Difference & advantages over SEED（tencentAI）

bytedance / 1d-tokenizer

This repo contains the code for our paper An Image is Worth 32 Tokens for Reconstruction and Generation

Apache License 2.0

244 stars 7 forks source link

Difference & advantages over SEED（tencentAI） #12

Closed baoxiaoyi closed 2 days ago

baoxiaoyi commented 4 days ago

Wonderful work and amazing performance！As I delve into the subject matter, I have encountered the "Planting a SEED of Vision in Large Language Model" paper, which discusses a similar topic and aims to address comparable research questions.

To gain a better understanding and comprehensive insight into both works, I would greatly appreciate it if you could provide me with some clarification regarding the distinctions and advantages of your work in comparison to SEED

cornettoyu commented 4 days ago

For the discussion regarding similar works working on CLIP feats including SEED, QFormer, EMU etc, please refer to our paper's related work section, Tokenization for Image Understanding part.