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, release open-source code, collaborate closely with leading academic labs, and work on AI research for Valeo automotive applications. Explore our publications or open-source code.
The team is led by Director Matthieu Cord and Deputy Director Andrei Bursuc.
Research
All research axes →
News
All news →| Apr 2026 | Marc Lafon is awarded with the 2026 AFRIF PhD award |
|---|---|
| Apr 2026 | One paper accepted at ACL Findings 2026: DRIV-EX. |
| Mar 2026 | Victor Letzelter defends his PhD entitled “Multiple Choice Learning from Ambiguous Signals”. |
| Mar 2026 | Renaud Marlet and Andrei Bursuc are recognized as serial outstanding reviewers at major computer vision conferences. |
| Feb 2026 | Nine papers accepted at CVPR 2026: DrivoR, OccAny, NAF, Franca, MAD, StableMTL, LIDAS, LAM3C, ICM. |
| Feb 2026 | Loick Chambon defends his PhD entitled "Efficient Representations for Autonomous Driving". |
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
