I am a Research Scientist at Google Research in Tel-Aviv where I work on vision-and-language. I completed my PhD in The Hebrew University of Jerusalem, Israel. During my time there, I had the privilege of being advised by Dr. Roy Schwartz and Dr. Gabriel Stanovsky.

The goal of my research is to improve vision and language generalization. Specifically, I aim to develop models with better compositionality abilities, less biased and better perform on real-world examples. My recent works and interest areas include image-text alignment, improving text-to-image models, and visual instruction tuning. See my publications for more details. My PhD talk "Bridging Vision and Language with Data: From Perception to Understanding" 🎬 record is available here.

I did my MSc with Prof. Michael Elhadad and Prof. Eitan Bachmat, at the Ben Gurion University.

Download my complete CV.

Students

I've had the opportunity to collaborate with several MSc and new PhD students towards their publication goals:

• Brian Gordon - Mismatch Quest - Visual and Textual Feedback for Image-Text Misalignment

• Hritik Bansal - Video-Con - Robust Video-Language Alignment via Contrast Captions

• Oren Sultan - Analogies research project (in-progress)

• Nitzan Bitton-Guetta - WHOOPS! - Commonsense-defying image with text-to-image models

• Netta Madvil - Read, Look or Listen? Multimodal models analysis

• Ron Yosef - IRFL - Figurative language and visual metaphors

If you want to work together on vision-and-language research, feel free to shoot me an email.