Federico Bianchi
Federico Bianchi
Home
Featured
Posts
Outreach
Research Philosophy
Talks
Publications
Multimodal
Contrastive Language-Image Pre-training for the Italian Language
CLIP (Contrastive Language-Image Pre-training) is a very recent multi-modal model that jointly learns representations of images and texts. The model is trained on a massive amount of English data and shows impressive performance on zero-shot …
Cite
×