PulseAugur
EN
LIVE 15:12:07

Humanoid-GPT achieves zero-shot motion tracking with massive dataset

By PulseAugur Editorial · [3 sources] ·

Researchers have developed Humanoid-GPT, a new Transformer model designed for zero-shot motion tracking and whole-body control. This model is trained on a massive corpus of two billion frames of motion data, unifying various motion capture datasets and in-house recordings. By scaling both data and model capacity, Humanoid-GPT demonstrates unprecedented generalization capabilities to unseen motions and control tasks, setting a new performance standard in the field. AI

IMPACT Establishes a new performance frontier for zero-shot motion tracking and whole-body control.

RANK_REASON The cluster describes a new research paper detailing a novel AI model for motion tracking.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 3 sources. How we write summaries →

COVERAGE [3]

  1. arXiv cs.AI TIER_1 English(EN) · 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 ·

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

    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…

  2. arXiv cs.AI TIER_1 English(EN) · Li Yi ·

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

    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…

  3. Hugging Face Daily Papers TIER_1 English(EN) ·

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

    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.

RELATED ENTITIES

RELATED TOPICS