arXiv AI
From Modes to Memories: Characterizing the Scale-Space Dynamics of Diffusion Models
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jun 24
Cyclic Denoising Reveals Ultrastable Memories in Diffusion Models
arXiv:2606. 24000v1 Announce Type: new Abstract: We introduce cyclic denoising -- repeated forward and reverse diffusion at controlled noise amplitudes -- as an extraction attack for image diffusion models.
arXiv AI
Jul 7
A Random Matrix Theory Perspective on the Consistency of Diffusion Models
arXiv:2602. 02908v2 Announce Type: replace-cross Abstract: Diffusion models trained on different, non-overlapping subsets of a dataset often produce strikingly similar outputs when given the same noise seed.
arXiv Computer Vision
Sep 2
ASSERT: Adaptive Stochastic Sampling for Robust Diffusion Models on Analog Compute-in-Memory Hardware
arXiv:2609.00955v1 Announce Type: new Abstract: Diffusion models achieve strong image generation quality but incur high iterative denoising costs. Analog compute-in-memory (CIM) can accelerate matrix...
arXiv Machine Learning
Jun 8
Generalization of Diffusion Models Arises with a Balanced Representation Space
arXiv:2512. 20963v3 Announce Type: replace Abstract: Diffusion models excel at generating high-quality, diverse samples, yet they risk memorizing training data when overfit to the training objective.
arXiv AI
Jul 20
Toward a mechanistic understanding of inference in visual cortex and diffusion models
arXiv:2607. 15693v1 Announce Type: cross Abstract: We describe a model of perceptual inference in primary visual cortex (V1) equivalent to a minimal diffusion model whose function can be readily understood from its parameters.
arXiv Machine Learning
Jun 9
Evaluating the Representation Space of Diffusion Models via Self-Supervised Principles
arXiv:2606. 09718v1 Announce Type: new Abstract: Diffusion models have demonstrated remarkable generative capabilities and have also emerged as powerful self-supervised representation learners, yet the connection between these two abilities remains less explored.