Update README.md

README.md

@@ -34,6 +34,14 @@ The primary intended users of the model are researchers in computer vision, natu
 Please kindly cite our paper if you find our resources useful:
 
 ```
+@misc{li2024text,
+      title={Text as Images: Can Multimodal Large Language Models Follow Printed Instructions in Pixels?}, 
+      author={Xiujun Li and Yujie Lu and Zhe Gan and Jianfeng Gao and William Yang Wang and Yejin Choi},
+      year={2024},
+      eprint={2311.17647},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}
 @misc{lu2023vim,
       title={VIM: Probing Multimodal Large Language Models for Visual Embedded Instruction Following}, 
       author={Yujie Lu and Xiujun Li and William Yang Wang and Yejin Choi},