The paper investigates why diffusion models, despite their practical success, can fully memorize training data when optimal. It shows that as training proceeds, the denoising objective causes overfitting at intermediate noise levels, creating a gap between validation and training performance. In a 2D toy model, this gap arises from the interplay between model error and the data distribution’s support density, leading to a smooth, generalizing flow field rather than exact recall of training points. The study also reveals that predictions from intermediate inference states become increasingly similar to training data in feature space, even as overall similarity to validation data remains unchanged.
By Tim Kaiser, Markus Kollmann
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.
By Rishabh Sharma, Stefano Martiniani
arXiv:2310. 05264v5 Announce Type: replace Abstract: In this work, we investigate an intriguing and prevalent phenomenon of diffusion models which we term as "consistent model reproducibility": given the same starting noise input and a deterministic sampler, different diffusion models often yield remarkably similar outputs.
By Huijie Zhang, Jinfan Zhou, Yifu Lu, Minzhe Guo, Peng Wang, Liyue Shen, Qing Qu
The paper investigates when language diffusion models, specifically Uniform-based Discrete Diffusion Models (UDDMs), shift from memorizing training data to generalizing to new data. It shows that UDDMs act as associative memories, forming basins of attraction around stored examples without requiring an explicit energy function. By measuring token recovery and conditional entropy, the authors identify a sharp transition governed by training set size, where memorization (vanishing entropy) gives way to generalization (finite entropy).
By Bao Pham, Mohammed J. Zaki, Luca Ambrogioni, Dmitry Krotov, Matteo Negri
arXiv:2609.39648v1 Announce Type: cross
Abstract: Diffusion models are typically viewed as stochastic processes that transform noise into data. We take a complementary perspective: a diffusion model...
By Cristina L\'opez Amado, Marco Fumero, Francesco Locatello
The paper critiques current memorization audits for generative models, arguing that lacking a proper null distribution leads to misleading conclusions. It introduces two exact null tests—one permutation test for whole models and a calibrated test for single images—showing that many previously flagged memorizations disappear under these stricter controls. The authors also propose a scale‑restricted statistic based on the Intersection Euler Characteristic Profile to better detect distinct copied images.
By Sushovan Majhi, Pramita Bagchi
The paper investigates how one-step generative models, which compress multi-step diffusion processes, handle denoising across a single forward pass. It introduces the concept of "depth as time," showing that intermediate layers of a model can be decoded to reveal a denoising trajectory similar to multi-step diffusion. The study finds that models trained with a time-indexed transport task, such as MeanFlow, exhibit this depthwise denoising and can be highly compressed, whereas models without such a task do not show the same behavior.
By Arnold Caleb Asiimwe, William Yang, Sanghyuk Chun, Esin Tureci, Olga Russakovsky
arXiv:2606. 13796v1 Announce Type: cross Abstract: Recursive training of generative models on their own outputs can lead to model collapse, a compounding drift away from the true data distribution.
By Na\"il B. Khelifa, Richard E. Turner, Ramji Venkataramanan
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.
By Binxu Wang, Jacob Zavatone-Veth, Cengiz Pehlevan
arXiv:2607. 08041v1 Announce Type: new Abstract: How diffusion models circumvent the curse of dimensionality to learn complex distributions over high dimensional spaces from a finite training set, instead of memorizing it, remains a fundamental mystery.
By Henry Hunt, Mason Kamb, Surya Ganguli
arXiv:2608. 02575v1 Announce Type: new Abstract: Diffusion models rely on stochastic inputs, yet on finite-precision hardware, the "randomness" they consume is realized as deterministic numerical orbits generated by pseudorandom rules.
By Shengzhi Deng, Chenqi Ye, Yanze Guo
How diffusion models circumvent the curse of dimensionality to learn complex distributions over high dimensional spaces from a finite training set, instead of memorizing it, remains a fundamental mystery. To address this, we introduce analytically tractable Bayesian information restricted diffusion (BIRD) models, in which each pixel observes restricted information about noisy data.