brains/go-1 · model record
Genie Operator-1 (GO-1)
3B-parameter ViLLA model: an InternVL2.5-2B vision-language backbone, a latent planner that predicts latent action tokens, and an action expert. Pretrained on the AgiBot World dataset; weights were published on Hugging Face under a non-commercial license.
Company
Kind
VLA
Access
Open weights
License
CC-BY-NC-SA-4.0
Released
9 Mar 2025
Embodiments
1
01
Embodiments
robots it has been shown on- AgiBot Genie-1
02
Papers naming this model
from the papers feedNo paper in the current feed names Genie Operator-1 (GO-1) in its title.