Check out our recent work on non-autoregressive music generation. Code and models are open-sourced. 🧲🧲🧲 We will present this work in ICLR2024.

Stable diffusion 3 uses Flow Matching! An amazing milestone ! Read more about flow matching here: arxiv.org/abs/2210.02747 Yaron Lipman Ricky T. Q. Chen Maximilian Nickel Matt Le

Thanks for sharing our work! joint work with Omri Puny, Itai Gat, Brian Karrer, Uriel Singer and Yaron Lipman

Party time! The SD3 paper made it to arxiv: arxiv.org/abs/2403.03206 Key takeaways: - flow matching is very nice. - back to work with Patrick Esser and a fantastic team ♥️ The paper is full of details on improved flow matching, scaling and engineering. Enjoy!

🔥New Video🔥 Flow matching (not classic diffusion) is the basis for state-of-the-art text to image models, like Stable Diffusion 3. Here is how it works: youtu.be/7NNxK3CqaDk

Happy to share that this work (w/ Yaron Lipman) was awarded an Outstanding Paper Honorable Mention at ICLR 2024. Come see me talk about "Flow Matching on General Geometries" tomorrow in the afternoon orals session!

Happy to share our ICLR 2024 paper, Approximately Piecewise E(3) Equivariant Point Networks. For those attending ICLR, I'll be presenting it today between 4:30 to 6:30 at #96, Halle B. For a quick overview, check out our 5-minute video: youtube.com/watch?v=gHqQMa…

Presenting M-SDF this week at #CVPR2024 ! Come to our poster on Wednesday morning to say hi and learn/hear about training Flow Matching generative model with our new 3D representation

Announcing our new model for materials! FlowMM... - Generates stable & novel materials efficiently - Predicts crystal structure accurately - Generalizes Riemannian Flow Matching to point clouds w/ periodic boundaries arxiv.org/abs/2406.04713 Ricky T. Q. Chen Anuroop Sriram Brandon Wood

Thank you for having me! Had a great time presenting at #GeMSS24!

𝑮𝒐𝒊𝒏𝒈 𝒘𝒊𝒕𝒉 𝒕𝒉𝒆 𝒇𝒍𝒐𝒘 at the Generative AI summer school #GeMSS2024 at TU Eindhoven ! What a wonderful, well-explained talk on Flow Matching by the brilliant Heli Ben-Hamu 🤩

Excited to share Discrete Flow Matching! A discrete flow framework that yields state-of-the-art non-autoregressive modeling. E.g., on code tasks (Pass@1): HumanEval 6.7/11.6, MBPP 6.7/13.1 w/ Tal Remez, Neta Shaul, Felix Kreuk, Ricky T. Q. Chen, Gabriel Synnaeve, Yossi Adi, Yaron Lipman

I'll be presenting D-Flow in the upcoming poster session at 11:30. Come say hi at poster #500! #ICML2024

It's time for some GRaM Workshop at ICML 2024 workshop updates happening at #ICML2024 on the 27th of July. We have a great list of invited speakers and panelists. We have Rose Yu Rose Yu , Phillip Isola Phillip Isola , Nina Mialone Nina Miolane , Joey Bose Joey Bose , Zahra Kadkhodaie

Excited to prepare for #GenU2024! 🎉 Thrilled to welcome an incredible lineup of speakers again this year! genu.ai/2024/ Wouter Boomsma Pierre-Alexandre Mattei Ole Winther

New paper! We cast reward fine-tuning as stochastic control. 1. We prove that a specific noise schedule *must* be used for fine-tuning. 2. We propose a novel algorithm that is significantly better than the adjoint method*. (*this is an insane claim) arxiv.org/abs/2409.08861