Javier

For those interested on covid vaccination stats, I’ve implemented @RaceCovid, a bot that posts daily vaccination stats and predictions per country, using the data in github.com/owid/covid-19-…

This is a superb visualization of European history (1500-2022). twitter.com/WallStreetSilv…

An excellent introduction (for beginners) to Graph Neural Networks distill.pub/2021/gnn-intro/

This may revolutionize data science: we introduce TabPFN, a new tabular data classification method that takes 1 second & yields SOTA performance (better than hyperparameter-optimized gradient boosting in 1h). Current limits: up to 1k data points, 100 features, 10 classes. 🧵1/6

Comparto con todo el que le pueda interesar el mapa de Nueva York que elaboré para mi reciente viaje a la ciudad eterna. Está todo lo que necesitas ordenado por capas: museos, rascacielos, parques, restaurantes, localizaciones míticas de películas y más. google.com/maps/d/viewer?…

@rhurtubia @fransalasa A unos 20-30 minutos hay un circo con un salto de agua bastante grande, supongo que es el “precipicio” que dices 🙂

@jabot Hola! Fuimos un par de veces. Si mal no recuerdo con @fransalasa comimos fondue en una de esas mismas mesas (¿es el restaurante cerca del "precipicio"?)

Para tu próxima visita a Suiza @rhurtubia g.co/kgs/dkrAcS #valais #suisse

. @DeepMind released this GOLD a couple days back. If you ever wanted to study Transformers from scratch I think this would be that one resource you wouldn't want to miss: arxiv.org/abs/2207.09238

For mathematicians studying Transformers, a very nice concise, precise and complete definition: apronus.com/math/transform…

At 37, Maryna Viazovska becomes the second woman in history to receive the prestigious #FieldsMedal🏅, widely described as the Nobel Prize of #Mathematics. #FieldsMedal actu.epfl.ch/news/an-epfl-m…

Read a bit about Grokking recently. Here's some learnings: "Grokking" is a curious neural net behavior observed ~1 year ago (arxiv.org/abs/2201.02177). Continue optimizing a model long after perfect training accuracy and it suddenly generalizes. Figure:

The video of my talk @EPFL_en today on Transformers and how to make sense of them is online! youtube.com/watch?v=brmidg…

It is probably the time of switching this bot off, now that countries are slowing down the publication of covid cases and vaccination stats. Bye, bye world! #CovidVaccineRace

@fchollet If you ever come to the Léman region, let me know, I’ll bring you here chocolatier-tristan.ch

Switzerland has the best chocolate in the world and it's not even close

I've been comparing a lot of transformer variants on large models (400M params): Post/Pre-LN, DeepNet, NormFormers, Swin v2, GLU variants, RMSNorm, Sandwich LN, with GELU, Swish, SmeLU… More than 2,000h of total training time on TPU v3's 😯 Here are my findings 🤓

New version of Tom Leinster's lovely lecture notes on Galois Theory maths.ed.ac.uk/~tl/gt/gt.pdf #GaloisTweets

Monday (March 28th) at 4PM EST @OriolVinyalsML (@DeepMind) will give a in person talk at the @MIT_CSAIL Embodied Intelligence seminar about The Deep Learning Toolbox: From AlphaFold to AlphaCode! Check it out in person in 34-101 and the livestream at: youtube.com/channel/UCnXGb…

I'm able to provide free VPN accounts to journalists in Ukraine. DMs open, reach out and I'll get you set up. 🇺🇦

The discovery of the TRAPPIST-1 system — an extraordinary collection of 7 Earth-size worlds — made us wonder: are any of these worlds suitable for life? #NASAWebb will look for signs of atmospheres around these planets to help find out: go.nasa.gov/3LQ5mtL #UnfoldTheUniverse

He(X)agon marks the spots 🏴‍☠️ Last week, 18 spots helped confirm that each of Webb's mirror segments can see starlight. Now we've arranged those dots into our primary mirror shape, completing the first of Webb's mirror alignment phases: go.nasa.gov/3s0pgKR #UnfoldTheUniverse

Hoy quiero hablar sobre conseguir objetivos y organizar mejor el tiempo. Como profesor, divulgador o empresario, he desarrollado mis técnicas a lo largo de los años. Así que me he tomado la molestia de recopilarlas todas en un solo lugar, por si les pueden ser útiles. Dentro hilo