A data curation and training recipe that scales CLIP from English-only data to 300+ languages from scratch, breaking the curse of multilinguality at ViT-H/14 scale.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Meta CLIP 2: A Worldwide Scaling Recipe
A data curation and training recipe that scales CLIP from English-only data to 300+ languages from scratch, breaking the curse of multilinguality at ViT-H/14 scale.