Gael Varoquaux 🦋
@GaelVaroquaux
Coder & Research director @inria ►Data, Health, & Computer science ►Python coder, (co)founder of @scikit_learn, joblib, @probabl_ai ►Art: @artgael ►Physics PhD
Ever wondered what goes on behind the scenes at #EuroSciPy? We're pulling back the curtain on the #EuroSciPy2025 Call for Papers (CfP) and program selection process. Get ready for all the nerdy details! A Thread 🧵➡️
This is a great development: while conferences are really useful, a European NeurIPS will help reduce the pressure to travel far, which is important for carbon footprint and inclusivity reasons.
NeurIPS is pleased to officially endorse EurIPS, an independently-organized meeting taking place in Copenhagen this year, which will offer researchers an opportunity to additionally present their accepted NeurIPS work in Europe, concurrently with NeurIPS. Read more in our blog…
NeurIPS is pleased to officially endorse EurIPS, an independently-organized meeting taking place in Copenhagen this year, which will offer researchers an opportunity to additionally present their accepted NeurIPS work in Europe, concurrently with NeurIPS. Read more in our blog…
Fully open machine learning requires not only GPU access but a community commitment to openness. (Some nostalgic lessons from the ImageNet decade.) argmin.net/p/an-open-mind…
I’ll present "TabICL: A Tabular Foundation Model for In‑Context Learning on Large Data" at ICML 2025. 🗓 Tuesday, July 15, 2025 | 4:30–7:00 PM PDT 📍 East Exhibition Hall A‑B, Booth hashtag#E‑320 If you're curious about TabICL, come by the poster — I'd love to chat !
👨🎓🧾✨#icml2025 Paper: TabICL, A Tabular Foundation Model for In-Context Learning on Large Data With @JingangQu, @DHolzmueller and @MarineLeMorvan TL;DR: a well-designed architecture and pretraining gives best tabular learner, and more scalable 1/9
TabICL offers two checkpoints: v1: Version in the paper, open-source pre-training code v1.1: Better, preview of upcoming work, same architecture, benchmarked in TabArena. Pre-training code not yet public. Outperforms TabPFNv2 for, roughly, >= 7,000 samples. Stay tuned for v2 😀
👨🎓🧾✨#icml2025 Paper: TabICL, A Tabular Foundation Model for In-Context Learning on Large Data With @JingangQu, @DHolzmueller and @MarineLeMorvan TL;DR: a well-designed architecture and pretraining gives best tabular learner, and more scalable 1/9
⚖️ Tutorial: Predictive Modeling with Imbalanced Datasets Using Scikit-learn! Real-world data is rarely balanced. Learn how to tackle class imbalance with confidence! 📣 Join Guillaume Lemaitre & Olivier Grisel 📅 euroscipy.org/schedule #MachineLearning #ScikitLearn
Chers amis physiciens, Je suis à Troyes pour le congrès de la SFP. Si vous y êtes, ravis de vous croiser demain au congrès. N'hésitez pas à m'aborder. La physique, mon premier amour 😀🥰