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)