Bibliography (5):

1. https://www.wikipedia.org/

2. Generating Diverse High-Fidelity Images with VQ-VAE-2

3. https://openai.com/blog/dall-e/

4. Unigram LM: Byte Pair Encoding is Suboptimal for Language Model Pretraining

5. WenLan: Bridging Vision and Language by Large-Scale Multi-Modal Pre-Training