BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature

By Alejandro Lozano, Min-Woo Sun, James Burgess, Liangyu Chen, Jeffrey J. Nirschl, Jeffrey Gu, Ivan Lopez, J. Aklilu, Anita Rau, Austin Wolfgang Katzer and 6 more. 2025

Subfields: Multimodal Learning, Medical & Health AI

Citations in the corpus

• CNS-Obsidian: A Neurosurgical Vision-Language Model Built From Scientific Publications. (2025, unknown): “19 Some works have explored converting figure captions to simple visual question-answering datasets using GPT-4o.”