A Good Score Does not Lead to A Good Generative Model

10 January 2024

Papers citing "A Good Score Does not Lead to A Good Generative Model"

6 / 6 papers shown

Title
A Geometric Framework for Understanding Memorization in Generative Models Brendan Leigh Ross Hamidreza Kamkari Tongzi Wu Rasa Hosseinzadeh Zhaoyan Liu George Stein Jesse C. Cresswell G. Loaiza-Ganem 55 6 0 31 Oct 2024
Statistically Optimal Generative Modeling with Maximum Deviation from the Empirical Distribution Elen Vardanyan Sona Hunanyan T. Galstyan A. Minasyan A. Dalalyan 26 2 0 31 Jul 2023
Stochastic Interpolants: A Unifying Framework for Flows and Diffusions M. S. Albergo Nicholas M. Boffi Eric Vanden-Eijnden DiffM 248 261 0 15 Mar 2023
Diffusion Models are Minimax Optimal Distribution Estimators Kazusato Oko Shunta Akiyama Taiji Suzuki DiffM 72 85 0 03 Mar 2023
Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions Sitan Chen Sinho Chewi Jungshian Li Yuanzhi Li Adil Salim Anru R. Zhang DiffM 132 246 0 22 Sep 2022
Diffusion-LM Improves Controllable Text Generation Xiang Lisa Li John Thickstun Ishaan Gulrajani Percy Liang Tatsunori B. Hashimoto AI4CE 173 773 0 27 May 2022