MSCA PhD student at AMLab with Erik Bekkers, interested in geometric deep learning, generative models and their intersection ๐ โจ
bit.ly/olga-zaghen
Olga Zaghen
Loading...
Checkout this cute blogpost on Jacobi fields! They were used to link Variational and Riemannian flow matching in Olgaโs paper โ๏ธ
Interested in the analysis of GNN expressive power, limitations of the WL test or more in general in the definition of complete metrics on graphs? ๐
Check out this super cool work led by
@martin.topology.rocks !๐ฅ
๐จ2 PhD positions with me @amlab.bsky.social on learning causally grounded concepts ๐จ
Are you interested in improving the #interpretability #robustness and #safety of AI by integrating #causal reasoning? Join us in beautiful Amsterdam ๐ณ๐ฑ๐ท๐ฒ
Deadline: 20 April
www.academictransfer.com/en/jobs/3593...
My hope is that by making this concept more intuitive, weโll see it unlock new applications in future ML research. Feedback welcome! :)
Best lab in the most wonderful city: the perfect opportunity! Come join us ๐ฆพ๐
๐ฎ Working on ML on curved manifolds? Don't miss out on Jacobi Fields! ๐ฎ
I wrote a quick, highly visual and hopefully accessible introduction to the topic: "Jacobi Fields in Machine Learning" ๐ค Check it out here: olgatticus.github.io/blog/jacobi-...!
In case you are wondering: they aren't just a theoretical curiosity! We actually relied on Jacobi fields to prove key results in our recent paper, Riemannian Variational Flow Matching for Material and Protein Design ๐ชฉ (arxiv.org/abs/2502.129...).
Olga Zaghen
Alison Pouplin
Super happy to share our work was accepted as an Oral at the Delta Workshop @ ICLR 2025! ๐
Canโt wait to talk about it in Singapore ๐
Congrats to the amazing team @eijkelboomfloor.bsky.social @alisometry.bsky.social @erikjbekkers.bsky.social ๐ฅ
