Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Models

22 May 2025

Papers citing "Bigger Isn't Always Memorizing: Early Stopping Overparameterized Diffusion Models"

8 / 8 papers shown

Title
Learning curves theory for hierarchically compositional data with power-law distributed features Francesco Cagnetta Hyunmo Kang Matthieu Wyart 127 1 0 11 May 2025
On the Generalization Properties of Diffusion Models Puheng Li Zhong Li Huishuai Zhang Jiang Bian 238 39 0 13 Mar 2025
On Memorization in Diffusion Models Xiangming Gu Chao Du Tianyu Pang Chongxuan Li Min Lin Ye Wang DiffM TDI 343 55 0 21 Feb 2025
How Compositional Generalization and Creativity Improve as Diffusion Models are Trained Alessandro Favero Antonio Sclocchi Francesco Cagnetta Pascal Frossard Matthieu Wyart DiffM CoGe 110 6 0 17 Feb 2025
Large Language Diffusion Models Shen Nie Fengqi Zhu Zebin You Xiaolu Zhang Jingyang Ou Jun Hu Jun Zhou Yankai Lin Ji-Rong Wen Chongxuan Li 261 55 0 14 Feb 2025
Simplified and Generalized Masked Diffusion for Discrete Data Jiaxin Shi Kehang Han Zehao Wang Arnaud Doucet Michalis K. Titsias DiffM 203 105 0 17 Jan 2025
An analytic theory of creativity in convolutional diffusion models Mason Kamb Surya Ganguli DiffM 79 25 0 28 Dec 2024
Probing the Latent Hierarchical Structure of Data via Diffusion Models Antonio Sclocchi Alessandro Favero Noam Itzhak Levi Matthieu Wyart DiffM 121 5 0 17 Oct 2024