Thank you Neil for always being so kind and reactive. And PMLR for publishing GRaM ☀️ Lots of love to @gram-org.bsky.social @erikjbekkers.bsky.social @sharvaree.bsky.social @sukjulian.bsky.social and many others ❤️

Neil Lawrence@lawrennd.bsky.social · 2w ago

Volume 326 Proceedings of Second Workshop on Geometry-grounded Representation Learning and Generative Modeling proceedings.mlr.press/v326/ Is now available on PMLR

Are you interested in uncertainties, reliable decision-making in ML, or probabilistic perspectives on model compression, and would like to work together? DigitalFutures currently has an open call for postdoc fellowship applications: www.digitalfutures.kth.se/call/up-to-t...

Our paper on a Hamiltonian description of non-reciprocal interactions is out @natphys.nature.com! With Yubo Shi, Roderich Moessner, and @marinbukov.bsky.social @mpipks.bsky.social @ub.edu @icreacommunity.bsky.social Check it out, and read more in the thread below! 👇 www.nature.com/articles/s41...

Hamiltonian description of non-reciprocal interactions - Nature Physics

Many active and driven systems exhibit non-reciprocal interactions, making them hard to describe with standard methods. Now a constrained Hamiltonian embedding with auxiliary variables reproduces thes...

nature.com

Ricard Alert Zenón@ricardalert.bsky.social · last yr.

New preprint! Non-reciprocal interactions don’t arise from a potential. Yet, we found a way to encode them in a Hamiltonian, which captures the phase transitions of non-reciprocal systems! With Yubo Shi, Roderich Moessner, and @marinbukov.bsky.social @mpipks.bsky.social. arxiv.org/pdf/2505.05246

In 1854, Bernhard Riemann introduced a theory about how to study geometric spaces in any dimension. Most mathematicians at the time found his ideas to be too vague to be of much use. They are now a mathematical staple. www.quantamagazine.org/what-is-a-ma...

Results for the GRaM Competition are online. Congratulations to the winner and runners-up 🎉 🥇 github.com/julka01 with SmoothSplatNet 🥈 github.com/jorgesarrato with CDFDoubleGridNet 🥉 github.com/v3ctr0id with VRTEnsemble 🔗 gram-competition.github.io

They have the best students and professors ❤️

Erik Bekkers@erikjbekkers.bsky.social · 4mo ago

We're looking for a new colleague at @amlab.bsky.social: Assistant Professor in AI for Science 🔬🤖 World-class ML research, Amsterdam's thriving AI ecosystem (ELLIS, startups, big tech), and some of the best academic labor conditions in Europe ❤️ Deadline: May 30 👉 werkenbij.uva.nl/en/vacancies...

🌻 Just 2️⃣ weeks left to apply for the Grace Chisholm Young Fellowship. Open to a mathematician who needs support when their mathematical career is interrupted by family responsibilities, relocation, or other similar circumstances. Deadline: 27 Apr ➡️ www.lms.ac.uk/grants/grace...

Thanks to the generous sponsorship from @newtheory.ai, @gram-org.bsky.social has a few remaining travel grants and virtual passes for authors of accepted papers that are in difficult financial situation. Please contact us directly at organizers@gram-workshop.org gram-workshop.github.io

We have a competition @gram-org.bsky.social! - MCML award: 500€ - Deadline: April 22nd - Publication of the results in our workshop proceedings (PMLR) ✨Thank you to @sukjulian.bsky.social, Gavin and BeyondMath for making this happen. ✨ gram-competition.github.io

Julian Suk@sukjulian.bsky.social · 4mo ago

One month left 'til @iclr-conf.bsky.social, about time to launch our ✨@gram-org.bsky.social Competititon✨ The theme is geometry x AI4science with a dataset kindly provided by BeyondMath. Deadline: April 22, 2026 (AoE) 🔗 gram-competition.github.io

Checkout this cute blogpost on Jacobi fields! They were used to link Variational and Riemannian flow matching in Olga’s paper ☀️

Olga Zaghen@olgatticus.bsky.social · 5mo ago

🔮 Working on ML on curved manifolds? Don't miss out on Jacobi Fields! 🔮 I wrote a quick, highly visual and hopefully accessible introduction to the topic: "Jacobi Fields in Machine Learning" 🤠 Check it out here: olgatticus.github.io/blog/jacobi-...!

🚀 LOGML26— Mentor applications! 📍 Imperial College London | 13–17 July 2026 Mentor a project team. Attend talks, socials, networking events. 💸 Travel support available. Deadline: 18 March 2026(AoE) Apply: logml.ai/apply.html #LOGML #MachineLearning #SummerSchool

I have been involved in two amazing projects, both accepted at ICLR: arxiv.org/abs/2505.17517 arxiv.org/abs/2502.12981 A true privilege to collaborate with such brilliant and kind coauthors. ❤️ We are also organizing an ICLR workshop on geometry. Consider submitting 🥰 gram-workshop.github.io

📢 The submission deadline for ✨GRaM workshop✨ at @iclr-conf.bsky.social is 5th February 2026. 🌟Submit your exciting works in Geometry-grounded representations. We welcome submissions in multiple tracks i.e. 📄 Proceedings 📝extended abstract 👩‍🏫Tutorial/blogpost as well as an exciting challenge!

Announcing SGI 2026! Undergrads and MS students: Apply for 6 weeks of paid summer geometry processing research. No experience needed: 1 week tutorials + 5 weeks of projects. Mentors are top researchers in this emerging branch of graphics/computing/math. sgi.mit.edu

Submit your work, then join us @iclr-conf.bsky.social in Rio! 😀☀️

GRaM Workshop @gram-org.bsky.social · 8mo ago

📢The second edition of ✨GRaM workshop✨ is here this time at #ICLR26. 🌟Submit your exciting works in Geometry-grounded representations. We welcome submissions in multiple tracks i.e. 📄 Proceedings 📝extended abstract 👩‍🏫Tutorial/blogpost as well as an exciting challenge!

It is hard to believe but it is already more than a week since we were all in Copenhagen for #EurIPS. It was a truly awesome event❄️

Martin is a kind PI with tons of ideas. (PhD students: the PI matters more than the project, and Martin is the one you want.) Now, go update your CV and send it! ✨💪

Martin Trapp@trappmartin.eurosky.social · 8mo ago

10 days left to apply for a PhD/PostDoc position in probabilistic machine learning together with me at @kthuniversity.bsky.social. Both positions are fully funded and part of WASP, the Swedish AI program! For details, see the links below. PhD: tinyurl.com/4bppbste PostDoc: tinyurl.com/2tasv6bd

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.”

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)

Serge Belongie@serge.belongie.com · last yr.

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)

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)

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 ...

docs.google.com

🌟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

LOGML 2025

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

logml.ai

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 🔥

Olga Zaghen@olgatticus.bsky.social · last yr.

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

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