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
Β· Apr 29
<proud advisor>
Hot off the arXiv! 𦬠"Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilation" π Appa is our novel 1.5B-parameter probabilistic weather model that unifies reanalysis, filtering, and forecasting in a single framework. A thread π§΅
Hot off the arXiv! 𦬠"Appa: Bending Weather Dynamics with Latent Diffusion Models for Global Data Assimilation" π Appa is our novel 1.5B-parameter probabilistic weather model that unifies reanalysis, filtering, and forecasting in a single framework. A thread π§΅
Reposted by Gilles Louppe
We introduce epiplexity, a new measure of information that provides a foundation for how to select, generate, or transform data for learning systems. We have been working on this for almost 2 years, and I cannot contain my excitement! arxiv.org/abs/2601.03220 1/7
January 7, 2026 at 5:28 PM
We introduce epiplexity, a new measure of information that provides a foundation for how to select, generate, or transform data for learning systems. We have been working on this for almost 2 years, and I cannot contain my excitement! arxiv.org/abs/2601.03220 1/7
Reposted by Gilles Louppe
A study shows that using AI tools like LLMs lowers cognitive engagement and critical thinking in essay writing, signaling a trade-off between convenience and growth. LLM users had weaker memory recall and ownership, raising vital talks about AI's role in education. https://arxiv.org/abs/2506.08872
Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task
ArXiv link for Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task
arxiv.org
January 7, 2026 at 4:12 AM
A study shows that using AI tools like LLMs lowers cognitive engagement and critical thinking in essay writing, signaling a trade-off between convenience and growth. LLM users had weaker memory recall and ownership, raising vital talks about AI's role in education. https://arxiv.org/abs/2506.08872
Reposted by Gilles Louppe
Truly this site hosts the most controversial of opinions
I feel like it is far more important to teach SVMs, and the machinery around them, in basic ML courses now than it was in 2012.
January 5, 2026 at 4:19 AM
Truly this site hosts the most controversial of opinions
Reposted by Gilles Louppe
2020s: AI "System Prompts" are lengthy, carefully constructed sets of expert rules about a particular domain, created by "prompt engineers".
1980s: AI "Expert Systems" were lengthy, carefully constructed sets of expert rules about a particular domain, created by "knowledge engineers".
1980s: AI "Expert Systems" were lengthy, carefully constructed sets of expert rules about a particular domain, created by "knowledge engineers".
January 1, 2026 at 8:59 PM
2020s: AI "System Prompts" are lengthy, carefully constructed sets of expert rules about a particular domain, created by "prompt engineers".
1980s: AI "Expert Systems" were lengthy, carefully constructed sets of expert rules about a particular domain, created by "knowledge engineers".
1980s: AI "Expert Systems" were lengthy, carefully constructed sets of expert rules about a particular domain, created by "knowledge engineers".
Reposted by Gilles Louppe
Happy New Year!
Do your plans for 2026 include...
- working with a great team lead by @wellingmax.bsky.social and @aronwalsh.github.io?
- living in Amsterdam, Berlin, London, or Cambridge?
- using fun tools from ML and material science?
- solving important problems?
Then join us at CuspAI!
1/2
Do your plans for 2026 include...
- working with a great team lead by @wellingmax.bsky.social and @aronwalsh.github.io?
- living in Amsterdam, Berlin, London, or Cambridge?
- using fun tools from ML and material science?
- solving important problems?
Then join us at CuspAI!
1/2
January 1, 2026 at 7:51 PM
Happy New Year!
Do your plans for 2026 include...
- working with a great team lead by @wellingmax.bsky.social and @aronwalsh.github.io?
- living in Amsterdam, Berlin, London, or Cambridge?
- using fun tools from ML and material science?
- solving important problems?
Then join us at CuspAI!
1/2
Do your plans for 2026 include...
- working with a great team lead by @wellingmax.bsky.social and @aronwalsh.github.io?
- living in Amsterdam, Berlin, London, or Cambridge?
