论文信息 - X 2 -VLM: All-In-One Pre-trained Model For Vision-Language Tasks - 字舞流文

X 2 -VLM: All-In-One Pre-trained Model For Vision-Language Tasks

Hang Li | Xinsong Zhang | Wangchunshu Zhou | Yan Zeng | Jiawei Wang | E. Zurich | Jipeng Zhang | Hkust Wangchunshu Zhou | Yan Zeng | Xinsong Zhang | Hang Li | Jiawei Wang | Jipeng Zhang | Eth Zurich