Reposted by Rémi EmonetGabriel Peyré @gabrielpeyre.bsky.social · 07/08/2026The Mathematical Nexus brings together 800 animated vignettes and 140 accompanying Python notebooks, encompassing most of the mathematical content I have shared on social media. www.gpeyre.com/mathematical... 26718
Reposted by Rémi Emonetaboisbunon.bsky.social @aboisbunon.bsky.social · 04/08/2026I'm happy to announce the #NeurIPS2026 workshop TS-LIMITS (Generalization for Time Series in Tight Settings: Latency, Inference, Memory, prIvacy and susTainability), which will be hosted in Paris, France 🇫🇷, Dec 12–13 2026! 🔗 Check out details and call for papers: ts-limits.github.io 096
Rémi Emonet @remiemonet.bsky.social · 04/08/2026This is not prepackaged, so it would take some work but one could go for OSM data (that may contain height sometimes, or number of levels) and possibly combining, in France, with Lidar HD from IGN. 110
Reposted by Rémi EmonetMathurin Massias @mathurinmassias.bsky.social · 08/07/2026thanks to @josephsalmon.sigmoid.social.ap.brid.gy my inkscape mentor + @remiemonet.bsky.social the HTML/slidev/JS GOAT Concatenated slides are now at icml.cc/media/icml-2... + on the project websiteicml.cc 121
Reposted by Rémi EmonetQuentin Bertrand @quentinbertrand.bsky.social · 08/07/2026We had a blast discussing memorization, generalization, and beyond for diffusion models at our @icml tutorial with @mathurinmassias.bsky.social ! Slides & material: memorization-generalization.github.io 042
Rémi Emonet @remiemonet.bsky.social · 28/03/2026💚 tmlr-beyond-pdf.org/abouttmlr-beyond-pdf.orgAbout | TMLR Beyond PDFTMLR Beyond PDFs 021
Reposted by Rémi EmonetNeurIPS Conference @neuripsconf.bsky.social · 23/03/2026Following 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.neurips.cc2025 ConferenceThe Thirty-Ninth Annual Conference on Neural Information Processing Systems 27017
Reposted by Rémi EmonetMathurin Massias @mathurinmassias.bsky.social · 12/12/2025Ecole 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 févriergretsi.fr GRETSI : 20ème École d'Été en Traitement du Signal et des Images 096
Reposted by Rémi Emonetsophie-xhonneux.bsky.social @sophie-xhonneux.bsky.social · 22/09/2025📣 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!abs-0.twimg.com 1168
Reposted by Rémi EmonetSamuel Vaiter @samuelvaiter.com · 29/09/2025Now accepted at #NeurIPS2025 :) 2186
Reposted by Rémi EmonetMathurin Massias @mathurinmassias.bsky.social · 19/09/2025Our work on the generalization of Flow Matching got an oral at Neurips ! Go see @quentinbertrand.bsky.social present it there :) 3253
Rémi Emonet @remiemonet.bsky.social · 04/09/2025It is more a full replacement of LaTeX than an integration (but it seems there is some kind of integration possible: you can use latex math syntax in typst if needed). 110
Rémi Emonet @remiemonet.bsky.social · 04/09/2025I find LaTeX is cumbersome (although Turing complete?) and slow, especially with the well known online service, while typst is redesigned from scratch and can run even fully in web browser, no install, no server, if needed. I was afraid I would miss the equation syntax but I'm not sure I will. 110
Rémi Emonet @remiemonet.bsky.social · 04/09/2025I wrote equations with @typst.app ... after (progressively) dropping latex for most things, I might also start (progressively) dropping the latex syntax for math equations! 110
Reposted by Rémi EmonetMathurin Massias @mathurinmassias.bsky.social · 04/09/2025One-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...gdr-iasis.cnrs.frModèles génératifs : diffusion, flow matching et leurs applications - GdR IASISLes modèles génératifs ont connu de récentes avancées spectaculaires, au point que leurs dernières versions sont désormais capables de produire des images et du texte synthétiques presque indiscernabl... 2107
Reposted by Rémi EmonetDiane Larlus @dlarlus.bsky.social · 03/09/2025Solenne Gaucher on 'statistical fairness' at #PAISS2025 172
Rémi Emonet @remiemonet.bsky.social · 29/08/2025Analyzing last year's UTMB split times (in french) home.heeere.com/teach/analyz... 000
Reposted by Rémi EmonetChristoph Lampert (MLCV@ISTA) @mlcv-at-ista.bsky.social · 28/08/2025Let'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. 25615
Rémi Emonet @remiemonet.bsky.social · 08/08/2025Maybe there should also be an equivalent EurIPS workshop www.eurips.cc for people who cannot or don't want to travel there?eurips.ccEurIPS Copenhagen 2025 - A NeurIPS-endorsed conference in EuropeA NeurIPS-endorsed conference in Europe held in Copenhagen, Denmark 041
Reposted by Rémi EmonetRémi Flamary @rflamary.bsky.social · 29/07/2025SKADA-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...openreview.netSKADA-Bench: Benchmarking Unsupervised Domain Adaptation Methods...Unsupervised Domain Adaptation (DA) consists of adapting a model trained on a labeled source domain to perform well on an unlabeled target domain with some data distribution shift. While many... 1167
Reposted by Rémi EmonetMathurin Massias @mathurinmassias.bsky.social · 18/06/2025New 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 👇👇👇 25617
Reposted by Rémi EmonetChristian Wolf @chriswolfvision.bsky.social · 06/06/2025The second Keynote of CVPR@Paris is given by @dlarlus.bsky.social of @naverlabseurope.bsky.social on "Breaking the mold", generalization in computer vision. 2223
