Wenlong Huang (@wenlong_huang)
2026-01-08 | โค๏ธ 1214 | ๐ 213
What if we can simulate an interactive 3D world, from a single image, in the wild, in real time?
Introducing PointWorld-1B: a large pre-trained 3D world model that predicts env dynamics given RGB-D capture and robot actions.
๐ https://point-world.github.io/
from @Stanford @nvidia
๐ ์๋ณธ ๋งํฌ
๋ฏธ๋์ด
![]()
๐ Related
Auto-generated - needs manual review