Excited to share that our paper "Moser Flow: Divergence-based Generative Modeling on Manifolds" won an Outstanding Paper Award at NeurIPS 2021!! blog.neurips.cc/2021/11/30/ann… Noam Rozen Aditya Grover Maximilian Nickel See thread for a short summary 👇

I've been fortunate to mentor an incredible AI resident, Keren Fuentes, with Maximilian Nickel & Levent Sagun ! I can't recommend this residency enough---it's a great way to bulk up AI/ML skills for a career in industry, and/or to prepare for PhD applications.

I just posted a new tutorial on amortized optimization! It covers foundations for learning to optimize and how they are key ingredients for VAEs, RL, meta-learning, and sparse coding with budding applications in DEQs, convex optimization, and beyond arxiv.org/abs/2202.00665 🧵

Huge congrats to Virginie Do, Sam Corbett-Davies, J. Atif, & N. Usunier for receiving the Outstanding Paper Award at AAAI-22 for "Online certification of preference-based fairness for personalized recommender systems". Amazing work! arxiv.org/abs/2104.14527 @MetaAI AAAI

In our new ICML paper, we introduce CNFM: Continuous Normalizing Flow Matching. A new approach for scalable CNFs on manifolds, the first generative model to scale to moderately high dimensional manifolds! arxiv.org/abs/2207.04711 (1/n)

Sharing our work on gradient-based learning of boundaries for probability distributions. Semi-Discrete Normalizing Flows through Differentiable Tessellation. arXiv: arxiv.org/abs/2203.06832 w/ Brandon Amos Maximilian Nickel

ICLR 2023 reviews are out! Incredible work by the entire community that went into this. 18500+ reviews and 99+% of submissions with 3+ reviews

This is probably my favorite graph from the #ICLR2023 review release. It's a heavy-tailed distribution that nicely shows 1) our anxiety-level around 10/23 😅 2) the amazing push of ACs, SACs & (emergency) reviewers to submit everything in time thru the bump at the end ❤️

**Flow Matching** (#ICLR2023 spotlight) offers a simple simulation-free method for training flow-based generative models, generalizing and improving upon diffusion models in training speed, sampling efficiency, and generation quality. Ricky T. Q. Chen Heli Ben-Hamu Maximilian Nickel Matt Le

Yaron Lipman Ricky T. Q. Chen Heli Ben-Hamu Maximilian Nickel Matt Le I wanted to check how Flow Matching-OT worked in practice and ... it is GREAT! It is very easy to implement and trains super fast. Here is a PyTorch demo in only a 100 lines of code: gist.github.com/francois-rozet…

Excited to share our new work on Riemannian Flow Matching. Unlike diffusion-based approaches, it’s - completely simulation-free on simple manifolds, - trivially applies to higher dimensions, - tractably generalizes to general geometries! arxiv.org/abs/2302.03660 w/ Yaron Lipman

📣 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

I'm very happy that I had the chance to collaborate with David Liu Maximilian Nickel (and twitterless Nico Usunier, as always!) on a #FAccT2023 paper on group fairness without demographics, a topic I particularly care about 😌 arxiv.org/abs/2305.11361 @MetaAI

I had a wonderful time attending and presenting ACM FAccT last week. To reflect on the experience and sum up what I learned, I wrote the following blog post, featuring data work, Algorithmic Impact Assessments, and hotpot (thanks to Angela Zhou!) medium.com/@david-liu/sev…

Excited to share our #icml2024 workshop on "Humans, Algorithmic-Decision Making, and Society"! See below for the amazing group of speakers and call for papers. Ana Stoica Fariba Karimi Manish Raghavan Milind Tambe Laura Weidinger Tina Eliassi Hoda Heidari

State of the are video generation with AI at Meta Movie Gen 😎 Brought to you by Flow Matching 🪭Fantastic work by Ishan Misra @ ECCV and team!