The Deep Visual Learning (DVL) Lab at Fondazione Bruno Kessler conducts research in machine learning and computer vision, with a growing focus on multimodal and foundation models. Our work aims to develop learning methodologies that make large-scale models more adaptable, efficient and trustworthy when deployed on real-world data. We are especially interested in how vision-language and multimodal foundation models can be adapted, specialized and continually updated without costly retraining, and in making them reliable: robust to distribution shifts, fair, interpretable and safe. Recent projects include training-free and open-vocabulary recognition with vision-language models, efficient adaptation and benchmarking of large multimodal models, video understanding, and human behaviour analysis.
Elisa Ricci gives keynote at EUVIP 2026 in Luxembo...
Oct 23, 2026 | News
4 Papers Accepted at NeurIPS 2026!
Oct 2, 2026 | News
Two papers accepted at ECCV 2026!
Sep 9, 2026 | News
Recent Posts
- Personalizing MLLMs via Reinforced Multimodal Reference Game
- SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models
- Towards Unconstrained Human-Object Interaction
- Training-free Online Video Step Grounding
- Training-Free Personalization via Retrieval and Reasoning on Fingerprints