Spyros Gidaris

Valeo (France) — France

Computer Science · Physical Sciences

17h-index4.6kcitations59works3.12yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Advanced Neural Network Applications(26), Domain Adaptation and Few-Shot Learning(25), Advanced Image and Video Retrieval Techniques(24), Multimodal Machine Learning Applications(16), Robotics and Sensor-Based Localization(7)

Publications59 total

Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning
arXiv (Cornell University)·2025Open Access
DIP: Unsupervised Dense In-Context Post-training of Visual Representations
arXiv (Cornell University)·2025Open Access
Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers
2025· 1 cited
Multi-Token Prediction Needs Registers
arXiv (Cornell University)·2025Open Access
Boosting Generative Image Modeling via Joint Image-Feature Synthesis
arXiv (Cornell University)·2025Open Access
EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling
arXiv (Cornell University)·2025Open Access
Unsupervised Semantic Segmentation of Urban Scenes via Cross-Modal Distillation
International Journal of Computer Vision·2025· 4 citedOpen Access
Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers
arXiv (Cornell University)·2025· 1 citedOpen Access
Valeo4Cast: A Modular Approach to End-to-End Forecasting
Lecture notes in computer science·2025· 1 cited
DINO-Foresight: Looking into the Future with DINO
arXiv (Cornell University)·2024· 1 citedOpen Access
Unsupervised Object Localization in the Era of Self-Supervised ViTs: A Survey
International Journal of Computer Vision·2024· 6 citedOpen Access
No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations
arXiv (Cornell University)·2024Open Access
OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks
2024· 9 citedOpen Access
Three Pillars Improving Vision Foundation Model Distillation for Lidar
2024· 17 cited
SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers
2024· 10 cited
Valeo4Cast: A Modular Approach to End-to-End Forecasting
arXiv (Cornell University)·2024Open Access
OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networks
arXiv (Cornell University)·2024Open Access
POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images
arXiv (Cornell University)·2024· 8 citedOpen Access
No Train, all Gain: Self-Supervised Gradients Improve Deep Frozen Representations
2024
SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers
arXiv (Cornell University)·2023Open Access
page 1 of 3Next →

Frequent Co-authors

Nikos Komodakis(26), Andrei Bursuc(22), Patrick Pérez(16), Oriane Siméoni(12), Gilles Puy(12), Renaud Marlet(9), Alexandre Boulch(8), Ioannis Kakogeorgiou(7), Matthieu Cord(7), Antonín Vobecký(6), David Hurych(4), Josef Šivic(4), Éloi Zablocki(4), Corentin Sautier(3), Κωνσταντίνος Καράντζαλος(3), Xi Shen(3), Ilaria Pastrolin(3), Oumayma Bounou(3), Marc Smith(3), Olivier Poncet(3)