Éloi Zablocki
Senior research scientist at valeo.ai
I am a senior research scientist at valeo.ai, working on:
- autonomous driving, scene understanding and forecasting, world-models, motion planning
- vision and language, explainability, foundation models
Before joining Valeo, I completed a Ph.D. at Sorbonne Université in 2019 on multi-modal machine learning with language and vision, supervised by Patrick Gallinari, Laure Soulier, and Benjamin Piwowarski.
Prior to this, I earned an Engineering Degree from École Polytechnique (X2012) and an MSc from ENS Paris-Saclay (“Master MVA”).
News
| Oct 2025 | New preprint: RAP. Lightweight 3D rasterized views can augment imitation learning data for end-to-end driving. | |
|---|---|---|
| Oct 2025 | I am an outstanding reviewer at ICCV 2025. | |
| Sep 2025 | I participate to CoRL 2025 in Seoul, Korea. I will present VaViM and VaVAM and PPT in workshops. | |
| Sep 2025 | VaViM and VaVAM and PPT are accepted at CoRL Workshops. 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. Pseudo-labeled trajectories can be used to pre-train trajectory prediction models: improved performance, efficiency, and generalization. | |
| Jun 2025 | GaussRender is accepted at ICCV 2025. A plug-and-play 3D-to-2D reprojection loss using Gaussian splatting enhances 3D semantic occupancy learning from multiple cameras. | |
| 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. | |
| 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. Pseudo-labeled trajectories can be used to pre-train trajectory prediction models: improved 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. |
Current Students
- Amaia Cardiel, 2024 - 2027: PhD student co-advised with Elias Ramzi and Eric Gaussier
Paper(s): GIFT (under review), Contrastive concepts (TMLR'25), LLM-wrapper (ICLR'25)
- Loïck Chambon, 2023 - 2026: PhD student co-advised with Alexandre Boulch and Matthieu Cord
Paper(s): GaussRender (ICCV'25), JAFAR (NeurIPS'25), VaViM and VaVAM (CoRL'25 Workshop), PointBeV (CVPR'24), E2E-MF (ICRA'24)
Alumni
- Valentin Gerard, 2024: Research intern co-advised with Eduardo Valle
Paper(s): GIFT (under-review)
Current position: PhD student at EPFL with Alexandre Alahi
- Yuan Yin, 2024: Postdoc co-advised with Alexandre Boulch
Paper(s): ReGenTs (ECCV'24 W-CODA Workshop), PPT (CoRL'25 Robot Data Workshop)
Current position: Research scientist at valeo.ai
- Florent Bartoccioni, 2020 - 2023: PhD student co-advised with Matthieu Cord, Patrick Pérez, and Karteek Alahari
Paper(s): LaRa (CoRL'22), LiDARTouch (CVIU'23)
Current position: Research engineer at valeo.ai
- Amaia Cardiel, 2023: Research intern co-advised with Oriane Simeoni
Paper(s): LLM-wrapper (ICLR'25)
Current position: PhD student at valeo.ai
- Pegah Khayatan, 2023: Research intern co-advised with Alexandre Boulch
Paper(s): ReGenTs (ECCV'24 W-CODA Workshop)
Current position: Visiting student at Sorbonne Université with Matthieu Cord
- Mehdi Zemni, 2022: Research intern co-advised with Mickaël Chen
Paper(s): OCTET (CVPR'23)
Current position: Data scientist at Criteo
- Paul Jacob, 2021: Research intern co-advised with Hédi Ben-Younes
Paper(s): STEEX (ECCV'22)
Current position: Research scientist at Mistral AI. Previously Research scientist at Owkin
Scientific Service
Reviewer:
Conferences: CVPR 2021–2025, ECCV/ICCV 2021–2025, ICLR 2025, ICML 2025, WACV 2024, IROS 2022, AAAI 2021
Journals: IJCV 2022,2025, TPAMI 2021–2022, T-ITS 2023
Workshops: ROAD++ (@ICCV 2023)
PhD Jury Member:
Florent Bartoccioni (Invited Member, 2023)