Introducing ♾OmniJARVIS, our latest venture to #AgentGPT, or vision-language-action (VLA) models for open-world instruction-following agents 🦾🕹️
tuning in 👉https://t.co/ofwOZuHgDH
by Team CraftJarvis, 🤿⏬
Morning today at #ICLR2024, @ShaofeiCai will be presenting our large-scale agent (to-be ;) as a spotlight poster, at Halle B #189, 10:45am-12:45pm. Come say Hi to baby GROOT, who is still growing!