Lecture notes: https://diffusion.csail.mit.edu/docs/lecture-notes.pdf
Slides: https://diffusion.csail.mit.edu/docs/slides_lecture_4.pdf
Course website: https://diffusion.csail.mit.edu/
Code exercises: https://diffusion.csail.mit.edu/
Next video: https://www.youtube.com/watch?v=7tsCN2hRBMg&list=PL57nT7tSGAAUDnli1LhTOoCxlEPGS19vH&index=6
Playlist: https://www.youtube.com/watch?v=GCoP2w-Cqtg&list=PL57nT7tSGAAUDnli1LhTOoCxlEPGS19vH&index=1
Class: MIT 6.S184: Generative AI with Stochastic Differential Equations
Lecture 01: Flow and Diffusion Models
Instructors: Peter Holderrieth, Ezra Erives
Reward fine-tuning: Carles Domingo-Enrich (https://cdenrich.github.io/)
Video editing: https://mitsoul.org/
Diffusion and flow-based models have become the state of the art algorithms for generative AI across a wide range of data modalities, including images, videos, shapes, molecules, music, and more! This MIT computer science course aims to build up the mathematical framework underlying these models from first principles. At the end of the class, students will have built a toy image diffusion model from scratch, and along the way, will have gained hands-on experience with the mathematical toolbox of stochastic differential equations that is useful in many other fields. This course is ideal for students who want to develop a principled understanding of the theory and practice of generative AI.