Termsslug: human-video-pretraining

Human Video Pretraining

人类视频预训练

Training on action-label-free egocentric human video to learn manipulation priors.

Curated Intelligence

1 items · Page 1/1
Rohan Paul (@rohanpaul_ai)T2·Models
78 pts
Nvidia Releases GR00T 2 World-Action Model Trained on 400K Hours of Human Video

Nvidia has released GR00T 2, an open world-action model that drives robotic arms, dexterous hands and humanoids. Its key advance is pretraining on 402,730 hours of human head-camera video plus 10,184 hours of handheld-gripper demos, requiring only 23,500 hours of teleoperated robot data and sharply reducing reliance on costly real-robot demonstrations.