Multimodal Large Language Model(MLLM)

1 CLIP

CLIP(Contrastive Language–Image Pre-training)

2 BLIP

3 BLIP 2

4 LLaVA

5 miniGPT

6 Instruction BLIP

Reference

靠谱女士的组会分享［多模态大模型之clip，blip，blip–2，llava | Bilibili
CLIP 论文逐段精读【论文精读】 - 李沐