Dyna-2 proves million-hour video scaling law, boosting robot skill transfer
Dyna-2, a world‑action model trained on over 1 M hours of egocentric human video, exhibits predictable scaling on held‑out human tasks and, for the first time, a human‑to‑robot transfer scaling law where more human data improves offline robot prediction despite no robot data in pre‑training. This shows that massive video pre‑training can directly benefit robot learning, shaping future cross‑embodiment models.