Back

NeuroVLM: A generative vision-language framework for human neuroimaging

Hammonds, R. P.; Aguirre-Chavez, J.; Omoma-Edosa, B.; Voytek, B. P.

2026-02-09 neuroscience
10.64898/2026.02.06.704508 bioRxiv
Show abstract

Neuroimaging research has produced tens-of-thousands of articles that pair natural language and activation coordinate tables. Recent advances in vision-language models (VLMs) have provided methods to model text and images simultaneously. In this work, we present NeuroVLM, a model architecture for learning from 30,000 human neuroimage-text pairs. The architecture supports contrastive and generative objectives. The contrastive model ranks similarity between neuroimages and text. The generative models include text-to-neuroimage and neuroimage-to-text. These models are evaluated on network images from a variety of atlases, statistical maps from diverse publications, and images created from coordinate tables. These models are capable of generating atlases or maps given a text corpus, generating text interpretations of neuroimages, labeling networks, finding publications most related to a neuroimage query, or finding neuroimages most related to a text query.

Matching journals

The top 7 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.