Florenz: Scaling Laws for Systematic Generalization in Vision-Language Models
Paper
•
2503.09443
•
Published
•
8
Caption via Translation
Models and datasets of the paper "Scaling Laws for Conditional Emergence of Multilingual Image Captioning via Generalization from Translation"
-
-
Spravil/caption-via-translation-0_4B
Image-Text-to-Text • 0.4B • Updated • 33 -
Spravil/caption-via-translation-1_0B
Image-Text-to-Text • 1B • Updated • 3 -
Spravil/caption-via-translation-3_5B
Image-Text-to-Text • 3B • Updated • 8 -
Spravil/caption-via-translation-11_2B
Image-Text-to-Text • 11B • Updated • 16 -
Spravil/caption-via-translation-0_4B-ft
Image-Text-to-Text • 0.4B • Updated • 32 -
Spravil/caption-via-translation-1_0B-ft
Image-Text-to-Text • 1B • Updated • 4 -
Spravil/caption-via-translation-3_5B-ft
Image-Text-to-Text • 3B • Updated • 10 -
Spravil/caption-via-translation-11_2B-ft
Image-Text-to-Text • 11B • Updated • 18 -
Spravil/cc12m_ccmatrix_captions_and_translations
Viewer • Updated • 11M • 5