VIMA

Modelactive

Stanford/NVIDIA multi-modal agent using heterogeneous prompts for robotic manipulation.

Details

Updated:6/21/2026

open sourcetrue

release date2022-10-06

github urlhttps://github.com/vimalabs/VIMA

paper urlhttps://arxiv.org/abs/2210.03094

model familyVIMA

https://vimalabs.github.io/

website

https://arxiv.org/abs/2210.03094

paper

https://github.com/vimalabs/VIMA

github

No related knowledge pages.