Yoav Gelberg
I'm a PhD student at the University of Oxford, supervised by Haggai Maron, Michael Bronstein and Yarin Gal. My research focuses on the symmetry and structure of neural network parameter spaces with application to deep (meta-)learning. I'm also interested in architecture reserach more broadly and in the way structure can inform learning. I spent the summer of 2025 at Sakana AI, working on positional embeddings and length generalization in LLMs.
Before Oxford, I completed my undergraduate studies at the Technion as a Rothschild scholar, studied expander graphs at the Weizmann Institute, developed fair learning algorithms at Fairgen, and taught math and programming at the ARDC. My PhD is funded by the EPSRC through the AIMS CDT program.
* denotes equal contribution; full list on Google Scholar
*, Yam Eitan*, Aviv Navon, Aviv Shamsian, Theo (Moe) Putterman, Michael Bronstein, Haggai Maron
Venue: NeurIPS 2025
Also at: Weight Space Learning Workshop @ ICLR 2025
Theo (Moe) Putterman*, Derek Lim*, , Stephanie Jegelka, Haggai Maron
Venue: LoG 2025, Oral Presentation 🎤
Also At: Weight Space Learning Workshop @ ICLR 2025
Yonatan Gideoni, , Tim G. J. Rudner, Yarin Gal
Venue: UniReps + CogInterp Workshops @ NeurIPS 2025
Fabrizio Frasca*, Guy Bar-Shalom*, Derek Lim, , Yftah Ziser, Ran El-Yaniv, Gal Chechik, Haggai Maron
Venue: R2-FM Workshop @ ICML 2025
Yam Eitan*, *, Guy Bar-Shalom, Fabrizio Frasca, Michael Bronstein, Haggai Maron
Venue: ICLR 2025, Oral Presentation 🎤
, Tycho van der Ouderaa, Mark van der Wilk, Yarin Gal
Venue: GRaM Workshop @ ICML 2024, Best Paper Award 🏆