研究人员开发了 Humanoid-GPT，这是一种新颖的 Transformer 模型，专为零样本运动跟踪和全身控制而设计。该模型在包含二十亿帧运动数据的海量语料库上进行训练，整合了各种运动捕捉数据集和内部录制数据。通过扩展数据和模型容量，Humanoid-GPT 在应对未见过的运动和控制任务方面展现出前所未有的泛化能力，为该领域树立了新的性能标准。 AI
影响 为零样本运动跟踪和全身控制确立了新的性能前沿。
排序理由 该集群描述了一篇关于用于运动跟踪的新型 AI 模型的最新研究论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2606.03985v1 Announce Type: cross 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 t…
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-fram…
Humanoid-GPT is a GPT-style Transformer with causal attention trained on a billion-scale motion corpus that achieves zero-shot generalization to unseen motions and control tasks through scalable pre-training on diverse motion data.