World Labs just unveiled Atlas, a multimodal world model built for spatial intelligence. It combines text, video, and 3D data into a shared spatial context to generate up to 1-minute 1440p clips with pixel-perfect camera control, while reconstructing spaces into 3D Gaussian splats from just a few photos.
Fei-Fei Li’s spatial AI startup World Labs just raised a massive $1B round, powered by a $200M strategic investment from design software titan Autodesk. The deal connects World Labs' generative 3D world models with Autodesk’s creative pipelines, initially targeting gaming and film production. Why it matters: Moving generative AI from flat 2D visuals into physics-aware 3D environments marks the industry's next big leap.
Fei-Fei Li, Yann LeCun, and DeepMind are all heavily betting on "world models," but they basically mean three completely different architectures. World Labs' Marble delivers interactive 3D Gaussian splats, LeCun's JEPA builds an internal predictive latent brain, and DeepMind's Genie 3 and SIMA 2 generate real-time video simulators. Why it matters: The industry is packaging front-end assets, robot gymnasiums, and core machine cognition under a single marketing buzzword.
World Labs just launched Marble, its first commercial world model that turns text prompts, photos, and videos into persistent, downloadable 3D environments. Unlike on-the-fly streaming demos, it exports clean Gaussian splats, meshes, and video assets while letting creators block out spatial layouts directly. Why it matters: It gives game developers and VFX artists real creative control instead of unpredictable hallucinations.
