mlsanityData to 13 Oct 2026

f-VAEs: Improve VAEs with Conditional Flows

arXiv 1809.05861 ↗First posted 16 Sep 2018cs.LG cs.CV stat.MLcited by 10

Not on the map. Why?

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.

Key facts. Cited by 10 papers in the map (data through 13 Oct 2026). First posted on arXiv 16 Sep 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 0; 2023: 1; 2024: 3; 2025: 3.

10 papers.

  1. 2021Cycle-free CycleGAN using Invertible Generator for Unsupervised Low-Dose CT Denoisingcited by 15
  2. 2025Flexible Language Modeling in Continuous Space with Transformer-based Autoregressive Flowscited by 8
  3. 2025SimFlow: Simplified and End-to-End Training of Latent Normalizing Flowscited by 7
  4. 2024Scaling Image Tokenizers with Grouped Spherical Quantizationcited by 4
  5. 2024Ultra-High-Resolution Image Synthesis with Pyramid Diffusion Modelcited by 1
  6. 2021BPLF: A Bi-Parallel Linear Flow Model for Facial Expression Generation from Emotion Set Imagescited by 0
  7. 2021Hierarchical Reinforcement Learning with Optimal Level Synchronization Based on Flow-Based Deep Generative Modelcited by 0
  8. 2023Towards Composable Distributions of Latent Space Augmentationscited by 0
  9. 2024CAVACHON: a hierarchical variational autoencoder to integrate multi-modal single-cell datacited by 0
  10. 2025Latent Thermodynamic Flows: Unified Representation Learning and Generative Modeling of Temperature-Dependent Behaviors from Limited Datacited by 0