List your company
ResearchFormerly WizWand

Aesthetic Quality Assessment on AVA v1 (test)

0.883Kendall's TauRARL
0.624040.691270.75850.82573Jan 28, 2026
Updated 8mo ago

Evaluation results

MethodLinks
RARLBackbone=Qwen2.5-VL-7B, Training strategy=RARL, Number of images=4-imgs2026.010.883—
RARLBackbone=Qwen2.5-VL-7B, Training strategy=RARL, Number of images=2-imgs2026.010.875—
RARLBackbone=Qwen2.5-VL-7B, Training strategy=RARL, Number of images=8-imgs2026.010.871—
RARLBackbone=Qwen2.5-VL-3B, Training strategy=RARL, Number of images=2-imgs2026.010.84—
RARLBackbone=Qwen2.5-VL-3B, Training strategy=RARL, Number of images=4-imgs2026.010.832—
Qwen2.5-VL-7B + SFTBackbone=Qwen2.5-VL-7B, Training strategy=SFT, Number of images=8-imgs2026.010.823—
RARLBackbone=Qwen2.5-VL-3B, Training strategy=RARL, Number of images=8-imgs2026.010.821—
Qwen2.5-VL-7B + SFTBackbone=Qwen2.5-VL-7B, Training strategy=SFT, Number of images=2-imgs2026.010.815—
Qwen2.5-VL-7B + SFTBackbone=Qwen2.5-VL-7B, Training strategy=SFT, Number of images=4-imgs2026.010.813—
Qwen2.5-VL-3B + SFTBackbone=Qwen2.5-VL-3B, Training strategy=SFT, Number of images=8-imgs2026.010.806—
Qwen2.5-VL-3B + SFTBackbone=Qwen2.5-VL-3B, Training strategy=SFT, Number of images=4-imgs2026.010.801—
Qwen2.5-VL-3B + SFTBackbone=Qwen2.5-VL-3B, Training strategy=SFT, Number of images=2-imgs2026.010.77—
Qwen2.5-VL-7BBackbone=Qwen2.5-VL-7B, Training strategy=Baseline, Number of images=8-imgs2026.010.731—
Qwen2.5-VL-7BBackbone=Qwen2.5-VL-7B, Training strategy=Baseline, Number of images=4-imgs2026.010.723—
Qwen2.5-VL-7BBackbone=Qwen2.5-VL-7B, Training strategy=Baseline, Number of images=2-imgs2026.010.714—
Qwen2.5-VL-3BBackbone=Qwen2.5-VL-3B, Training strategy=Baseline, Number of images=4-imgs2026.010.677—
Qwen2.5-VL-3BBackbone=Qwen2.5-VL-3B, Training strategy=Baseline, Number of images=2-imgs2026.010.656—
Qwen2.5-VL-3BBackbone=Qwen2.5-VL-3B, Training strategy=Baseline, Number of images=8-imgs2026.010.634—
Qwen2.5-VL-3BBackbone=Qwen2.5-VL-3B, Training strategy=Baseline, Number of images=1-img2026.01—0.527
Qwen2.5-VL-3B + SFTBackbone=Qwen2.5-VL-3B, Training strategy=SFT, Number of images=1-img2026.01—0.755
Qwen2.5-VL-7BBackbone=Qwen2.5-VL-7B, Training strategy=Baseline, Number of images=1-img2026.01—0.643
Qwen2.5-VL-7B + SFTBackbone=Qwen2.5-VL-7B, Training strategy=SFT, Number of images=1-img2026.01—0.771
RankingCLIPNumber of images=1-img2026.01—0.747
RARLBackbone=Qwen2.5-VL-3B, Training strategy=RARL, Number of images=1-img2026.01—0.783
RARLBackbone=Qwen2.5-VL-7B, Training strategy=RARL, Number of images=1-img2026.01—0.803
VILA-RNumber of images=1-img2026.01—0.774