VIMA: General Robot Manipulation with Multimodal Prompts

Yunfan Jiang, Agrim Gupta, Zichen Zhang, Guanzhi Wang, Yongqiang Dou, Yanjun Chen, Li Fei-Fei, Anima Anandkumar, Yuke Zhu, Linxi "Jim" Fan
October, 2022
Go to Project Site Cite Project PDF Arxiv Twitter FMDM Workshop Code Models Benchmark Dataset
VIMA
Type
Preprint
Foundation Model Policy Learning Multimodal Robotics
Linxi "Jim" Fan
Linxi "Jim" Fan
Senior Research Scientist
Lead of AI Agents

My research interests span foundation models, general-purpose agents, robotics, multimodal learning, and large-scale AI systems.