Published multiple papers in top conferences and journals such as ICCV, CVPR, NeurIPS, ECCV, covering areas like vision-language pretraining, zero-shot image classification, learning attention propagation, etc.
Research Experience
Works as a Research Consultant with Google in Zurich and collaborates closely with Google Deepmind on Foundational Vision Language Models. Has also been an intern at Nvidia.
Education
Ph.D. Candidate at ETH Zürich, Computer Vision lab, supervised by Prof. Luc Van Gool and PD. Dr. Federico Tombari; Master's degree from Technical University of Munich, with a focus on Generative Models (Naver AI Lab) and Zero-shot Learning (UniTübingen AI Research).
Background
Interested in building strong multimodal foundational models and distilling the world knowledge of foundational models to smaller task-specific models that can adapt and generalize to novel classes and environments.
Miscellany
Personal interests and other information not provided.