Gilles Louppe
@glouppe.bsky.social
AI for Science, deep generative models, inverse problems. Professor of AI and deep learning @universitedeliege.bsky.social. Previously @CERN, @nyuniversity. https://glouppe.github.io
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 🧵
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 🧵
Reposted by Gilles Louppe
I am incredibly honored to have received the inaugural AI in Science Research Excellence Prize from the Margot and Tom Pritzker Foundation
dsi.wisc.edu/2025/11/10/d...
dsi.wisc.edu/2025/11/10/d...
November 10, 2025 at 7:22 PM
I am incredibly honored to have received the inaugural AI in Science Research Excellence Prize from the Margot and Tom Pritzker Foundation
dsi.wisc.edu/2025/11/10/d...
dsi.wisc.edu/2025/11/10/d...
Once again an interdisciplinary research project gets poor, even condescending this time, evaluations because reviewers make little effort to understand the maths. Science is not only about killing rat models and to see if some random drug worked. Tired of this game.
November 10, 2025 at 8:53 AM
Once again an interdisciplinary research project gets poor, even condescending this time, evaluations because reviewers make little effort to understand the maths. Science is not only about killing rat models and to see if some random drug worked. Tired of this game.
Reposted by Gilles Louppe
This Nature retrospective is quite interesting.
To me, the only solution to the credit assignment problem is obvious: stop believing a single person is responsible for every big discovery. It's an artifact of our monkey brain requiring a face for storage, not the reality of how knowledge progresses.
To me, the only solution to the credit assignment problem is obvious: stop believing a single person is responsible for every big discovery. It's an artifact of our monkey brain requiring a face for storage, not the reality of how knowledge progresses.
"stole Rosalind Franklin's work" has become the new orthodoxy. While she was certainly the victim of sexism from Watson, I think her colleague Wilkins was the real villain. Events 1951-53 well covered in Nature in 2023 www.nature.com/articles/d41...
What Rosalind Franklin truly contributed to the discovery of DNA’s structure
Franklin was no victim in how the DNA double helix was solved. An overlooked letter and an unpublished news article, both written in 1953, reveal that she was an equal player.
www.nature.com
November 8, 2025 at 8:22 AM
This Nature retrospective is quite interesting.
To me, the only solution to the credit assignment problem is obvious: stop believing a single person is responsible for every big discovery. It's an artifact of our monkey brain requiring a face for storage, not the reality of how knowledge progresses.
To me, the only solution to the credit assignment problem is obvious: stop believing a single person is responsible for every big discovery. It's an artifact of our monkey brain requiring a face for storage, not the reality of how knowledge progresses.
Reposted by Gilles Louppe
New paper, with @rkhashmani.me @marielpettee.bsky.social @garrettmerz.bsky.social Hellen Qu. We introduce a framework for generating realistic, highly multimodal datasets with explicitly calculable mutual information. This is helpful for studying self-supervised learning
arxiv.org/abs/2510.21686
arxiv.org/abs/2510.21686
October 28, 2025 at 5:23 PM
New paper, with @rkhashmani.me @marielpettee.bsky.social @garrettmerz.bsky.social Hellen Qu. We introduce a framework for generating realistic, highly multimodal datasets with explicitly calculable mutual information. This is helpful for studying self-supervised learning
arxiv.org/abs/2510.21686
arxiv.org/abs/2510.21686
Reposted by Gilles Louppe
"The Principles of Diffusion Models" by Chieh-Hsin Lai, Yang Song, Dongjun Kim, Yuki Mitsufuji, Stefano Ermon. arxiv.org/abs/2510.21890
It might not be the easiest intro to diffusion models, but this monograph is an amazing deep dive into the math behind them and all the nuances
It might not be the easiest intro to diffusion models, but this monograph is an amazing deep dive into the math behind them and all the nuances
The Principles of Diffusion Models
This monograph presents the core principles that have guided the development of diffusion models, tracing their origins and showing how diverse formulations arise from shared mathematical ideas. Diffu...
arxiv.org
October 28, 2025 at 8:35 AM
"The Principles of Diffusion Models" by Chieh-Hsin Lai, Yang Song, Dongjun Kim, Yuki Mitsufuji, Stefano Ermon. arxiv.org/abs/2510.21890
It might not be the easiest intro to diffusion models, but this monograph is an amazing deep dive into the math behind them and all the nuances
It might not be the easiest intro to diffusion models, but this monograph is an amazing deep dive into the math behind them and all the nuances
EM algorithm: 1977 vintage, 2025 relevant. New lecture notes on a classic that refuses to age. From fitting a GMM on the Old Faithful data to training modern diffusion models in incomplete data settings, the same simple math applies. 👉 glouppe.github.io/dats0001-fou...
