I am currently Assistant Professor (Maîtresse de Conférences en Informatique) at Paris-Saclay University. I am a member of the LISN laboratory (Laboratoire Interdisciplinaire des Sciences du Numérique > Sciences et Technologies des Langues > Sémantique et Extraction d'Information), and I teach at UFR des Sciences d'Orsay.

My research aims to develop adaptive and resource-efficient machine learning systems that can learn continuously from evolving data while operating under realistic computational constraints. In order to be reliably deployed in real-world scenarios, AI models must not only achieve high performance but also adapt over time, remain robust to changing environments, and use computation efficiently. My work brings together continual learning, representation learning, computer vision, and efficient deep learning architectures. I investigate how learning systems can acquire new knowledge without catastrophic forgetting, generalize beyond their initial training conditions, and make effective use of limited resources such as data and compute.

My current research interests include :
- Resource-efficient training of deep neural networks, including continual learning
- Visual representation learning and semantic aspects in computer vision
- Multimodal learning, with a focus on vision and language

Current affiliation : Université Paris-Saclay, CNRS, LISN, 91400, Orsay, France

Previously, I was a postdoctoral researcher in frugal deep learning (ANR SHARP) at Université Paris-Dauphine, where I worked with Pr. Alexandre Allauzen in the MILES team of LAMSADE laboratory.
I hold a PhD from Université Paris-Saclay, where I worked on deep continual learning for image classification under the supervision of Pr. Céline Hudelot (CentraleSupélec MICS), Dr. Adrian Popescu (CEA-list) and Dr. Marina Reyboz (CEA-list).
I hold an engineering degree from CentraleSupélec Engineering school (equivalent to M.Sc. in AI).