mlsanityData to 7 Oct 2026

Hierarchical VAE with a Diffusion-based VampPrior

arXiv 2412.01373 ↗First posted 2 Dec 2024cs.LG stat.MLcited by 8

Not on the map. Why?

Abstract (arXiv)

Deep hierarchical variational autoencoders (VAEs) are powerful latent variable generative models. In this paper, we introduce Hierarchical VAE with Diffusion-based Variational Mixture of the Posterior Prior (VampPrior). We apply amortization to scale the VampPrior to models with many stochastic layers. The proposed approach allows us to achieve better performance compared to the original VampPrior work and other deep hierarchical VAEs, while using fewer parameters. We empirically validate our method on standard benchmark datasets (MNIST, OMNIGLOT, CIFAR10) and demonstrate improved training stability and latent space utilization.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 32 of its 48 references that are in the map. First posted on arXiv 2 Dec 2024.

Builds on

32 of 48 references.

References · 32

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  3. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  4. 2017Neural Discrete Representation Learningcited by 4,650
  5. 2021Variational Diffusion Modelscited by 1,145
  6. 2016Automatic chemical design using a data-driven continuous representation of moleculescited by 762
  7. 2022Equivariant Diffusion for Molecule Generation in 3Dcited by 666
  8. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 636
  9. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 635
  10. 2021Score-based Generative Modeling in Latent Spacecited by 634
  11. 2019Variational Autoencoders and Nonlinear ICA: A Unifying Frameworkcited by 494
  12. 2015Importance Weighted Autoencoderscited by 454
20 more
  1. 2016Ladder Variational Autoencoderscited by 315
  2. 2020Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Imagescited by 261
  3. 2017VAE with a VampPriorcited by 247
  4. 2016Variational Deep Embedding: An Unsupervised and Generative Approach to Clusteringcited by 219
  5. 2021A Variational Perspective on Diffusion-Based Generative Models and Score Matchingcited by 182
  6. 2016Variational Lossy Autoencodercited by 175
  7. 2019Neural Stochastic Differential Equations: Deep Latent Gaussian Models in the Diffusion Limitcited by 168
  8. 2019BIVA: A Very Deep Hierarchy of Latent Variables for Generative Modelingcited by 109
  9. 2015Hierarchical Variational Modelscited by 89
  10. 2016Auxiliary Deep Generative Modelscited by 72
  11. 2016PixelVAE: A Latent Variable Model for Natural Imagescited by 69
  12. 2023One-Step Diffusion Distillation via Deep Equilibrium Modelscited by 60
  13. 2018Resampled Priors for Variational Autoencoderscited by 56
  14. 2019Learning Hierarchical Priors in VAEscited by 53
  15. 2021Consistency Regularization for Variational Auto-Encoderscited by 50
  16. 2018Avoiding Latent Variable Collapse With Generative Skip Modelscited by 47
  17. 2022Efficient-VDVAE: Less is morecited by 26
  18. 2019BooVAE: Boosting Approach for Continual Learning of VAEcited by 18
  19. 2019PixelVAE++: Improved PixelVAE with Discrete Priorcited by 15
  20. 2021Cauchy-Schwarz Regularized Autoencodercited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 4.

8 papers.

  1. 2024DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Spacecited by 32
  2. 2025Distribution Matching Variational AutoEncodercited by 5
  3. 2025Training Latent Diffusion Models with Interacting Particle Algorithmscited by 4
  4. 2025On Designing Diffusion Autoencoders for Efficient Generation and Representation Learningcited by 1
  5. 2026Iterative Amortized Hierarchical VAEcited by 0
  6. 2026Phase-Type Variational Autoencoders for Heavy-Tailed Datacited by 0
  7. 2026VAMP-Diff: VampPrior Latent Diffusion for Photoplethysmography Modelingcited by 0
  8. 2026Implicit Variational Rejection Samplingcited by 0