Yuanmin Tang

icon company UCAS icon location Beijing icon location Ph.D. student in Institute of Information Engineering, Chinese Academy of Sciences, interest in Vision-Language Alignment.

Results 2 comments of Yuanmin Tang

MAE prediction visualization code

> ```python > expand_pos_embed = self.pos_embed > ``` Thank you for your contribution! I have a question about this change. Why this change does not update in the latest code?

The link to the pre-training model file is not working

The original link to the pre-training model is indeed no longer working. However, you can find the updated link to the Pic2Word checkpoint in the following issue discussion on GitHub:...