- using fun tools from ML and material science?
- solving important problems?
Then join us at CuspAI!
1/2
I just started playing with Claude Code too. It is really impressive π€―
December 30, 2025 at 12:55 PM
I just started playing with Claude Code too. It is really impressive π€―
Reposted by Gilles Louppe
A biologically detailed brain model has matched animal learning performance and uncovered previously overlooked neuron activity linked to errors during visual categorization tasks. doi.org/hbhcsn
Biology-inspired brain model matches animal learning and reveals overlooked neuron activity
A new computational model of the brain based closely on its biology and physiology has not only learned a simple visual category learning task exactly as well as lab animals, but even enabled the discovery of counterintuitive activity by a group of neurons that researchers working with animals to perform the same task had not noticed in their data before, reports a team of scientists at Dartmouth College, MIT, and the State University of New York at Stony Brook.
phys.org
December 29, 2025 at 4:50 PM
A biologically detailed brain model has matched animal learning performance and uncovered previously overlooked neuron activity linked to errors during visual categorization tasks. doi.org/hbhcsn
I have been in AI for science for 10+ years now. Real benefits, real impact. But 'AI' feels like a bad word now, with the media running 10:1 negative. Yet almost everyone around me uses LLMs daily. Honestly lost.
December 28, 2025 at 7:13 PM
I have been in AI for science for 10+ years now. Real benefits, real impact. But 'AI' feels like a bad word now, with the media running 10:1 negative. Yet almost everyone around me uses LLMs daily. Honestly lost.
Reposted by Gilles Louppe
Reposted by Gilles Louppe
Very nice arxiv.org/abs/2512.20003
Control Variate Score Matching for Diffusion Models
Diffusion models offer a robust framework for sampling from unnormalized probability densities, which requires accurately estimating the score of the noise-perturbed target distribution. While the sta...
arxiv.org
December 27, 2025 at 11:15 AM
Very nice arxiv.org/abs/2512.20003
Reposted by Gilles Louppe
What an amazing Yule gift from @stefanradev.bsky.social & colleagues: a tour-de-force tutorial on diffusion models for simulator-based inference.
This is one of the most comprehensive and useful review/tutorials I have ever seen -- a must read! Kudos to all the authors!
arxiv.org/abs/2512.20685
This is one of the most comprehensive and useful review/tutorials I have ever seen -- a must read! Kudos to all the authors!
arxiv.org/abs/2512.20685
Diffusion Models in Simulation-Based Inference: A Tutorial Review
Diffusion models have recently emerged as powerful learners for simulation-based inference (SBI), enabling fast and accurate estimation of latent parameters from simulated and real data. Their score-b...
arxiv.org
December 26, 2025 at 11:16 AM
What an amazing Yule gift from @stefanradev.bsky.social & colleagues: a tour-de-force tutorial on diffusion models for simulator-based inference.
This is one of the most comprehensive and useful review/tutorials I have ever seen -- a must read! Kudos to all the authors!
arxiv.org/abs/2512.20685
This is one of the most comprehensive and useful review/tutorials I have ever seen -- a must read! Kudos to all the authors!
arxiv.org/abs/2512.20685
Reposted by Gilles Louppe
Doing a PhD is - at heart - one long discussion with your mentor. The discussion changes over time - with unexpected turns and ups & downs - but through it all is a pair of people discussing a topic endlessly to make sense of it.
PhD students: choose someone you like to talk to!
PhD students: choose someone you like to talk to!
December 19, 2025 at 4:35 PM
Doing a PhD is - at heart - one long discussion with your mentor. The discussion changes over time - with unexpected turns and ups & downs - but through it all is a pair of people discussing a topic endlessly to make sense of it.
PhD students: choose someone you like to talk to!
PhD students: choose someone you like to talk to!
