I am super happy to share that our project on training biophysical models with Jaxley is now published in Nature Methods: www.nature.com/articles/s41...

It's remarkable how AI generated images have gone from remarkable and visually attractive to repulsive AI slop in just a few years.

I am incredibly honored to have received the inaugural AI in Science Research Excellence Prize from the Margot and Tom Pritzker Foundation dsi.wisc.edu/2025/11/10/d...

‪Once again an interdisciplinary research project gets poor, even condescending this time, evaluations because reviewers make little effort to understand the maths. Science is not only about killing rat models and to see if some random drug worked. Tired of this game.

This Nature retrospective is quite interesting. To me, the only solution to the credit assignment problem is obvious: stop believing a single person is responsible for every big discovery. It's an artifact of our monkey brain requiring a face for storage, not the reality of how knowledge progresses.

New paper, with @rkhashmani.me @marielpettee.bsky.social @garrettmerz.bsky.social Hellen Qu. We introduce a framework for generating realistic, highly multimodal datasets with explicitly calculable mutual information. This is helpful for studying self-supervised learning arxiv.org/abs/2510.21686

"The Principles of Diffusion Models" by Chieh-Hsin Lai, Yang Song, Dongjun Kim, Yuki Mitsufuji, Stefano Ermon. arxiv.org/abs/2510.21890 It might not be the easiest intro to diffusion models, but this monograph is an amazing deep dive into the math behind them and all the nuances

EM algorithm: 1977 vintage, 2025 relevant. New lecture notes on a classic that refuses to age. From fitting a GMM on the Old Faithful data to training modern diffusion models in incomplete data settings, the same simple math applies. 👉 glouppe.github.io/dats0001-fou...

Fisher meets Feynman! 🤝 We use score matching and a trick from quantum field theory to make a product-of-experts family both expressive and efficient for variational inference. To appear as a spotlight @ NeurIPS 2025. #NeurIPS2025 (link below)

What if we did a single run and declared victory

Excited to share SamudrACE, the first 3D AI ocean–atm–sea-ice #climate emulator! 🚀 Simulates 800 years in 1 day on 1 GPU, ~100× faster than traditional models, straight from your laptop 👩‍💻 Collaboration with @ai2.bsky.social and GFDL, advancing #AIforScience with #DeepLearning. tinyurl.com/Samudrace

🕳️🐇 𝙄𝙣𝙩𝙤 𝙩𝙝𝙚 𝙍𝙖𝙗𝙗𝙞𝙩 𝙃𝙪𝙡𝙡 – 𝙋𝙖𝙧𝙩 𝙄 (𝑃𝑎𝑟𝑡 𝐼𝐼 𝑡𝑜𝑚𝑜𝑟𝑟𝑜𝑤) 𝗔𝗻 𝗶𝗻𝘁𝗲𝗿𝗽𝗿𝗲𝘁𝗮𝗯𝗶𝗹𝗶𝘁𝘆 𝗱𝗲𝗲𝗽 𝗱𝗶𝘃𝗲 𝗶𝗻𝘁𝗼 𝗗𝗜𝗡𝗢𝘃𝟮, one of vision’s most important foundation models. And today is Part I, buckle up, we're exploring some of its most charming features. :)

Thrilled to have two years' of work out, in a pair of papers led by @gradientrider.bsky.social and @maxecharles.bsky.social. We've built a data-driven calibration of the James Webb Interferometer to near its fundamental limits for high-res imaging - explainer at @aunz.theconversation.com!

Dans cette interview avec la JASRAC (équivalent japonais de la SACEM), Nobuo Uematsu a donné son avis sur la musique générée par IA. À sa façon, il relaie ce nouvel adage : si personne ne s'est fatigué à l'écrire, je ne me fatiguerai pas à l'écouter. 📃 www.jasrac.or.jp/magazine/int...

🚀 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...

Had never read Jane Goodall's original 1963 article in Nat Geo on the wild chimpanzees in Tanzania until now. It's a wonderful blend of science and journalism, and well worth your time. www.nationalgeographic.com/pdf/jane-goo...

Yeah, I think that "AI is the new petrol" is about right...

Rudolf Kalman put it nicely (and provocatively): link.springer.com/chapter/10.1...

How do you type all these long long hyphens? — I keep seeing them everywhere. I learned the UTF-8 code by now but there must be something easier 🤔

🔭 It's paper day! Today I'm sharing the latest in a series of papers looking at the weather on other worlds, in this case bringing you the weather report from a nearby T-dwarf, SIMP-0136. 🪐 🧵 to follow...

We’re excited to introduce ShinkaEvolve: An open-source framework that evolves programs for scientific discovery with unprecedented sample-efficiency. It leverages LLMs to find state-of-the-art solutions, orders of magnitude faster! Blog: sakana.ai/shinka-evolve/ Paper: arxiv.org/abs/2509.19349

For folks considering grad school in ML, my advice is to explore programs that mix ML with a domain interest. ML programs are wildly oversubscribed while a lot of the fun right now is in figuring out what you can do with it

Cecilia Payne-Gaposchkin ✨ figured out what stars are made of ✨ when she was just 25. 🔭🧪 Her PhD thesis basically established the Harvard astro department — at a time when Harvard didn't officially allow woman students. I wrote this little profile to mark the 100th anniversary of her thesis:

"It's the greatest con job ever perpetrated on the world.” In his remarks at the United Nations General Assembly, President Trump addressed climate change, saying, "If you don't get away from this green scam, your country is going to fail."

