Tag
WorldRover is a scalable synthetic data engine that generates long-range, richly annotated video sequences with depth and camera motion to support training models for coherent world exploration.
Wonder is a general-purpose video world model that enables real-time, camera-controllable world exploration from an image or conditional video. It introduces camera conditioning via dense coordinate fields, a sparse attention memory mechanism, and techniques to improve distillation, allowing minute-scale video generation at 16 FPS.