作者位次 #7/10ICML 2026Poster· Applications / Robotics
RoboOmni: Actions Are Just Another Modality for Vision-Language Models
Dong Wang · Zilong Chen · Jirong Liu · Ziqing Qiao · Xin Xiao · Bingyi Kang · Hongtao Wu · Xiao Ma · Tao Kong · Huaping Liu
多模态OpenReview