MIT 6.S184: Flow Matching and Diffusion Models (2026)

MIT 6.S184: Generative AI with Stochastic Differential Equations Year: 2026 Lecture notes: https://diffusion.csail.mit.edu/ Course website: https://diffusion.csail.mit.edu/2026/index.html Code exercises: https://diffusion.csail.mit.edu/2026/index.html Playlist: Instructor: Peter Holderrieth (https://www.peterholderrieth.com/) Video editing: https://mitsoul.org/ Diffusion and flow models are the cutting edge generative AI methods for images, videos, and many other data types. This course offers a comprehensive introduction for students and researchers seeking a deeper understanding of these models. Lectures will teach the core mathematical concepts necessary to understand diffusion models, including stochastic differential equations and the Fokker-Planck equation, and will provide a step-by-step explanation of the components of each model. Labs will accompany each lecture allowing students to gain practical, hands-on experience with the concepts learned in a guided manner. At the end of the class, students will have built a latent diffusion model from scratch – and along the way, will have gained hands-on experience with the mathematical toolbox of stochastic analysis that is useful in many other fields. This course is ideal for those who want to explore the frontiers of generative AI through a mix of theory and practice. We recommend some prior experience with probability theory and deep learning.