🎉 Congratulations to our researchers who were selected by the European Research Council (ERC) as part of the 2024 call for proposals for the Advanced Grant competition: A. Ailamaki, C. Brès, P. Gönczy, E. Matioli, K. Moselund, M. Payer, F. Stellacci and L. Zdeborova. go.epfl.ch/ERC-grants25

Without the support of EPFL the colleagues here and the students this would be hardly possible. I feel lucky working here in: amazing science with amazing environment!!

🎉 Congratulations to Anastasia Ailamaki, Mathias Payer, Lenka Zdeborová & Pascal Fua for receiving Advanced Grants for research in data systems, security, neural networks & computer-assisted engineering, a record 4 awards for EPFL’s IC School! 🏆

A co třeba zvážit možnost, že velká část českých vědců, kteří dosáhnou na takový grant, z Česka odešla? Možná by stálo za to se systematicky zeptat, co by je mohlo přivést zpět. ct24.ceskatelevize.cz/clanek/veda/v-…

Thank you EPFL for this news article about our recent PRX paper on the bilinear sequence model. actu.epfl.ch/news/how-ais-u…

Applying the dynamical cavity method to hypergraphs allows for the analysis of interactions with more than two variables. This study uses that method to study the quench dynamics of the k-XOR-SAT problem. Check it out: go.aps.org/46AAOcj

🏆 Naše laureátka Lenka Zdeborová (Lenka Zdeborova) získala nejprestižnější evropský grant. 💡 Její projekt posune hranice umělé inteligence. Cílem je zjistit, jak trénovat AI modely efektivněji – s menším množstvím dat, nižší spotřebou energie a větší odolností. Gratulujeme!

I'm happy to share the recording of a lecture I gave in Prague in May 2025: "Towards Understanding of Scaling, Emergence and Transformers." slideslive.com/39043090/towar…

Looking for a very superb job in theoretical physics. Consider joining us at EPFL epfl.ch/about/working/…

Another cool faculty opening in EPFL AI & biophysics: epfl.ch/about/working/…

From August 05 to August 15, l'IES Cargese will be hosting "Statisticial Physic and Machine Learning : Moving Forward" organized by Florent Krzakala & Lenka Zdeborova Krzakala Florent Lenka Zdeborova Università di Corsica Université Côte d'Azur CNRS Provence et Corse EPFL

First talk today, given by Giulio Biroli, LPENS on “Statistical physics and diffusion models” during the conference “Statistical physics and machine learning: Moving forward” organized at IES Cargese by Krzakala Florent & Lenka Zdeborova EPFL Università di Corsica Université Côte d'Azur CNRS Provence et Corse

Today at the IES Cargese during conference “Statistical Physics & Machine Learning: Moving Forward”, Michael Bronstein Michael M. Bronstein, University of Oxford /#AITHYRA, gave a presentation on “Geometric Deep Learning”. Krzakala Florent Lenka Zdeborova EPFL Università di Corsica Université Côte d'Azur CNRS Provence et Corse

Presentation on Thursday, August 7, given by Bruno Loureiro Bruno Loureiro, École normale supérieure | PSL Paris, on “An overview on Gaussian Multi-Index Model" during the conference organized by Krzakala Florent & Lenka Zdeborova EPFL Université Côte d'Azur Università di Corsica CNRS Provence et Corse #statisticalPhysics #machinelearning

Very classy blackboard lecture in Cargese. Cool ideas about how empirical deep learning performance constraints complexity of data distributions. Adding a handle of the speaker Dan Roy

Saturday during the conference organized by Krzakala Florent & Lenka Zdeborova, Yue Lu from Harvard University gave a presentation on "Gaussian Equivalence for Nonlinear random matrices:Why it works, and when it fails" EPFL Université Côte d'Azur Università di Corsica CNRS Provence et Corse #statisticalPhysics #machinelearning

Peter Bartlett UC Berkeley gave a talk yesterday at IES Cargese about "Optimization in neural nets, large steps size and implicit bias" during the conference organized by Krzakala Florent & Lenka Zdeborova EPFL Università di Corsica Université Côte d'Azur CNRS Provence et Corse #statisticalPhysic #MachineLearning

Today's presentation was given by Andrew Saxe, Andrew Saxe Gatsby Computational Neuroscience Unit "Models of representation learning dynamics " during the conference organized by Krzakala Florent & Lenka Zdeborova EPFL Università di Corsica Université Côte d'Azur CNRS Provence et Corse #statisticalPhysic #MachineLearning

This morning, the presentation was given by Pragya Sur Harvard University "Two problems at the intersection of statistics and machine learning: Calibration and Data Integration" during the conference organized by Krzakala Florent & Lenka Zdeborova EPFL Università di Corsica Université Côte d'Azur CNRS Provence et Corse

Brice Huang, Stanford University gave a talk this morning at IES Cargese about "Spins Glass, Algorithms, and Inference" during the conference organized by Krzakala Florent & Lenka Zdeborova EPFL Università di Corsica Université Côte d'Azur CNRS Provence et Corse #statisticalPhysic #MachineLearning