👋 Hello There !
I am an Assistant Professor and Hi! Paris Chair Holder at Télécom Paris, Institut Polytechnique de Paris. I am a member of the LTCI lab, in the S2A team. Prior to this, I was a post-doctoral researcher in the Explainable Machine Learning, at the Technical University of Munich and Helmholtz Munich.
My main line of research revolves around Deep Representation Learning, and my current research interests include:
- mechanistic interpretability of representations in foundation models across modalities
- alignment of representation between modalities, mainly vision-language
- robustness, distribution shift, uncertainty quantification, learning with limited labeled data
📢 Hiring
I’m hiring a PhD student for Fall 2026, on the topic of:
Understanding and Characterizing the Geometry of Representations within Foundation Models and across layers
Don’t hesitate to contact me if you are interested! 👉 Check here for more details!
📰 News
- May 2026 - 5 papers accepted @ ICML 2026! See you in Seoul 🇰🇷 Check them out 👇
- SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport
Simon Roschmann, Paul Krzakala, Sonia Mazelet, Quentin Bouniot, Zeynep Akata - Dissecting Multimodal In-Context Learning: Modality Asymmetries and Circuit Dynamics in modern Transformers (✨Spotlight✨)
Yiran Huang, Karsten Roth, Quentin Bouniot, Wenjia Xu, Zeynep Akata - The Latent Color Subspace: Emergent Order in High-Dimensional Chaos
Mateusz Pach, Jessica Bader, Quentin Bouniot, Serge Belongie, Zeynep Akata - Mantis: Lightweight Foundation Model for Time Series Classification
Vasilii Feofanov, Songkang Wen, Shifeng Xie, Simon Roschmann, Marius Alonso, Hongbo Guo, Romain Ilbert, Malik Tiomoko, Quentin Bouniot, Zeynep Akata, Lujia Pan, Jianfeng Zhang, Ievgen Redko - TimeSAE: Sparse Decoding for Faithful Explanations of Black-Box Time Series Models
Khalid Oublal, Quentin Bouniot, Qi Gan, Stephan Clémençon, Zeynep Akata
- SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport
- Apr 2026:
- The 3rd iteration of our workshop on "Explainable Computer Vision: Quo Vadis?" was accepted @ ECCV 2026! Stay tuned for more information 👀
- I will present our CVPR paper @ CVPR in Paris! See you there 🥐
- I gave a talk at the Hi! Paris Reading group on "AI Robustness & Security"!
- Mar 2026 - I started as an Assistant Professor at Télécom Paris! 🎉
- Feb 2026 - 1 paper accepted @ CVPR 2026! 👉 Check it out!
- Dec 2025 - I will be presenting our NeurIPS paper @ EurIPS in Copenhagen! ❄️
- Oct 2025 - Check out the 2nd iteration of our workshop @ ICCV 2025 on "Explainable Computer Vision: Quo Vadis?"
- Sep 2025 - 1 paper accepter @ NeurIPS 2025! 👉 Check it out!