François Rozet

I'll be in Copenhagen from Tuesday to Saturday for the @euripsconf.bsky.social experiment! Please let me know if you want to chat about diffusion, flow, ml for science, or anything really. 🇩🇰

Our Montefiore Science with AI lab will be at #NeurIPS2025 presenting 1 paper at the main conference and 3 papers at workshops. If you are attending, feel free to reach out with the crew to discuss science, AI, or just to say hi! (I won't attend this year unfortunately 🌱)

Typst Code: #image("logo.pdf")

Logo of GlorboCorp

You can now use PDFs as images: Just pass a PDF file to the image function and Typst will handle the rest. PDF images let you use vector and raster graphics from almost any other app. PDF images can be used for every Typst export target, including HTML.

Image saying Typst 0.14. It has a holographic effect. The background is a pattern of checkmarks, at the top, it changes to a pattern of the string "0.14". The horizontal bar across the top reads "Title Elementm Skewed Fractions, Table Subheaders, Accessible Documents, Character-level Justification, PDF/A compliance, PDF Images, Typed HTML API"

Typst 0.14 is out now! Get ready for production with accessibility, PDFs as images, character-level justification, and more. Learn about more of the highlights in Typst 0.14 in the thread below ⤵️

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

🚀 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...

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...

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

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 🤗

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!

cc @polymathicai.bsky.social @flatironinstitute.org

Sorry I mistyped @sedielem.bsky.social handle!

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!

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

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

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!

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

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...

Generative modelling in latent space Latent representations for generative models.

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/...

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...

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

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

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!

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.

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 👇

@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...

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!

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

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...

🎉 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

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

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

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

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).

📝 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.

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!

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.