LLaVA-o1: Let Vision Language Models Reason Step-by-Step

The researchers introduce LLaVA-o1, a vision language model designed to perform structured reasoning by breaking down problem-solving into four distinct stages: summary, caption, reasoning, and conclusion. They compiled a new dataset, LLaVA-o1-100k, and proposed a stage-level beam search method to improve model performance during inference. Experimental results demonstrate that LLaVA-o1 outperforms existing open-source and even some closed-source models on multimodal reasoning benchmarks, emphasizing the effectiveness of its structured reasoning approach.