Sotabase

Career

· Reseach Scientist Intern, Sakana AI (Current)2025–
· AI Consultant, Creator Fund2024–2025
· Security Researcher, JSOF2023–2023
· Doctor of Philosophy - PhD, Machine Learning, University of Oxford2023–2027
· Machine Learning Researcher, Fairgen2022–2023
· Master's student, Computer Science, Tel Aviv University2021–2022
· Research Fellow, Weizmann Institute of Science2017–2018
· Bachelor of Science - BS, Mathematics, Summa Cum Laude, Technion - Israel Institute of Technology2014–2018

Publications (9)

Learning on LoRAs: GL-Equivariant Processing of Low-Rank Weight Spaces for Large Finetuned Models
arXiv.org · 2024
13
cited
Topological Blind Spots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity
arXiv.org · 2024
10
cited
Variational Inference Failures Under Model Symmetries: Permutation Invariant Posteriors for Bayesian Neural Networks
arXiv.org · 2024
6
cited
Beyond Next Token Probabilities: Learnable, Fast Detection of Hallucinations and Data Contamination on LLM Output Distributions
2025
4
cited
GradMetaNet: An Equivariant Architecture for Learning on Gradients
arXiv.org · 2025
3
cited
Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity
International Conference on Learning Representations · 2025
3
cited
Extending the Context of Pretrained LLMs by Dropping Their Positional Embeddings
arXiv.org · 2025
1
cited
Iterative Deployment Improves Planning Skills in LLMs
arXiv.org · 2025
On The Expressive Power of GNN Derivatives
arXiv.org · 2025
Sotabase
Yoav Gelberg | Researcher Profile | Sotabase | Sotabase