The a16z Show · Sunday, September 13, 2026
World Labs has announced Atlas, described as the world's first multimodal world model capable of generating image and video frames with pixel-perfect camera control and reconstructing them in 3D. Justin Johnson, co-founder of World Labs, explained that Atlas can generate new worlds from text or image prompts, reconstruct existing spaces from a few photos, and simulate robot behavior in virtual environments.
“And our thesis is that there exists another category of model, called world models, that should be based in visual understanding, should be based in physical understanding, that can be used to generate, simulate, reconstruct worlds.”
“And just today, they announced Atlas, the world's first multimodal world model that generates image and video frames with pixel-perfect camera control and reconstructs them in 3D.”
“Um, at its heart, it's a world model. Um, it does basically three different kinds of things: generation, reconstruction, and simulation.”