A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective

NeurIPSSpotlight2025

Authors
Lianghe Shi, Meng Wu, Huijie Zhang, Zekai Zhang, Molei Tao, Qing Qu
Venue
NeurIPS 2025
Track
Spotlight

TL;DR

The widespread use of diffusion models has led to an abundance of AI-generated data, raising concerns about model collapse---a phenomenon in which recursive iterations of training on synthetic data le…

Opening excerpt from the authors’ abstract. source

Read the paper

Topics

generalization diffusion

← All NeurIPS 2025 Spotlight papers · Browse the whole archive