💚 tmlr-beyond-pdf.org/about

Don't forget this!

Following the success of the EurIPS and NeurIPS-Mexico City pilots in 2025, we are thrilled to announce two official NeurIPS 2026 satellite events for this year! These will be held in Paris, France and Atlanta, USA, respectively, running alongside the main venue in Sydney, Australia.

Ecole d'été de Peyresq sur les modèles génératifs et le transport optimal : www.gretsi.fr/peyresq2026 (cours en français). Date limite de candidature le 27 février

📣 Call for Blog Posts at #ICLR2026 @iclr_conf Following the success of the past iterations, we are opening the Call for Blog Posts 2026! iclr-blogposts.github.io/2026/about/#... Please retweet!

Now accepted at #NeurIPS2025 :)

Our work on the generalization of Flow Matching got an oral at Neurips ! Go see @quentinbertrand.bsky.social present it there :)

I wrote equations with @typst.app ... after (progressively) dropping latex for most things, I might also start (progressively) dropping the latex syntax for math equations!

One-day workshop on Diffusion models and Flow matching, October 24th at @ensdelyon.bsky.social Registration and call for contributions (short talk and poster) are open at gdr-iasis.cnrs.fr/reunions/mod...

Solenne Gaucher on 'statistical fairness' at #PAISS2025

Analyzing last year's UTMB split times (in french) home.heeere.com/teach/analyz...

Let's push for the obvious solution: Dear @neuripsconf.bsky.social ! Allow authors to present accepted papers at EurIPS instead of NeurIPS rather than just additionally. Likely, at least 500 papers would move to Copenhagen, problem solved.

Maybe there should also be an equivalent EurIPS workshop www.eurips.cc for people who cannot or don't want to travel there?

SKADA-Bench : Benchmarking Unsupervised Domain Adaptation Methods with Realistic Validation On Diverse Modalities, has been published published in TMLR today 🚀. It was a huge team effort to design (and publish) an open source fully reproducible DA benchmark 🧵1/n. openreview.net/forum?id=k9F...

New paper on the generalization of Flow Matching www.arxiv.org/abs/2506.03719 🤯 Why does flow matching generalize? Did you know that the flow matching target you're trying to learn *can only generate training points*? w @quentinbertrand.bsky.social @annegnx.bsky.social @remiemonet.bsky.social 👇👇👇

The second Keynote of CVPR@Paris is given by @dlarlus.bsky.social of @naverlabseurope.bsky.social on "Breaking the mold", generalization in computer vision.

🔴 [TUTO] : Comment économiser légalement PLUSIEURS CENTAINES D'EUROS sur son loyer chaque mois à Paris. Il suffit de faire respecter ✨l'encadrement des loyers✨ à son propriétaire. Petit tuto en thread pour vous montrer comment faire. Pour l'exemple on va prendre cet appart.

It was received quite enthusiastically here so time to share it again!!! Our #ICLR2025 blog post on Flow Matching was published yesterday : iclr-blogposts.github.io/2025/blog/co... My PhD student @annegnx.bsky.social will present it tomorrow in ICLR, 👉poster session 4, 3 pm, #549 in Hall 3/2B 👈

I had a blast giving a summer school on generative models at AI Hub Senegal, in particular flow matching, with @quentinbertrand.bsky.social and @remiemonet.bsky.social Our material is publicly available !!! github.com/QB3/SenHubIA... ensdelyon.bsky.social

Wow, this tutorial is really a tour de force! The one I had written is super "dumbed down" as a basic intro for beginners, but to really learn the material on an intermediate/advanced level, you should check out this post...

We have been reworking the Quickstart guide of POT to show multiple examples of OT with the unified API that facilitates access to OT value/plan/potentials. It allows to select regularization/unbalancedness/lowrank/Gaussian OT with just a few parameters. pythonot.github.io/master/auto_...

"Flow" won the Oscar for Best Animated Film ♡

Nice! Convert your latex (mostly equations) to @typst.app with MiTeX, two choices: - directly write latex in your typst typst.app/universe/pac... - migrate your equations (in your browser) mitex-rs.github.io/mitex/

Here is a first output of our project on Baby Cries. Better understanding your baby thanks to the site comprendrebebe.com/en/ @saintetienne.bsky.social, ENES, Lab. Hubert Curien, @chu-st-etienne.fr #axa

Voici un premier résultat de notre projet sur les pleurs de bébés. Mieux comprendre son bébé grace au site comprendrebebe.com @saintetienne.bsky.social, ENES, Lab. Hubert Curien, @chu-st-etienne.fr #axa

⚔️ One for all and all for one ⚔️ Efficient computation of PArtial Wasserstein distances on the Line (PAWL) is accepted to @iclr-conf.bsky.social Joint work with Laetitia Chapel: we introduce an 𝑂(𝑛 𝑙𝑜𝑔 𝑛) solver for partial Optimal Transport (OT) in 1D openreview.net/forum?id=kzE... 🧵 1/2

You like to writes you apps in Vue.js? You want to easily run a component as a small app? You want it to access the working directory and to use Python code too? Here is the (new) vuejspython github.com/twitwi/vuejs...

This review paper by @guillaume-garrigos.com on SGD-related algorithms is a fantastic resource, offering elegant, self-contained, and concise proofs in a single, accessible reference. arxiv.org/pdf/2301.11235

On the theoretical limit of gradient descent for Simple Recurrent Neural Networks with finite pre... Volodimir Mitarchuk, Rémi Emonet, Remi Eyraud, Amaury Habrard Action editor: Lechao Xiao https://openreview.net/forum?id=4c9UzDhg49 #automata #recurrent #deterministic

Titouan Vayer and I are organizing a one day workshop on optimal transport and machine learning in ENS Lyon on Feb. 17. Registration is free but mandatory. The incredible keynote speakers are Laetitia Chapel, Filippo Santambrogio and @brunolevy01.bsky.social. gdr-iasis.cnrs.fr/reunions/tra...

Today something crazy happened. POT has reached 1000 citations (total) 🤩🚀. Very proud to be part of a scientific community that acknowledges open source research software. Please continue to use, cite and contribute to POT ! Small🧵below for those interested pythonot.github.io

Daily animation.

Tutorial on flow matching today at @neuripsconf.bsky.social. I'll miss it 😿. The presenters released a very comprehensive document+code+library on flow matching arxiv.org/pdf/2412.06264 Need visuals and interactive animations? There is still our blog post dl.heeere.com/cfm (among others).

About Conditional Flow Matching (CFM) with **linear interpolation**. (1/3) In Optimal Transport (OT) terms, this CFM induces a probability path that corresponds to the (much non-optimal) independent coupling. That means every cat point is split and sent to every donut point.

This caption is a lie! 😉 We actually have a 4th visual in the blog post. Take a hot beverage ☕, play some 🎵 www.youtube.com/watch?v=3jfI... Welcome to the playground! The Conditional Flow Matching playground!

This blog post provides intuition and nice illustrations to understand normalizing flows and flow matching techniques! w. @annegnx.bsky.social, Ségolène Martin, @mathurinmassias.bsky.social, and @remiemonet.bsky.social (the king for figures)

Anne Gagneux, Ségolène Martin, @quentinbertrand.bsky.social Remi Emonet and I wrote a tutorial blog post on flow matching: dl.heeere.com/conditional-... with lots of illustrations and intuition! We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423