List your company

Image Captioning on MSCOCO 500-sample subset (val)

175.3Caption LengthQwen2.5-VL-7B (Base)
68.28496.067123.85151.633Jan 30, 2026

Evaluation results

MethodLinks
Qwen2.5-VL-7B (Base)Backbone=Qwen2.5-VL-7B, Method=Greedy Decoding2026.01175.335.69.974.48.528.7
Self-Val. (w/ BoN. N=10)Backbone=Qwen2.5-VL-7B, Strategy=Best-of-N Selection, N=102026.01172.816.64.172.78.949.13
Self-Val. (w/ FtA. N=3)Backbone=Qwen2.5-VL-7B, Strategy=Filter-then-Aggregate, N=32026.01156.98.43.170.68.578.81
Self-Val. (w/ FtA. N=3)Backbone=LLaVA-1.5-13B, Strategy=Filter-then-Aggregate, N=32026.01121.721.25.176.77.968.32
Self-Val. (w/ FtA. N=3)Backbone=LLaVA-v1.5-7B, Strategy=Filter-then-Aggregate, N=32026.01115.222.85.376.17.88.3
mPLUG-Owl2-7B (Base)Backbone=mPLUG-Owl2-7B, Method=Greedy Decoding2026.01105.860.818.971.67.287.66
Self-Val. (w/ BoN. N=10)Backbone=mPLUG-Owl2-7B, Strategy=Best-of-N Selection, N=102026.01101.234.29.474.57.387.96
LLaVA-1.5-13B (Base)Backbone=LLaVA-1.5-13B, Method=Greedy Decoding2026.0110145.813777.657.29
LLaVA-v1.5-7B (Base)Backbone=LLaVA-v1.5-7B, Method=Greedy Decoding2026.01100.65015.475.17.57.89
VCDBackbone=LLaVA-v1.5-7B2026.01100.448.614.975.27.548.13
NulluBackbone=LLaVA-v1.5-7B2026.0199.949.413.576.67.718.18
DeCoBackbone=LLaVA-v1.5-7B2026.019942.412.973.36.967.66
Self-Val. (w/ FtA. N=3)Backbone=mPLUG-Owl2-7B, Strategy=Filter-then-Aggregate, N=32026.0198.413.24.270.57.227.76
Self-Val. (w/ BoN. N=10)Backbone=LLaVA-v1.5-7B, Strategy=Best-of-N Selection, N=102026.0198.228.87.376.77.758.26
Self-Val. (w/ BoN. N=10)Backbone=LLaVA-1.5-13B, Strategy=Best-of-N Selection, N=102026.0197.2246.677.27.728.2
CGDBackbone=LLaVA-v1.5-7B2026.0189.637.211.478.27.768.23
LessBackbone=LLaVA-v1.5-7B2026.017938.81277.67.648.07
HALCBackbone=LLaVA-v1.5-7B2026.0172.432.210.9696.376.51