Discussion closed

#22

by Marvian - opened Jun 7, 2024

Jun 7, 2024

This comment has been hidden

Marvian changed discussion status to closed Jun 7, 2024

Marvian changed discussion title from 为什么当前的VL大模型在提取图片特征时都用的图片内部的self-attention而不是依据问题内容做cross-attention，原因是什么？ to Discussion closed Jun 7, 2024

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment