Foundation models

Foundation models break free from predefined and restricted ontologies, enabling them to perceive a wider range of elements in their surroundings. By pretraining these foundation models in an unsupervised way, we can adapt them to a diverse set of tasks.

Selected publications

  1. Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers
    Efstathios Karypidis, Ioannis Kakogeorgiou, Spyros Gidaris, and Nikos Komodakis
    CVPR, 2025
    pdf Code
  3. VaViM and VaVAM: Autonomous Driving through Video Generative Modeling
    Florent Bartoccioni, Elias Ramzi, Victor Besnier, Shashanka Venkataramanan, Tuan-Hung Vu, Yihong Xu, Loick Chambon, Spyros Gidaris, Serkan Odabas, David Hurych, Renaud Marlet, Alexandre Boulch, Mickael Chen, Éloi Zablocki, Andrei Bursuc, Eduardo Valle, Matthieu Cord
    preprint, 2025
    Project page pdf Code
  4. LLM-wrapper: Black-Box Semantic-Aware Adaptation of Vision-Language Models for Referring Expression Comprehension
    Amaia Cardiel, Éloi Zablocki, Elias Ramzi, Oriane Siméoni, Matthieu Cord
    ICLR, 2025
    pdf Code
  5. Fine-Tuning CLIP's Last Visual Projector: A Few-Shot Cornucopia
    Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Patrick Pérez, Raoul de Charette
    under review, 2025
    pdf Code
  6. Test-Time Contrastive Concepts for Open-World Semantic Segmentation
    Monika Wysoczańska, Antonin Vobecky, Amaia Cardiel, Tomasz Trzciński, Renaud Marlet, Andrei Bursuc, Oriane Siméoni
    under review, 2025
    pdf
  7. GIFT: A Framework for Global Interpretable Faithful Textual Explanations of Vision Classifiers
    Éloi Zablocki*, Valentin Gerard*, Amaia Cardiel, Eric Gaussier, Matthieu Cord, Eduardo Valle
    under review, 2025
    pdf Code
  8. A Concept-Based Explainability Framework for Large Multimodal Models
    Jayneel Parekh, Pegah Khayatan, Mustafa Shukor, Alasdair Newson, Matthieu Cord
    NeurIPS, 2024
    Project page pdf Code
  9. DiffCut: Catalyzing Zero-Shot Semantic Segmentation with Diffusion Features and Recursive Normalized Cut
    Paul Couairon, Mustafa Shukor, Jean-Emmanuel Haugeard, Matthieu Cord, Nicolas Thome
    NeurIPS, 2024
    Project page pdf Code
  10. No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations
    Walter Simoncini, Spyros Gidaris, Andrei Bursuc, Yuki M. Asano
    NeurIPS, 2024
    pdf Code
  12. The BRAVO Semantic Segmentation Challenge Results in UNCV2024
    Tuan-Hung Vu, Eduardo Valle, Andrei Bursuc, Tommie Kerssies, Daan de Geus, Gijs Dubbelman, Long Qian, Bingke Zhu, Yingying Chen, Ming Tang, Jinqiao Wang, Tomáš Vojíř, Jan Šochman, Jiří Matas, Michael Smith, Frank Ferrie, Shamik Basu, Christos Sakaridis, Luc Van Gool
    ECCV, 2024
    pdf Code
  13. Reliability in Semantic Segmentation: Can We Use Synthetic Data?
    Thibaut Loiseau, Tuan-Hung Vu, Mickael Chen, Patrick Pérez, Matthieu Cord
    ECCV, 2024
    pdf Code
  14. UniTraj: A Unified Framework for Scalable Vehicle Trajectory Prediction
    Lan Feng, Mohammadhossein Bahari, Kaouther Messaoud Ben Amor, Éloi Zablocki, Matthieu Cord, Alexandre Alahi
    ECCV, 2024
    pdf Code
  15. A Simple Recipe for Language-guided Domain Generalized Segmentation
    Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Patrick Pérez, Raoul de Charette
    CVPR, 2024
    pdf Code
  16. OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks
    Sophia Sirko-Galouchenko, Alexandre Boulch, Spyros Gidaris, Andrei Bursuc, Antonin Vobecky, Patrick Pérez, Renaud Marlet
    CVPR Workshop WAD, 2024
    pdf Code
  17. Three Pillars improving Vision Foundation Model Distillation for Lidar
    Gilles Puy, Spyros Gidaris, Alexandre Boulch, Oriane Siméoni, Corentin Sautier, Patrick Pérez, Andrei Bursuc, Renaud Marlet
    CVPR, 2024
    pdf Code
  18. BEVContrast: Self-Supervision in BEV Space for Automotive Lidar Point Clouds
    Corentin Sautier, Gilles Puy, Alexandre Boulch, Renaud Marlet, Vincent Lepetit
    3DV, 2024
    pdf Code
  19. MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments
    Spyros Gidaris, Andrei Bursuc, Oriane Siméoni, Nikos Komodakis, Matthieu Cord, Patrick Pérez
    TMLR, 2024
    pdf
  20. POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images
    Antonin Vobecky, Oriane Siméoni, David Hurych, Spyros Gidaris, Andrei Bursuc, Patrick Pérez, Josef Sivic
    NeurIPS, 2023
    pdf Code
  21. PØDA: Prompt-driven Zero-shot Domain Adaptation
    Mohammad Fahes, Tuan-Hung Vu, Andrei Bursuc, Patrick Pérez, Raoul de Charette
    ICCV, 2023
    pdf Code
  22. ALSO: Automotive Lidar Self-supervision by Occupancy estimation
    Alexandre Boulch, Corentin Sautier, Björn Michele, Gilles Puy, Renaud Marlet
    CVPR, 2023
    pdf Code
  23. What to Hide from Your Students: Attention-Guided Masked Image Modeling
    Ioannis Kakogeorgiou, Spyros Gidaris, Bill Psomas, Yannis Avrithis, Andrei Bursuc, Konstantinos Karantzalos, and Nikos Komodakis
    ECCV, 2022
    pdf Code
  24. Online Bag-of-Visual-Words Generation for Unsupervised Representation Learning
    Spyros Gidaris, Andrei Bursuc, Gilles Puy, Nikos Komodakis, Patrick Pérez, and Matthieu Cord
    CVPR, 2021
    pdf Code
  25. Learning Representations by Predicting Bags of Visual Words
    Spyros Gidaris, Andrei Bursuc, Nikos Komodakis, Patrick Pérez, and Matthieu Cord
    CVPR, 2020
    pdf Code