Recent years have witnessed significant progress in developing effective training and fast sampling techniques for diffusion models. A remarkable advancement is the use of stochastic differential equations (SDEs) and their marginal-preserving ordinary differential equations (ODEs) to describe data perturbation and generative modeling in a unified framework. In this paper, we carefully inspect the ODE-based sampling of a popular variance-exploding SDE and reveal several intriguing structures of its sampling dynamics. We discover that the data distribution and the noise distribution are smoothly connected with a quasi-linear sampling trajectory and another implicit denoising trajectory that even converges faster. Meanwhile, the denoising trajectory governs the curvature of the corresponding sampling trajectory and its finite differences yield various second-order samplers used in practice. Furthermore, we establish a theoretical relationship between the optimal ODE-based sampling and the classic mean-shift (mode-seeking) algorithm, with which we can characterize the asymptotic behavior of diffusion models and identify the empirical score deviation. Code is available at \url{https://github.com/zju-pi/diff-sampler}.
Confronting Reward Overoptimization for Diffusion Models: A Perspective of Inductive and Primacy Biases
Institute of Artificial Intelligence, School of Computer Science, Wuhan University, China;Hubei Luojia Laboratory, Wuhan, China;The University of Sydney, Australia;JD Explore Academy, Beijing, China;Nanyang Technological University, Singapore
Unraveling the Smoothness Properties of Diffusion Models: A Gaussian Mixture Perspective
The University of Hong Kong(香港大学);University of Wisconsin-Madison(威斯康星大学麦迪逊分校);The Simons Institute for the Theory of Computing at the University of California, Berkeley(加州大学伯克利分校西蒙斯理论计算研究所);University of Pennsylvania(宾夕法尼亚大学)
Diffusion Models Meet Remote Sensing: Principles, Methods, and Perspectives
College of Electrical and Information Engineering, Hunan University(湖南大学电气与信息工程学院);School of Automation, Central South University(中南大学自动化学院);Changsha University of Science and Technology(长沙理工大学);Helmholtz-Zentrum Dresden-Rossendorf (HZDR)(德累斯顿-罗森多夫亥姆霍兹中心);Lancaster University(兰卡斯特大学);Xidian University(西安电子科技大学)
Loss Curvature as a Sampling-Free Proxy for Memorization in Diffusion Models
Department of Mathematics, University of California, Los Angeles(加州大学洛杉矶分校数学系);Elmore Family School of Electrical and Computer Engineering, Purdue University(普渡大学埃尔默电气与计算机工程学院)
Memorization Control in Diffusion Models from Denoising-centric Perspective
Department of Computer Science(计算机科学系);Brunel University of London(布鲁内尔大学);Hanoi University of Science and Technology(河内科学技术大学);Faculty of Electrical and Electronic Engineering School of Engineering(电气电子工程系工程学院);Phenikaa University(Phenikaa大学);Greenwich Vietnam FPT University(格林威治越南FPT大学);College of Engineering(工程学院);Shibaura Institute of Technology(Shibaura技术学院)
Expressivity of Bi-Lipschitz Normalizing Flows: A Score-Based Diffusion Perspective
Center for Industrial Mathematics, University of Bremen(工业数学中心,不莱梅大学);Department of Theoretical Physics and Applied Mathematics, University of Cambridge(理论物理与应用数学系,剑桥大学)
Geometric Image Editing via Effects-Sensitive In-Context Inpainting with Diffusion Transformers
PRIS, Beijing University of Posts and Telecommunications(北京邮电大学);Institute of Artificial Intelligence (TeleAI), China Telecom(中国电信人工智能研究院);Beijing Institute of Technology(北京理工大学)
Geometric Origins of Bias in Deep Neural Networks: A Human Visual System Perspective
Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China(中国人民大学北京校区人工智能学院);Tsinghua University, Beijing, China(清华大学);University of Manchester, Manchester, M13 9PS, United Kingdom(曼彻斯特大学)