Interested in learning more about both flow matching and diffusion models from first principles? Check out our new publicly available course! Was a wonderful experience bringing this to life with Peter Holderrieth! We hope you enjoy :)

Tomorrow in our reading group we will discuss "Action-Minimization Meets Generative Modeling: Efficient Transition Path Sampling with the Onsager-Machlup Functional" arxiv.org/abs/2504.18506 On zoom 9am PT / 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeaking

In 24h on zoom (Tue 12pm ET) Saro Passaro Gabriele Corso Jeremy Wohlwend will present Boltz-2! bit.ly/boltz2-pdf Structure models and careful affinity data handling result in an affinity predictor approaching FEP accuracy at 1000x the speed. Luma: lu.ma/4bpuwbsr

Monday Starkly Speaking: we understand a core diffusion model ingredient better - classifier free guidance. Via "Classifier-Free Guidance: From High-Dimensional Analysis to Generalized Guidance Forms" arxiv.org/abs/2502.07849 On Zoom 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeaking

Starkly Speaking tomorrow: Brandon Wood will present "UMA: A Family of Universal Models for Atoms" ai.meta.com/research/publi… Join us on Zoom 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeaking

Tomorrow we discuss diffusion models for sampling unnormalized densities "Adjoint Sampling: Highly Scalable Diffusion Samplers via Adjoint Matching" arxiv.org/abs/2504.11713 Join us on zoom at 9am PT / 12pm ET / 6pm CEST: portal.valencelabs.com/starklyspeaking

🚀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:

Great seeing Peter and Ron bring the course to life again this year! Check the notes out if you haven't already :)