Today we are introducing Dyna-2, a world-action model pre-trained on one million hours of human video. At this scale, for the first time, we discovered several new scaling laws:
โข world-action models exhibit scaling law on human data across four orders of magnitude, from 1000 to 1,000,000 hours,
โข this human data scaling law implied a scaling law on never seen robot data,
โข both data and objective matter; world modeling and scaling on video data are essential for cross-embodiment scaling transfer to emerge
๐งต