Research
Publications, projects, and supervisions
Research Overview
My research focuses on modern AI technologies, from fundamental model development to healthcare applications. I identify major AI trends and adapt them for domains underserved by major industry players, particularly in health.
My research interests include (but are not limited to):
- Few-Shot Learning — Learning with limited labeled data
- Diversity in data & models — Integrating diversity of data and model representations to improve learning
- Large Language Models — Diffusion models, transformers, and multimodal architectures
- AI for Healthcare — Multimodal medical data integration with possibly missing modalities
- Graph Signal Processing — Signal analysis on irregular domains, neuroimaging applications
Selected Publications
-
Yassine El Ouahidi, Jonathan Lys, Philipp Thölke, Nicolas Farrugia, Bastien Pasdeloup, Vincent Gripon, Karim Jerbi, and Giulia Lioi (2025). REVE: A Foundation Model for EEG — Adapting to Any Setup with Large-Scale Pretraining on 25,000 Subjects. Annual Conference on Neural Information Processing Systems (NeurIPS).
-
Yassir Bendou, Yuqing Hu, Raphael Lafargue, Giulia Lioi, Bastien Pasdeloup, Stéphane Pateux, and Vincent Gripon (2022). EASY — Ensemble Augmented-Shot-Y-Shaped Learning: State-of-the-Art Few-Shot Classification with Simple Components. MDPI Journal of Imaging (2022 Best Paper Award).
-
Amine El Ouahidi, Yassine El Ouahidi, Pierre-Philippe Nicol, Sinda Hannachi, Clément Benic, Jacques Mansourati, Bastien Pasdeloup, and Romain Didier (2024). Machine Learning for Pacemaker Implantation Prediction After TAVI Using Multimodal Imaging Data. Nature Scientific Reports.
-
Bastien Pasdeloup, Vincent Gripon, Grégoire Mercier, Dominique Pastor, and Michael G. Rabbat (2017). Characterization and Inference of Graph Diffusion Processes from Observations of Stationary Signals. IEEE Transactions on Signal and Information Processing over Networks.
Full publication list on Google Scholar
Selected Projects
ENDIVE
Encouraging diversity in few-shot learning — Exploring how diversity can improve learning with limited data.
ANR Project Page →STRATIF-AI
Continuous stratification for improved prevention, treatment, and rehabilitation of stroke patients using digital twins and artificial intelligence.
FUSCHIA
AI for heterogeneous component fusion — Multimodal image segmentation.
Supervisions
PhD Students
MD Students
Post-Doctoral Researchers
Research Engineers
| Name | Topic | Period | Links |
|---|---|---|---|
| Manon Renault | Embedded Deep Learning for Sensors | 2023 — 2025 | |
| Mervyn Guillou | AI for Hyperfrequency Components | 2021 — 2023 |
Scientific Dissemination
I regularly participate in scientific dissemination activities to promote science and research to the general public, including:
- Fête de la science — Annual science festival presentations on AI and machine learning
- Nuit des chercheurs — Public engagement events explaining research to general audiences
- Un chercheur à l’école — AI introduction workshops for primary school students
Academic Service
-
Reviewing: IEEE TSP, IEEE SPL, IEEE TSIPN, Elsevier Signal Processing, EURASIP, GRETSI, ACM Sigmetrics, Oxford Bioinformatics, ANR JCJC
-
Event Organization: GSP Workshop (2018), GdR ISIS Day (2019), Foundation Day (2024), Few-Shot Learning Workshop (2024)