Article

To text and back again, a vision-language model's tale
A forum piece on vision-language models and the round trip between text and visual representations.
Hammonds, Ryan, Kent, James, Omoma-Edosa, Borngreat, Aguirre-Chavez, Jerjes, Voytek, Bradley
PDF DOI
NeuroVLM: A generative vision-language framework for human neuroimaging
A generative vision-language framework for human neuroimaging, built to support scientific discovery from neuroscience literature and brain imaging data.
Hammonds, Ryan, Aguirre-Chavez, Jerjes, Omoma-Edosa, Borngreat, Patel, Aarya, Voytek, Bradley
PDF DOI