Stéphane Lathuilière

Télécom Paris — France

Computer Science · Physical Sciences

19h-index1.6kcitations120works2.02yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

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

Research Topics

Domain Adaptation and Few-Shot Learning(31), Generative Adversarial Networks and Image Synthesis(30), Multimodal Machine Learning Applications(23), Advanced Vision and Imaging(21), Human Pose and Action Recognition(21)

Publications120 total

Di[M]O: Distilling Masked Diffusion Models into One-step Generator
SPIRE - Sciences Po Institutional REpository·2025Open Access
Soft-Di[M]O: Improving One-Step Discrete Image Generation with Soft Embeddings
arXiv (Cornell University)·2025Open Access
Make me an Expert: Distilling from Generalist Black-Box Models into Specialized Models for Semantic Segmentation
ArXiv.org·2025Open Access
Don’t Forget Your Inverse DDIM for Image Editing
IEEE Computational Intelligence Magazine·2025Open Access
Di$\mathtt{[M]}$O: Distilling Masked Diffusion Models into One-step Generator
arXiv (Cornell University)·2025Open Access
Group-robust Machine Unlearning
arXiv (Cornell University)·2025Open Access
Ask and Remember: A Questions-Only Replay Strategy for Continual Visual Question Answering
arXiv (Cornell University)·2025Open Access
OVOSE: Open-Vocabulary Semantic Segmentation in Event-Based Cameras
Lecture notes in computer science·2024Open Access
TACO: Training-free Sound Prompted Segmentation via Semantically Constrained Audio-visual CO-factorization
arXiv (Cornell University)·2024Open Access
Privacy-Preserving Adaptive Re-Identification Without Image Transfer
Lecture notes in computer science·2024Open Access
Weighted Ensemble Models Are Strong Continual Learners
Lecture notes in computer science·2024· 9 cited
An Eye for an Ear: Zero-shot Audio Description Leveraging an Image Captioner using Audiovisual Distribution Alignment
arXiv (Cornell University)·2024Open Access
OVOSE: Open-Vocabulary Semantic Segmentation in Event-Based Cameras
arXiv (Cornell University)·2024Open Access
Specify and Edit: Overcoming Ambiguity in Text-Based Image Editing
arXiv (Cornell University)·2024Open Access
Privacy-Preserving Adaptive Re-Identification without Image Transfer
arXiv (Cornell University)·2024Open Access
Unlearning Personal Data from a Single Image
arXiv (Cornell University)·2024Open Access
Collaborating Foundation Models for Domain Generalized Semantic Segmentation
2024· 17 citedOpen Access
Less is more: Summarizing Patch Tokens for efficient Multi-Label Class-Incremental Learning
arXiv (Cornell University)·2024· 1 citedOpen Access
Source-Guided Similarity Preservation for Online Person Re-Identification
arXiv (Cornell University)·2024Open Access
Mini but Mighty: Finetuning ViTs with Mini Adapters
2024· 8 citedOpen Access
page 1 of 6Next →

Frequent Co-authors

Elisa Ricci(18), Nicu Sebe(15), Radu Horaud(11), Pablo Mesejo(9), Aliaksandr Siarohin(9), Subhankar Roy(7), Enver Sangineto(6), Xavier Alameda-Pineda(5), Sergey Tulyakov(5), Moin Nabi(3), Benoît Massé(3), Cristiano Saltori(3), Fabio Galasso(3), Marlène Careil(3), Jakob Verbeek(3), Goluck Konuko(3), Giuseppe Valenzise(3), Willi Menapace(3), Enzo Tartaglione(3), Enrico Fini(2)