🎉 Our paper "What to align in Multimodal Contrastive Learning?" has been accepted to ICLR 2025! 🎉
See you in Singapore! 🥳
📚About Me
I am an Assistant Professor (maître de conférences in French) in the Vertigo team at Cnam, Paris. Previously, I was a postdoctoral researcher at EPFL, Switzerland, in the ECEO lab, advised by Devis Tuia. I obtained my PhD in computer science under the supervision of Sébastien Lefèvre, Bertrand Le Saux, and Alexandre Boulch, where I developed semi-supervised learning methods for semantic segmentation and classification.
My research 🤓 focuses on computer vision, representation learning, and multimodal learning, including (but not limited to) vision-and-language models.
Interests
- Artificial Intelligence
- Multimodal learning
- Representation learning
- Computer vision
- Earth observation
Education
PhD Artificial Intelligence
Université de Bretagne Sud & ONERA
MSc Data Science
École Polytechnique & Université Paris-Saclay
MEng Applied Mathematics
École Centrale Paris & Universidad de Chile
BSc Mathematical Engineering
Universidad de Chile
Recent News
🎉 Our paper "ConGeo: Robust Cross-View Geo-Localization Across Ground View Variations" has been accepted to ECCV 2024! 🎉
See you in Milano! 🥳 Congrats Li!
Featured Publications
Recent Publications
(2025).
What to align in multimodal contrastive learning?.
International Conference on Learning Representations.
(2024).
Knowledge-aware Text-Image Retrieval for Remote Sensing Images.
IEEE Transactions on Geoscience and Remote Sensing (accepted).
(2024).
ConGeo: Robust Cross-View Geo-Localization Across Ground View Variations.
European Conference on Computer Vision (ECCV).
(2024).
Knowledge-Aware Visual Question Generation for Remote Sensing Images.
IEEE International Geoscience and Remote Sensing Symposium.
(2024).
Training Visual Language Models with Object Detection: Grounded Change Descriptions in Satellite Images.
IEEE International Geoscience and Remote Sensing Symposium (IGARSS).
Talks
