Lumen: Parameter-Efficient Alignment of Pretrained Vision and Language Encoders for Zero-Shot Computational Pathology

Kiarash Tajbakhsh, Abdelrahman Faqieh, Michael Jopiti +9

Pathology vision-language models are commonly built by pretraining or fine-tuning large encoders on paired image-caption data. We asked whether a pathology vision-language model ca…