Doctor Sun: A Bilingual Multimodal Large Language Model for Biomedical AI
This work addresses the problem of limited medical training data and ineffective text-image integration in biomedical AI for researchers and practitioners, representing an incremental advancement by combining pre-trained components with novel training strategies.
The paper tackles the challenge of existing multimodal biomedical AI models struggling with intricate medical concepts and text-image relationships by introducing Doctor Sun, a bilingual multimodal large language model specialized in medicine, which achieves improved performance through two-stage training on diverse datasets and the release of a new bilingual medical multimodal dataset.
Large multimodal models (LMMs) have demonstrated significant potential in providing innovative solutions for various biomedical tasks, including pathology analysis, radiology report generation, and biomedical assistance. However, the existing multimodal biomedical AI is typically based on foundation LLMs, thus hindering the understanding of intricate medical concepts with limited medical training data. Moreover, recent LLaVA-induced medical LMMs struggle to effectively capture the intricate relationship between the texts and the images. Therefore, we introduce Doctor Sun, a large multimodal generative model specialized in medicine, developed to encode, integrate, and interpret diverse biomedical data modalities such as text and images. In particular, Doctor Sun integrates a pre-trained vision encoder with a medical LLM and conducts two-stage training on various medical datasets, focusing on feature alignment and instruction tuning. Moreover, we release SunMed-VL, a wide-range bilingual medical multimodal dataset, along with all associated models, code, and resources, to freely support the advancement of biomedical multimodal research.