Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
MagicLens
text, image · discriminative ·
anchor
Findings
IC-250
Existing multimodal embedding models show highly uneven performance across MMEB's four meta-task categories, with VQA scores as low as 4.2 and overall scores ranging from 13.3 to 44.7
IC-250
Existing multimodal embedding models show highly uneven performance across MMEB's four meta-task categories, with VQA scores as low as 4.2 and overall scores ranging from 13.3 to 44.7
[compared-to]