valeo.ai — AI research for autonomous driving
valeo.ai is an international research team based in Paris, working at the intersection of computer vision, AI, and autonomous driving. We publish at top venues (see our papers), release open-source code, collaborate with leading academic labs, and shape the AI future of Valeo.
The team is led by Director Matthieu Cord and Deputy Director Andrei Bursuc.
Research
All research axes →
News
View all news →| Jun 2026 | Two papers accepted at ECCV 2026: Re2Pix and CoReDi, both with available code (Re2Pix, CoReDi). |
|---|---|
| Jun 2026 | Amaia Cardiel spoke about AI explainability at two events: an invited talk at the CNRS Normastic Explainable AI Day (GREYC / LITIS) and a roundtable at Craft AI’s “Petits Dej’ de l’IA” at Le Village by CA Paris. |
| May 2026 | Efstathios Karypidis joined the team as a visiting PhD intern. |
| May 2026 | Multiple outstanding reviewer awards from the team and alumni! Congrats Quan, David, Nermin, Tetiana, Yihong, and alumni Gilles, Shashank, Florent, Björn! |
| May 2026 | Marion Hubler joined the team as a pre-doc. |
| Apr 2026 | One paper accepted at ICIP 2026: SSC-Priors, with available code. |
Featured work
All publications →
CVPR 2026Highlight
NAF: Zero-Shot Feature Upsampling via Neighborhood Attention Filtering
3DV 2026oral
LOSC: LiDAR Open-voc Segmentation Consolidator
NeurIPS'25 CCFM Workshop and TMLR 2026outstanding paper award
IPA: An Information-Preserving Input Projection Framework for Efficient Foundation Model Adaptation
TMLR 2026Featured Certification
GIFT: A Framework for Global Interpretable Faithful Textual Explanations of Vision Classifiers
IV 2025oral
LiDPM: Rethinking Point Diffusion for Lidar Scene Completion
IROS 2025oral
Tracking-Aware Deformation Field Estimation for Non-rigid 3D Reconstruction in Robotic Surgeries