Reposted by Rémi EmonetCamille @k1000journaliste.bsky.social · 10/05/2025🔴 [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. 431232764
Reposted by Rémi EmonetMathurin Massias @mathurinmassias.bsky.social · 24/04/2025It 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 👈iclr-blogposts.github.ioA Visual Dive into Conditional Flow Matching | ICLR Blogposts 2025Conditional flow matching (CFM) was introduced by three simultaneous papers at ICLR 2023, through different approaches (conditional matching, rectifying flows and stochastic interpolants). <br/> The m... 1106
Reposted by Rémi EmonetMathurin Massias @mathurinmassias.bsky.social · 14/04/2025I 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 1173
Reposted by Rémi EmonetScott H. Hawley @drscotthawley.bsky.social · 25/03/2025Wow, 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... 143
Reposted by Rémi EmonetRémi Flamary @rflamary.bsky.social · 26/03/2025We 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_... 03211
Reposted by Rémi EmonetCatsuka @catsuka.bsky.social · 03/03/2025"Flow" won the Oscar for Best Animated Film ♡ 155182183252
Rémi Emonet @remiemonet.bsky.social · 20/02/2025Combining with latexocr (pip install pix2tex) gives something not bad at all. 000
Rémi Emonet @remiemonet.bsky.social · 20/02/2025Nice! 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/ 101
Rémi Emonet @remiemonet.bsky.social · 18/02/2025An ambitious project lead by @nicolasmathevon.bsky.social 000
Rémi Emonet @remiemonet.bsky.social · 18/02/2025Un projet ambitieux porté par @nicolasmathevon.bsky.social 000
Rémi Emonet @remiemonet.bsky.social · 18/02/2025Here 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 #axacomprendrebebe.comUnderstanding BabyExplore ENES Lab's research on baby cries and gain insights into your child's needs with scientifically reliable information. 132
Rémi Emonet @remiemonet.bsky.social · 18/02/2025Voici 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 #axacomprendrebebe.comComprendre son bébéDécouvrez les recherches de l'ENES Lab sur les pleurs des bébés et apprenez à mieux comprendre votre enfant grâce à des informations scientifiques fiables. 1115
Reposted by Rémi EmonetRomain Tavenard @rtavenar.bsky.social · 04/02/2025⚔️ 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 1138
Rémi Emonet @remiemonet.bsky.social · 04/02/2025You can also use it just to host your videos (e.g. on a raspberrypi). pip install vuejspython cd videos/ vjspy --host 0.0.0.0 :serve-videos 000
Rémi Emonet @remiemonet.bsky.social · 04/02/2025You 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...github.comGitHub - twitwi/vuejs-python: Vue.js component runner with filesystem and python accessVue.js component runner with filesystem and python access - twitwi/vuejs-python 101
Reposted by Rémi EmonetGabriel Peyré @gabrielpeyre.bsky.social · 29/01/2025This 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 118940
Reposted by Rémi EmonetTMLR Published Papers @tmlr-pub.bsky.social · 31/12/2024On 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 openreview.net/forum?id=4c9UzDhg49 #automata #recurrent #deterministic 031
Reposted by Rémi EmonetRémi Flamary @rflamary.bsky.social · 17/01/2025Titouan 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...gdr-iasis.cnrs.frTransport optimal et ses applications en machine learning et analyse de données - GdR IASISPour les journées scientifiques organisées en 2025 : les inscriptions seront ouvertes à partir de mi-janvier et les demandes de prise en charge de missions seront traitées à partir du 27 janvier. En r... 21812
Reposted by Rémi EmonetRémi Flamary @rflamary.bsky.social · 13/12/2024Today 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 14912
Rémi Emonet @remiemonet.bsky.social · 10/12/2024Ok. Thank you. I'll investigate further at some point. 000
Rémi Emonet @remiemonet.bsky.social · 10/12/2024Tutorial 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).arxiv.org 042
Rémi Emonet @remiemonet.bsky.social · 10/12/2024Yes, indeed. Do you have any pointers on 2D or more dimensions? E.g., is there a good equivalent (under which constraints) of "paths do no cross"? 100
Rémi Emonet @remiemonet.bsky.social · 09/12/2024To better grasp what this CFM mapping/corresp. contains, let's move points linearly and at a regular speed (from source cat location to target donut loc.). We get a different probability path that looks much more like OT. This idea is used in the rectified flow approach github.com/gnobitab/Rec... 100
Rémi Emonet @remiemonet.bsky.social · 09/12/2024It is still not optimal from the OT perspective (same path as before). Indeed, the points do not move in a constant-speed manner (as they would do with optimal transport). However, we see that the mapping between cat and donut points has a strong spatial coherence (colors don't get shuffled). 100
Rémi Emonet @remiemonet.bsky.social · 09/12/2024Now, we look at the mapping/correspondance that is induced by CFM, a mapping between cat points and donut points. To get a clearer view, let's map a stripped cat to a donut. Color encodes the initial position of the points on the cat. 100