October 27, 2025 at 2:53 PM
EM algorithm: 1977 vintage, 2025 relevant. New lecture notes on a classic that refuses to age. From fitting a GMM on the Old Faithful data to training modern diffusion models in incomplete data settings, the same simple math applies. 👉 glouppe.github.io/dats0001-fou...
Reposted by Gilles Louppe
Fisher meets Feynman! 🤝
We use score matching and a trick from quantum field theory to make a product-of-experts family both expressive and efficient for variational inference.
To appear as a spotlight @ NeurIPS 2025.
#NeurIPS2025 (link below)
We use score matching and a trick from quantum field theory to make a product-of-experts family both expressive and efficient for variational inference.
To appear as a spotlight @ NeurIPS 2025.
#NeurIPS2025 (link below)
October 27, 2025 at 12:51 PM
Fisher meets Feynman! 🤝
We use score matching and a trick from quantum field theory to make a product-of-experts family both expressive and efficient for variational inference.
To appear as a spotlight @ NeurIPS 2025.
#NeurIPS2025 (link below)
We use score matching and a trick from quantum field theory to make a product-of-experts family both expressive and efficient for variational inference.
To appear as a spotlight @ NeurIPS 2025.
#NeurIPS2025 (link below)
Reposted by Gilles Louppe
What if we did a single run and declared victory
October 23, 2025 at 2:28 AM
What if we did a single run and declared victory
Reposted by Gilles Louppe
Excited to share SamudrACE, the first 3D AI ocean–atm–sea-ice #climate emulator! 🚀 Simulates 800 years in 1 day on 1 GPU, ~100× faster than traditional models, straight from your laptop 👩💻 Collaboration with @ai2.bsky.social and GFDL, advancing #AIforScience with #DeepLearning.
tinyurl.com/Samudrace
tinyurl.com/Samudrace
SamudrACE: A fast, accurate, efficient 3D coupled climate AI emulator
A fast digital twin of a state-of-the-art coupled climate model, simulating 800 years in 1 day with 1 GPU. SamudrACE combines two leading…
medium.com
October 15, 2025 at 4:11 PM
Excited to share SamudrACE, the first 3D AI ocean–atm–sea-ice #climate emulator! 🚀 Simulates 800 years in 1 day on 1 GPU, ~100× faster than traditional models, straight from your laptop 👩💻 Collaboration with @ai2.bsky.social and GFDL, advancing #AIforScience with #DeepLearning.
tinyurl.com/Samudrace
tinyurl.com/Samudrace
Reposted by Gilles Louppe
🕳️🐇 𝙄𝙣𝙩𝙤 𝙩𝙝𝙚 𝙍𝙖𝙗𝙗𝙞𝙩 𝙃𝙪𝙡𝙡 – 𝙋𝙖𝙧𝙩 𝙄 (𝑃𝑎𝑟𝑡 𝐼𝐼 𝑡𝑜𝑚𝑜𝑟𝑟𝑜𝑤)
𝗔𝗻 𝗶𝗻𝘁𝗲𝗿𝗽𝗿𝗲𝘁𝗮𝗯𝗶𝗹𝗶𝘁𝘆 𝗱𝗲𝗲𝗽 𝗱𝗶𝘃𝗲 𝗶𝗻𝘁𝗼 𝗗𝗜𝗡𝗢𝘃𝟮, one of vision’s most important foundation models.
And today is Part I, buckle up, we're exploring some of its most charming features. :)
𝗔𝗻 𝗶𝗻𝘁𝗲𝗿𝗽𝗿𝗲𝘁𝗮𝗯𝗶𝗹𝗶𝘁𝘆 𝗱𝗲𝗲𝗽 𝗱𝗶𝘃𝗲 𝗶𝗻𝘁𝗼 𝗗𝗜𝗡𝗢𝘃𝟮, one of vision’s most important foundation models.
And today is Part I, buckle up, we're exploring some of its most charming features. :)
October 14, 2025 at 9:00 PM
🕳️🐇 𝙄𝙣𝙩𝙤 𝙩𝙝𝙚 𝙍𝙖𝙗𝙗𝙞𝙩 𝙃𝙪𝙡𝙡 – 𝙋𝙖𝙧𝙩 𝙄 (𝑃𝑎𝑟𝑡 𝐼𝐼 𝑡𝑜𝑚𝑜𝑟𝑟𝑜𝑤)
𝗔𝗻 𝗶𝗻𝘁𝗲𝗿𝗽𝗿𝗲𝘁𝗮𝗯𝗶𝗹𝗶𝘁𝘆 𝗱𝗲𝗲𝗽 𝗱𝗶𝘃𝗲 𝗶𝗻𝘁𝗼 𝗗𝗜𝗡𝗢𝘃𝟮, one of vision’s most important foundation models.
