Roy Friedman

rfphoto.jpg

I am a Hebrew University of Jerusalem Ph.D. candidate at Yair Weiss’ lab for computer vision.

I research generative models in computer vision, specifically how (and if) they can be used for tasks other than generating data. Currently I am also the TA for HUJI’s course on Bayesian Machine Learning, which Yair Weiss and I have built together.

Selected publications

  1. Control+Shift: Generating Controllable Distribution Shifts
    Roy Friedman, and Rhea Chowers
    ECCV2024, Synthetic Data for Computer Vision Workshop 2024
    PDF
  2. Intriguing Properties of Modern GANs
    Roy Friedman, and Yair Weiss
    arXiv preprint arXiv:2402.14098v1 2024
    HTML PDF
  3. HIGlow: Conditional Normalizing Flows for High-Fidelity HI Map Modeling
    Roy Friedman, and Sultan Hassan
    Machine Learning and the Physical Sciences Workshop, Conference on Neural Information Processing Systems 2022
    PDF
  4. Posterior Sampling for Image Restoration using Explicit Patch Priors
    Roy Friedman, and Yair Weiss
    arXiv preprint arXiv:2104.09895 2021
    PDF