Mathurin Massias @mathurinmassias.bsky.social · 24/08/2026Having fun with 2D Gaussian visualization : mathurinm.github.io/gaussian/mathurinm.github.io2D Gaussian Visualizer 082
Mathurin Massias @mathurinmassias.bsky.social · 21/07/2026I organize a 1 day workshop on Generative modelling @ENS Lyon, October 9th Call for oral/poster contributions is open; details at gdr-iasis.cnrs.fr/reunions/mod...gdr-iasis.cnrs.frModèles génératifs : diffusion, flow matching - GdR IASISLes demandes de prise en charge de missions par le GdR IASIS doivent parvenir à la gestionnaire du GdR avant le 25 septembre. Les modèles génératifs ont connu de récentes avancées spectaculaires, au p... 0128
Mathurin Massias @mathurinmassias.bsky.social · 10/07/2026Automatic captioning during talks at ICML is a neverending source of joy for me : can't wait to go back home to start working on these new "ultra agressive models" and "discrete infusion" 030
Reposted by Mathurin MassiasQuentin 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
Mathurin Massias @mathurinmassias.bsky.social · 07/07/2026Slides for our ICML tutorial on Memorization and Generalization of Diffusion and Flow Matching Models are now available ! 🌀 memorization-generalization.github.io @quentinbertrand.bsky.socialmemorization-generalization.github.ioICML 2026 Tutorial - Generalization and Memorization in Flow Matching and Diffusion 22212
Reposted by Mathurin Massiaslebellig @lebellig.bsky.social · 03/07/2026Heading to #ICML2026 🇰🇷 and interested in diffusion models, flow matching, and their generalization capabilities? Don't miss the excellent tutorial by @mathurinmassias.bsky.social and @quentinbertrand.bsky.social on Monday! 📍 Hall D1 🗓️ Monday, July 6 🕘 9:00–11:30 AM Details: icml.cc/virtual/2026... 2116
Reposted by Mathurin Massiaslebellig @lebellig.bsky.social · 28/04/2026My PhD thesis manuscript will be available in the coming months, but I’ve written two blog posts based on the related work chapter: 1. Generative modeling with flow-based models 🪚 2. Data-translation with flow and diffusion bridges 🔨 Open to feedback and discussions! lebellig.github.io/blog/ 1357
Reposted by Mathurin MassiasNicolas Audebert @nshaud.bsky.social · 28/04/2026Georges is too humble to mention he brilliantly defended his PhD two weeks ago. 🎉 Check out his blog and look out for the manuscript, he has written the best recap on flow matching I have ever read. ⤵️ 0152
Reposted by Mathurin Massiaslebellig @lebellig.bsky.social · 28/04/2026Delighted to have successfully defended my PhD thesis on "Generative models for Earth Observation, from denoising to domain adaptation" 🪴 This wouldn’t have been possible without the support of my colleagues, my PhD advisor, and my family and friends. Thank you all! 4275
Reposted by Mathurin MassiasICML Conference @icmlconf.bsky.social · 02/04/2026Announcing the #ICML2026 tutorials! All ten tutorials will be presented the first day of the conference, Monday July 6. Read the blog post for more details on the selection process! blog.icml.cc/2026/04/02/a... 0138
Mathurin Massias @mathurinmassias.bsky.social · 16/02/2026With @quentinbertrand.bsky.social we have one offer for a Marie Sklodowska-Curie postdoctoral fellowships at Inria, to work on generative models : www.inria.fr/en/marie-skl... contact me if interested! RT appreciated ❤️inria.frMarie Skłodowska-Curie Actions Postdoctoral Fellowships: 2026 Inria Training Programme & Hosting OffersInria proposes a full-fledged training programme for Marie Skłodowska-Curie Actions Postdoctoral Fellowships (MSCA PF) candidates, as well as numerous project hosting offers. This will allow you, thro... 032
Reposted by Mathurin MassiasRémi Flamary @rflamary.bsky.social · 06/02/2026We are recruiting four positions connected to Machine Learning, Statistical Learning, and AI for Science in the Applied Mathematics department at École polytechnique. Join our vibrant community at IP Paris and Hi! Paris IA center. List below🧵 tinyurl.com/3jpw9t26tinyurl.comCalliopé 11218
Mathurin Massias @mathurinmassias.bsky.social · 05/02/2026There is an Associate Professor position in CS at ENS Lyon, with potential integration in my team, starting in sept 2026: DM me in interested! Details at www.ens-lyon.fr/LIP/images/P...ens-lyon.fr 078
Reposted by Mathurin MassiasSkrub @skrub-data.bsky.social · 05/02/2026Did you know that the skrub Data Ops support Optuna as backend to run hyperparameter search? It's as easy as writing "backend='optuna'": this will set up a default Optuna study (and the TPE sampler) to replace the standard random sampler. 142
