Journal article · 2026 · Open access
Emergence of diffusion models from associative memory through memorization and generalization
Nature Communications · Published 25 October 2026 · DOI 10.1038/s41467-026-78727-y
In brief
“Emergence of diffusion models from associative memory through memorization and generalization” is a 2026 journal article by Bao Pham and 5 co-authors, published in Nature Communications. OpenAlex counts 35 citations as of 16 November 2026, which puts it in the top 4% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at Nature Communications.
- Citations
- 35
- Most cited in
- 2026 (31)
- Field-weighted impact
- 43.31
- References
- 33
- Authors
- 6
Abstract
Dense Associative Memories (DenseAMs) are generalizations of Hopfield networks that store training data at local minima of the energy landscape. When the amount of training data exceeds the critical memory storage capacity, new local minima (different from the training data) emerge. These emergent local minima, known as spurious states, can hinder memory retrieval. We examine diffusion models (DMs) through the DenseAM lens, viewing their generative process as an attempt of a memory retrieval. In the small data regime, DMs create distinct attractors for each training sample, akin to DenseAMs below the critical capacity. As the training set size increases, DMs transition to generalization. We identify a critical intermediate phase, predicted by DenseAM theory, characterized by the emergence of spurious states. In generative modeling, these previously overlooked states are no longer negative artifacts but rather are the first signs of generative capabilities. Their existence is demonstrated across a wide range of architectures and datasets.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Pham, B., Raya, G., Negri, M., Zaki, M. J., Ambrogioni, L., & Krotov, D. (2026). Emergence of diffusion models from associative memory through memorization and generalization. Nature Communications. https://doi.org/10.1038/s41467-026-78727-y
MLA 9
Pham, Bao, et al. “Emergence of diffusion models from associative memory through memorization and generalization.” Nature Communications, 2026. https://doi.org/10.1038/s41467-026-78727-y.
Chicago
Pham, Bao, Gabriel Raya, Matteo Negri, Mohammed Javeed Zaki, Luca Ambrogioni, and Dmitry Krotov. 2026. “Emergence of diffusion models from associative memory through memorization and generalization.” Nature Communications. https://doi.org/10.1038/s41467-026-78727-y.
Harvard
Pham, B. et al. (2026) ‘Emergence of diffusion models from associative memory through memorization and generalization’, Nature Communications. doi:10.1038/s41467-026-78727-y.
IEEE
B. Pham, G. Raya, M. Negri, M. J. Zaki, L. Ambrogioni, and D. Krotov, “Emergence of diffusion models from associative memory through memorization and generalization,” Nature Communications, 2026, doi: 10.1038/s41467-026-78727-y.
BibTeX
@article{pham2026emergence,
title = {{Emergence of diffusion models from associative memory through memorization and generalization}},
author = {Pham, Bao and Raya, Gabriel and Negri, Matteo and Zaki, Mohammed Javeed and Ambrogioni, Luca and Krotov, Dmitry},
journal = {Nature Communications},
year = {2026},
doi = {10.1038/s41467-026-78727-y},
url = {https://doi.org/10.1038/s41467-026-78727-y}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- diffusion models
- dense associative memory
- Hopfield neural network
- spurious states
- memory retrieval
- energy landscape
- memory capacity
- generalization
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Pham, B., Raya, G., Negri, M., Zaki, M. J., Ambrogioni, L., & Krotov, D. (2026). Emergence of diffusion models from associative memory through memorization and generalization. Nature Communications. https://doi.org/10.1038/s41467-026-78727-y
How many times has this paper been cited?
35 times, according to OpenAlex on 16 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at Nature Communications: sign in and open the PDF from this page.
Who wrote this paper?
Bao Pham, Gabriel Raya, Matteo Negri, Mohammed Javeed Zaki, Luca Ambrogioni, Dmitry Krotov.
What is the DOI of this paper?
10.1038/s41467-026-78727-y, permanently at https://doi.org/10.1038/s41467-026-78727-y. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.