Reposted by Gilles Louppe
New AI models from @polymathicai.bsky.social use knowledge from scientific fields and apply it to others. Walrus (seen below) can tackle systems from exploding stars to Wi-Fi signals: https://www.simonsfoundation.org/these-new-ai-models-are-trained-on-physics-not-words-and-theyre-driving-discovery/
December 19, 2025 at 7:14 PM
New AI models from @polymathicai.bsky.social use knowledge from scientific fields and apply it to others. Walrus (seen below) can tackle systems from exploding stars to Wi-Fi signals: https://www.simonsfoundation.org/these-new-ai-models-are-trained-on-physics-not-words-and-theyre-driving-discovery/
Reposted by Gilles Louppe
Your pretty picture of the day π πwith of course many interesting processes! Water rich in suspended sediments is moved around by ocean currents in the Bay of Biscay. I'm curious about the long-range waves seen in the dark region, can't decide if these are oceanic, atmospheric, or an artifact π
December 17, 2025 at 9:55 AM
Your pretty picture of the day π πwith of course many interesting processes! Water rich in suspended sediments is moved around by ocean currents in the Bay of Biscay. I'm curious about the long-range waves seen in the dark region, can't decide if these are oceanic, atmospheric, or an artifact π
Reposted by Gilles Louppe
New orbit movie just dropped. This one is for the newly discovered circumbinary planet HD 143811 AB b. This 9-year timelapse was made through an international collaboration with me, Nathalie Jones (Northwestern graduate student), and Vito Squicciarini (Exeter postdoc)
A discovery fit for Star Wars: CIERA astronomers have directly imaged a Tatooine-like planet orbiting two suns β and itβs closer to its stars than any other directly imaged planet in a binary system. πππͺhttps://bit.ly/4q8Dfto
@thejason.wang #Exoplanets #Astronomy #Northwestern #CIERA
@thejason.wang #Exoplanets #Astronomy #Northwestern #CIERA
December 12, 2025 at 5:54 PM
New orbit movie just dropped. This one is for the newly discovered circumbinary planet HD 143811 AB b. This 9-year timelapse was made through an international collaboration with me, Nathalie Jones (Northwestern graduate student), and Vito Squicciarini (Exeter postdoc)
Reposted by Gilles Louppe
Excellent post d'une traductrice juridique qui ne mÒche pas ses mots à propos de la post-édition (MTPE). Il y a beaucoup de punchlines percutantes, mais en résumé : nous ne sommes pas des serpillières juste là pour nettoyer les flaques de d-IA-rrhée.
"Machine translation would handle the heavy lifting, and weβd add the expert polish. Except the machine made a mess. And weβre doing expert-level cognitive labour to clean it up for cleaning wages.
Weβre not mops. Weβre translators."
#translation #xl8
www.linkedin.com/pulse/open-l...
Weβre not mops. Weβre translators."
#translation #xl8
www.linkedin.com/pulse/open-l...
An open letter to colleagues: we are not mops
After more than two decades working in legal translation across four languages and multiple jurisdictions, Iβve watched our profession reshaped by forces that claim efficiency as a path to our expenda...
www.linkedin.com
December 10, 2025 at 2:50 PM
Excellent post d'une traductrice juridique qui ne mÒche pas ses mots à propos de la post-édition (MTPE). Il y a beaucoup de punchlines percutantes, mais en résumé : nous ne sommes pas des serpillières juste là pour nettoyer les flaques de d-IA-rrhée.
Reposted by Gilles Louppe
Repeat after me: This is NOT a paper contribution, itβs an expected component!
December 8, 2025 at 6:01 PM
Repeat after me: This is NOT a paper contribution, itβs an expected component!
Reposted by Gilles Louppe
was at an event on AI for science yesterday, a panel discussion here at NeurIPS. The panelists discussed how they plan to replace humans at all levels in the scientific process. So I stood up and protested that what they are doing is evil.
Full post:
togelius.blogspot.com/2025/12/plea...
Full post:
togelius.blogspot.com/2025/12/plea...
Please, don't automate science!
