We are an international team based in Paris, conducting AI research for Valeo automotive applications, in collaboration with world-class academics. Our main research is towards better, clearer & safer automotive AI. Find out more about our research here!


Florent Bartoccioni, research engineer | page | scholar
Victor Besnier, research scientist | scholar
Alexandre Boulch, research scientist | page | scholar| github | twitter
Andrei Bursuc, deputy scientific director | page | scholar | github | twitter
Amaia Cardiel, PhD student w/ Université Grenoble Alpes | linkedin
Loïck Chambon, PhD student w/ Sorbonne U. | page | linkedin
Mickaël Chen, research scientist | page | scholar | github | twitter
Matthieu Cord, scientific director (and prof. at Sorbonne U.) | page | scholar | twitter
Spyros Gidaris, research scientist | scholar | github
David Hurych, research scientist | scholar
Victor Letzelter, PhD student w/ Telecom Paris | scholar | github
Renaud Marlet, principal scientist (and researcher at ENPC) | page | scholar
Tetiana Martyniuk, PhD student w/ Inria Paris | scholar
Björn Michele, PhD student w/ U. Bretagne Sud | page | scholar | twitter
Gilles Puy, research scientist | page | scholar
Elias Ramzi, research scientist | page | scholar
Nermin Samet, research scientist | page | scholar
Corentin Sautier, PhD student w/ ENPC | page | scholar
Oriane Siméoni, research scientist | page | scholar | github
Sophia Sirko-Galouchenko, PhD student w/ Sorbonne U. | linkedin
Eduardo Valle, senior scientist | scholar | github | linkedin
Shashanka Venkataramanan, research scientist | page | scholar | twitter
Antonín Vobecký, PhD student w/ CTU | page | scholar | github
Tuan-Hung Vu, research scientist | page | scholar | github | twitter
Yihong Xu, research scientist | scholar
Yuan Yin, PostDoc | page | scholar | twitter
Éloi Zablocki, research scientist | scholar | twitter

Human Resource Partner: Marine Michaud
Collaborative projects manager: Serkan Odabas
Assistant: Alicia Heurtefeu
Location: 100 rue de Courcelles, Paris

Academic partners

CTU, Prague (Josef Sivic)
EPFL, Lausanne (Alexandre Alahi)
ENPC, Paris (Vincent Lepetit)
Inria Paris (Raoul de Charette)
Sorbonne, Paris (Matthieu Cord, Nicolas Thome)
Télécom, Paris (Gaël Richard, Slim Essid, Mathieu Fontaine)
UBS, Vannes (Nicolas Courty)
Université Grenoble Alpes (Eric Gaussier)

