Alison Pouplin

“Artwork by Agnes..” 🥹❤️

If you want to meet up at any point to talk about

-> physics-informed ML, autodiff, linear algebra, Bayesian DL, or probabilistic numerics,

just let me know. Always happy to talk research, collaboration, (jobs!), or just grab a coffee/beer.

Looking forward to seeing everyone in Copenhagen! 🇩🇰

I am hiring a PhD & postdoc to work together with me at KTH on probabilistic machine learning. Both positions are fully funded and part of WASP.

I will be attending @euripsconf.bsky.social, if you are around and want to talk about the positions or what we do at KTH, then ping me and we can meet.

“Dear mathematician, can you explain to me what mass is?”

“Very simple, dear: the mass of a dynamical system is the cohomology class of the Galilean group representing lack of equivariance of the moment map on the symplectic manifold that is the phase space of the system.”

CNNs have the one similarity with classical vision, that (biological) neurons do react to borders. But I don’t know about attention. pubmed.ncbi.nlm.nih.gov/3956609/

I think it would really help to have reviewers talking to each other. I know we might not want reviewers to influence each other but sometimes, discussions spark good points and consensus.

I tend to read the appendix first for this specific reason 😅

I am sorry it happened.

If you are still considering presenting your paper, @euripsconf.bsky.social has a dedicated “Salon des Refusés” session.

Still, it’s completely unacceptable.

Est-ce que les non-francophones peuvent y participer (potentiellement à distance)? :)

Any predictions for 2026? :)

And at 80 years old, he is extremely productive, publishing impactful papers and giving lectures at the IHES 🥲

Some entertaining myth-making (from mathoverflow.net/a/491227/121...):

Four Tenure-track positions in AI exclusively for female applicants at @jkulinz.bsky.social! Details available soon at www.jku.at/en/lit-artif...

So far, 2,135 people have responded to the poll Søren and I posted a few days ago. Of those, 94.4% replied “Yes” to being interested in officially presenting accepted @neuripsconf.bsky.social papers in Europe. (1/7)

NeurIPS participation in Europe We seek to understand if there is interest in being able to attend NeurIPS in Europe, i.e. without travelling to San Diego, US. In the following, assume that it is possible to present accepted papers ...

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)

LOGML 2025 London Geometry and Machine Learning Summer School, July 7-11 2025

🌟Applications open- LOGML 2025🌟

👥Mentor-led projects, expert talks, tutorials, socials, and a networking night
✍️Application form: logml.ai
🔬Projects: www.logml.ai/projects.html
📅Apply by 6th April 2025
✉️Questions? logml.committee@gmail.com

#MachineLearning #SummerSchool #LOGML #Geometry

Super happy to share our work was accepted as an Oral at the Delta Workshop @ ICLR 2025! 🎉

Can’t wait to talk about it in Singapore 😎

Congrats to the amazing team @eijkelboomfloor.bsky.social @alisometry.bsky.social @erikjbekkers.bsky.social 🔥

Since she was in graduate school, Laura Monk has been developing mathematical theories that Maryam Mirzakhani didn’t have a chance to finish before her death. Monk feels she’s gotten to know the mathematician through her proofs. www.quantamagazine.org/years-after-...

Are interested in making #computervision models more #reliable and #robust by accounting for #uncertainties?

Then consider submitting your awesome work to our @cvprconference.bsky.social workshop!

uncertainty-cv.github.io/2025/

Variational Flow Matching goes Riemannian! 🔮

In this preliminary work, we derive a variational objective for probability flows 🌀 on manifolds with closed-form geodesics, and discuss some interesting results.

Dream team: Floor, Alison & Erik (their @ below) 💥

📜 arxiv.org/abs/2502.12981
🧵1/5

Is the universe a sphere, like the surface of Earth? Or maybe it’s shaped like a doughnut? Cosmologists believe that these possibilities could leave clues in the sky. New methods could help find them. https://buff.ly/3PTCOTo

The Mathematics of Artificial Intelligence: In this introductory and highly subjective survey, aimed at a general mathematical audience, I showcase some key theoretical concepts underlying recent advancements in machine learning. arxiv.org/abs/2501.10465

I would love to be added if it’s possible :)