And today is Part I, buckle up, we're exploring some of its most charming features. :)
𝗔𝗻 𝗶𝗻𝘁𝗲𝗿𝗽𝗿𝗲𝘁𝗮𝗯𝗶𝗹𝗶𝘁𝘆 𝗱𝗲𝗲𝗽 𝗱𝗶𝘃𝗲 𝗶𝗻𝘁𝗼 𝗗𝗜𝗡𝗢𝘃𝟮, one of vision’s most important foundation models.
And today is Part I, buckle up, we're exploring some of its most charming features. :)
Reposted by Gilles Louppe
Thrilled to have two years' of work out, in a pair of papers led by @gradientrider.bsky.social and @maxecharles.bsky.social.
We've built a data-driven calibration of the James Webb Interferometer to near its fundamental limits for high-res imaging - explainer at @aunz.theconversation.com!
We've built a data-driven calibration of the James Webb Interferometer to near its fundamental limits for high-res imaging - explainer at @aunz.theconversation.com!
How we sharpened the James Webb telescope’s vision from a million kilometres away
The only Australian hardware on board the legendary telescope is starting to fulfil its duties.
theconversation.com
October 14, 2025 at 3:35 AM
Thrilled to have two years' of work out, in a pair of papers led by @gradientrider.bsky.social and @maxecharles.bsky.social.
We've built a data-driven calibration of the James Webb Interferometer to near its fundamental limits for high-res imaging - explainer at @aunz.theconversation.com!
We've built a data-driven calibration of the James Webb Interferometer to near its fundamental limits for high-res imaging - explainer at @aunz.theconversation.com!
Reposted by Gilles Louppe
Dans cette interview avec la JASRAC (équivalent japonais de la SACEM), Nobuo Uematsu a donné son avis sur la musique générée par IA. À sa façon, il relaie ce nouvel adage : si personne ne s'est fatigué à l'écrire, je ne me fatiguerai pas à l'écouter.
📃 www.jasrac.or.jp/magazine/int...
📃 www.jasrac.or.jp/magazine/int...
October 12, 2025 at 7:11 PM
Dans cette interview avec la JASRAC (équivalent japonais de la SACEM), Nobuo Uematsu a donné son avis sur la musique générée par IA. À sa façon, il relaie ce nouvel adage : si personne ne s'est fatigué à l'écrire, je ne me fatiguerai pas à l'écouter.
📃 www.jasrac.or.jp/magazine/int...
📃 www.jasrac.or.jp/magazine/int...
Reposted by Gilles Louppe
🚀 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...
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
github.com
October 8, 2025 at 10:33 AM
🚀 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...
Check the repo and the complete wiki!
github.com/montefiore-s...
Reposted by Gilles Louppe
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...
www.nationalgeographic.com/pdf/jane-goo...
October 1, 2025 at 8:15 PM
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...
www.nationalgeographic.com/pdf/jane-goo...
Reposted by Gilles Louppe
Yeah, I think that "AI is the new petrol" is about right...
October 1, 2025 at 5:51 AM
Yeah, I think that "AI is the new petrol" is about right...
Reposted by Gilles Louppe
Rudolf Kalman put it nicely (and provocatively): link.springer.com/chapter/10.1...
September 27, 2025 at 5:42 PM
Rudolf Kalman put it nicely (and provocatively): link.springer.com/chapter/10.1...
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 🤔
September 26, 2025 at 4:33 PM
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
🔭 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...
🧵 to follow...
September 26, 2025 at 9:05 AM
🔭 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...
🧵 to follow...
Reposted by Gilles Louppe
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
Blog: sakana.ai/shinka-evolve/
Paper: arxiv.org/abs/2509.19349
September 25, 2025 at 5:56 AM
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
Blog: sakana.ai/shinka-evolve/
Paper: arxiv.org/abs/2509.19349
Reposted by Gilles Louppe
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
September 25, 2025 at 3:25 AM
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 Gilles Louppe
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:
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:
September 24, 2025 at 9:14 AM
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:
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
"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."
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."
September 23, 2025 at 3:53 PM
"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."
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 Gilles Louppe
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...
September 23, 2025 at 3:24 PM
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
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. 🧠💻
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
September 16, 2025 at 12:33 PM
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. 🧠💻
We now call it the Turing Test. 🧠💻
Reposted by Gilles Louppe
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.
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.
September 19, 2025 at 7:49 PM
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.
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.