Stanford Robotics Seminar ENGR319 | Winter 2026 | ๐šฟ0: An Open Foundation Model

Stanford Online ยท 64:09

Rui Wang presents Sai Zero, an open vision-language-action (VLA) foundation model for unified humanoid loco-manipulation: pre-train on egocentric human video (not generic internet video), post-train an action expert o...

Read the full summary on tuber

Redirecting...