Latest News

[07/2024] team Elias Ramzi starts as research scientist
[06/2024] challenge team The team wins the Argoverse 2 “Unified Detection, Tracking and Forecasting” challenge, held at CVPR WAD 2024.
[06/2024] pres Tuan-Hung Vu gives an invited talk at GDR IASIS on “Language-guided Adaptation and Generalization in Semantic Segmentation”
[06/2024] team Shashanka Venkataramanan starts as research scientist
[05/2024] team Laura Calem and Léon Zheng defend their PhD at CNAM and ENS Lyon respectively
[05/2024] award Gilles Puy is an outstanding reviewer at CVPR 2024
[05/2024] paper One paper accepted at IJCV: Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Survey
[05/2024] award Yuan Yin is awarded with the honorable runner-up prize for the best PhD thesis in AI in 2024, granted by the French Association on AI (AFIA)
[05/2024] conference Yihong participates to ICRA 2024 in Okinawa, Japan. He presents Towards Motion Forecasting with Real-World Perception Inputs
[04/2024] service Seven researchers from the team serve as reviewers for ECCV. Andrei, Oriane, and Renaud serve as Area Chairs
[04/2023] team The 2024 cohort of interns has joined us. Welcome Achraff, Baptiste, Ellington, Matteo, Valentin, and Walter!
[04/2023] team Yuan Yin starts as Postdoc
[03/2024] conference Björn and Corentin participate to 3DV 2024 in Davos, Switzerland. They will present SALUDA and BEVContrast
[03/2024] team Björn, Corentin, Sophia, and Tetiana participate to the FOMO Winter School on Foundation Models, in Amsterdam.
[02/2024] paper code Eight papers accepted at CVPR 2024: ABNN, SegAD, Don’t drop your samples!, FAMix, NOPE, PointBeV, ScaLR, SPOT. Some of them already have available code
[01/2024] paper code One paper accepted at ICRA 2024 with available code (Towards Motion Forecasting with Real-World Perception Inputs)
[01/2024] paper code One paper accepted at ICLR 2024 with available code (EvALign-ICL)
[01/2024] service Eleven researchers from the team serve as reviewers for CVPR. Matthieu serves as an Area Chair.
[12/2023] pres Oriane Siméoni gives an invited lecture on “Object localization (almost) for free harnessing self-supervised features” at the 46th Pattern Recognition and Computer Vision Colloquium in Prague
[12/2023] service Andrei Bursuc is a Top Reviewer at NeurIPS’23
[11/2023] code Victor Besnier and Mickaël Chen release a pytorch reimplementation of MaskGIT
[10/2023] paper code Two papers accepted at WACV 2024, one with code (CLIP-DIY)
[10/2023] paper code Two papers accepted at 3DV 2024 with available code (BEVContrast and SALUDA)
[09/2023] conference Valeo.ai participates in mass to ICCV 2023 in Paris, from interns to senior researchers, spot our dark green hoodies and engage with us!
[09/2023] team Nermin Samet starts as research scientist
[09/2023] service Eloi Zablocki is an Outstanding Reviewer at ICCV’23
[09/2023] paper Four papers accepted at NeurIPS’23
[07/2023] paper code Five papers accepted at ICCV’23, several with code so far (WaffleIron, PØDA, SeedAL, eP-ALM)
[07/2023] service Renaud Marlet and Oriane Siméoni join ICCV’23 organization as Logistic Chair (Patrick Pérez serving as Industrial Relation co-chair)
[06/2023] pres Oriane Siméoni runs “Object localization for free: Going beyond self-supervised learning” CVPR’23 Tutorial
[06/2023] pres Nine Valeo.ai researchers participate to CVPR’23
[06/2023] pres Patrick Pérez delivers keynote at Vision4AllSeasons CVPR’23 workshop
[06/2023] team Florent Bartoccioni defends his PhD at Inria-Grenoble and joins Valeo.ai as research engineer
[05/2023] service Andrei Bursuc, Gilles Puy and Spyros Gidaris are Outstanding Reviewers at CVPR’23
[04/2023] presBRAVO: Robustness and Reliability of Autonomous Vehicles in the Open-world” accepted as ICCV’23 workshop
[04/2023] presUncertainty Quantification for Computer Vision” accepted as ICCV’23 workshop
[04/2023] presThe Many Faces of Reliability of Deep Learning for Real-World Deployment” accepted as ICCV’23 tutorial. Slides and videos are online
[03/2023] team Valeo.ai celebrates its 5th anniversary!
[02/2023] paper code Six papers accepted at CVPR’23, four with codes (FOUND, ALSO, Range-ViT, OCTET)
[01/2023] team Eduardo Valle starts as senior scientist
[12/2022] team Cédric Rommel starts as research scientist
[11/2022] team Huy Van Vo defends his PhD at ENS and joins FAIR at META
[10/2022] collab Astra-Vision, part of Inria-Valeo joint team Astra, starts research on perception
[10/2022] team Yihong Xu starts as research scientist
[10/2022] paper code data Six papers presented at ECCV’22, five with codes (BiB, D&S, STEEX, AttMask, LDU) and one with dataset (HULC)
[10/2022] pres Andrei Bursuc and Spyros Gidaris run Self-supervision on wheels: Advances in self-supervised learning from autonomous driving data ECCV’22 Tutorial
[09/2022] challenge ObsNet ranks first on SegmentMeIfYouCan benchmark (Anomaly Track) among methods with no OoD training data

Main research themes

Multi-sensor scene understanding and forecasting — Driving monitoring and automatization relies first on a variety of sensors (cameras, radars, laser scanners) that deliver complementary information on the surroundings of a vehicle and on its cabin. Exploiting at best the outputs of each of these sensors at any instant is fundamental to understand the complex environment of the vehicle and to anticipate its evolution in the next seconds. To this end, we explore various machine learning approaches where sensors are considered either in isolation or collectively.

Data/annotation-efficient learning — Collecting diverse enough real data, and annotating it precisely, is complex, costly, time-consuming and doomed insufficient for complex open-world applications. To reduce dramatically these needs, we explore various alternatives to full supervision, in particular for perception tasks: self-supervised representation learning for images and point clouds, visual object detection with no or weak supervision only, unsupervised domain adaptation for semantic segmentation of images and point clouds, for instance. We also investigate training with fully-synthetic or generatively-augmented data.

Dependable models — When the unexpected happens, when the weather badly degrades, when a sensor gets blocked, embedded safety-critical models should continue working or, at least, diagnose the situation to react accordingly, e.g., by calling an alternative system or human oversight. With this in mind, we investigate ways to assess and improve the robustness of neural nets to perturbations, corner cases and various distribution shifts. Making their inner workings more interpretable, by design or in a post-hoc way, is also an important and challenging venue that we explore towards more trust-worthy models.

