U-Nets as Belief Propagation: Efficient Classification, Denoising, and
Diffusion in Generative Hierarchical Models

v1v2 (latest)

U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models

29 April 2024

ArXiv (abs)PDF HTML

Papers citing "U-Nets as Belief Propagation: Efficient Classification, Denoising, and Diffusion in Generative Hierarchical Models"

5 / 5 papers shown

Title
Learning curves theory for hierarchically compositional data with power-law distributed features Francesco Cagnetta Hyunmo Kang Matthieu Wyart 132 1 0 11 May 2025
Physics-informed 4D X-ray image reconstruction from ultra-sparse spatiotemporal data Zisheng Yao Yuhe Zhang Zhe Hu Robert Klöfkorn Tobias Ritschel Pablo Villanueva-Perez AI4CE 136 1 0 04 Apr 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
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
How transformers learn structured data: insights from hierarchical filtering Jerome Garnier-Brun Marc Mézard Emanuele Moscato Luca Saglietti 167 6 0 27 Aug 2024