AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Humanoid Generative Pre-Training for Zero-Shot Motion Tracking

Zekun Qi, Xuchuan Chen, Jilong Wang, Chenghuai Lin, Yunrui Lian, Wenyao Zhang, Xinqiang Yu, He Wang, Li Yi

CVPR 2026 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Transductive and semantic-dictionary zero-shot

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
replace 3-layer MLP backbone with causal Transformer (small) (ablation)Humanoid-GPT tracker · AMASS-test (MuJoCo sim)MPKPE: 100.49 -> 62.65Improved
replace 8-layer TCN with small causal Transformer (ablation)Humanoid-GPT tracker · AMASS-test (MuJoCo sim)SR: 81.48 -> 83.26Improved
scale training tokens from 2M to 20M (small model) (ablation)Humanoid-GPT-S · AMASS-test (MuJoCo sim)SR: 83.26 -> 86.02Improved
scale training tokens from 200M to 2B (base model) (ablation)Humanoid-GPT-B · AMASS-test (MuJoCo sim)SR: 88.27 -> 90.43Improved
scale model from 22.1M to 80.4M params at 2B tokens (ablation)Humanoid-GPT · AMASS-test (MuJoCo sim)SR: 90.43 -> 92.58Improved
scale model from 22.1M to 80.4M params at 2B tokens (ablation)Humanoid-GPT · AMASS-test (MuJoCo sim)RootVelErr: 0.1756 -> 0.1785Hurt
scale data and model capacity together (ablation)Humanoid-GPT · AMASS-test (MuJoCo sim)MPKPE: 62.65 -> 40.99Improved
use larger Transformer (B vs S) on real G1 dances (ablation)Humanoid-GPT · Real G1 dances (4 clips)MPJPE: 0.1024 -> 0.0974 (Can Do Can Go); 0.1180 -> 0.1075 (Gokuraku); 0.0825 -> 0.0858 (HuoYuanJia)Mixed
curated 2B-frame corpus vs AMASS for motion diversitytraining data · HME embedding spacelog-volume: approximately 4-5 increase in log-volume compared with AMASSImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy