Chen Zeno — accepted AI-conference papers

2025

When Diffusion Models Memorize: Inductive Biases in Probability Flow of Minimum-Norm Shallow Neural Nets

Chen Zeno, Hila Manor, Greg Ongie, Nir Weinberger, Tomer Michaeli, Daniel Soudry

ICML 2025poster

While diffusion models generate high-quality images via probability flow, the theoretical understanding of this process remains incomplete. A key question is when probability flow converges to training samples or more general points on the data manifold. We analyze this by studying the probability f…

Cited by 0 Source ↗PDF ↗Scholar ↗

2023

How do Minimum-Norm Shallow Denoisers Look in Function Space?

Chen Zeno, Greg Ongie, Yaniv Blumenfeld, Nir Weinberger, Daniel Soudry

NeurIPS 2023poster

Neural network (NN) denoisers are an essential building block in many common tasks, ranging from image reconstruction to image generation. However, the success of these models is not well understood from a theoretical perspective. In this paper, we aim to characterize the functions realized by shall…

Cited by 7 Source ↗PDF ↗Scholar ↗