Alibaba and CUHK’s RynnWorld-4D predicts a robot scene’s future from one image

jiqizhixin · x · 2026-07-26

Alibaba and CUHK’s RynnWorld-4D predicts a robot scene’s future in 4D from one image and a prompt

Alibaba DAMO Academy and CUHK researchers introduce RynnWorld-4D, a model that takes a single 3D image plus a text instruction and generates future frames, depth, and motion flow in one unified step.

Original post →

More from Embodied

Embodied channel →