Publications

Factorized Gradients for Scalable Highly-expressive Parametric Diffeomorphisms

Amit Aflalo, Eran Treister, Chaim Baskin, Oren Freifeld

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.

Papersoon Code Project Page

Fast and Memory-Efficient Wavelet Convolutions via I/O-Aware Reformulation

Amit Aflalo, Shahaf E. Finder, Roy Amoyal, Eran Treister, Oren Freifeld

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.

arXiv Code

DeepCut: Unsupervised Segmentation using Graph Neural Networks Clustering

Amit Aflalo, Shai Bagon, Tamar Kashti, Yonina Eldar

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.

Paper arXiv Project Page