mlsanityData to 7 Oct 2026

The Diffusion Encoder

arXiv 2605.13399 ↗First posted 13 May 2026cs.LG cs.IT math.ITcited by 0

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

We construct a new kind of encoder, leveraging the expressive power of diffusion models. In a traditional variational autoencoder, the encoder and decoder jointly negotiate a latent representation of the input. This is made possible by the reparameterization trick, which simplifies training at the cost of restricting the encoder to a simple family of distributions. Replacing this encoder with a diffusion model requires rethinking how the decoder pressure can be transmitted back to the encoder, given that they tend to update their internal estimates of the latent in opposing directions. We solve this problem with an alternating training scheme, inspired by the expectation-maximization algorithm. Our method enables more reliable synchronization between encoder and decoder, while preserving the simple and efficient training objective of standard diffusion models.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 29 of its 42 references that are in the map. First posted on arXiv 13 May 2026.

Builds on

29 of 42 references.

Closest ancestors · 10

Same direction, newest first

  1. 2025On the Separability of Information in Diffusion Models28 Sep
  2. 2024Neural Entropy5 Sep
  3. 2023Interpretable Diffusion via Information Decomposition12 Oct
  4. 2023Information-Theoretic Diffusion7 Feb
  5. 2022Scalable Diffusion Models with Transformers19 Dec
  6. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  7. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  8. 2021Maximum Likelihood Training of Score-Based Diffusion Models22 Jan
  9. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  10. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2022Flow Matching for Generative Modelingcited by 5,426
  3. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  4. 2018Neural Ordinary Differential Equationscited by 3,733
  5. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  6. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  7. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  8. 2015Variational Inference with Normalizing Flowscited by 2,161
  9. 2019An Introduction to Variational Autoencoderscited by 997
  10. 2024Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Controlcited by 222
  11. 2018Inference Suboptimality in Variational Autoencoderscited by 131
  12. 2019Lagging Inference Networks and Posterior Collapse in Variational Autoencoderscited by 124
7 more
  1. 2019Don't Blame the ELBO! A Linear VAE Perspective on Posterior Collapsecited by 120
  2. 2020Interacting particle solutions of Fokker-Planck equations through gradient-log-density estimationcited by 87
  3. 2018Semi-Amortized Variational Autoencoderscited by 83
  4. 2025DIME:Diffusion-Based Maximum Entropy Reinforcement Learningcited by 52
  5. 2023Stochastic Optimal Control Matchingcited by 39
  6. 2026Q-learning with Adjoint Matchingcited by 33
  7. 2023MINDE: Mutual Information Neural Diffusion Estimationcited by 31

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Generalization in VAE and Diffusion Models: A Unified Information-Theoretic Analysis
  2. 2025Diffusion Transformers with Representation Autoencoders
  3. 2023DiffEnc: Variational Diffusion with a Learned Encoder
  4. 2025Geometry-Preserving Encoder/Decoder in Latent Generative Models
  5. 2025Generalization of Diffusion Models Arises with a Balanced Representation Space
  6. 2022Understanding Diffusion Models: A Unified Perspective
  7. 2023Variational Diffusion Auto-encoder: Latent Space Extraction from Pre-trained Diffusion Models
  8. 2025Masked Autoencoders Are Effective Tokenizers for Diffusion Models