Domain Neighborhood
Generative Models
How models generate: likelihood, latent variables, diffusion/score models, flows, and the training tricks that make sampling work.
Recommended Route
Start here, then follow the prerequisites forward.
This sequence is ordered for learning rather than inventory: lower difficulty, fewer prerequisites, and more central concepts come first.
- 01Diffusion, Score-Based Models & Flow Matching
Denoise noise into data: the diffusion forward process, score matching, and modern sampling via reverse-time dynamics and flow matching.
22 mincodedemoafter Maximum Likelihood, Variational AutoencodersCheck Maximum Likelihood first if the symbols feel slippery.
- 02Flow Matching & Rectified Flows
Learn flow matching as velocity-label regression: straight conditional paths use x_t=(1-t)x0+t x1 but supervise the full target u_t=x1-x0.
16 mincodedemoafter Diffusion, Score-Based Models & Flow Matching, Normalizing Flows: Tractable Density via Invertible TransformsWhy this follows: Flow Matching & Rectified Flows uses Diffusion, Score-Based Models & Flow Matching directly.
- 03Normalizing Flows: Tractable Density via Invertible Transforms
Invertible transforms trained with change-of-variables: tractable transformed densities and sampling, with architectural constraints to make the needed Jacobian determinants tractable.
18 mincodedemoafter Maximum Likelihood, Variational AutoencodersWhy this follows: both pages keep the generative models thread active.
- 04Score Matching & Score-Based Generative Models
Learn the score field grad_x log p(x) without normalizing constants. Denoising score matching turns diffusion training into simple regression on noise.
18 mincodedemoafter Maximum Likelihood, Diffusion, Score-Based Models & Flow MatchingWhy this follows: both pages keep the generative models thread active.
- 05Variational Autoencoders
A latent-variable model trained by maximizing an evidence lower bound; the gap is KL(q_phi(z|x) || p_theta(z|x)), so the encoder is learned inference rather than just compression.
20 mincodedemoafter Maximum Likelihood, Bayesian Inference, KL Divergence (Relative Entropy)Why this follows: both pages keep the generative models thread active.
All Published Notebooks
Browse the territory.
Diffusion, Score-Based Models & Flow Matching
Denoise noise into data: the diffusion forward process, score matching, and modern sampling via reverse-time dynamics and flow matching.
Flow Matching & Rectified Flows
Learn flow matching as velocity-label regression: straight conditional paths use x_t=(1-t)x0+t x1 but supervise the full target u_t=x1-x0.
Normalizing Flows: Tractable Density via Invertible Transforms
Invertible transforms trained with change-of-variables: tractable transformed densities and sampling, with architectural constraints to make the needed Jacobian determinants tractable.
Score Matching & Score-Based Generative Models
Learn the score field grad_x log p(x) without normalizing constants. Denoising score matching turns diffusion training into simple regression on noise.
Variational Autoencoders
A latent-variable model trained by maximizing an evidence lower bound; the gap is KL(q_phi(z|x) || p_theta(z|x)), so the encoder is learned inference rather than just compression.
Advanced Bridges