List your company

Image Captioning on MC-LLaVA

83.6Caption Recall (Single)GPT4o+Prompt
2.27223.38644.565.614Nov 18, 2024

Evaluation results

MethodLinks
GPT4o+PromptT (Tokens)=10^12024.1183.681.683
MC-LLaVAT (Tokens)=10^1, Auxiliary Loss=true2024.1177.278.477.5
MC-LLaVAT (Tokens)=10^1, Auxiliary Loss=false2024.1174.176.375.4
PeKitT (Tokens)=02024.1172.974.373.3
MyVLMT (Tokens)=12024.1171.4—71.4
RAP-MLLMT (Tokens)=10^22024.1171.174.872.3
Yo'LLaVA-ST (Tokens)=10^12024.1170.1—70.1
Yo'LLaVA-MT (Tokens)=10^12024.1162.261.161.9
LLaVA+PromptT (Tokens)=10^12024.1110.81612.3
LLaVAT (Tokens)=02024.119.658.2
LLaVA+PromptT (Tokens)=10^22024.115.412.27.5