Skip to content
English

Switch theme

Discover▾

Not sure where to start? This week’s hottest software, models and stacks in three minutes.

AI Apps▾

AI software people use: from assistants like ChatGPT to tools for coding, video and workflows, picked by purpose.

For Agents▾

Software for AI: tools that let your agent (Claude Code, Codex, Cursor…) browse, read docs, run code and remember.

Models▾

Choose models, estimate cost, self-host: prices, rankings, benchmarks, free tiers and compute.

Solutions▾

A goal or an error message? Ready-made stacks, steps and fixes by scenario.

Learn▾

A systematic course from zero to the frontier, with an algorithm library, must-read papers and tutorials.

Frontier▾

Daily AI news, weekly highlights, the latest papers and how AI is changing every discipline.

// ✦ Diffusion, Flow Matching & Generative Models

Flow Matching

Learns a velocity field that flows noise into data.

流匹配 2022 Advanced core

Original paper ↓ What to learn first →

IN PLAIN WORDS

Define simple paths from noise to data (e.g., straight lines), regress the velocity along them, and sample by solving an ODE. Simpler than diffusion with fewer steps; now the mainstream objective for image and video models.

Used in: Stable Diffusion 3, FLUX, Meta Movie Gen

TIMELINE · prerequisites → this → what builds on it

2020 Denoising Dif…2020 Score-Based M…2022 Flow Matching2022 Rectified Flow

01Original paper

Flow Matching for Generative Modeling

Yaron Lipman, Ricky T. Q. Chen, Heli Ben-Hamu, et al. · 2022

arXiv ↗ ✓ Verified · arXiv API

02Where it sits

Learn the left column first; the right column builds on this one.

Learn first

Flow Matching

Then you can learn

Related:Diffusion Transformer (DiT)Normalizing Flows (RealNVP / Glow)

Denoising Diffu…Score-Based Mod…Rectified FlowDiffusion Trans…Normalizing Flo… Flow Matching

Left: prerequisites · right: builds on this · dashed: related. Full map →

03Learning resources

Official docs, explainers, courses and reference code. All links checked.

Explainers

Papers

04Where the course teaches it

U72 Diffusion, Flow Matching & Image Generation VAE/GAN, DDPM/DDIM, score SDEs, latent diffusion, CFG, DiT, flow matching and ControlNet. 14 h15 algorithms6 papers U95 Tracking the Frontier: Reading & Reproducing Papers The three-pass reading method, tracking arXiv and conferences, reproduction and writing. 6 h3 algorithms0 papers

On learning paths:Generative Models & Frontier Research

For AI / data

Data updated: AI algorithms & curriculum(UTC+8)