Published multiple papers on topics such as object insertion, consistent text-to-image generation, fast personalization of text-to-image models, and learning to initiate and reason in event-driven cascading processes. Some of the papers were presented at top international conferences like ICLR, SIGGRAPH, ECCV, and ICML.
Research Experience
Research areas include Computer Graphics, Computer Vision, and Artificial Intelligence and Machine Learning.
Education
I obtained my Ph.D. under the guidance of Prof. Gal Chechik at Bar-Ilan University. My M.Sc. and B.Sc. are in Electrical Engineering from the Technion, Israel Institute of Technology.
Background
My main fields of interest are computer vision and machine learning, focusing on compositional generalization from few or zero examples and reasoning across different data modalities (like natural-language, images and action). Recently, I have focused on integrating these ideas, with the emergence of generative and discriminative vision-and-language foundation models.