Odyssey · World Model

Odyssey-3

Announced 15 September as Odyssey's most capable foundation world model, an autoregressive diffusion transformer trained on a large corpus of visual observations to build a working understanding of physics, dynamics, cause and effect, and human behaviour. Named uses run from controlling robots and humanoids to driving vehicles, piloting drones, training other models and playing games. The data-efficiency claims are the substance: usable robot control from tens of hours of demonstrations and autonomous driving from 20 hours of simulated data. The announcement publishes no resolution, frame rate, latency or interactivity detail, and release is only given as coming weeks.