The people I work with are not stupid people and our climate predictions of 30 years ago of global warming have proved to be accurate. Just saying. www.bbc.co.uk/news/live/cp...

In 1950, Alan Turing - while at @manchester.ac.uk - proposed a simple but profound experiment: can a machine convincingly imitate human thought? We now call it the Turing Test. 🧠💻

As an SAC for @neuripsconf.bsky.social, I don't agree with PCs approach to reject papers based on ranking. I ranked my accepted papers as requested and explicitly stated that I support the acceptance of all papers. I was not given an explanation of why papers at the end of the rank were rejected.

Is this the year we finally break up @neuripsconf.bsky.social?

After years of complaining about cancel culture, the current administration has taken it to a new and dangerous level by routinely threatening regulatory action against media companies unless they muzzle or fire reporters and commentators it doesn’t like.

To celebrate the 10 year anniversary of the first gravitational wave detection, I made a tutorial for high school students that explains how to use python to visualize the original gravitational wave data of GW150914. (Tested and approved by a very motivated German 10th grade student 😄) #GW10Years

I'm very excited to introduce P3D: our PDE-Transformer architecture in 3 dimensions by . Demonstrated for unprecedented 512^3 resolutions! That means the Transformer produces over 400 million degrees of freedom in one go 😀 a regime that was previously out of reach: arxiv.org/abs/2509.10186

We promise this pandemic was only virtual. 20 years ago, an unexpected event in the online game "World of Warcraft" caught the attention of players and researchers. A new dungeon introduced a boss whose special attack temporarily drained a player’s health and could spread to others nearby. 🧵⬇️ (1/3)

Most industrial reactions happen on catalyst surfaces, but predicting which surfaces actually form is costly. Jun Yin and coauthors present SurFF, a foundation model that predicts surface exposure across intermetallic crystals with DFT-level accuracy, 100k× faster. www.nature.com/articles/s43...

Locality in Image Diffusion Models Emerges from Data Statistics, by Artem Lukoianov et al. (arxiv.org/abs/2509.09672), retweet if you want your model to generate samples in the "sampling voids".

The application for a research fellowship at the Flatiron Institute in the Center for Computational Math is now live! This includes positions for ML and stats. The deadline is Dec 1. apply.interfolio.com/173401 ML@CCM group: users.flatironinstitute.org/~lsaul/ml_cc...

I skimmed a paper of an author I dislike and it's amazing how a certain style of writing --overly complicated explanations of trivial claims, new jargon that hides how vacuous it all is, an overemphasize on mathematization regardless of whether it actually maps onto the claims made-- just wrecks me.

In @science.org, Buchli et al. have applied sophisticated machine learning techniques to the control electronics of @ligo.org. This improves the sensitivity of the detector at low frequencies - expanding its cosmological reach, particularly for low-mass mergers. ⚛️☄️ www.science.org/doi/10.1126/...

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!

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 👇

Flying ✈️ to Stockholm for 2 days of AI for Science at the Royal Swedish Academy of Sciences scienceacademyswe.bsky.social Anyone around?

Very proud to see the #ML4PS2025 workshop thrive! ... but where will we put so many posters? 👀 (subtweet)

Thanks for raising this issue. As someone on the authors' and reviewers' side, this feels like a violation of the reviewing process. One might wonder, “Why do we put so much time and effort into the peer-review process if decisions are ultimately made arbitrarily?”.

Just finished delivering a course on 'Robust and scalable simulation-based inference (SBI)' at Greek Stochastics. This covered an introduction to SBI, open challenges, and some recent contributions from my own group. The slides are now available here: fxbriol.github.io/pdfs/slides-....

Let's push for the obvious solution: Dear @neuripsconf.bsky.social ! Allow authors to present accepted papers at EurIPS instead of NeurIPS rather than just additionally. Likely, at least 500 papers would move to Copenhagen, problem solved.

Luca Ambrogioni The Information Dynamics of Generative Diffusion https://arxiv.org/abs/2508.19897

What a wild thing to read. "If such a prompt injection is included in a submission and it consequently results in a positive LLM-generated review, we consider this a form of collusion...that both the paper authors and the reviewer would be held accountable for, blog.iclr.cc/2025/08/26/p...

When a crystal is placed near a magnet, its electrons can only have certain amounts of energy. When this phenomenon is graphed, fractal patterns called Cantor sets emerge. www.quantamagazine.org/ten-martini-...

Next plenary talk at #GRETSI2025 my colleague Marc Bocquet from @ecoledesponts.bsky.social on AI in geosciences and data assimilation

Une longue succession de témoignages déprimants (j'ai failli envoyer le mien) pour témoigner de la mort rapide de la traduction humaine, remplacée par une automatisation pourtant très défaillante. Ce paragraphe est absolument pertinent : l'hystérie autour de l'IAgen a permis ce basculement.