The Redwood City, California-based company said its DYNA-2 World-Action Model was trained entirely on human egocentric video rather than robot action data. Human video becomes training data Dyna’s model uses a world-modeling architecture that combines next-frame and next-action prediction. Instead of learning only from actions performed by robots, the system uses human video to develop an understanding of how physical environments change and how objects respond to movement. Across 15 benchmark tasks, Dyna said models trained with more human video consistently performed better. Scaling robots beyond teleoperation Dyna said the model also showed better resilience when physical disturbances disrupted a task.