-
Where Do Multilingual Vision-Language Encoders Fail on Low-Resource Languages?
Paper • 2608.30725 • Published -
dnotitia/geometric-bottleneck-metaclip2
Zero-Shot Image Classification • 2B • Updated • 9 • 1 -
dnotitia/geometric-bottleneck-siglip2
Zero-Shot Image Classification • 1B • Updated • 13 -
dnotitia/geometric-bottleneck-altclip
Zero-Shot Image Classification • 0.9B • Updated • 12
Collections
Discover the best community collections!
Collections trending this week
-
Where Do Multilingual Vision-Language Encoders Fail on Low-Resource Languages?
Paper • 2608.30725 • Published -
dnotitia/geometric-bottleneck-metaclip2
Zero-Shot Image Classification • 2B • Updated • 9 • 1 -
dnotitia/geometric-bottleneck-siglip2
Zero-Shot Image Classification • 1B • Updated • 13 -
dnotitia/geometric-bottleneck-altclip
Zero-Shot Image Classification • 0.9B • Updated • 12