Viggle releases JST-2, a 3D physics-native world model
According to ViggleAI via X, the company released JST-2, a full-stack physics-native world foundation model that builds in 3D rather than pixels and generates expandable 3D scenes and motion-ready characters in seconds.
SourceAnalysis
ViggleAI announced the release of JST-2, described as the world's first full-stack physics-native world foundation model, with the development focused on building the entire architecture in 3D rather than pixel or video space.
According to ViggleAI, the model enables generation of 3D scenes in seconds with real-time expansion, along with creation of characters that include built-in motion through a single general architecture. This approach returns to first principles for world modeling as highlighted in commentary from industry observers such as Huang Song.
Huang Song
@huang_song_Founder & CEO of typeless