# VQ-DRAW: A Sequential Discrete VAE

arXiv: https://arxiv.org/abs/2003.01599 · HTML: https://mlsanity.com/paper/2003.01599/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Mar 2020.

## Built on by (most cited first, 2 of 2)

- [NP-DRAW: A Non-Parametric Structured Latent Variable Model for Image Generation](https://mlsanity.com/paper/2106.13435/) (2021)
- [Meta-Learning with Variational Bayes](https://mlsanity.com/paper/2103.02265/) (2021)

## Abstract (arXiv)

In this paper, I present VQ-DRAW, an algorithm for learning compact discrete representations of data. VQ-DRAW leverages a vector quantization effect to adapt the sequential generation scheme of DRAW to discrete latent variables. I show that VQ-DRAW can effectively learn to compress images from a variety of common datasets, as well as generate realistic samples from these datasets with no help from an autoregressive prior.