Stephane Chretien

[Stephane Chretien @GrdCrf]

@__paleologo Ionescu Tulcea, C. T. (1949). "Mesures dans les espaces produits". Atti Accad. Naz. Lincei Rend. 7: 208–211.

[Martial Gervaise @argevise]

✳️ Formation à  l’#IA  FIDLE du @CNRS. Elle est gratuite, en français, récente et très bien faite. 
Via @capt_ad_hoc
https://t.co/DAx1ob0mfZ

[Etienne KLEIN @EtienneKlein]

Demain, à 16 heures sur @franceculture, nous ne ménagerons pas nos méninges, en compagnie de Richard Lévy.
Un cerveau, comment ça marche ? via @franceculture https://t.co/ph00EMkdZL

[Alfredo Canziani @alfcnz]

«A 2020 Vision of Linear Algebra» six brief videos for teaching and learning linear algebra by… yasss! Him! A 85 years old William Gilbert Strang! ❤️❤️❤️

I hope to have just a fraction of your stamina, dear Gilbert!
I’ll try to keep opening eyes!
https://t.co/wXMJfchynv

[Stephane Chretien @GrdCrf]

@laurentduval Otherwise, we really live in a nightmare...

[Gregoire Simpson @GregoireSimpson]

Je viens de numériser un livre d'Elias et Scotson assez dur à trouver si jamais ça vous intéresse. C'est une étude d'un quartier anglais qui essaye de comprendre sociologiquement comment se créent les logiques de groupe et d'exclusion.

Je vous mets un lien juste en dessous.

[Ben Recht @beenwrekt]

There is no data-generating distribution. https://t.co/y7Wi4lmGnI

[Chelsea Finn @chelseabfinn]

All of my Deep RL course lecture videos from Spring 2025 are now online! 🥳

Youtube playlist: https://t.co/o5ykWMaWbQ

[Stephane Chretien @GrdCrf]

@laurentduval OMG.... il faut plutôt boire la vie en rose !

[Weijie Su @weijie444]

A new tokenizer is introduced for LLMs:

https://t.co/3P0Z2blvBN

Idea: Instead of merging tokens by frequency (BPE), optimize the tokenizer directly for maximizing average token length, yielding longer, more efficient tokens.

Results: 14–18% fewer tokens, faster training & inference, and better downstream accuracy across (small) GPT-style models.

[Quentin Bertrand @Qu3ntinB]

This is happening now in Ballroom AB #NeurIPS2025 !!

[Quanta Magazine @QuantaMagazine]

“So much of physics comes down to understanding geometry. And often in surprising ways.” —Jonathan Sorce, a theoretical physicist at Princeton University https://t.co/953Kc4Pduj

[Stephane Chretien @GrdCrf]

@Michel_Broue Nonnn ....

[Stephane Chretien @GrdCrf]

@ColmezPierre @Sonic_urticant Hilarant ... cela s'appelle du grand n'importe quoi, non ?

[François Chollet @fchollet]

Deep learning is not a collection of black-box tricks, contrary to what many believe. It can be learned as a principled engineering discipline.

This latest edition of Deep Learning with Python is my best attempt so far at teaching it. It focuses on building deep intuition -- the theory and mental models -- alongside all of the practical programming patterns.

You will learn this on a truly modern stack: Keras 3 as a high-productivity, framework-agnostic API, and preferably JAX for SotA performance and scalability (PyTorch and TensorFlow are also fully supported).

[Patrick Fournier @PatricFournier]

Une lecture en soutien à Henry Laurens pour analyser les enjeux de l'annulation du colloque sur la Palestine & l'Europe au College de France : "Le Passé imposé" montre la nécessité de l'histoire pour dépasser l'affrontement des mémoires.
Vertigineux et plus que jamais nécessaire.

[Boaz Barak @boazbaraktcs]

New lectures posted on CS 2881 YouTube playlist https://t.co/yefE1GcNS6

Economic impacts with @RonnieChatterji & Bharat Chandar

Interpretabilty with @NeelNanda5, @Jack_W_Lindsey, @bobabowen & @nabla_theta

[Stephane Chretien @GrdCrf]

@GaryMarcus @FT what happened to FT ? This is not serious.

[Weijie Su @weijie444]

Why and how does gradient/matrix orthogonalization work in Muon for training #LLMs?

We introduce an isotropic curvature model to explain it. Take-aways:

1. Orthogonalization is a good idea, "on the right track".

2. But it might not be optimal. [1/n]