Andrei Bursuc

Andrei Bursuc is a Research Scientist and Deputy Scientific Director at Valeo.ai, where he focuses on perception for autonomous driving. Concurrently, he serves as a Research Associate at the Astra Inria project team and teaches the Deep Learning DIY course at Paris Institute of Technology (École Polytechnique) since 2019. He holds a PhD from Mines ParisTech and Telecom SudParis (2012) and a BSc from Polytechnic University of Bucharest (2009).

His research spans computer vision and machine learning, with applications in autonomous driving, uncertainty quantification, self-supervised learning, and foundation models. Recent work emphasizes scalable representation learning, open-vocabulary segmentation, and generative modeling for driving scenarios.

His publications (2024–2025) cluster around themes of semantic segmentation, depth estimation, and vision-language models, with innovations in unsupervised learning, cross-modal distillation, and efficiency. Trends indicate a focus on robustness, real-world generalization, and multi-sensor integration.

He co-organizes workshops (e.g., Uncertainty Quantification at CVPR/ECCV) and serves as Area Chair for NeurIPS/CVPR/ECCV. He contributes to EU projects (e.g., ELLIOT) and open-source initiatives.