Registration and call for contribution are still open for the Sacl-AI 4 Science Workshop, July 8-12! Fundamental training in ML for scientists of all background (Mon-Tues) and inspiring demonstrations of how ML already assists research (Wed-Fri). indico.mathrice.fr/e/saclai

[EVENT 📣] Don't forget: the GAP scientific #seminar takes place next week from May 29 to 30 at the Maison de la Création et de l'Innovation (MaCI) 💡 Good news if you can't attend in person: we'll be streaming the event here ➡ videos.univ-grenoble-alpes.fr/live/events/ #MachineLearning #Physics

adding that delicious final touch

The first day of the Grenoble AI for Physical sciences workshop (gap2024.sciencesconf.org) has finished! Thanks to our speakers for their great talks - Marc Bouquet, Marylou Gabrié Marylou Gabrié, Nicolas Brodu, Gilles Louppe Gilles Louppe. #gap2024 #grenoble #ai4science

new paper on simulation-based inference using Gaussian mixtures to learn likelihood and posterior, without neural networks 😱😱😱 Our SeMPLE (Sequential Mixture Posterior and Likelihood Estimation) provides excellent inference and excels when the posterior is multimodal. 1/n

Great article on how the current AI arms race is making is increasingly unlikely that BigTech will meet their net-zero pledges. Arms races made humanity smart through evolution, but will it also be its demise? Source: the Guardian search.app/szor4fvupc85zT…

#neurips2024 rebuttal feelings

We just released a new version of `sbi`, and this one has _a ton_ of new features! Many of these features are thanks to more than 30 (mostly new) contributors. We are very excited about the growing community and the new release! 🧵 1/8

"... it is entirely possible that future generations will look back, from the vantage point of a more sophisticated theory, and wonder how we could have been so gullible." — The closing sentence of Introduction to Quantum Mechanics by David J. Griffiths.

We’re stoked to share: “A Practical Guide to Sample-based Statistical Distances for Evaluating Generative Models in Science”. Now out in TMLR: openreview.net/forum?id=isEFz… This was an incredibly special project for us, as it involved the **entire** lab getting together!

recent *review paper* on (neural) amortised simulation-based inference. I haven't seen it publicized much here among my connections, so there you go

Whaou! I did not expect that! Congrats Sam Altman

Fully-funded #PhD in #ML at The University of Edinburgh (School of Informatics, The University of Edinburgh, ANC@Edinburgh), in 𝐠𝐞𝐨𝐦𝐞𝐭𝐫𝐢𝐜 𝐥𝐞𝐚𝐫𝐧𝐢𝐧𝐠 and 𝐮𝐧𝐜𝐞𝐫𝐭𝐚𝐢𝐧𝐭𝐲 𝐪𝐮𝐚𝐧𝐭𝐢𝐟𝐢𝐜𝐚𝐭𝐢𝐨𝐧. Application deadline: 15 Dec '24. Starting Sep '25. Details in the reply. Please RT and share with anyone interested!

I'm talking at a conference later this year (on UX+AI). I just saw an ad for the conference with my photo and was like, wait, that doesn't look right. Is my bra showing in my profile pic and I've never noticed...? That's weird. I open my original photo. No bra showing. I put

Say hi to the new Statify members Centre Inria de l'Université Grenoble Alpes: Alice Chevaux, Pearl Laveur, Camille and Eloïse Touron, Antoine Franchini (PhD students) Rafael Mouallem Rosa, Loïc Chalmandrier (postdoc) 👋 team.inria.fr/statify/member… 1/3

I am recruiting PhD students for 2025!😃 You want to reveal the geometric signatures of natural and artificial intelligence, and unlock the mysteries of the brain?🤖🧠 Apply to the UCSB Geometric Intelligence Lab✨ This is the view you'd have from... well, your desk🌴

The sbi package is growing into a community project 🌎 To reflect this and the algorithms, neural nets, and diagnostics that have been added since its initial release, we have written a new software paper. Reach out if you want to get involved: arxiv.org/abs/2411.17337

Anne Gagneux, Ségolène Martin, @qu3ntinb, Remi Emonet and I wrote a tutorial blog post on flow matching: dl.heeere.com/cfm/ with lots of illustrations and intuition! We got this idea after their cool work on improving Plug and Play with FM: arxiv.org/abs/2410.02423

just 2 dudes in 2003 not realizing they just made one of the best songs ever x.com/copiumx/status…

How to schedule your thesis defense? So you think publishing top-tier papers is hard? Wait until you need to schedule your prelim/defense! Some common mistakes and tips: