Lightnews — Scholar-powered news

Reposted by François Rozet

Signal @signal.org · 5d

We are alarmed by reports that Germany is on the verge of a catastrophic about-face, reversing its longstanding and principled opposition to the EU’s Chat Control proposal which, if passed, could spell the end of the right to privacy in Europe. signal.org/blog/pdfs/ge...

signal.org

40 2.4K 3.9K

Reposted by François Rozet

Richard Gao @rdgao.bsky.social · 15d

I've been waiting some years to make this joke and now it’s real:

I conned somebody into giving me a faculty job!

I’m starting as a W1 Tenure-Track Professor at Goethe University Frankfurt in a week (lol), in the Faculty of CS and Math

and I'm recruiting PhD students 🤗

a man wearing a white shirt and tie smiles in front of a window

ALT: a man wearing a white shirt and tie smiles in front of a window

media.tenor.com

30 31 180

Reposted by François Rozet

Lukas Heinrich @lukasheinrich.com · Sep 4

Big grant news today! I feel very lucky and honored for this opportunity from @erc.europa.eu . We will attempt to go for a big qualitative step up in how we use AI/ML to predict how particles interact with matter. Stoked to get started on this in 2026. we will release job advertisements soon!

Technische Universität München @tum.de · Sep 4

Congratulations to six of our #researchers, including Lukas Heinrich, who receive prestigious ERC #StartingGrants worth up to 1.5 million euros each for projects in #informatics, #medicine, #LifeSciences & #NaturalSciences: go.tum.de/682017 👏

#ERCStG @erc.europa.eu

📷A.Eckert

Six ERC Starting Grants for researchers at TUM

Six further researchers at TUM are to receive the prestigious ERC Starting Grants for their projects.

go.tum.de

9 5 27

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

cc @polymathicai.bsky.social @flatironinstitute.org

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

Sorry I mistyped @sedielem.bsky.social handle!

1

Reposted by François Rozet

Mike McCabe @michael-mccabe.bsky.social · Sep 3

Great work by @francois-rozet.bsky.social. Some really unexpected insights about compression in LDMs. It was such a privilege to have him with us @polymathicai.bsky.social!

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 👇

1 1

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

cc @rubenohana.bsky.social, @michael-mccabe.bsky.social, @glouppe.bsky.social, François Lanusse and Shirley Ho

1 1

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

This work marks the final chapter of my PhD. Next up: writing my thesis and embark on a new adventure! Stay tuned 🚀

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

This work was conducted as part of my internship with @PolymathicAI at the @FlatironInst in New York 🗽 It was an amazing experience to be part of a talent-dense team in such an outstanding environment. I wholeheartedly recommend it to anyone!

2

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

The paper is full of details and insights. We also release the code and model weights. Go check it out!

Thanks to my co-authors ❤️

Paper: arxiv.org/abs/2507.02608
Data: github.com/PolymathicA...
Code: github.com/polymathicA...
Blog: polymathic-ai.org/blog/lostin...

GitHub - PolymathicAI/lola: Official implementation of "Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation"

Official implementation of "Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation" - PolymathicAI/lola

github.com

2 1

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

I am beyond proud to finally release this work. We started with a simple question, and we ended up with totally unexpected results. We had to read and do tons of experiments to convince ourselves. S/O @sedielem for the insights on LDMs and V-information!

sander.ai/2025/04/15/...

Generative modelling in latent space

Latent representations for generative models.

sander.ai

2 1

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

While these results seemingly violate the data processing inequality, they are well aligned with @xuyilun2's theory of usable information, where a representation can hold more V-information from the point of view of a computationally constrained observer.

arxiv.org/abs/2002.10689

A Theory of Usable Information Under Computational Constraints

We propose a new framework for reasoning about information in complex systems. Our foundation is based on a variational extension of Shannon's information theory that takes into account the...

arxiv.org

1 4

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

Our experiments also show that latent diffusion models are consistently more accurate than deterministic neural solvers while producing diverse, statistically plausible trajectories.