Code and data

BEVContrast Self-Supervision for Lidar Point Clouds (3DV’24)
SALUDA Unsupervised Domain Adaptation for LiDAR point clouds (3DV’24)
CLIP-DIY Open-Vocabulary Semantic Segmentation (WACV’24)
POCO Point Convolution for Surface Reconstruction (CVPR’22)
SFRIK Self-supervised learning with rotation-invariant kernels (ICLR’23)
FOUND Observing the background to discover objects (CVPR’23)
ALSO Automotive Lidar self-supervision by occupancy estimation (CVPR’23)
RangeViT ViT for 3D Semantic Segmentation in autonomous driving (CVPR’23)
OCTET Object-aware counterfactual explanations (CVPR’23)
WaffleIron Automotive point cloud semantic segmentation (ICCV’23)
LidarTouch Monocular metric depth estimation with a few-beam LiDAR (CVIU 2022)
DenseMTL Cross-task attention mechanism for dense multi-task learning (WACV’23)
LaRa Latents and rays for multi-camera BEV semantic segmentation (CoRL’22)
BiB Active learning strategies for weakly-supervised object detection (ECCV’22)
D&S Unsupervised semantic segmentation of urban scenes via cross-modal distillation (ECCV’22)
STEEX Steering Counterfactual Explanations with Semantics (ECCV’22)
CAB Raising Context Awareness in Motion Forecasting (workshop CVPR’22)
MuHDi Multi-head distillation for continual unsupervised domain adaptation in semantic segmentation (CLVision’22)
DIVA Diverse Probabilistic Trajectory Forecasting with Admissibility Constraints (ICPR 2022)
SLidR Image-to-Lidar self-supervised distillation for autonomous driving data (CVPR’22)
RADIal (dataset) HR radar dataset (+ camera & lidar) for vehicle and free space detection (CVPR’22)
LOST Object localization with self-supervised transformers (BMVC’21)
MTAF Multi-Target Adversarial Frameworks for domain adaptation (ICCV’21)
PCAM Product of Cross-Attention Matrices for rigid registration of point clouds (ICCV’21)
SP4ASC Separable convolutions for acoustic scene classification in DCASE’21 Challenge
MVRSS Multi-view radar semantic segmentation (ICCV’21)
ObsNet Out-Of-Distribution detection by learning from local adversarial attacks in semantic segmentation (ICCV’21)
Semantic Palette Guiding scene generation with class proportions (CVPR’21)
Attributes with Fields Detecting 32 pedestrian attributes with composite fields (T-ITS)
OBoW Online BoW generation for unsupervised representation learning (CVPR’21)
DummyNet Artificial Dummies for Urban Dataset Augmentation (AAAI’21)
CARRADA (dataset) Camera and Automotive Radar with Range-Angle-Doppler Annotations dataset (ICPR’20)
ESL Entropy-guided Self-supervised Learning for Domain Adaptation in Semantic Segmentation (workshop CVPR’20)
FLOT Scene flow on point clouds guided by optimal transport (ECCV’20)
AdamSRT Adam exploiting BN-induced pherical invariance of CNN (arXiv 2020)
LightConvPoint Convolution for points (ACCV’20)
xMUDA Cross-modal UDA for 3D semantic segmentation (CVPR’20)
LearningByCheating End-to-End driving using implicit affordances (CVPR’20)
rOSD Unsupervised object discovery at scale (ECCV’20)
ConvPoint Convolutions for unstructured point clouds (Computer \& Graphics 2020)
BEEF Driving behavior explanation with multi-level fusion (workshop NeurIPS’20 and Pattern Recognition’22)
Woodscape Driving fisheye multi-task dataset (ICCV’19)
ZS3 Zero-Shot Semantic Segmentation (NeurIPS’19)
BF3S Boosting few-shot visual learning with self-supervision (ICCV’19)
ConfidNet Addressing failure prediction by learning model confidence (NeurIPS’19)
Rainbow-IQN Ape-X effective RL combination for Atari games
DADA Depth-aware Domain Adaptation in Semantic Segmentation (ICCV’19)
AdvEnt Adversarial Entropy minimization for domain adaptation in semantic segmentation (CVPR’19)
OSD Unsupervised object discovery as optimization (CVPR’19)

Previous news



Hédi Ben-younes, research scientist (scholar), now at BNP Paribas
Maxime Bucher, research scientist (scholar), now at TOBAM
Laura Calem, PhD student w/ CNAM (scholar)
Charles Corbière, PhD student with CNAM (scholar), now at EPFL
Maximilian Jaritz, PhD student (scholar), now at Amazon
Himalaya Jain, research scientist (scholar), now at Helsing
Gabriel de Marmiesse, research engineer (github), now at Datadog
Arthur Ouaknine, PhD student with Telecom (scholar), now at McGill
Patrick Pérez, scientific director (scholar), now at Kyutai
Julien Rebut, research scientist (scholar), now at Hexagon|AutonomouStuff
Simon Roburin, PhD student with Ponts (scholar), now at EPFL
Cédric Rommel, research scientist (scholar), now at Meta
Antoine Saporta, PhD student with Sorbonne U. (scholar), now at Meero
Tristan Schultz, research engineer, now at Valeo IS Direction
Marin Toromanoff, PhD student (scholar), now at Valeo Driving Assistance Research
Huy Van Vo, PhD student with Inria (scholar), now at Meta
Emilie Wirbel, research scientist (scholar), now at Helsing
Léon Zheng, PhD student w/ ENS Lyon (scholar)