News
| Feb 2025 | New release from the team: VaViM & VaVAM. VaViM is a 1.2B parameter video generative model trained on 1,800+ hours of raw Youtube videos. Its derived video-action model, VaVAM, achieves state-of-the-art results on NeuroNCAP driving benchmark. We open-source code, model weights, training recipes and scaling laws. | |
|---|---|---|
| Feb 2025 | New preprint: GaussRender. A plug-and-play 3D-to-2D reprojection loss using Gaussian splatting enhances 3D semantic occupancy learning from multiple cameras. | |
| Jan 2025 | Annealed Winner-Takes-All for Motion Forecasting is accepted at ICRA 2025. We show that using an annealing loss enhances training stability and performance of state-of-the-art trajectory prediction models. | |
| Jan 2025 | LLM-wrapper is accepted at ICLR 2025. It shows that LLMs can learn to adapt black-box VLMs for new tasks and domains, by wrapping and reasoning on the vision models’ outputs. | |
| Dec 2024 | New preprint: PPT. Pre-training trajectory prediction models with pseudo-labeled trajectories improves performance, efficiency, and generalization. | |
| Nov 2024 | New preprint  : GIFT. A framework for generating global, interpretable textual explanations of vision classifiers, combining counterfactual visual explanations with VLMs and LLMs. | |
| Sep 2024 | I participate to ECCV 2024 in Milan. I will present UniTraj, LLM-wrapper, ReGentS, and Valeo4Cast. | |
| Aug 2024 | 3 papers accepted in workshops at ECCV: LLM-wrapper, ReGentS, and Valeo4Cast. | |
| Jul 2024 | UniTraj is accepted at ECCV 2024. | |
| Jun 2024 | Valeo4Cast wins the Argoverse 2 “Unified Detection, Tracking and Forecasting” challenge held at CVPR WAD 2024. | |
| Mar 2024 | PointBeV is accepted at CVPR 2024. | |
| Jan 2024 | Our paper on Motion Forecasting with Real-World Perception Inputs is accepted at ICRA 2024. | |
| Sep 2023 | I am an outstanding reviewer at ICCV 2023. | |
| Jul 2023 | Interview in millefeuille.ai in French. | |
| Jun 2023 | Our survey on Unsupervised Object Localization in the Era of Self-Supervised ViTs is accepted at IJCV 2024. | |
| Feb 2023 | Two papers accepted at CVPR 2023: OCTET and FOUND. | |
| Jan 2023 | LiDARTouch is accepted at CVIU 2023. | |
| Oct 2022 | LaRa is accepted at CoRL 2022. | |
| Jul 2022 | Our survey on Explainability for vision-based driving systems is accepted at IJCV 2022. | |
| Jul 2022 | STEEX is accepted at ECCV 2022. | |
| Apr 2022 | CAB is accepted at CVPR Workshop on Autonomous Driving (WAD) 2022. | |
| Nov 2021 | BEEF, our self-driving model that explains its decisions with natural language, is accepted at Pattern Recognition 2021. | |
| Feb 2020 | I am a runner-up for the best PhD thesis in AI, granted by the French Association on Artificial Intelligence (AFIA). | |
| Jan 2020 | I am starting as research scientist at valeo.ai. | |
| Oct 2019 | I defend my PhD titled “Multimodal machine learning: complementarity of textual and visual contexts”. Jury: Antoine Bordes, Patrick Gallinari, Guillaume Gravier, Marie-Francine Moens, Benjamin Piwowarski, Xavier Tannier. |