Published numerous papers, including those accepted by top conferences such as ECCV'24, CVPR'24, ICCV'23. Specific works include: 'ProLIP' on few-shot learning, 'GenVal' on synthetic evaluation in semantic segmentation, 'TTYD' on robust source-free domain adaptation, 'FAMix' on domain generalized semantic segmentation, 'SALUDA' on point-cloud domain adaptation, and 'PODA' on prompt-driven zero-shot domain adaptation. Additionally, organized several workshops and was recognized as a top reviewer at NeuRIPS’22.
Research Experience
Serves as a senior research scientist at valeo.ai, overseeing multiple research projects. Also works as a part-time researcher in the Computer Vision group Astra-vision at INRIA Paris.
Education
Received his PhD from École Normale Supérieure in 2014, under the supervision of Ivan Laptev; also obtained an engineering degree from Télécom Paris and a parallel “Master 2” degree in Mathematics, Machine Learning, and Computer Vision (MVA) from École Normale Supérieure Paris-Saclay in the same year.
Background
Research interests include deep learning, scene understanding, domain adaptation, and data augmentation. Currently a Senior Research Scientist at valeo.ai (R&D Technical Manager, Valeo expert) and a part-time Researcher in the Computer Vision group Astra-vision at INRIA Paris.