Image
About
Diffusion models are now the de facto approach to generative modeling across a wide range of data modalities including images, audio, videos, and visuomotor policies. In recent years, there has been a surge of interest in building the mathematical foundations undergirding this family of methods. This research has driven a rich transfusion of ideas between the practice of generative modeling on the one hand, and research in physics, TCS, statistics, and the foundations of machine learning on the other. This workshop will serve as a "preview" to the upcoming Simons semester on Diffusion Generative Modeling to be held in Fall '27, in which we will take stock of recent progress on both theoretical and empirical fronts. Participants will have the opportunity to provide their input on directions that they would like to see represented in the programming next year.
Chairs/Organizers
Invited Participants
Michael Albergo (Harvard University), Joey Bose (Imperial College London), Sitan Chen (Harvard University), Yongxin Chen (Georgia Institute of Technology), Sinho Chewi (Yale University), Valentin de Bortoli (Google DeepMind), Carles Domingo-Enrich (Microsoft Research), Yilun Du (Harvard University), Ahmed El Alaoui (Cornell), Surbhi Goel (University of Pennsylvania), Brice Huang (Stanford University), Zahra Kadkhodaie (MIT), Volodymyr Kuleshov (Cornell University), Holden Lee (Johns Hopkins University), Sergey Levine (UC Berkeley), Jerry Li (University of Washington), Qiang Liu (UT Austin), Jianfeng Lu (Duke University), Aram-Alexandre Pooladian (Yale University), Saeed Saremi (Genentech), Jiaxin Shi (Meta), Max Simchowitz (Carnegie Mellon University), Marta Skreta (Mila Quebec), Molei Tao (Georgia Tech), Kevin Tian (UT Austin), Thuy-Duong (June) Vuong (UC San Diego)