https://wezteoh.github.io/tags/latent-variable-models/ Recent content in Latent Variable Models on Some days I delve https://wezteoh.github.io/%3Clink%20or%20path%20of%20image%20for%20opengraph,%20twitter-cards%3E https://wezteoh.github.io/%3Clink%20or%20path%20of%20image%20for%20opengraph,%20twitter-cards%3E Hugo -- 0.148.0 en-us Mon, 20 Apr 2026 00:00:00 +0000 https://wezteoh.github.io/posts/understanding-diffusion-through-vae/ Mon, 20 Apr 2026 00:00:00 +0000 https://wezteoh.github.io/posts/understanding-diffusion-through-vae/ <blockquote> <p>This post is an introduction on diffusion written for my younger self. If you are new to diffusion and already familiar with VAE, this may be a good entry point for you.</p></blockquote> <hr> <p>Diffusion has blown up over the past few years, with a huge amount of literature produced, but many differ in how they frame this modeling paradigm<sup id="fnref:1"><a href="#fn:1" class="footnote-ref" role="doc-noteref">1</a></sup>. I do not intend to approach this via the most standardized or unified theory. I am not the best person to do that, nor do I think that angle helped me the most when approaching the subject (see my previous <a href="https://wezteoh.github.io/posts/ranting-about-the-engineering-science-of-ml/">post</a>). While many explanations derive diffusion from first principles, I found it useful to start by understanding how the objective is shaped into something we can actually train.</p>