I was at an event on AI for science yesterday, a panel discussion here at NeurIPS. The panelists discussed how they plan to replace humans a...
togelius.blogspot.com
December 8, 2025 at 6:51 AM
was at an event on AI for science yesterday, a panel discussion here at NeurIPS. The panelists discussed how they plan to replace humans at all levels in the scientific process. So I stood up and protested that what they are doing is evil.
Full post:
togelius.blogspot.com/2025/12/plea...
Full post:
togelius.blogspot.com/2025/12/plea...
Reposted by Gilles Louppe
Why can neurons with completely different ion channels fire identically? π§
Neuronal degeneracy isn't a bug - it's a feature. Come see how we reconstruct entire degenerate populations from spike times within an interpretable feedback framework.
Poster @dataonbrainmind.bsky.social
#NeurIPS2025 #DBM
Neuronal degeneracy isn't a bug - it's a feature. Come see how we reconstruct entire degenerate populations from spike times within an interpretable feedback framework.
Poster @dataonbrainmind.bsky.social
#NeurIPS2025 #DBM
December 7, 2025 at 4:13 PM
Why can neurons with completely different ion channels fire identically? π§
Neuronal degeneracy isn't a bug - it's a feature. Come see how we reconstruct entire degenerate populations from spike times within an interpretable feedback framework.
Poster @dataonbrainmind.bsky.social
#NeurIPS2025 #DBM
Neuronal degeneracy isn't a bug - it's a feature. Come see how we reconstruct entire degenerate populations from spike times within an interpretable feedback framework.
Poster @dataonbrainmind.bsky.social
#NeurIPS2025 #DBM
Reposted by Gilles Louppe
If you are interested in diffusion models for dynamical systems and posterior inference, stop by our poster at ML4PS workshop (@neuripsconf.bsky.social) at 11am!
Come and see how we apply modern methods to the challenging field of global weather inference!
Come and see how we apply modern methods to the challenging field of global weather inference!
December 6, 2025 at 6:53 PM
If you are interested in diffusion models for dynamical systems and posterior inference, stop by our poster at ML4PS workshop (@neuripsconf.bsky.social) at 11am!
Come and see how we apply modern methods to the challenging field of global weather inference!
Come and see how we apply modern methods to the challenging field of global weather inference!
Reposted by Gilles Louppe
The Nobel Prize committee should announce the World Cup winner tomorrow
December 6, 2025 at 4:29 AM
The Nobel Prize committee should announce the World Cup winner tomorrow
Reposted by Gilles Louppe
Later we did early work using message passing graph NNs with @joanbruna.bsky.social and @johannbrehmer.bsky.social. Fully connected message passing NNs are pretty similar to transformers, but this was in 2017.
ml4physicalsciences.github.io/2017/files/n...
ml4physicalsciences.github.io/2017/files/n...
ml4physicalsciences.github.io
December 5, 2025 at 4:50 PM
Later we did early work using message passing graph NNs with @joanbruna.bsky.social and @johannbrehmer.bsky.social. Fully connected message passing NNs are pretty similar to transformers, but this was in 2017.
ml4physicalsciences.github.io/2017/files/n...
ml4physicalsciences.github.io/2017/files/n...
Reposted by Gilles Louppe
An unexpected shoutout from @kyunghyuncho.bsky.social in his NeurIPS keynote. @glouppe.bsky.social & I collaborated with him to bring ideas from natural language to high-energy physics back in 2016.
arxiv.org/abs/1702.00748
arxiv.org/abs/1702.00748
December 5, 2025 at 4:50 PM
An unexpected shoutout from @kyunghyuncho.bsky.social in his NeurIPS keynote. @glouppe.bsky.social & I collaborated with him to bring ideas from natural language to high-energy physics back in 2016.
arxiv.org/abs/1702.00748
arxiv.org/abs/1702.00748
Reposted by Gilles Louppe
Beautiful keynote by @gaelvaroquaux.bsky.social at @euripsconf.bsky.social .
December 5, 2025 at 12:50 PM
Beautiful keynote by @gaelvaroquaux.bsky.social at @euripsconf.bsky.social .