Projects

VIMA
A transformer that ingests multimodal prompt and controls a robot arm for a wide range of manipulation tasks.
Website Paper Code Dataset Announcement
VIMA
MineDojo
✨NeurIPS Outstanding Paper Award✨. Open-ended generalist agent.
Website Paper Code Open Database Doc Blog Announcement TwoMinutePapers
MineDojo
MetaMorph
Learning universal controller over diverse morphologies with transformers
Website Arxiv ICLR 2022 Code Video
MetaMorph
Training and Deploying Visual Agents at Scale
My Stanford Ph.D. thesis advised by Fei-Fei Li. Learn the rules like a pro, so you can break them like an artist — Picasso.
PDF SECANT iGibson SURREAL RubiksNet
Training and Deploying Visual Agents at Scale