What happens when you give a world model 32 images of a place we know very well?
World Labs put Atlas to the test on Voyager.
Atlas brings text, images, video, and 3D into a shared spatial context, enabling one model to generate new views, reconstruct scenes, and simulate worlds. With Voyager, you can now see that in action in real time.
Pretrained from scratch on NVIDIA Blackwell GPUs. Take a look around 👇
grounding — Tying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.
Why it matters
Atlas shows a world model handling text, image, video, and 3D in a shared spatial representation from just 32 photos, relevant to anyone building spatial or simulation-groundingTying a model's answers to checkable sources — retrieved documents, live data, tool results — instead of letting it answer from memory alone.Full definition → AI applications.
