Congratulation Edwige Cyffers, @pierremarion.bsky.social, and all of team Paris on this milestone for the machine learning community! 🎉🇫🇷

Watched the premiere of Mariinka at this years CPH:DOX. A film that captures a fascinating story but utterly fails to tell it well. Haphazard editing, tasteless scenes and morally decadent storytelling make it a dangerous film on the edge of being Russian propaganda.

Really looking forward to Eurips next week! 🇩🇰 😎

Not just because Bella Centre is literally a metro ride from home, but because it's really excellent to see the ML community gathering in Europe!

If you're around, say hi! Here's where I'll be 🔽🔽

Wednesday poster session at @euripsconf.bsky.social I'll be around to talk about this recent work and hopefully see some of the last author folks take the stage and present.

2d of December at ELLIS UnConference poster session I'll present: Identifying Metric Structures of Deep Latent Variable Models.

Going to a ML conference from the comfort of my own city is a special and exciting thing happening next week at @euripsconf.bsky.social in Copenhagen.

Looking forward to give our latest ICML paper another presentation at ELLIS UnConference and see how our new @neuripsconf.bsky.social paper fares!

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

Three weeks ago I had the pleasure of mentoring a project at @logml.bsky.social. We looked into cortical surface parcellation from a geometric angle and had a lot of fun! Thanks to my project group (including @mustas.bsky.social and @zhengdiyu.bsky.social) for the trust...

EurIPS is coming! 📣 Mark your calendar for Dec. 2-7, 2025 in Copenhagen 📅

EurIPS is a community-organized conference where you can present accepted NeurIPS 2025 papers, endorsed by @neuripsconf.bsky.social and @nordicair.bsky.social and is co-developed by @ellis.eu

eurips.cc

6/
👀 Learn more:
📝 Blog: syrota.me/posts/2025/0...
📄 Paper: syrota.me/files/identi...
🙏 With Eugene Zainchkovskyy, Quanhan Xi, Benjamin Bloem-Reddy, and Søren Hauberg.

5/
📍 Presenting at ICML:
🗓️ Tuesday, 11:00 AM–1:30 PM
📌 West Exhibition Hall B2–B3
🎨 Poster: syrota.me/files/imsdlv...

4/
I’m especially curious about the implications for disentanglement and causality. Would love to chat with anyone working on these topics! 🔍

3/
Why does this matter?
Because it allows trustworthy computations of relations between latent variables — which is essential in scientific applications where latent variables are of interest.

It also strengthens reliability and explainability in generative models in general.

2/
The core idea:
We prove that the pullback metric is identifiable.
This means geodesic distances, volumes, and optimal transport in latent space are now meaningful & model-invariant. ✅

1/
🚨 New paper at #ICML2025!
Identifying Latent Metric Structures in Deep Latent Variable Models 🎉
We solve part of the identifiability puzzle in generative models — using geometry. 🧵

🛩️ On my way to #NeurIPS2024 and excited to chat about (ML applications of) linear algebra, differentiable programming, and probabilistic numerics!

Feel free to DM if you’d like to meet up, hang out, and/or discuss any of these topics 😊

(Where to find me & paper info? -> Thread)