🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Join us tomorrow, 9:30 am at East Exhibition Hall C! neurips.cc/virtual/2024/t…

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.

Flow Matching tutorial slides: drive.google.com/file/d/1-QKAT8…

We're presenting FoldFlow-2 right now! Come check it out in West Ballroom poster # 7210 Alex Tong Mila - Institut québécois d'IA Michael Bronstein Guillaume Huguet @FatrasKilian

📢 Super excited to announce the first ever Frontiers of Probabilistic Inference: Learning meets Sampling workshop at #ICLR2025 ICLR 2026! 🔗 website: sites.google.com/view/fpiworksh… We invite submissions on sampling, Bayesian inference, accelerating sampling in AI4Science,

📢 My team at Meta is hiring visiting PhD students from CMU, UW, Berkeley, and NYU! We study core ML, optimization, amortization, transport, flows, and control for modeling and interacting with complex systems. Please apply here and message me: metacareers.com/jobs/395022364…

Flow matching can transform one distribution to another. So why do text-to-image models map noise to images instead of directly mapping text to images? Wouldn't it be cool to directly connect modalities together? CrossFlow accomplishes exactly that! cross-flow.github.io

Looking for strong candidates for a *postdoc* position with our team at FAIR NYC! We develop foundational methods for generative modeling at scale. If you're interested and familiar with some of our works, please reach out via email. metacareers.com/jobs/145969190…

🧠 Can we train models to manipulate NN weights? Join us at the first Weight Space Learning Workshop @ICLR_conf to explore learning directly from neural network parameters! 📝 CfP: weight-space-learning.github.io/cfp/ ⏰ Deadline: Feb 4, 2025 🌐 More Info: weight-space-learning.github.io

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

On monday in our reading group we discuss "Flow Matching with General Discrete Paths: A Kinetic-Optimal Perspective" arxiv.org/abs/2412.03487 With Neta Shaul. Join on zoom on Monday at 9am PT / 12pm ET / 6pm CET: portal.valencelabs.com/logg

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.

📣I'll be at the poster session with our follow-up on Discrete Flow Matching. We derive a closed-form solution to the kinetic optimal problem for conditional velocity on discrete spaces. Into flow models? come chat! 💬 🗓Poster: Sat 10am (#191), 🎤Oral: Sat 3:30pm (6E) #ICLR2025

Padding in our non-AR sequence models? Yuck. 🙅 👉 Instead of unmasking, our new work *Edit Flows* perform iterative refinements via position-relative inserts and deletes, operations naturally suited for variable-length sequence generation. Easily better than using mask tokens.

Excited to share our recent work on corrector sampling in language models! A new sampling method that mitigates error accumulation by iteratively revisiting tokens in a window of previously generated text. With: Neta Shaul Uriel Singer Yaron Lipman Link: arxiv.org/abs/2506.06215

Adjoint-based diffusion samplers have simple & scalable objectives w/o impt weight complication. Like many, though, they solve degenerate Schrödinger bridges, despite all being SB-inspired. 📢 Proudly introduce #Adjoint #Schrödinger #Bridge #Sampler, a full SB-based sampler that

[1/n] New paper alert! 🚀 Excited to introduce 𝐓𝐫𝐚𝐧𝐬𝐢𝐭𝐢𝐨𝐧 𝐌𝐚𝐭𝐜𝐡𝐢𝐧𝐠 (𝐓𝐌)! We're replacing short-timestep kernels from Flow Matching/Diffusion with... a generative model🤯, achieving SOTA text-2-image generation! Uriel Singer Itai Gat Yaron Lipman

**Transition Matching** is a new iterative generative paradigm using Flow Matching or AR models to transition between generation intermediate states, leading to an improved generation quality and speed!

Excited to release AlgoTune!! It's a benchmark and coding agent for optimizing the runtime of numerical code 🚀 algotune.io 📚 algotune.io/paper.pdf 🤖 github.com/oripress/AlgoT… with Ofir Press Ori Press Patrick Kidger Bartolomeo Stellato Arman Zharmagambetov & many others 🧵

Somewhat dissatisfying that the predominant usage of "world model" is restricted to videos. Beyond just photons, a true foundation model of the world should model arbitrary physics. Very excited to introduce PhysiX co-led by my students Tung Nguyen , Arsh Koneru, Shufan (Jack) Li .