Lightnews — Scholar-powered news

LightNews

Gilles Louppe

@glouppe.bsky.social

3.7K followers 730 following 64 posts

AI for Science, deep generative models, inverse problems. Professor of AI and deep learning @universitedeliege.bsky.social. Previously @CERN, @nyuniversity. https://glouppe.github.io

Computer science 62%

Physics 22%

more

Posts Media Videos Starter Packs

Pinned

Gilles Louppe @glouppe.bsky.social · Apr 29

<proud advisor>
Hot off the arXiv! 🦬 "Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilation" 🌍 Appa is our novel 1.5B-parameter probabilistic weather model that unifies reanalysis, filtering, and forecasting in a single framework. A thread 🧵

Gilles Louppe @glouppe.bsky.social · 1d

Bravo Gaël pour cette reconnaissance amplement méritée! Tu dis que la science est un sport d'équipe, et c'est vrai, mais une équipe a besoin d'un leader qui l'inspire. Je suis sûr que l'équipe scikit-learn, passée et présente, est fière de toi et de ce que nous avons construit ensemble. Champagne!

Reposted by Gilles Louppe

Gérôme Andry @gandry.bsky.social · 3d

🚀 After more than a year of work — and many great discussions with curious minds & domain experts — we’re excited to announce the public release of 𝐀𝐩𝐩𝐚, our latent diffusion model for global data assimilation!

Check the repo and the complete wiki!
github.com/montefiore-s...

GitHub - montefiore-sail/appa: Code for the publication "Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilation".

Code for the publication "Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilation". - montefiore-sail/appa

Reposted by Gilles Louppe

Dan Garisto @dangaristo.bsky.social · 9d

Had never read Jane Goodall's original 1963 article in Nat Geo on the wild chimpanzees in Tanzania until now. It's a wonderful blend of science and journalism, and well worth your time.

www.nationalgeographic.com/pdf/jane-goo...

David Greybeard, a wild chimpanzee, gets a handout of bananas from author Goodall, who studies the apes under a National Geographic Society grant. This scene near
her camp represents a triumph for Miss Goodall; at first the animals fled if she came
within 500 yards. Knapsack holds camera and notebook. She carries a whistle in her
pocket to summon searchers in case of accident in the rugged Tanganyika hills.

Reposted by Gilles Louppe

Gaël Varoquaux @gaelvaroquaux.bsky.social · 10d

Yeah, I think that "AI is the new petrol" is about right...

Reposted by Gilles Louppe

Maxim Raginsky @mraginsky.bsky.social · 13d

Rudolf Kalman put it nicely (and provocatively): link.springer.com/chapter/10.1...

Quote from R. Kalman, "Identification from real data": For an objective outsider, much of the historical development
of statistics is a long series of attempts to dodge the inevitable
implications of uncertainty. Whenever the conventional statistical
treatment of a problem gives a unique (certain) answer, as in
maximum likelihood estimation, in least squares, ... , common sense
should tell us that such a miracle is possible only if additional
assumptions (deus ex machina) are imposed on the data which
somehow succeed in neutralizing the intrinsic uncertainty. We
shall use the technical term "prejudice" for such assumptions.
In other words, statistical methodology has been handicapped
because statisticians have become mesmerized by the deep-seated
hope of giving certain answers to problems where the uncertainty
is intrinsic. This is politics, not science. For example, least
squares is very popular because it always gives a unique answer.
But this is exactly where its fatal weakness lies; when we pose
Nature a question, as in identification problems, we must not
phrase that question in such terms that the answer is
predetermined regardless of the nature of the data.

Gilles Louppe @glouppe.bsky.social · 14d

How do you type all these long long hyphens? — I keep seeing them everywhere. I learned the UTF-8 code by now but there must be something easier 🤔

Reposted by Gilles Louppe

Evert Nasedkin @evertnasedkin.bsky.social · 15d

🔭 It's paper day! Today I'm sharing the latest in a series of papers looking at the weather on other worlds, in this case bringing you the weather report from a nearby T-dwarf, SIMP-0136. 🪐

🧵 to follow...

Reposted by Gilles Louppe

sakanaai.bsky.social @sakanaai.bsky.social · 16d

We’re excited to introduce ShinkaEvolve: An open-source framework that evolves programs for scientific discovery with unprecedented sample-efficiency. It leverages LLMs to find state-of-the-art solutions, orders of magnitude faster!

