I am an AI/ML researcher at Mobileye, working on ML for autonomous vehicles.
I did my Ph.D. at Weizmann Institute of Science,
advised by Prof. Michal Irani, where I worked on machine learning and computer vision,
and more specifically, Generative AI and understanding memorization in neural networks.
BibTeX /
ArXiv /
Code /
Video
Training set reconstruction from multiclass classifiers and models trained with regression loss with some inriguing observations on the implications of weight decay on reconstructability.
(Earlier version appeared in ICLR Workshop on Trustworthy ML, 2023)
BibTeX /
ArXiv /
Code /
Project Page Diffusion models can be trained on a single image or video, giving rise to diverse video generation and extrapolation.
BibTeX /
ArXiv /
Code /
Project Page /
Video We show that a large portion of the training data can be reconstructed from the parameters of trained MLP binary classifiers. Our method stems from theoretical results about the implicit bias of neural networks trained with gradient descent
BibTeX /
ArXiv /
Code /
Video /
Project Page We generate diverse video samples from a single video using patch-based methods. Our results outperform single-video GANs in visual quality and are orders of magnitude faster to generate
(Extended abstract appeared at AI For Content Creation Workshop @ CVPR, 2022)
BibTeX /
ArXiv /
Code /
Video Using an "Eikonal regularization" term with implicit neural representation works surprisingly well for modelling complex surfaces
BibTeX /
ArXiv /
Code /
Poster Making input points differentiable (w.r.t model parameters), and using it for shape modelling, improved robustness to adversrial examples and more
BibTeX /
ArXiv /
Code Transforming 3D shapes to image representation so we can feed them to off-the-shelf CNNs and do classification, human-parts segmentation and more
BibTeX /
ArXiv /
Code Ever wondered if your hierarchical three-body system will eventually collide? find out by plugging your initial conditions into our analytical prediction formula (that works with high probability)