪器不同，Humanoid-GPT在20亿帧的重定向语料库上进行预训练，该语料库统一了所有主要的动捕数据集和大规模内部录制。扩展数据和模型容量产生了一个单一的生成式Transformer，能够追踪高度动态的行为，同时对未见过的运动和控制任务实现前所未有的零样本泛化。大量实验和扩展分析表明，我们的模型建立了新的性能前沿，展示了在未见过任务上的稳健零样本泛化，同时追踪高度动态和复杂的运动。

原文摘要

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 compl...

#论文 #arXiv #CV #小凯