<ul><li>AstroLLaVA is a vision language model for astronomy that enables interaction with astronomical imagery through natural dialogue.</li><li>It is fine-tuned on a diverse dataset of approximately 30k images with captions and question-answer pairs.</li><li>AstroLLaVA is capable of answering open-ended questions about astronomical concepts depicted visually.</li><li>The model weights, code, and training set of AstroLLaVA are released for further open-source work in the field of astronomy.</li></ul>

AstroLLaVA: towards the unification of astronomical data and natural language

Discover more