Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate

Open paper

Benchmark	Model	Rank	Results
visual-question-answering-on-mm-vet	Mini-Gemini (+MoCa)	#91	GPT-4 score: 42.9
visual-question-answering-on-mm-vet	LLaVA-v1.5 (+MoCa)	#159	GPT-4 score: 32.2