Physics-native world foundation model generating 3D scenes, characters and motion in a shared world
JST-2 (Joint Space-and-Time, gen 2) is Viggle's physics-native world foundation model, introduced on October 19, 2026. Rather than learning only in pixel space, it learns 3D structure directly, bringing scenes, characters and motion into a shared 3D world that users can enter, explore and expand in seconds. It powers Viggle's creator products and is available to try and build with through the Viggle API.
For people
For agents
Nothing listed yet.