A Geometric Unification of Generative AI with Manifold-Probabilistic Projection Models
Preprint, 2025
arXiv:2510.00666About
I am a PhD candidate in Applied Mathematics at Tel Aviv University, jointly supervised by Dr. Inbar Seroussi and Dr. Dmitry Batenkov.
My research focuses on mathematical models of neural networks in high-dimensional settings. Previously, I completed my MSc at Tel Aviv University, where I studied physics-informed neural networks for atmospheric radiative transfer.
International Conference on Learning Representations (ICLR), 2026
Paper on OpenReviewJournal of Quantitative Spectroscopy and Radiative Transfer, 331, 109253
Published articlePreprint, 2025
arXiv:2510.00666Thesis: Physics-Informed Neural Networks for Modeling Atmospheric Radiative Transfer.
Program for gifted youth in mathematics.
Teaching assistant at Tel Aviv University for undergraduate engineering courses, 2021–2022 and 2024–2026.
Minimax Rates for Learning Pairwise Interactions in Attention-Style Models
Minimax Rates for Learning Pairwise Interactions in Attention-Style Models
Minimax Rates for Transformer Attention via Interacting Particle Systems
Physics-Informed Neural Networks for Modeling Atmospheric Radiative Transfer
Utilization of Convolutional Neural Networks and Physics-Informed Neural Networks to Retrieve Cloud and Aerosol Properties from Polarimetric Observations