📣 A new #ICML2023 paper investigates the Kinetic Energy of Gaussian Probability Paths which are key in training diffusion/flow models. A surprising takeaway: In high dimensions *linear* paths (Cond-OT) are Kinetic Optimal! Led by Neta Shaul w/ Ricky T. Q. Chen Matt Le Maximilian Nickel

A new (and comprehensive) Flow Matching guide and codebase released! Join us tomorrow at 9:30AM NeurIPS Conference for the FM tutorial to hear more... arxiv.org/abs/2412.06264 github.com/facebookresear…

We are presenting 3 orals and 1 spotlight at #ICLR2025 on two primary topics: On generalizing the data-driven flow matching algorithm to jump processes, arbitrary discrete corruption processes, and beyond. And on highly scalable algorithms for reward-driven learning settings.

Had an absolute blast presenting at #ICLR2025! Thanks to everyone who came to visit my poster🙌 Special shoutout to Scott H. Hawley for taking a last-minute photo 📸

Against conventional wisdom, I will be giving a talk with particular focus on the "how" and the various intricacies of applying stochastic control for generative modeling. Mon 9:50am Hall 1 Apex #ICLR2025 Also check out the other talks at delta-workshop.github.io!

🚀 Excited to share our latest work led by @itaigat! We incorporate corrector sampling into autoregressive models for text generation — achieving significant gains in code generation performance. Check it out 👇

Difference Transition Matching (DTM) process is so simple to Illustrate, you can calculate it on a whiteboard! At each step: Draw all lines connecting source and target (shaded) ⬇️ List those intersecting with the current state (yellow) ⬇️ Sample a line from the list (green)

If you're curious to dive deeper into Transition Matching (TM)✨🔍, a great starting point is understanding the similarities and differences between 𝐃𝐢𝐟𝐟𝐞𝐫𝐞𝐧𝐜𝐞 𝐓𝐫𝐚𝐧𝐬𝐢𝐭𝐢𝐨𝐧 𝐌𝐚𝐭𝐜𝐡𝐢𝐧𝐠 (𝐃𝐓𝐌) and Flow Matching (FM)💡.