Física y Ciencia
423 posts
🚀MIT Flow Matching and Diffusion Lecture 2026 Released (diffusion.csail.mit.edu)! We just released our new MIT 2026 course on flow matching and diffusion models! We teach the full stack of modern AI image, video, protein generators - theory and practice. We include: 📺 Videos: Step-by-step derivations. 📝 Notes: Mathematically self-contained lecture notes 💻 Coding: Hands-on exercises for every component We fully improved last years’ iteration and added new topics: latent spaces, diffusion transformers, building language models with discrete diffusion models. Everything is available here: diffusion.csail.mit.edu A huge thanks to Tommi Jaakkola for his support in making this class possible and Ashay Athalye (MIT SOUL) for the incredible production! Was fun to do this with @RShprints! #MachineLearning #GenerativeAI #MIT #DiffusionModels #AI
Physicist Yakir Aharonov argues that the standard story of quantum mechanics is wrong, proposing a time-symmetric “two-state vector” view in which reality is defined by wavefunctions from both past and future. He explains weak measurements (information without collapse), nonlocal dynamics behind interference, and phenomena like the “quantum Cheshire Cat.” Aharonov recounts the birth of the Aharonov–Bohm effect, why gauge potentials mislead about locality, and how pre and post-selection restore causal insight without determinism. He shares memories of Bohm, Heisenberg, and Feynman, touches on gravitational and non-Abelian AB analogs, and lays out why a clear narrative—not just math—is essential to understanding quantum theory.
