mlsanityData to 14 Oct 2026

Diffusion Priors In Variational Autoencoders

arXiv 2106.15671 ↗First posted 29 Jun 2021cs.LGcited by 25

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Among likelihood-based approaches for deep generative modelling, variational autoencoders (VAEs) offer scalable amortized posterior inference and fast sampling. However, VAEs are also more and more outperformed by competing models such as normalizing flows (NFs), deep-energy models, or the new denoising diffusion probabilistic models (DDPMs). In this preliminary work, we improve VAEs by demonstrating how DDPMs can be used for modelling the prior distribution of the latent variables. The diffusion prior model improves upon Gaussian priors of classical VAEs and is competitive with NF-based priors. Finally, we hypothesize that hierarchical VAEs could similarly benefit from the enhanced capacity of diffusion priors.

Key facts. Cited by 25 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 20 of its 23 references that are in the map. First posted on arXiv 29 Jun 2021.

Builds on

20 of 23 references.

Closest ancestors · 5

Same direction, newest first

  1. 2021Score-based Generative Modeling in Latent Space10 Jun
  2. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  3. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  5. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 15

  1. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  2. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 6,013
  3. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  4. 2013Auto-Encoding Variational Bayescited by 4,053
  5. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,988
  6. 2015Variational Inference with Normalizing Flowscited by 2,170
  7. 2015Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networkscited by 2,054
  8. 2016Conditional Image Generation with PixelCNN Decoderscited by 862
  9. 2016Improving Variational Inference with Inverse Autoregressive Flowcited by 640
  10. 2020NVAE: A Deep Hierarchical Variational Autoencodercited by 637
  11. 2015Adversarial Autoencoderscited by 364
  12. 2016Ladder Variational Autoencoderscited by 318
3 more
  1. 2017VAE with a VampPriorcited by 248
  2. 2016Variational Lossy Autoencodercited by 176
  3. 2019Video Compression With Rate-Distortion Autoencoderscited by 97

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 6; 2023: 5; 2024: 6; 2025: 3; 2026: 3.

25 papers.

Sort:

By area:

  1. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,700
  2. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  3. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representationcited by 449
  4. 2022From data to functa: Your data point is a function and you can treat it like onecited by 187
  5. 2023Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstructioncited by 180
  6. 2022Latent Diffusion Energy-Based Model for Interpretable Text Modelingcited by 67
  7. 2023DINOISER: Diffused Conditional Sequence Learning by Manipulating Noisescited by 50
  8. 2021Global Context with Discrete Diffusion in Vector Quantised Modelling for Image Generationcited by 40
  9. 2022On Analyzing Generative and Denoising Capabilities of Diffusion-based Deep Generative Modelscited by 31
  10. 2022NVDiff: Graph Generation through the Diffusion of Node Vectorscited by 18
  11. 2023Deep Generative Models for Detector Signature Simulation: A Taxonomic Reviewcited by 18
  12. 2024Error bounds for particle gradient descent, and extensions of the log-Sobolev and Talagrand inequalitiescited by 13
13 more
  1. 2026Making Reconstruction FID Predictive of Diffusion Generation FIDcited by 13
  2. 2024Unified Generation, Reconstruction, and Representation: Generalized Diffusion with Adaptive Latent Encoding-Decodingcited by 10
  3. 2023Diffusion Models with Deterministic Normalizing Flow Priorscited by 7
  4. 2025Training Latent Diffusion Models with Interacting Particle Algorithmscited by 4
  5. 2024Text Diffusion with Reinforced Conditioningcited by 3
  6. 2024Denoising Diffusion Variational Inference: Diffusion Models as Expressive Variational Posteriorscited by 2
  7. 2024VAE-QWGAN: Addressing Mode Collapse in Quantum GANs via Autoencoding Priorscited by 2
  8. 2023Discouraging posterior collapse in hierarchical Variational Autoencoders using contextcited by 1
  9. 2025Diffusion Autoencoders with Perceivers for Long, Irregular and Multimodal Astronomical Sequencescited by 1
  10. 2024VaeDiff-DocRE: End-to-end Data Augmentation Framework for Document-level Relation Extractioncited by 0
  11. 2025Disentangled representations via score-based variational autoencoderscited by 0
  12. 2026VAMP-Diff: VampPrior Latent Diffusion for Photoplethysmography Modelingcited by 0
  13. 2026BattVAE-GP: Generative Modeling of Long-Horizon Battery Degradation with Uncertainty Quantificationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Frequentist Statistical Introduction to Variational Inference, Autoencoders, and Diffusion Models
  2. 2023Variational Diffusion Auto-encoder: Latent Space Extraction from Pre-trained Diffusion Models
  3. 2025Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis
  4. 2023DiffEnc: Variational Diffusion with a Learned Encoder
  5. 2022Understanding Diffusion Models: A Unified Perspective
  6. 2022DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents
  7. 2022Diffusion bridges vector quantized Variational AutoEncoders
  8. 2022Image Generation with Multimodal Priors using Denoising Diffusion Probabilistic Models