List your company
ResearchFormerly WizWand

High-Resolution Visual Question Answering on HR-4k

65.13AccuracyQwen 2.5 VL + CropVLM
34.054842.122450.1958.2576Nov 25, 2025
Updated 7mo ago

Evaluation results

MethodLinks
Qwen 2.5 VL + CropVLMBase Model=Qwen 2.5 VL, Cropping Strategy=CropVLM, Input Resolution=2048x20482025.1165.13
Qwen 2.5 VL + ViCrop (rel-att)Base Model=Qwen 2.5 VL, Cropping Strategy=ViCrop (rel-att), Input Resolution=448x4482025.1156.25
Qwen 2.5 VL + ViCrop (grad-att)Base Model=Qwen 2.5 VL, Cropping Strategy=ViCrop (grad-att), Input Resolution=448x4482025.1154.38
Qwen 2.5 VL + UV-CoTBase Model=Qwen 2.5 VL, Cropping Strategy=UV-CoT, Input Resolution=336x3362025.1153.62
Qwen 2.5 VLBase Model=Qwen 2.5 VL, Cropping Strategy=None, Input Resolution=448x4482025.1151.88
LLaVA 1.5 + ViCrop (rel-att)Base Model=LLaVA 1.5, Cropping Strategy=ViCrop (rel-att), Input Resolution=336x3362025.1144.25
LLaVA 1.5 + ViCrop (grad-att)Base Model=LLaVA 1.5, Cropping Strategy=ViCrop (grad-att), Input Resolution=336x3362025.1143.62
LLaVA 1.5 + CropVLMBase Model=LLaVA 1.5, Cropping Strategy=CropVLM, Input Resolution=2048x20482025.1141.38
LLaVA 1.5 + UV-CoTBase Model=LLaVA 1.5, Cropping Strategy=UV-CoT, Input Resolution=336x3362025.1137.88
LLaVA 1.5Base Model=LLaVA 1.5, Cropping Strategy=None, Input Resolution=336x3362025.1135.25