1 3

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!

1 1 2

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

Our methodology is quite simple: we train auto-encoders to compress the state of dynamical systems (fluids, stars, ...) and train a latent diffusion model to emulate the dynamics in the compressed space. We then study the impact of the compression rate on the emulation accuracy.

1 2

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 👇

1 8 27

François Rozet @francois-rozet.bsky.social · Jul 26

@neuripsconf.bsky.social removed the global rebuttal option?!? This was super useful (for authors AND reviewers AND area chairs AND readers) to get a summary of the common concerns of the reviewers and how the authors addressed them...

2

François Rozet @francois-rozet.bsky.social · Jul 17

It would be fantastic if EurIPS posted the number of registrations. It could convince more people to register and have a snowball effect. Maybe more people would go to EurIPS than NeurIPS!

1 1 4

Reposted by François Rozet

Gaspard Lambrechts @gsprd.be · Jul 16

At #ICML2025, we will present a theoretical justification for the benefits of « asymmetric actor-critic » algorithms (#W1008 Wednesday at 11am).

📝 Paper: hdl.handle.net/2268/326874
💻 Blog: damien-ernst.be/2025/06/10/a...

ICML poster of the paper « A Theoretical Justification for Asymmetric Actor-Critic Algorithms » by Gaspard Lambrechts, Damien Ernst and Aditya Mahajan.

3 8

Reposted by François Rozet

Kyle Cranmer @kylecranmer.bsky.social · Jul 10

🎉 Great news: Our Machine Learning and Physical Sciences workshop will be back again this year! 🎉
Keep an eye out for updates on deadlines etc, we will be updating the website soon
ml4physicalsciences.github.io
#ML4PS2025

9 33

Reposted by François Rozet

Kyle Cranmer @kylecranmer.bsky.social · Jul 3

As always, a very nice talk from Francois Lanusse: Generative Al for Inverse Problems and Forecasting
Slides: eiffl.github.io/talks/Paris2...

6 25

Reposted by François Rozet

ELLIS @ellis.eu · Jun 12

🏹 Job alert: PhD/postdoc positions in Scientific Foundation Models at the University of Liège (Belgium)

📍 Liège 🇧🇪
🔗 More info: https://bit.ly/43SJtUG

PhD/postdoc positions in Scientific Foundation Models at the University of Liège (Belgium)

The ELLIS mission is to create a diverse European network that promotes research excellence and advances breakthroughs in AI, as well as a pan-European PhD program to educate the next generation of AI...

bit.ly

5 13

Reposted by François Rozet

Gaspard Lambrechts @gsprd.be · Jun 9

📝 Our paper "A Theoretical Justification for Asymmetric Actor-Critic Algorithms" was accepted at #ICML!

Never heard of "asymmetric actor-critic" algorithms? Yet, many successful #RL applications use them (see image).

But these algorithms are not fully understood. Below, we provide some insights.

Slide showing three recent successes of reinforcement learning that have used an asymmetric actor-critic algorithm:
- Magnetic Control of Tokamak Plasma through Deep RL (Degrave et al., 2022).
- Champion-Level Drone Racing using Deep RL (Kaufmann et al., 2023).
- A Super-Human Vision-Based RL Agent in Gran Turismo (Vasco et al., 2024).

1 7 16

Reposted by François Rozet

Gilles Louppe @glouppe.bsky.social · Jun 4

Positions remain open! Both PhD and postdoctoral opportunities are available on scientific foundation models. An additional position is also available on AI for regional climate models (jointly with @xavierfettweis.bsky.social). Do not hesitate to apply!

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.

8 14

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

It is hard to describe. I think it has a lot to do with the density. The figures are never too crowded. Each figure convey one message well. Distractions are stripped away.

Lines are also thick enough that it can be read without zooming in and the color palettes are nice.