Introduction
We present SlideChat, the first open-source vision-language assistant capable of understanding gigapixel whole-slide images. We have released model weight.
Citation
If you find this project useful in your research, please consider citing:
@article{chen2024slidechat,
title={SlideChat: A Large Vision-Language Assistant for Whole-Slide Pathology Image Understanding},
author={Chen, Ying and Wang, Guoan and Ji, Yuanfeng and Li, Yanjun and Ye, Jin and Li, Tianbin and and Ming, Hu and Yu, Rongshan and Qiao, Yu and He, Junjun},
journal={arXiv preprint arXiv:2410.11761},
year={2024}
}