PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs.
Soroush NasirianyFei XiaWenhao YuTed XiaoJacky LiangIshita DasguptaAnnie XieDanny DriessAyzaan WahidZhuo XuQuan VuongTingnan ZhangTsang-Wei Edward LeeKuang-Huei LeePeng XuSean KirmaniYuke ZhuAndy ZengKarol HausmanNicolas HeessChelsea FinnSergey LevineBrian IchterPublished in: CoRR (2024)