2026 new team members!
Welcome to Quentin Bouniot and Patricia Chiril!
We are delighted to welcome two new members to the S2A (Signal, Statistics and Learning) team at Télécom Paris. This spring marks the arrival of Quentin Bouniot and Patricia Chiril, who bring complementary expertise in statistical learning theory and natural language processing.
Quentin Bouniot — Assistant Professor in Statistical Learning Theory
Quentin Bouniot has taken up his position as Assistant Professor in Statistical Learning Theory within the S2A team. Let us warmly welcome him to the department!
Prior to joining Télécom Paris, Quentin was a Postdoctoral Researcher in the Explainable Machine Learning group at TU Munich & Helmholtz Munich, where he studied mechanistic interpretability and representational alignment for vision-language models. He previously held a postdoctoral position at Télécom Paris (LTCI), working on uncertainty and interpretability in deep learning.
Quentin earned his PhD from CEA-List and Université Jean-Monnet Saint-Étienne on the topic of few-shot learning and meta-learning for computer vision. His research bridges representation learning and mechanistic interpretability, using foundation models as a case study.
Originally from Tahiti, French Polynesia, Quentin is also a strong advocate for safe, responsible, and sustainable AI applications.
Patricia Chiril — Associate Professor in Natural Language Processing
Patricia Chiril joined the S2A team as an Associate Professor (Maîtresse de Conférences) in May 2026. Before this, she was a Postdoctoral Scholar at the Data Science Institute at the University of Chicago, a position she held from 2022 following the completion of her PhD at the University of Toulouse.
Her research focuses on Natural Language Processing (NLP), with a particular interest in modelling meaning construal across both reporting (journalistic, academic) and sharing (social media) contexts. Her work covers:
- Hate speech detection and the modelling of gender representational bias online;
- The study of how language is used to frame sustainability and environmental discourse, accounting for diverse stakeholder perspectives.