References & Further Reading

References

1. D. P. Kingma and M. Welling, Auto-Encoding Variational Bayes, ICLR, 2013

   The VAE paper introducing the reparameterisation trick.

2. I. Goodfellow et al., Generative Adversarial Nets, NeurIPS, 2014

   The GAN paper introducing adversarial training for generation.

3. J. Ho, A. Jain, and P. Abbeel, Denoising Diffusion Probabilistic Models, NeurIPS, 2020

   DDPM: simple denoising objective for high-quality generation.

4. Y. Lipman, R. T. Q. Chen, H. Ben-Hamu, M. Nickel, and M. Le, Flow Matching for Generative Modeling, ICLR, 2023

   Flow matching: simplified training of continuous normalizing flows.

Further Reading

• Understanding diffusion models

  Lilian Weng's blog (lilianweng.github.io)

  Excellent tutorial on diffusion models with derivations.

• Score-based generative models

  Yang Song's blog and SDE tutorial

  Unifies diffusion and score matching under stochastic differential equations.