Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Multi-task Image-Text Understanding on VQAv2, GQA, NLVR2, and COCO Caption

66.9VQAv2 Accuracy

FT

65.13265.59166.0566.509Feb 14, 2024
Updated 4d ago

Evaluation Results

MethodLinks
2024.02
66.956.773.711277.3
2024.02
65.854.773.1115.977.4
2024.02
65.253.671.9115.376.5