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!

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!

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...

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

📝 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!

📣 New paper alert — To be presented at ICML 2025! arxiv.org/abs/2405.08719 What does it really mean for a simulator to be misspecified, if our goal is to estimate parameters with calibrated uncertainty? A 🧵on our new method, RoPE, and what it means for real-world SBI ⬇️

I can't recommend @francois-rozet.bsky.social enough👇He is both this excellent researcher and coder that any ML team would dream having onboard CC: @danilojrezende.bsky.social @awehwe.bsky.social @bkmi.bsky.social @yann-lecun.bsky.social @johannbrehmer.bsky.social

📢 I am looking for AI post-doc/research/engineer positions in Europe (Paris, London, Zurich, ...) starting 2026. My work revolves around generative modeling and AI for Science, with 4+ publications at top conferences during my PhD. If you are hiring, please reach out! If not, please repost 🔁

We've open sourced Adjoint Sampling! It's part of a bundled release showcasing FAIR's research and open source commitment to AI for science. github.com/facebookrese... There's also a blog about the release ai.meta.com/blog/meta-fa...

Today, we’re announcing the preview release of ty, an extremely fast type checker and language server for Python, written in Rust. In early testing, it's 10x, 50x, even 100x faster than existing type checkers. (We've seen >600x speed-ups over Mypy in some real-world projects.)

<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 🧵

For my first🧵on bsky, what if a single UNet could solve all inverse problems? In our latest preprint with Samuel Hurault, Maxime Song and @tachellajulian.bsky.social, we build a single multitask UNet for computational imaging — and show it generalizes surprisingly well 👇 arxiv.org/abs/2503.08915

Have you ever been curious to try Causal Normalizing Flows for your project but found them intimidating? Say no more 😜 I just released a small library to easily implement and use causal-flows: github.com/adrianjav/ca...

Would you present your next NeurIPS paper in Europe instead of traveling to San Diego (US) if this was an option? Søren Hauberg (DTU) and I would love to hear the answer through this poll: (1/6)

Just got a puzzle rated 3748 on @chess.com. Obviously, I failed 😂 The first move was insane, but the rest wasn't too far fetched.

The two postdoctoral positions remain open! (the PhD position has been filled) Applications from deep learning researchers or atmospheric scientists are welcome! Ping me if you have any questions!

🔥 Azula 0.3.0 is out with many new features, including new super fast samplers (LMS, DPM-Solver), new guidance methods (DPS, MMPS) and new plugins (VDM, EMD, EMD2). Check it out!

For anyone interested in trying a higher-order optimizer, here is a clean and fast implementation of SOAP 🧼 in PyTorch, with support for low-precision. I recommend using the same learning rate as you would for AdamW. gist.github.com/francois-roz...

The slides of my NeurIPS lecture "From Diffusion Models to Schrödinger Bridges - Generative Modeling meets Optimal Transport" can be found here drive.google.com/file/d/1eLa3...

The template for this poster is now available on GitHub! github.com/francois-roz...

📣 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.

My favourite talk of NeurIPS 2024!

Great to see such engagement with your poster!

A common question nowadays: Which is better, diffusion or flow matching? 🤔 Our answer: They’re two sides of the same coin. We wrote a blog post to show how diffusion models and Gaussian flow matching are equivalent. That’s great: It means you can use them interchangeably.

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!

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...

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 !

Hello World!

I'm making a list of AI for Science researchers on bluesky — let me know if I missed you / if you'd like to join! go.bsky.app/AcP9Lix

i just love @typst.app