Login / Signup

OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents.

Zihao WangShaofei CaiZhancun MuHaowei LinCeyao ZhangXuejie LiuQing LiAnji LiuXiaojian MaYitao Liang
Published in: CoRR (2024)
Keyphrases