Reposted by Mathurin MassiasSamuel Vaiter @samuelvaiter.com · 15/12/2025Les inscriptions aux journées MODE 2026 à Nice sont désormais ouvertes. Elles se dérouleront du 18 au 20 mars à l'Hôtel Saint-Paul. Les inscriptions sont ouvertes jusqu'au 1 mars (majoration > 9/02). La deadline pour soumettre une communication est le **15 janvier**. 157
Reposted by Mathurin MassiasGRETSI info (Laurent DUVAL, admin.) @gretsi-info.bsky.social · 16/12/2025L'école d'été #Peyresq2026 #GRETSI portera sur le thème "Modèles génératifs et transport optimal" du 21 au 27 juin 2026 gretsi.fr/peyresq2026 Inscription du 18 décembre 2025 au 27 février 2026gretsi.fr GRETSI : 20ème École d'Été en Traitement du Signal et des Images 022
Mathurin 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 Mathurin MassiasRémi Flamary @rflamary.bsky.social · 12/12/2025Openreview opened the door to continuous and major revisions that nobody has time to check properly. I think that we should come back to short one pdf page replies to reviews. It would mean having decisions quicker so that we actually have time to work on papers before resubmitting them. 1197
Reposted by Mathurin MassiasMargot Giacinti @margotgiacinti.bsky.social · 08/12/2025[Concours CNRS] Si comme moi, vous attendiez et que vous n'aviez pas vu passer ça. Ouverture du concours : (a priori) aujourd'hui 8/12 Dépôt des candidatures : jusqu'au 7 janvier 048
Reposted by Mathurin MassiasGRETSI info (Laurent DUVAL, admin.) @gretsi-info.bsky.social · 21/11/2025Une raison de plus de vous abonner à la chaîne YouTube du colloque #GRETSI : "Transport optimal, de Monge à l’apprentissage profond", conférence plénière de Julie Delon au colloque #GRETSI2025 www.youtube.com/watch?v=ujYS...youtube.comPlénière de Julie DelonYouTube video by GRETSI 075
Reposted by Mathurin MassiasNicolas Keriven @nicolaskeriven.bsky.social · 06/11/2025I have several offers for Master internships / PhDs on graph ML funded by ERC MALAGA for 2026. Don't hesitate to contact me to apply! All infos here: nkeriven.github.io/malaga/nkeriven.github.ioMALAGA: Reinventing the Theory of Machine Learning on Large Graphs (ERC StG) 088
Reposted by Mathurin MassiasMarco Z @ocramz.bsky.social · 05/11/2025The JMLR story and operating model should be widely known in academia as a clear success story for full open access. I have friends in the humanities and pure sciences that have no clue this is even possible 1137
Mathurin Massias @mathurinmassias.bsky.social · 05/11/2025🌀🌀🌀New paper on the generation phases of Flow Matching arxiv.org/abs/2510.24830 Are FM & diffusion models nothing else than denoisers at every noise level? In theory yes, *if trained optimally*. But in practice, do all noise level equally matter? with @annegnx.bsky.social, S Martin & R Gribonval 1204
Mathurin Massias @mathurinmassias.bsky.social · 24/10/2025Kickstarting our workshop on Flow matching and Diffusion with a talk by Eric Vanden Eijnden on how to optimize learning and sampling in Stochastic Interpolants! Broadcast available at gdr-iasis.cnrs.fr/reunions/mod... 1155
Reposted by Mathurin MassiasTony S.F. @tonysf.bsky.social · 19/09/2025My paper on Generalized Gradient Norm Clipping & Non-Euclidean (L0, L1)-Smoothness (together with collaborators from EPFL) was accepted as an oral at NeurIPS! We extend the theory for our Scion algorithm to include gradient clipping. Read about it here arxiv.org/abs/2506.01913 1163
Mathurin 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
Reposted by Mathurin MassiasPierre Marion @pierremarion.bsky.social · 16/09/2025🔥 Excited to announce the Workshop on the Principles of Generative Models at @euripsconf.bsky.social (the European conference parallel to NeurIPS 2025) 🇩🇰 Dec 6–7, Copenhagen 📝 Deadline for contributions: Oct 17 🔗 Website: sites.google.com/view/prigm-e...sites.google.comPriGM@EurIPS2025Workshop summary Machine learning theory has long focused on classical supervised learning settings, where a model is trained on input–label pairs drawn from a well-defined data distribution, with the... 052
Mathurin 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
Mathurin 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
Mathurin 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 Mathurin MassiasSamuel Vaiter @samuelvaiter.com · 15/04/2025The proximal operator generalizes projection in convex optimization. It converts minimisers to fixed points. It is at the core of nonsmooth splitting methods and was first introduced by Jean-Jacques Moreau in 1965. www.numdam.org/article/BSMF... 0203
