Ben-Gurion University of the Negev
I am an M.Sc. student in Computer Science at Ben-Gurion University of the Negev, advised by Oren Freifeld and Chaim Baskin. I received my B.Sc. in Computer Science from the Open University of Israel.
I spend most of my time making neural networks run faster and use less memory, usually by rethinking the math, sometimes by arguing with GPU kernels. I'm also interested in computer vision and graph neural networks.
NeurIPS 2026 Conference on Neural Information Processing Systems
FG-CPAB separates trajectory integration from parameter-space projection, reducing the gradient cost of CPAB transformations from $\mathcal{O}(dTN)$ to $\mathcal{O}(TN + dC)$. This yields up to $10^4\times$ faster gradients and $500\times$ lower memory, making fine-tessellation diffeomorphisms practical in 2D and 3D.
arXiv preprint 2026
An I/O model of wavelet convolutions (WTConv) guides three algebraic reformulations that enable a fused, I/O-aware implementation, reducing memory traffic by about $2.55\times$ and yielding up to $4.35\times$ faster training at roughly half the peak memory.
ICCVW 2023 IEEE/CVF International Conference on Computer Vision Workshops
A lightweight graph neural network replaces classical clustering on top of self-supervised vision transformer features, enabling unsupervised object localization and semantic segmentation.