Check out our new Flow Matching guide and codebase! It also includes an extended explanation of Generator Matching with more examples! arxiv.org/abs/2412.06264

Want to learn continuous & discrete Flow Matching? We've just released: 📙 A guide covering Flow Matching basics & advanced methods arxiv.org/abs/2412.06264. 💻 An open source codebase with image & text examples github.com/facebookresear…. 🗣️ A Flow Matching tutorial #NeurIPS2024.

Our **Flow Matching Tutorial** from #NeurIPS2024 is now publicly available: neurips.cc/virtual/2024/t… Heli Ben-Hamu Ricky T. Q. Chen

New paper (and #ICLR2025 Oral :)): ProtComposer: Compositional Protein Structure Generation with 3D Ellipsoids arxiv.org/abs/2503.05025 Condition on your 3D layout (of ellipsoids) to generate proteins like this or to get better designability/diversity/novelty tradeoffs. 1/6

Course material for an MIT class "Introduction to Flow Matching and Diffusion Models", looks great if you want a principled and hands on understanding of diffusion models/flow matching

What if you could build any kind of generative AI model using one universal tool? Peter Holderrieth, an @mit PhD student in the lab of @aihealthmit PI Tommi Jaakkola, explains what the future of genAI could look like in ~2 minutes!

Generator Matching is a unifying framework for Markov processes beyond diffusion. This framework allows jumps to update states, and naturally enables combinations of flows and jumps via a Markov superposition of stochastic processes. Oral by Peter Holderrieth Sat 3:30pm.

Congratulations to Peter Holderrieth Michael Albergo @ICLR2025 and Tommi Jaakkola for winning the best paper award for their work entitled "LEAPS: A discrete neural sampler via locally equivariant networks" at this year's Frontiers in Probabilistic Inference workshop #ICLR2025!

#FPIworkshop best paper award goes to Peter Holderrieth Michael Albergo and Tommi Jaakkola. Congrats and great talk Peter!