一种完全透明的开源、自适应且高效的截断式视觉 - 语言 - 动作模型 A1 A Fully Transparent Open-Source, Adaptive and Efficient Truncated Vision-Language-Action Model.pdfVIP

SYSU|MBZUAI|SpatialtemporalAI|ATeam

A:AFullyTransparentOpen-Source,Adaptiveand

1

EfficientTruncatedVision-Language-ActionModel

KaidongZhang*1,3,JianZhang*2,RongtaoXu*†2,3,YuSun1,ShuoshuoXue1,YoupengWen1,Xiaoyu

Guo3,MinghaoGuo2,WeijiaLiufu1,LiuZihou3,KangyiJi3,YangsongZhang2,JiarunZhu3,JingzhiLiu1,

ZihangLi1,RuiyiChen1,MengCao2,JingmingZhang3,ShenZhao1,XiaojunChang2