# An Introduction to Variational Autoencoders

## TL;DR

This paper introduces variational autoencoders, a framework for learning deep latent-variable models, and discusses key extensions to enhance their capabilities.

## Contribution

It offers an accessible introduction to variational autoencoders along with an overview of significant extensions that improve their performance.

## Key findings

- Provides foundational understanding of variational autoencoders
- Summarizes important extensions to the basic framework
- Highlights applications in deep generative modeling

## Abstract

Variational autoencoders provide a principled framework for learning deep latent-variable models and corresponding inference models. In this work, we provide an introduction to variational autoencoders and some important extensions.