Released DINOv3, a state-of-the-art computer vision model trained with self-supervised learning (August 2025); Published a paper on Automatic data curation for self-supervised learning (May 2024); Released DINOv2, a family of foundation models (April 2023); Successfully defended his thesis titled 'Annotation-efficient learning for object discovery and detection' (November 2022); Multiple papers accepted by international conferences such as ECCV 2022, BMVC 2021, NeurIPS 2021, MIDL 2021, ECCV 2020, CVPR 2019.
Research Experience
Currently a Research Scientist at FAIR, Meta; Visited Center for Data Science, New York University for 3 months (October 2019); Conducted a 6-month research internship with the WILLOW team of INRIA and Center for Data Science (New York University), working on object discovery under the supervision of Prof. Jean Ponce and Prof. Yann LeCun (April 2018 - September 2018); Undertook a 5-month internship at Technicolor, working on Image inpainting under the supervision of Dr. Patrick Pérez (April 2017 - August 2017).
Education
Started PhD in Computer Science at Ecole Normale Superieure under the supervision of Prof. Jean Ponce and Dr. Patrick Pérez in October 2018; Obtained PhD from Ecole Normale Superieure in November 2022.
Background
Research interests include self-supervised learning, automatic data curation and any learning problems that require less supervision including object discovery, weakly supervised object detection/segmentation and active learning.