Omni-R1: Towards the Unified Generative Paradigm for Multimodal Reasoning

Open paper

Benchmark	Model	Rank	Results
visual-question-answering-vqa-on-blink	Omni-R1-M	#50	Accuracy: 35.61
visual-question-answering-on-mm-vet	Omni-R1-Zero-S	#197	GPT-4 score: 22.02