human-video

Tag

Cards List
#human-video

@FinanceYF5: What surprised me most: Dyna-2 never trained on a single robot trajectory, yet the more human video it saw, the better …

X AI KOLs Timeline · 2026-08-11 Cached

Dyna Robotics introduces Dyna-2, a world-action model pre-trained on one million hours of human video, revealing scaling laws and suggesting the embodiment gap is an adaptation problem rather than a knowledge problem.

0 favorites 0 likes
#human-video

@heyshrutimishra: This is how robotics scales at an absurd pace. One million+ hours of people doing everyday tasks. No robot data at all.…

X AI KOLs Timeline · 2026-08-10 Cached

Dyna Robotics introduces Dyna-2, a world-action model pre-trained on one million hours of human video, discovering new scaling laws for robot manipulation.

0 favorites 0 likes
← Back to home

Submit Feedback