Olga Zaghen
@olgatticus.bsky.social
480 followers 130 following 27 posts
MSCA PhD student at AMLab with Erik Bekkers, interested in geometric deep learning, generative models and their intersection 🌐 ✨ bit.ly/olga-zaghen
Posts Media Videos Starter Packs
Pinned
olgatticus.bsky.social
A starter pack for researchers interested in Geometric Deep Learning - in the broadest sense possible!

Let me know if you would like to be listed. :)

Thanks @sharvaree.bsky.social for the idea!

go.bsky.app/7h8sek
olgatticus.bsky.social
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 🔥
olgatticus.bsky.social
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
Reposted by Olga Zaghen
maxxxzdn.bsky.social
🤹 Excited to share Erwin: A Tree-based Hierarchical Transformer for Large-scale Physical Systems

joint work with @wellingmax.bsky.social and @jwvdm.bsky.social

preprint: arxiv.org/abs/2502.17019
code: github.com/maxxxzdn/erwin
Reposted by Olga Zaghen
eijkelboomfloor.bsky.social
Super excited about this project!! Amazing work by @olgatticus.bsky.social and others ❤️
olgatticus.bsky.social
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
olgatticus.bsky.social
Stay tuned for further analyses and experiments! ✨

A huge thanks to my brilliant collaborators for all their efforts and invaluable guidance: @eijkelboomfloor.bsky.social, @alisometry.bsky.social and @erikjbekkers.bsky.social 🔥

🧵5/5
olgatticus.bsky.social
We test our method on a checkerboard distribution on the sphere 🏁🌐, yielding promising results when compared to Euclidean and non-variational methods.

🧵4/5
olgatticus.bsky.social
By directly encoding the manifold, we introduce Riemannian-Gaussian-VFM, offering a fresh perspective on geometry-informed generative modeling. We also discuss how our approach relates to the previously mentioned methods. 🌍🌎🌏

🧵3/5
olgatticus.bsky.social
Inspired by Riemannian Flow Matching, we extend the Variational Flow Matching (VFM) objective to build a geometry-aware flow model. 🌊

Interestingly, VFM is particularly well-suited for explicitly parametrizing the support manifold of the distribution! 💅💪

🧵2/5
olgatticus.bsky.social
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
Reposted by Olga Zaghen
combayns-workshop.bsky.social
Welcome to our Bluesky account! 🦋

We're excited to announce ComBayNS workshop: Combining Bayesian & Neural Approaches for Structured Data 🌐

Submit your paper and join us in Rome for #IJCNN2025! 🇮🇹

📅 Papers Due: March 20th, 2025 📜
Webpage: combayns2025.github.io
Home - ComBayNS 2025 Workshop @ IJCNN 2025
combayns2025.github.io
Reposted by Olga Zaghen
federico-errica.bsky.social
🌟 Call for Papers – ComBayNS Workshop at IJCNN 2025 🌟

Workshop page: combayns2025.github.io

We are thrilled to announce the #workshop “ComBayNS: Combining Bayesian and Neural approaches for Structured data” at the upcoming International Joint Conference on Neural Networks (#IJCNN).

A thread 🧵
Home - ComBayNS 2025 Workshop @ IJCNN 2025
combayns2025.github.io
Reposted by Olga Zaghen
maxxxzdn.bsky.social
This is how it should be: one file, ctrl+c ctrl+v runnable from a notebook. I really do not want to mess with omegaconf, hydra or, the worst, a custom configuration system just to figure out how your model runs.
olgatticus.bsky.social
👮‍♀️🚨🚔
olgatticus.bsky.social
❤️❤️❤️
amlab.bsky.social
The Christmas spirit has arrived at AMLab! 🎄✨
Yesterday we kicked off the holidays with a festive group dinner and a fun Secret Santa exchange. 🎅

Wishing everyone a restful and joyful winter break and a happy new year! ❄️💫
olgatticus.bsky.social
we also celebrate it in some areas of Italy - like where I come from - where "Santa Lucia" is even more popular than Santa Claus for children!!
olgatticus.bsky.social
haters will say photoshop!!
Reposted by Olga Zaghen
amlab.bsky.social
If you are attending #NeurIPS2024🇨🇦, make sure to check out AMLab's 11 accepted papers ...and to have a chat with our members there! 👩‍🔬🍻☕

Submissions include generative modelling, AI4Science, geometric deep learning, reinforcement learning and early exiting. See the thread for the full list!

🧵1 / 12
Reposted by Olga Zaghen
algarciacast.bsky.social
Come and check out our poster on the UniReps workshop at @neuripsconf.bsky.social !

Thanks again to the amazing Giovanni Marchetti, Martina Scolamiero, and Danica Kragic ❤️

See more at: arxiv.org/abs/2409.10967
Reposted by Olga Zaghen
eijkelboomfloor.bsky.social
🐑 Come and check out Variational Flow Matching for Graph Generation next week at @neuripsconf.bsky.social ! 🐑

Wed 11 Dec 11 a.m. PST — 2 p.m. PST
West Ballroom A-D #7103

arxiv.org/abs/2406.04843
olgatticus.bsky.social
Go chat with ✨the Davids✨, super smart and cool guys!
dafidofff.bsky.social
Now still RV'ing w/ @davidmknigge.bsky.social around Vancouver Island, but looking forward to Neurips2024!

We will present our work on solving PDEs with space-time continuous representations using Equivariant Neural Fields (ENF) 🏄‍♀️🌊

Would love to meet and chat if interested!!
Reposted by Olga Zaghen
saiprasanna.in
Arxiv sharing reminder

pdf ❌
abs ✅
Reposted by Olga Zaghen
shwartzzzivravid.bsky.social
Looking at ICLR submissions with the lowest score - What a work of art! 🧵