DALL·E 论文

BEiT 模型代码解读

BEiT: BERT Pre-Training of Image Transformers

VLMO: Unified Vision-Language Pre-Training with Mixture-of-Modality-Experts 论文简析

BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation 论文解读

多模态论文中常用的改编版本的Bert代码实现记录

Momentum Contrast for Unsupervised Visual Representation Learning 论文简析

Align before Fuse: Vision and Language Representation Learning with Momentum Distillation 论文简析

InternVL 1.0: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks 论文简析

How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites 论文简析