Blog: sakana.ai/shinka-evolve/
Paper: arxiv.org/abs/2509.19349

Reposted by Gilles Louppe

Eugene Vinitsky 🍒 @eugenevinitsky.bsky.social · 16d

For folks considering grad school in ML, my advice is to explore programs that mix ML with a domain interest. ML programs are wildly oversubscribed while a lot of the fun right now is in figuring out what you can do with it

Reposted by Mark D. White, Lesley A. Hall, Kate Lancaster , and 4 more Mark D. White, Lesley A. Hall, Kate Lancaster, Rebecca Tushnet, James Goodwin, Michael Hancher, Gilles Louppe

Elise Cutts @elisecutts.bsky.social · 17d

Cecilia Payne-Gaposchkin ✨ figured out what stars are made of ✨ when she was just 25. 🔭🧪

Her PhD thesis basically established the Harvard astro department — at a time when Harvard didn't officially allow woman students.

I wrote this little profile to mark the 100th anniversary of her thesis:

Reposted by Gilles Louppe

MSNBC @msnbc.com · 17d

"It's the greatest con job ever perpetrated on the world.”

In his remarks at the United Nations General Assembly, President Trump addressed climate change, saying, "If you don't get away from this green scam, your country is going to fail."

Reposted by Peter Thorne, Jamie Hannaford, Ben Bond‐Lamberty , and 3 more Peter Thorne, Jamie Hannaford, Ben Bond‐Lamberty, Gavin A. Schmidt, Ed Hawkins, Gilles Louppe

Peter Stott @stottpeter.bsky.social · 17d

The people I work with are not stupid people and our climate predictions of 30 years ago of global warming have proved to be accurate. Just saying. www.bbc.co.uk/news/live/cp...

Reposted by Gilles Louppe

Dima Damen @dimadamen.bsky.social · 21d

As an SAC for @neuripsconf.bsky.social, I don't agree with PCs approach to reject papers based on ranking.
I ranked my accepted papers as requested and explicitly stated that I support the acceptance of all papers.
I was not given an explanation of why papers at the end of the rank were rejected.

Reposted by Gilles Louppe

Guillaume Dalle @gdalle.bsky.social · 22d

Is this the year we finally break up @neuripsconf.bsky.social?

Distracted boyfriend meme, featuring NeurIPS as the boyfriend.
Angry girlfriend: “allow authors to present in Copenhagen”
Girl passing by: “drop 400 accepted papers due to San Diego venue constraints”

Reposted by Mark A. Lemley, Stefan Reis, Jesse H. Kroll , and 42 more Mark A. Lemley, Stefan Reis, Jesse H. Kroll, Steve Peers, Andrew Scott, Serge Guimond, Caroline Krafft, Elizabeth Stokoe, Vincent Tiberj, Eric Goldman, Richard Kay, Sabine Pahl, Alan Lester, Fionnuala Ní Aoláin, Robert Black, Michael Kevane, Jussi T. Eronen, Laurent Pech, David R. Miller, Robert Wolfe, W. Andy Knight, Gerald Friedman, Richard Larouche, Jonathan Birch, Anne Norton, Dean Eckles, Molly Scott Cato, Andrew Watkins, Stuart White, Henrik Skaug Sætra, Paul Ekblom, Noah L. Nathan, Simon Lester, Hilde De Weerdt, Christina Pagel, Gilles Louppe, Daxton R. Stewart, Manisha Sinha, Olúfẹ́mi Táíwò, Nathan P. Kalmoe, Dan Immergluck, Guy Dewsbury, Virginia Sapiro, Markus W. Gehring, Southern Africa

Barack Obama @barackobama.bsky.social · 23d

After years of complaining about cancel culture, the current administration has taken it to a new and dangerous level by routinely threatening regulatory action against media companies unless they muzzle or fire reporters and commentators it doesn’t like.

Let’s be clear about what happened to Jimmy Kimmel

Trump’s most brazen attack on free speech yet.

Reposted by Gilles Louppe

Annalena Kofler @annalenakofler.bsky.social · 24d

To celebrate the 10 year anniversary of the first gravitational wave detection, I made a tutorial for high school students that explains how to use python to visualize the original gravitational wave data of GW150914. (Tested and approved by a very motivated German 10th grade student 😄)
#GW10Years

Reposted by Gilles Louppe

The University of Manchester @manchester.ac.uk · 25d

In 1950, Alan Turing - while at @manchester.ac.uk - proposed a simple but profound experiment: can a machine convincingly imitate human thought?

