List your company

Image-to-Text Retrieval on Flickr8k-Rephrased

89.4Recall@5CLIMP (VMamba)
74.42478.31282.286.088Jan 11, 2026

Evaluation results

MethodLinks
CLIMP (VMamba)Vision Tower=VMamba, Text Tower=Mamba-12026.0189.4
CLIMP (VMamba)Vision Tower=VMamba, Text Tower=Mamba-22026.0188.2
RoPE-ViTVision Tower=RoPE-ViT, Text Tower=LLaMA2026.0185.8
ViTVision Tower=ViT, Text Tower=LLaMA2026.0182
NaFlexVision Tower=NaFlex, Text Tower=LLaMA2026.0180.2
FlexViTVision Tower=FlexViT, Text Tower=LLaMA2026.0175