Vibeleaderboard
Index / article

Flow-based Deep Generative Models

lilianweng.github.io
Visit lilianweng.github.io
Category
Other
Type
ARTICLE
Added
Jul 21, 2026

About

So far, I’ve written about two types of generative models, GAN and VAE . Neither of them explicitly learns the probability density function of real data, $p(\mathbf{x})$ (where $\mathbf{x} \in \mathcal{D}$) — because it is really hard! Taking the generative model with latent variables as an example, $p(\mathbf{x}) = \int p(\mathbf{x}\vert\mathbf{z})p(\mathbf{z})d\mathbf{z}$ can hardly be calculated as it is intractable to go through all possible values of the latent code $\mathbf{z}$

Why it made the leaderboard

A rigorous walkthrough of normalizing flows and models like RealNVP and Glow that explicitly learn tractable data likelihoods — useful for practitioners who need exact density estimation rather than the implicit distributions of GANs/VAEs.

Comments (0)

No comments yet

Indexed by a proprietary survey. Corrections welcome.