← Search

Zhengyu Fang

1 accepted papers

2025

Understanding and Mitigating Memorization in Diffusion Models for Tabular Data

ICML 2025poster

Tabular data generation has attracted significant research interest in recent years, with the tabular diffusion models greatly improving the quality of synthetic data. However, while memorization—where models inadvertently replicate exact or near-identical training data—has been thoroughly investiga…