0.2 Gen-AI Jun 13, 2026 · 2 min read
Gaussians & the Reparameterization Trick
The Gaussian is the workhorse of generative modeling. Here's everything you need — mean, covariance, and the one trick (x = μ + σε) that makes diffusion trainable.
Generative AI: Diffusion & Flow Models from First Principles
🌀 // generative ai series · 2 published modules
A build-from-scratch journey through modern generative modeling which includes diffusion, score matching, and flow matching, derived from first principles, implemented in code, and made interactive so intuition sticks. This is a deliberately learner-first reordering: we build the probability you need first, go DDPM-first before any SDEs, live in 1-D/2-D where you can see the math, and arrive at flow matching as the payoff. Related teaching: my Fall 2026 guest lecture on diffusion models and flow matching for MAE 6291 at GWU.
// part 0 · Foundations you can see
// part 1 · The core idea — discrete & concrete
1.1 Gen-AI Jun 13, 2026 · 2 min read
Diffusion from First Principles: From Data to Noise and Back
The one idea behind every diffusion model — gradually destroy structure with noise, then learn to undo it — with an interactive forward-diffusion explorable to build intuition.