LION: Empowering Multimodal Large Language Model with Dual-Level Visual Knowledge

Open paper

Benchmark	Model	Rank	Results
visual-question-answering-on-gqa-test-dev	LION-12B	#10	Accuracy: 51.56
visual-question-answering-vqa-on-mmbench-en	LION-12B	#30	Accuracy: 73.4