Lightnews — Scholar-powered news

Reposted by Matthias Pirlet

Gérôme Andry @gandry.bsky.social · Apr 29

After several month, our work is out! 🦬

Look at our new paper with the team!

Thanks to all of them!!

@glouppe.bsky.social
@sachalewin.bsky.social
@francois-rozet.bsky.social
@orochman.bsky.social
@mapirlet.bsky.social
Victor Mangeleer
Elise Faulx

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 🧵

2 4 9

Reposted by Matthias Pirlet

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 🧵

2 15 50

Matthias Pirlet @mapirlet.bsky.social · Apr 26

Happy birthday! Enjoy!

1

Matthias Pirlet @mapirlet.bsky.social · Apr 10

The greatest act of insider trading ever committed...

Outspoken™️ @out5p0ken.bsky.social · Apr 10

“He made 2.5 million today and he made $900 million. That’s not bad.”

Sounds like market manipulation to me. That’s bad.

Reposted by Matthias Pirlet

Gilles Louppe @glouppe.bsky.social · Dec 30

📣 Hiring! I am looking for PhD/postdoc candidates to work on foundation models for science at @ULiege, with a special focus on weather and climate systems. 🌏 Three positions are open around deep learning, physics-informed FMs and inverse problems with FMs.

4 35 79

Reposted by Matthias Pirlet

Adrien Bolland @adrienbolland.bsky.social · Dec 13

Check our work on max entropy RL! We introduce an off-policy method to maximize the entropy of the future state-action visitation distribution, leading to policies that explore effectively and achieve high performance 🎯

Link 📑 arxiv.org/abs/2412.06655

#RL #MaxEntRL #Exploration

Off-Policy Maximum Entropy RL with Future State and Action Visitation Measures

We introduce a new maximum entropy reinforcement learning framework based on the distribution of states and actions visited by a policy. More precisely, an intrinsic reward function is added to the re...

arxiv.org

4 8

Matthias Pirlet @mapirlet.bsky.social · Dec 11

Great to see such engagement with your poster!

1 7

Reposted by Matthias Pirlet

François Rozet @francois-rozet.bsky.social · Dec 7

I'll be in Vancouver from Dec 9 to Dec 16 to present our work at NeurIPS 2024 🇨🇦 If you want to talk about generative models, ML for science, open-source software, or bouldering, send me a DM, a comment or an email!

4 24

Reposted by Matthias Pirlet

François Rozet @francois-rozet.bsky.social · Dec 2

Deep learning can do more than generating cute cat pictures. It is a game changer for Science as a whole. But benchmarking DL methods on scientific data is complex ... until today!

I am super proud to have contributed to The Well as part of my internship at @polymathicai.bsky.social !

Ruben Ohana @rubenohana.bsky.social · Dec 2

Generating cat videos is nice, but what if you could tackle real scientific problems with the same methods? 🧪🌌
Introducing The Well: 16 datasets (15TB) for Machine Learning, from astrophysics to fluid dynamics and biology.
🐙: github.com/PolymathicAI...
📜: openreview.net/pdf?id=00Sx5...

4 23

Matthias Pirlet @mapirlet.bsky.social · Nov 21

Great! See you there!

Reposted by Matthias Pirlet

Gilles Louppe @glouppe.bsky.social · Nov 8

After weeks of coding, reviewing and debugging, our GPUs can finally go brrrr! Can't wait to see early results 👀

1 4