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 • 192 -
ryokamoi/VisOnlyQA_Eval_Synthetic
Viewer • Updated • 700 • 156 • 2 -
ryokamoi/VisOnlyQA_Train
Viewer • Updated • 70k • 374 • 2 -
ryokamoi/VisOnlyQA_metadata
Viewer • Updated • 3 • 105 -
ryokamoi/VisOnlyQA_Eval_Real
Viewer • Updated • 500 • 124 • 2 -
ryokamoi/VisOnlyQA_eval_analysis_2
Viewer • Updated • 150 • 84 -
ryokamoi/VisOnlyQA_eval_analysis_3
Viewer • Updated • 150 • 78 -
ryokamoi/VisOnlyQA_eval_analysis_4
Viewer • Updated • 150 • 106 -
ryokamoi/VisOnlyQA_eval_analysis_5
Viewer • Updated • 150 • 108 -
ryokamoi/VisOnlyQA_eval_analysis_6
Viewer • Updated • 150 • 123 -
ryokamoi/VisOnlyQA_length_angle
Viewer • Updated • 150 • 95