Diffusion part 2: A first principles approach. This article is the second in a multi-article series exploring the fundamentals of deep generative models where we discuss Hierarchical Markovian Variational Autoencoders (HMVAE). With advances in text-to-image generation (OpenAI’s DALL-E, Imagen, Midjourney, Stable Diffusion, HuggingFace, etc.), text-to-text (ChatGPT, Chinchilla, Flamingo), speech-to-text (Assembly…