I am a Research Scientist Intern at Meta (GenAI) and a PhD student in Computer Science at the School of Computer Science and Engineering, Hebrew University of Jerusalem, under the joint supervision of Yossi Adi and Sagie Benaim.
I spent the summer of 2024 as a Research Scientist Intern at Meta (GenAI) and worked as an AI Researcher at Spot by NetApp from winter 2022 to summer 2024.
My research interests include machine learning and generative AI. I’m passionate about achieving full controllability in media generation.
We propose Through-The-Mask, a two-stage framework for Image-to-Video generation that uses mask-based motion trajectories to enhance object-specific motion accuracy and consistency, achieving state-of-the-art results, particularly in multi-object scenarios.
We improve large language models' visual commonsense by generating multiple images from text prompts and integrating them into decision-making via late fusion, boosting performance on visual commonsense reasoning and NLP tasks.
We propose a method to generate realistic, audio-aligned videos by adapting a text-to-video model with a lightweight adaptor.
We adapt text-conditioned diffusion models for audio-to-image generation by encoding audio into a token compatible with text representations.
Feel free to reach out:
guyyariv.mail at gmail dot com