VisOnlyQA: Large Vision Language Models Still Struggle with Visual Perception of Geometric Information
Paper
• 2412.00947 • Published
• 8
VisOnlyQA
Dataset for evaluating the visual perception capabilities of LVLMs.
-
-
ryokamoi/VisOnlyQA_Eval_Real_v1.1
Viewer • Updated • 900 • 200 -
ryokamoi/VisOnlyQA_Eval_Synthetic
Viewer • Updated • 700 • 149 • 2 -
ryokamoi/VisOnlyQA_Train
Viewer • Updated • 70k • 433 • 2 -
ryokamoi/VisOnlyQA_metadata
Viewer • Updated • 3 • 90 -
ryokamoi/VisOnlyQA_Eval_Real
Viewer • Updated • 500 • 103 • 2 -
ryokamoi/VisOnlyQA_eval_analysis_2
Viewer • Updated • 150 • 102 -
ryokamoi/VisOnlyQA_eval_analysis_3
Viewer • Updated • 150 • 100 -
ryokamoi/VisOnlyQA_eval_analysis_4
Viewer • Updated • 150 • 123 -
ryokamoi/VisOnlyQA_eval_analysis_5
Viewer • Updated • 150 • 104 -
ryokamoi/VisOnlyQA_eval_analysis_6
Viewer • Updated • 150 • 117 -
ryokamoi/VisOnlyQA_length_angle
Viewer • Updated • 150 • 128