The paper demonstrates that diffusion models encode memorization in the geometry of their learned energy landscape before it becomes visible in generated samples. By analyzing score divergence and basin volume, the authors show that localized basins form around training images early in training, and that cyclic denoising can recover these images even when one‑shot generation shows no copies. Experiments on Gaussian mixtures, CelebA, CIFAR‑10, and Stable Diffusion v1.4 confirm that basin geometry reveals memorization across various settings.
By Nikhil Verma, Siddharthan Dileep, Anoop Singh, Srikanth Sastry, Ramya Hebbalaguppe, Sayan Ranu, N. M. Anoop Krishnan
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
arXiv:2610.19042v1 Announce Type: new
Abstract: Understanding the mechanism behind why diffusion models memorize their training data remains an open question in generative modeling. In this paper, we...
By Shashank Sule, Xinyue Yu, Boonam Shin, Yuxuan Liu, Abolfazl Hashemi, Hayden Schaeffer
arXiv:2601. 21628v2 Announce Type: replace-cross Abstract: Diffusion models have achieved remarkable progress in image generation, but their increasing deployment raises serious concerns about privacy and copyright.
By Puwei Lian, Yujun Cai, Songze Li, Bingkun Bao
Understanding the mechanism behind why diffusion models memorize their training data remains an open question in generative modeling. In this paper, we examine this question from two perspectives: (a)...
arXiv:2609.37974v1 Announce Type: cross
Abstract: Masked diffusion models (MDMs) generate text by unmasking several tokens per step, but they are trained and sampled under different conditions. The m...
By Manuel Madeira, Amitis Shidani, Alice Bizeul, Victor Turrisi, Louis B\'ethune, Bhavika Devnani, Dan Busbridge, Pierre Ablin, Jo\~ao Monteiro
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:2603. 13421v2 Announce Type: replace Abstract: Generative models based on the Flow Matching objective, particularly Rectified Flow, have emerged as a dominant paradigm for efficient, high-fidelity image synthesis.
By Mingxing Rao, Daniel Moyer
The paper introduces an information-theoretic measure called model information to quantify how much a diffusion model’s outputs depend on its specific training dataset. By analyzing how this measure scales with model size and dataset size, the authors identify two distinct regimes: a nonlinear regime where memorization transitions to imperfect generalization, and a linear regime where generalization improves and sample quality rises. They propose a scaling law that captures these regimes and demonstrate that it can predict memorization and sample quality beyond the fitted data range.
By Druv Pai, Dejan Stancevic, Yi Ma, Luca Ambrogioni
arXiv:2610.14136v2 Announce Type: new
Abstract: Iterative sampling in diffusion models can lead to error accumulation due to exposure bias. The denoiser is trained on real images interpolated with no...
By Donghoon Ahn, Runqian Wang, Alexei A. Efros, Taesung Park, Yash Belhe
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
arXiv:2605.27813v2 Announce Type: replace-cross
Abstract: Text-to-image diffusion models generate images by iterative denoising, so their internal layers produce trajectories of activations rather th...
By Calvin Yeung, Prathyush Poduval, Ali Zakeri, Zhuowen Zou, Mohsen Imani