Alain Rakotomamonjy

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. Both satellite events will feature keynotes, oral and poster presentations of accepted NeurIPS 2026 papers, as well as workshops. We are planning tutorials, affinity events, and other elements for the satellite sites and we'll share more information as planning advances. Wherever you choose to join us, the entire NeurIPS organizing committee is working hard to deliver an outstanding experience for the whole community! neurips.cc

@train_nomad @RocTredudon Du coup on risque de voyager debout?

@RocTredudon Bonjour Kerfany, bon mercredi également 🙂

Bonjour ici Quentin ✌️ Je vous retrouve pour une nouvelle session info trafic jusqu'à 14h🤳 Une question sur votre train ? Sollicitez-moi 🚆 Bonne journée😊 Quentin

@train_nomad Bonjour est ce le 3104 est ej placement libre?

Beaucoup de monde hier lors du forum "Poursuite d'Etudes" sur le stand de notre Master, preuve de l'engouement pour les métiers de l'IA. Ce temps fort a permis des échanges privilégiés entre étudiants de licence & enseignants-chercheurs. Post complet: bit.ly/48ed5hi

🌀New paper on the generation phases of Flow Matching arxiv.org/abs/2510.24830 Are FM & diffusion models nothing else than denoisers trained at every noise level? In theory yes, *if trained optimally*. But in practice, do all noise level matter equally?

Kickstarting 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/model…

My latest @criteo article — The Future of Commerce Recommendation: Why Hybrid Systems Will Win — explores the pros and cons of today’s Performance Recommenders and LLM-based Agents, and how the next generation of RecSys Agents will blend both bit.ly/3J8reEg

@Guillaumemp Unpopular opinion. Le seul "fuoriclasse" dans l équipe est raspadori. Il mérite son 8 et mériterait de jouer plus.

Les notes de la Nazionale après la victoire face à l’Estonie, Retegui (8,5) homme du match. Gattuso hérite d’un 8 pour sa première réussie : “le temps donne raison à tous ses choix (…) une équipe avec son âme” 🗞️ (Gazzetta)

One-day workshop on Diffusion models and Flow matching, October 24th at ENS Lyon Registration and call for contributions (short talk and poster) are open at gdr-iasis.cnrs.fr/reunions/model…

"I use AI in a separate window. I don't enjoy Cursor or Windsurf, I can literally feel competence draining out of my fingers." @dhh, the legendary programmer and creator of Ruby on Rails has the most beautiful and philosophical idea about what AI takes away from programmers.

🔍 We are sponsoring #COLT conference this year in Lyon 🇫🇷 Don't hesitate to engage with our Criteos in place, @jlnzhou & Vianney Perchet (Open Problems Chair) 👏

#MlssSenegal2025 Full Schedule 🤓😎

🔴 A new Research Card is out! 🧪 Pareto-Optimality, Smoothness, and Stochasticity in Learning-Augmented One-Max-Search 🔎 A rule for choosing when to sell/buy an asset when facing a sequence of prices. #AdTech Read our article to discover more! 👇 techblog.criteo.com/pareto-optimal…

🔴 A new tech meetup in our BCN office is coming up! Don't miss 🎤 @albertlumbreras' talk: "The #agentic paradigm: planning the future for machines that plan" - A new reality where #AI evolves from predictive models to autonomous agents. 🔗 RSVP here! lnkd.in/dx3ctHe3

New paper on the generalization of Flow Matching 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**? with @Qu3ntinB, Anne Gagneux & Rémi Emonet 👇👇👇

I would be very helpful to have back the keyword-based selection on a larger batch of the paper! 😵‍💫😵‍💫

coucou @MistralAI , à quand un abonnement famille pour LeChat avec une formule entre le gratuit et le pro?

We are thrilled to announce this deserved award at #ALT25. Congrats to Marc Abeille, David Janz, @CiaraPikeBurke 👏 Paper: When and why randomised exploration works (in linear bandits) arxiv.org/abs/2502.08870

@criteo, through its @CriteoAILab, is open-sourcing the largest bidding dataset to shape the future of the open internet : private & economically viable! CriteoPrivateAd dataset is a available on @huggingface (huggingface.co/datasets/crite…) and associated with a companion paper.

As a run-up to the #AIActionSummit, @Criteo organized a symposium on Trustworthy AI, featuring viewpoints from Science, Legal, and Public Policy. Here are the highlights of the day : techblog.criteo.com/trustworthy-ai… cc @CriteoAILab @iamvladimirova @LivaRalaivola @jy_franceschi