Dyna-2 Robot Model Released, Pre-trained on 1M Hours of Human Video
JasonMa2020 · x · 2026-08-11
Dyna-2 is a world-action model pre-trained on one million hours of human video data. At this unprecedented scale, the team discovered several new scaling laws:
- World-action models exhibit scaling laws on human data across four orders of magnitude (from 1,000 to 1,000,000 hours).
- This human data scaling law implies a corresponding scaling law on never-before-seen robot data.
- Both data and training objectives matter; world modeling and scaling on video data are essential for cross-embodiment transfer to emerge.
More from Embodied
- Kyle Vogt's Bot Company Sued for Turning Airbnb into Robot Lab — MarwaEldiwiny · 2026-08-11
- Dyna-2 Model Transfers to WUJI2 Dex Hand, Adapts in 13 Minutes of Data — JasonMa2020 · 2026-08-11
- MIT's GeoPT Model Cuts Simulation Data Needs by 60% with Built-in Physics — nordicinst · 2026-08-11
- MIT and Tsinghua introduce GeoPT: physics as AI's third modality — MIT News AI · 2026-08-11
- Amazon Gutting Nova AI Models, Pivoting Hard to Robotics — max_paperclips · 2026-08-11
- Big Tech Robotics Engineers Make $400K+, Startups Face a Math Problem — ATTlKA · 2026-08-11