List your company

Long-form Image Captioning on CapMAS IIW-400

46.78ALOHaILVAD
43.639244.454645.2746.0854May 20, 2026

Evaluation results

MethodLinks
ILVADBackbone=LLaVA-1.5-7B, Evaluator=GPT-4o2026.0546.7865.4534.851.949.73
VHRBackbone=LLaVA-1.5-7B, Evaluator=GPT-4o2026.0544.0562.4925.854.846.79
GreedyBackbone=LLaVA-1.5-7B, Evaluator=GPT-4o2026.0543.7662.7833.350.747.64