Bibliography (7):

1. CogView: Mastering Text-to-Image Generation via Transformers

2. https://agc.platform.baai.ac.cn/CogView/index.html

3. https://model.baai.ac.cn/model-detail/100041

4. MAE: Masked Autoencoders Are Scalable Vision Learners

5. Hierarchical Text-Conditional Image Generation with CLIP Latents

6. https://github.com/THUDM/CogView2

7. Wikipedia Bibliography:

   1. International Mathematical Olympiad