Shenzhen Research Institute of Big Data

Open medical multimodal LLMs (7B and 34B) for visual question answering over radiology, pathology, and endoscopy images, trained on PubMedVision.

Medical vision-language pretraining unifying fusion-encoder and dual-encoder designs, handling image-only, text-only, and paired inputs in one model.

Medical vision-language pretraining framework that injects structured medical knowledge into radiology image-text learning for VQA and retrieval.

Self-supervised medical vision-and-language pretraining via multi-modal masked autoencoders that reconstruct masked image patches and text tokens.