LiveWorld: Simulating Out-of-Sight Dynamics in Generative Video World Models

ArXi:2603.07145v1 Announce Type: new Recent generative video world models aim to simulate visual environment evolution, allowing an observer to interactively explore the scene via camera control. However, they implicitly assume that the world only evolves within the observer's field of view. Once an object leaves the observer's view, its state is "frozen" in memory, and revisiting the same region later often fails to reflect events that should have occurred in the meantime.