Welcome to the GitHub page of the AI team of U2IS, the computer science 💻 and robotics 🤖 laboratory of ENSTA Paris!

This GitHub organization includes codes and resources mostly centered on uncertainty, vision, and deep learning.

Reach out and follow if you are interested!

🎉 Five papers from the lab were accepted at ICLR 2024 🎉

🎉 One paper from the lab was accepted at AAAI 2024 🎉

Gianni presented a Tutorial at 🌴 WACV 2024 🌴: The Nuts and Bolts of Uncertainty Quantification 🎉

• Lafage, A., Barbier, M., Franchi, G., & Filliat, D. Hierarchical Light Transformer Ensembles for Multimodal Trajectory Forecasting. In [WACV, 2025].
• Franchi, G., Laurent, O., Leguéry, M., Bursuc, A., Pilzer, A., & Yao, A. Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models. In [CVPR, 2024].
• Laurent, O., Aldea E. & Franchi, G. A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors. In [ICLR, 2024].
• Ammar, M. B., Belkhir, N., Popescu, S., Manzanera, A., & Franchi, G. NECO: NEural Collapse Based Out-of-distribution Detection. In [ICLR, 2024].
• Zadem, M., Mover, S., & Nguyen, S. M. Reconciling Spatial and Temporal Abstractions for Goal Representation. In [ICLR, 2024].
• Brellmann, D., Berthier, E., Filliat, D., & Frehse, G. On Double-Descent in Reinforcement Learning with LSTD and Random Features. In [ICLR, 2024].
• Xu, K., Chen, R., Franchi, G., & Yao, A. Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement. In [ICLR, 2024].
• Kazmierczak, R., Berthier, E., Frehse, G., & Franchi, G. (2023). CLIP-QDA: An Explainable Concept Bottleneck Model. arXiv preprint arXiv:2312.00110. [ArXiv].
• Yu, X., Franchi, G., Gu, J., & Aldea, E. Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regression. In [AAAI, 2024].
• Franchi, G., Bursuc, A., Aldea, E., Dubuisson, S., & Bloch, I. Encoding the latent posterior of Bayesian neural networks for uncertainty quantification. [TPAMI].
• Laroudie, C., Bursuc, A., Ha, M. L., & Franchi, G. Improving CLIP Robustness with Knowledge Distillation and Self-Training. [ArXiv].
• Franchi, G., Hariat, M., Yu, X., Belkhir, N., Manzanera, A., & Filliat, D. InfraParis: A multi-modal and multi-task autonomous driving dataset. In [WACV, 2024].
• Hariat, M., Laurent, O., Kazmierczak, R., Bursuc, A., Yao, A., & Franchi, G. Learning to Generate Training Datasets for Robust Semantic Segmentation. In [WACV, 2024].
• Laurent, O., Lafage, A., Tartaglione, E., Daniel, G., Martinez, J. M., Bursuc, A., & Franchi, G. Packed-Ensembles for Efficient Uncertainty Estimation. In [ICLR, 2023].
• Hariat, M., Manzanera, A., & Filliat, D. Rebalancing Gradient To Improve Self-Supervised Co-Training of Depth, Odometry and Optical Flow Predictions. In [WACV, 2023].
• Franchi, G., Yu, X., Bursuc, A., Aldea, E., Dubuisson, S., & Filliat, D. Latent Discriminant Deterministic Uncertainty. In [ECCV, 2022].
• Yu, X., Franchi, G., & Aldea, E. On Monocular Depth Estimation and Uncertainty Quantification using Classification Approaches for Regression. In [ICIP, 2022].