We now call it the Turing Test. 🧠💻

a man wearing suspenders and a watch looks down in front of a machine

Alt: Alarn Turing looks down in front of a machine

media.tenor.com

Reposted by Gilles Louppe

N. Thuerey's research group at TUM @thuereygroup.bsky.social · 25d

I'm very excited to introduce P3D: our PDE-Transformer architecture in 3 dimensions by . Demonstrated for unprecedented 512^3 resolutions! That means the Transformer produces over 400 million degrees of freedom in one go 😀 a regime that was previously out of reach: arxiv.org/abs/2509.10186

Reposted by Gilles Louppe

Jorge Bravo Abad @bravo-abad.bsky.social · 28d

Most industrial reactions happen on catalyst surfaces, but predicting which surfaces actually form is costly. Jun Yin and coauthors present SurFF, a foundation model that predicts surface exposure across intermetallic crystals with DFT-level accuracy, 100k× faster. www.nature.com/articles/s43...

SurFF: a foundation model for surface exposure and morphology across intermetallic crystals - Nature Computational Science

A foundation machine learning model, SurFF, enables DFT-accurate predictions of surface energies and morphologies in intermetallic catalysts, achieving over 105-fold acceleration for high-throughput m...

Reposted by Gilles Louppe

Wikipedia @wikipedia.org · 28d

We promise this pandemic was only virtual.

20 years ago, an unexpected event in the online game "World of Warcraft" caught the attention of players and researchers. A new dungeon introduced a boss whose special attack temporarily drained a player’s health and could spread to others nearby. 🧵⬇️ (1/3)

Two adults in elaborate fantasy cosplay, one as a pink-skinned elf and the other as a green-skinned orc, at a convention. Text says: What happens during a virtual pandemic? 20 years ago, the Corrupted Blood Incident took place in the online game World of Warcraft.

Reposted by Gilles Louppe

lebellig @lebellig.bsky.social · 28d

Locality in Image Diffusion Models Emerges from Data Statistics, by Artem Lukoianov et al. (arxiv.org/abs/2509.09672), retweet if you want your model to generate samples in the "sampling voids".

Locality in Image Diffusion Models Emerges from Data Statistics

Among generative models, diffusion models are uniquely intriguing due to the existence of a closed-form optimal minimizer of their training objective, often referred to as the optimal denoiser. Howeve...

Reposted by Gilles Louppe

Diana Cai @dianarycai.bsky.social · 28d

The application for a research fellowship at the Flatiron Institute in the Center for Computational Math is now live! This includes positions for ML and stats.

The deadline is Dec 1.

apply.interfolio.com/173401

ML@CCM group: users.flatironinstitute.org/~lsaul/ml_cc...

Apply - Interfolio {{$ctrl.$state.data.pageTitle}} - Apply - Interfolio

apply.interfolio.com

Reposted by Gilles Louppe, Elisa Freschi

Julia M. Rohrer @dingdingpeng.the100.ci · Sep 11

I skimmed a paper of an author I dislike and it's amazing how a certain style of writing --overly complicated explanations of trivial claims, new jargon that hides how vacuous it all is, an overemphasize on mathematization regardless of whether it actually maps onto the claims made-- just wrecks me.

Gilles Louppe @glouppe.bsky.social · Sep 10

Ça faisait un moment qu'on avait plus vu ces jolis diagrammes par ici :-)

Reposted by Gilles Louppe

Keith Smith @drkeithsmith.bsky.social · Sep 4

In @science.org, Buchli et al. have applied sophisticated machine learning techniques to the control electronics of @ligo.org. This improves the sensitivity of the detector at low frequencies - expanding its cosmological reach, particularly for low-mass mergers. ⚛️☄️
www.science.org/doi/10.1126/...

Gilles Louppe @glouppe.bsky.social · Sep 4

Wow congratulations!!

Reposted by Gilles Louppe

François Rozet @francois-rozet.bsky.social · Sep 3

When we started this project, we expected accuracy to degrade as the compression rate increased. To our surprise, we found that accuracy remained constant or even improved!

Reposted by Gilles Louppe

François Rozet @francois-rozet.bsky.social · Sep 3

Does a smaller latent space lead to worse generation in latent diffusion models? Not necessarily! We show that LDMs are extremely robust to a wide range of compression rates (10-1000x) in the context of physics emulation.

We got lost in latent space. Join us 👇

Gilles Louppe @glouppe.bsky.social · Sep 2

Flying ✈️ to Stockholm for 2 days of AI for Science at the Royal Swedish Academy of Sciences scienceacademyswe.bsky.social Anyone around?

Gilles Louppe @glouppe.bsky.social · Sep 1

Very proud to see the #ML4PS2025 workshop thrive! ... but where will we put so many posters? 👀 (subtweet)