Gianni Franchi

Gianni Franchi is an Assistant Professor at ENSTA Paris, part of Institut Polytechnique de Paris. His research focuses on robust computer vision, uncertainty quantification, and explainable AI (XAI). He has been teaching Deep Learning, Computer Vision, and Machine Learning courses since 2020 at ENSTA Paris and Télécom Paris.

• PhD in Fusion of Information, Machine Learning, and Image Processing (2016) from Mines de Paris
• Postdoctoral experience at Paris Saclay University (2018-2020) and Seigen University (2016-2018)
• Current PhD students: Rémi Kazmierczak, Olivier Laurent, Adrien Lafage, Mouïn Ben Ammar
• Alumni: Xuanlong Yu (2020-2023)

Research interests include robust computer vision, anomaly detection, uncertainty quantification, out-of-distribution detection, certifiable AI, and explainable AI. He leads the development of the PyTorch library Torch Uncertainty for uncertainty quantification in deep learning.

Recent publications span uncertainty quantification in foundation models, trajectory forecasting, vision-language adaptation, and explainability benchmarks. Gianni actively collaborates on multimodal autonomous driving datasets and uncertainty-aware systems for human-agent interaction.