// ✦ Algorithms Atlas
Diffusion, Flow Matching & Generative Models
VAEs, GANs, diffusion, flow matching and DiT — the algorithms behind image, video and audio generation.
8 core7 extended2013–2024
TIMELINE
01Core algorithms
Learn these first. Sorted by year.
Variational Autoencoder (VAE) Encodes data as a distribution in latent space and decodes samples into new data. 2013core VQ-VAE (Neural Discrete Representation) Encodes images or audio into discrete codebook tokens. 2017core Denoising Diffusion Probabilistic Models (DDPM) Learns to turn noise into images step by step. 2020core Latent Diffusion Models Runs diffusion in a VAE's compressed latent space to cut cost. 2021core Classifier-Free Guidance (CFG) Extrapolates between conditional and unconditional predictions to follow prompts. 2022core Diffusion Transformer (DiT) Replaces the U-Net denoiser with a Transformer. 2022core Flow Matching Learns a velocity field that flows noise into data. 2022core ControlNet Adds precise spatial control (edges, pose, depth) to diffusion models. 2023core
02Extended
Variants and follow-ups worth knowing once the core is clear.
Generative Adversarial Network (GAN) A generator and a discriminator improve by competing. 2014ext Normalizing Flows (RealNVP / Glow) Chains invertible maps from a simple distribution to a complex one, with exact likelihood. 2016ext DDIM Makes diffusion sampling deterministic, cutting steps from ~1000 to tens. 2020ext Score-Based Models via SDEs Unifies diffusion as SDEs; generation solves the reverse-time equation. 2020ext Rectified Flow Straightens generative paths so few or one step suffices. 2022ext Consistency Models Maps any point on a trajectory directly to its endpoint for one-step generation. 2023ext Visual Autoregressive Modeling (VAR) Autoregressive image generation by next-scale rather than next-token prediction. 2024ext
03Course units that teach these
U13 Probability, Statistics & Information Theory Distributions, expectation, Bayes, maximum likelihood, cross-entropy and KL divergence. 12 h3 algorithms0 papers U72 Diffusion, Flow Matching & Image Generation VAE/GAN, DDPM/DDIM, score SDEs, latent diffusion, CFG, DiT, flow matching and ControlNet. 14 h15 algorithms6 papers U73 Speech, Video & World Models Whisper, video diffusion (Sora-style DiT), 3-D reconstruction, world models, Dreamer and Genie. 8 h10 algorithms4 papers U95 Tracking the Frontier: Reading & Reproducing Papers The three-pass reading method, tracking arXiv and conferences, reproduction and writing. 6 h3 algorithms0 papers