Discussion on Diffusion models beat GANs on image synthesis

Today I led the Machine Learning Journal Club discussion on the paper:

Dhariwal, P., & Nichol, A. (2021). Diffusion models beat gans on image synthesis. Advances in Neural Information Processing Systems, 34, 8780-8794.

This time instead of making slides for overview, I put the focus of discussion on the trick, i.e. Classifier Guidance (section 4 of the paper), which makes the whole thing work well.