# f-VAEs: Improve VAEs with Conditional Flows

arXiv: https://arxiv.org/abs/1809.05861 · HTML: https://mlsanity.com/paper/1809.05861/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Sep 2018.

## Built on by (most cited first, 10 of 10)

- [Cycle-free CycleGAN using Invertible Generator for Unsupervised Low-Dose CT Denoising](https://mlsanity.com/paper/2104.08538/) (2021)
- [Flexible Language Modeling in Continuous Space with Transformer-based Autoregressive Flows](https://mlsanity.com/paper/2507.00425/) (2025)
- [SimFlow: Simplified and End-to-End Training of Latent Normalizing Flows](https://mlsanity.com/paper/2512.04084/) (2025)
- [Scaling Image Tokenizers with Grouped Spherical Quantization](https://mlsanity.com/paper/2412.02632/) (2024)
- [Ultra-High-Resolution Image Synthesis with Pyramid Diffusion Model](https://mlsanity.com/paper/2403.12915/) (2024)
- [BPLF: A Bi-Parallel Linear Flow Model for Facial Expression Generation from Emotion Set Images](https://mlsanity.com/paper/2106.07563/) (2021)
- [Hierarchical Reinforcement Learning with Optimal Level Synchronization Based on Flow-Based Deep Generative Model](https://mlsanity.com/paper/2107.08183/) (2021)
- [Towards Composable Distributions of Latent Space Augmentations](https://mlsanity.com/paper/2303.03462/) (2023)
- [CAVACHON: a hierarchical variational autoencoder to integrate multi-modal single-cell data](https://mlsanity.com/paper/2405.18655/) (2024)
- [Latent Thermodynamic Flows: Unified Representation Learning and Generative Modeling of Temperature-Dependent Behaviors from Limited Data](https://mlsanity.com/paper/2507.03174/) (2025)

## Abstract (arXiv)

In this paper, we integrate VAEs and flow-based generative models successfully and get f-VAEs. Compared with VAEs, f-VAEs generate more vivid images, solved the blurred-image problem of VAEs. Compared with flow-based models such as Glow, f-VAE is more lightweight and converges faster, achieving the same performance under smaller-size architecture.