BriefGPT.xyz
May, 2023
去噪扩散模型和抽样器的表达能力注记
Expressiveness Remarks for Denoising Diffusion Models and Samplers
HTML
PDF
Francisco Vargas, Teodora Reu, Anna Kerekes
TL;DR
本论文探讨将随机控制方法运用于泛化的去噪扩散模型及样本生成中，并尝试将现有的神经网络近似方法应用于去噪扩散模型及样本生成中。
Abstract
denoising diffusion models
are a class of
generative models
which have recently achieved state-of-the-art results across many domains. Gradual noise is added to the data using a diffusion process, which transform
→