Pith. sign in

REVIEW 4 cited by

Memory in Plain Sight: Surveying the Uncanny Resemblances of Associative Memories and Diffusion Models

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2309.16750 v2 pith:PBQOYM6N submitted 2023-09-28 cs.LG cs.AImath.DS

Benjamin Hoover , Hendrik Strobelt , Dmitry Krotov , Judy Hoffman , Zsolt Kira , Duen Horng Chau This is my paper · ORCID
classification cs.LGcs.AImath.DS
keywords memoryprocessassociativedescribediffusionenergy-basedfieldsgenerative
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

The generative process of Diffusion Models (DMs) has recently set state-of-the-art on many AI generation benchmarks. Though the generative process is traditionally understood as an "iterative denoiser", there is no universally accepted language to describe it. We introduce a novel perspective to describe DMs using the mathematical language of memory retrieval from the field of energy-based Associative Memories (AMs), making efforts to keep our presentation approachable to newcomers to both of these fields. Unifying these two fields provides insight that DMs can be seen as a particular kind of AM where Lyapunov stability guarantees are bypassed by intelligently engineering the dynamics (i.e., the noise and step size schedules) of the denoising process. Finally, we present a growing body of evidence that records DMs exhibiting empirical behavior we would expect from AMs, and conclude by discussing research opportunities that are revealed by understanding DMs as a form of energy-based memory.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. An analytic theory of creativity in convolutional diffusion models

    cs.LG 2024-12 conditional novelty 8.0 of 10

    Convolutional diffusion models generate novel images by assembling locally consistent patch mosaics of training patches, and this mechanism is captured by an analytic score machine that predicts individual model outputs.

  2. Memorization and Generalization in Generative Diffusion under the Manifold Hypothesis

    cond-mat.dis-nn 2025-02 conditional novelty 6.0 of 10

    For manifold-structured data, the authors derive explicit collapse (memorization) and optimal stopping times for empirical-score diffusion, showing the best generation occurs inside the memorization phase and the samp...

  3. In-context denoising with one-layer transformers: connections between attention and associative memory retrieval

    cs.LG 2025-02 accept novelty 6.0 of 10

    Softmax attention with identity weights is the Bayes optimal denoiser for spherical data, and trained one-layer transformers learn such weights.

  4. Classifier-Free Guidance inside the Attraction Basin May Cause Memorization

    cs.CV 2024-11 conditional novelty 6.0 of 10

    Delaying classifier-free guidance until a 'transition point' in the denoising process reduces verbatim memorization in diffusion models, with a new 'opposite guidance' variant to escape memorization basins sooner.

Pith tools