Francisco Villaescusa-Navarro

Don’t miss this week’s entry in the AI & Scientific Discovery Online Seminar! Featuring Boris Bolliet (assistant professor, @Cambridge_Uni) and @paco_astro (Researcher, @FlatironInst) Join us on Friday, March 13th ai-scientific-discovery.github.io

Call for graduate students interested in building AI agents for scientific discovery. Joint us in New York City! simonsfoundation.org/flatiron-insti… #Denario github.com/AstroPilot-AI/…

Discovery is not search - it is thermodynamics! I'll explain this & much more at the @AImeetsScience Seminar on Jan 30, 2026, including how we are teaching machines to lead this process - forcing new worlds into existence when old ones can no longer remain stable. Link in the reply! Thank you @ChenhaoTan for organizing this exciting series of talks with amazing co-presenters @boknilev @yisongyue @cgeorgiaw @HannesStaerk @borisbolliet @paco_astro

Happy new year! The AI & Scientific Discovery Seminar is returning this quarter. Last quarter was incredible, from protein design to AI scientists to automated bio labs. Huge thanks to all our amazing speakers and attendees 🙌 We’re kicking off Winter Quarter with an 🔥 lineup, starting this Friday at 11am CT! 👉 @boknilev will share how interpretability methods are driving scientific discovery. Links in the thread. @yisongyue @cgeorgiaw @HannesStaerk @borisbolliet @paco_astro

Just read the Denario paper from @paco_astro and @FlatironInst - a multi-agent AI scientist with a clean API. What caught my eye: they report ~10% of outputs across domains raised an intriguing question or finding. That's a trainable signal. If you can reliably identify interesting vs. not, that's possibly an RL opportunity waiting to happen. Curious where this goes. Link to paper and code in comments.

The Denario project: Deep knowledge AI agents for scientific discovery - arXiv👇 arxiv.org/abs/2510.26887

Can we advance cosmology via ML? Can we build better benchmarks for graph learning? Introducing CosmoBench: a large-scale cosmology benchmark for graph/geometric ML, with 34k clouds and 25k trees from SOTA simulations (2PB+ data, 41M+ core hours) Now accepted to @NeurIPSConf !

Why does NVIDIA is using CAMELS image to talk about JAMBA?!? developer.nvidia.com/blog/jamba-1-5… see it here youtu.be/0ntjD7PDWG0?si… @physicskaze @paco_astro

Deadline is September 20th.

We are organizing a workshop in New York City to discuss how to combine numerical simulations with machine learning techniques to improve our knowledge of cosmology and galaxy formation. If you are interested in attending, please register here events.simonsfoundation.org/event/51977633…

Excited to share our latest paper, in collaboration with @paco_astro and Marco Baldi! We perform the first application of the Wavelet Scattering Transform technique to test theories of gravity, finding very promising results! Arxiv link: arxiv.org/abs/2407.18647

ten institutions worldwide. If you want to learn more about DREAMS take a look at our presentation paper arxiv.org/abs/2405.00766 and our website dreams-project.org

We will produce the largest collection of these simulations ever created and use AI to find new and robust observables of dark matter properties on astrophysical data. Our team contains experts on galaxy formation, cosmology, particle physics, and machine learning from more than

The DREAMS (DaRk mattEr and Astrophysics with Machine learning and Simulations) project just started! We are combining astrophysics, particle physics, and machine learning to learn about the nature and properties of dark matter.

The newest ‘hump’ of the CAMELS project is live! We present and make publicly available 768 hydrodynamical zoomed-in simulations of massive halos varying 5 cosmological parameters and 23 astrophysical parameters within the IllustrisTNG model. Check out arxiv.org/abs/2403.10609

predoctoral program in New York City. Applications from (astro-)physics and CS students are very welcome! For more information, see this: simonsfoundation.org/flatiron-insti…

Do you want to work on creating the largest collection of virtual universes to date? Would you like to explore these with state-of-the-art deep-learning techniques? Do you want to use these simulations to unveil the mysteries of the Universe? Consider applying to our 4.5 months

🔍Worried about the presence of interlopers in your galaxy catalog? 📢We developed a new method based on GNNs to infer the interloper fraction in a catalog using likelihood-free inference. 📄 Check out our new paper: arxiv.org/abs/2309.05850

- @licia_verde - Lawrence Saul - Torsten Ensslin - ... Abstract submissions deadline? - August 31st, 2023

- Jens Jasche - Tomasz Kacprzak - @SoledadVillar5 - Tiziana DiMatteo - David Shih - Nabila Aghanim - Pierre Casenove - Aleksandra Ciprijanovic - Helena Domínguez Sánchez - @davidwhogg - @kchonyc - François Lanusse - Luisa Lucie-Smith - Henry Joy McCracken - @DavidSpergel

Interested in machine learning and astronomy? Please attend the international conference we are organizing: indico.iap.fr/event/1/ When? - November 27th - December 1st Where? - New York - Paris - Online Who? - @MilesCranmer - Marylou Gabrié +