Reposted by Mathurin MassiasJulian Tachella @tachellajulian.bsky.social · 14/04/2025🚢🚢 deepinv v0.3.0 is here, with many new features! 🚢 🚢 Our passionate team of contributors keeps shipping more exciting tools! Deepinverse (deepinv.github.io) is a library for solving imaging inverse problems with deep learning.deepinv.github.ioRedirecting to https://deepinv.github.io/deepinv/ 1114
Mathurin 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 Mathurin MassiasScott 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 Mathurin MassiasELLIS @ellis.eu · 28/02/2025🎓🌞 Join the PhD course on Theoretical Foundations of Machine Learning at 🇮🇹 ELLIS Unit Genoa, June 23-27, 2025, hosted by Machine Learning Genoa Center. 🗓️ Apply by: March 16, 2025 📍 University of Genoa (in-person only) 💡 More info: malga.unige.it/education/sc...malga.unige.itTFMLUniGe ¦ MaLGa 1134
Mathurin Massias @mathurinmassias.bsky.social · 28/02/20251-day workshop on Bilevel optimization and hyperparameter tuning at ENS de Lyon, on March 25th : gdr-iasis.cnrs.fr/reunions/bil... Keynote talks by @jmairal.bsky.social @tonysf.bsky.social @samuelvaiter.com, Saverio Salzo and Luce Brotcorne, contributed talks are welcome!gdr-iasis.cnrs.frBilevel Optimization and Hyperparameter Learning - GdR IASISBilevel optimization has become a crucial framework in machine learning for addressing hierarchical problems, where one optimization task depends on the outcome of another. This approach plays a pivot... 0183
Reposted by Mathurin MassiasPaul Hagemann @yungbayesian.bsky.social · 23/01/2025Our paper "PnP-Flow: Plug-and-Play Image Restoration with Flow Matching" has been accepted to ICLR 2025. Here a short explainer: We want to restore images (i.e., solve inverse problems) using pretrained velocity fields from flow matching. However, using change of variables is super costly. 1155
Reposted by Mathurin MassiasRémi 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
Mathurin Massias @mathurinmassias.bsky.social · 12/12/2024MLSS coming to Senegal ! 📍 AIMS Mbour, Senegal 📅 June 23 - July 4, 2025 An international summer school to explore, collaborate, and deepen your understanding of machine learning in a unique and welcoming environment. Details: mlss-senegal.github.iomlss-senegal.github.ioMLSS Senegal 2025 031
Reposted by Mathurin MassiasJames Kirk @jiminykirket.bsky.social · 27/11/2024every cool thing I've ever done happened because I had one-or-two people I could constantly annoy with messages like "ooh look what I found" "ooh look what I learned" "ooh look what I broke" and who did the same in return 4668
Mathurin Massias @mathurinmassias.bsky.social · 27/11/2024Anne 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 1235299
Mathurin Massias @mathurinmassias.bsky.social · 25/11/2024Johnson-Lindenstrauss lemma in action: it is possible to embed any cloud of N points from R^d into R^k without distorting their respective distances too much, provided k is not too small (independently of d!) Better: any random Gaussian embedding works with high proba! 081
Reposted by Mathurin MassiasDavid Picard @davidpicard.eurosky.social · 23/11/2024This year, there are 16 positions at CNRS in computer science (8 in "applied" domains → ask me - 8 on "fundamental" domains → ask the other David). @mathurinmassias.bsky.social has a good list of advice mathurinm.github.io/cnrs_inria_a... Official 🔗 www.ins2i.cnrs.fr/en/cnrsinfo/... Don't wait!mathurinm.github.ioAdvice for CNRS and INRIA recruitmentINRIA and CNRS “chargé de recherche” positions offer unique conditions of freedom to do first-grade research: lifelong contract, no teaching involved. The application process is challenging, but it’s ... 23218
Mathurin Massias @mathurinmassias.bsky.social · 22/11/2024Conditioning of a function = ratio between highest and smallest eigenvalues of its Hessian. Higher conditioning => harder to minimize the function Gradient Descent gets faster on function with decreasing conditioning L/mu 👇 2284
Reposted by Mathurin MassiasTony S.F. @tonysf.bsky.social · 20/11/2024If you have a PhD and you're interested in doing a postdoc near paris on nonsmooth frank Wolfe methods for machine learning, apply for an fmjh post doc here www.fondation-hadamard.fr/fr/programme... deadline is dec 9!fondation-hadamard.frPost-Docs thématiquesAccueil 175
Mathurin Massias @mathurinmassias.bsky.social · 21/11/2024New blog post: the Hutchinson trace estimator, or how to evaluate divergence/Jacobian trace cheaply. Fundamental for Continuous Normalizing Flows mathurinm.github.io/hutchinson/ 0146
Mathurin Massias @mathurinmassias.bsky.social · 20/11/2024Time to unearth posts from the previous network! 1°: Two equivalent views on PCA: maximize the variance of the projected data, or minimize the reconstruction error 091