World Labs launches Atlas: an omni world model natively spanning text, images, video and 3D

YunzhuLiYZ · x · 2026-09-16

Fei-Fei Li's World Labs introduced Atlas, a next-generation omni world model pretrained from scratch to natively operate on text, images, video, and 3D. It's a multimodal autoregressive diffusion transformer that combines all inputs into a shared spatial context and stays 3D-consistent while imagining beyond what it sees, with performance scaling with compute.

Key capabilities:

Atlas will power future versions of Marble. World Labs is also hiring in robot learning (Yunzhu Li, Fei-Fei Li) around Atlas for Robotics and Real-to-Sim-to-Real.

Related event: Fei-Fei Li's World Labs Raises $1.2B and Launches Atlas World Model(2 posts)→

Original post →

More from Embodied

Embodied channel →