Domain Neighborhood
Generative Models
How models generate: likelihood, latent variables, diffusion/score models, flows, and the training tricks that make sampling work.
Start here. Predict once, then carry the invariant forward.
x_tε_θdenoisex_0Learner lensWhat makes this domain feel navigable?
Take this lensStabilize the first mechanism, make one prediction, then move one node forward.
Recommended Route
Start here, then follow the prerequisites forward.
This sequence is ordered for learning rather than inventory. Published notebooks with an unavailable prerequisite—or a same-domain route step that depends on one—are labeled in the full inventory instead of being presented as ready steps.
- 01Variational 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)Check Maximum Likelihood first if the symbols feel slippery.
- 02Diffusion, 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 AutoencodersWhy this follows: Diffusion, Score-Based Models & Flow Matching uses Variational Autoencoders 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.
- 04Flow 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 Normalizing Flows: Tractable Density via Invertible Transforms directly.
- 05Score 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.
All Published Notebooks
Browse the territory.
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.
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.
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.
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.
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.
Advanced Bridges