vimalabs / VIMA

Official Algorithm Implementation of ICML'23 Paper "VIMA: General Robot Manipulation with Multimodal Prompts"
MIT License
778 stars 87 forks source link

LVLM Implementation #58

Open GasolSun36 opened 2 months ago

GasolSun36 commented 2 months ago

Hi,

Thanks for your excellent work! I observed that the output of the model is an embedding. Is there an implementation of LVLM that allows the model to output actions in natural language?

Looking forward to reply.