Publications: ICML 2025, ICML 2024, TMLR 2024, ICCV 2023, CVPR 2022, CVPR 2021, IROS 2019, ICDM 2018, etc. Google Scholar stats: Citations: 319, h-index: 9, i10-index: 9. Reviewer for various academic conferences and journals: CVPR, NeurIPS, ICLR, ICML, ICCV, ECCV, ICRA, IROS, ACCV, RA-L, IJCV, AISTATS, TPAMI, TMLR.
Research Experience
Research Scientist at NVIDIA, working on semantic video search and vision-language models (VLMs). Previously worked at Apple, Amazon, and Samsung AI on deep learning and computer vision.
Education
PhD: EPFL (🇨🇭), Advisor: Pascal Fua, Research focus: uncertainty and robustness.
Background
Research interests: vision-language models (VLMs) and video understanding, building scalable retrieval and reasoning pipelines that turn complex video data into searchable, interpretable knowledge. Professional field: deep learning and computer vision.
Miscellany
Invited talks: Presented at AI Tinkerers, LauzHack DL Bootcamp, Mila - Quebec AI Institute, UiT The Arctic University of Norway, MBZUAI, CVLAB Group Meeting, Nordic AI Conference, etc.