Update app.py

app.py

@@ -21,7 +21,7 @@ through `human language vocabulary`, all made possible by using multimodal large
 
 🤝 This demo is still under construction. Your comments or suggestions are welcome!
 
-⚡ For faster inference without waiting in queue, you may duplicate the space and use the GPU setting:
+⚡ For faster inference without waiting in the queue, you may duplicate the space and use the GPU setting:
 <a href="https://huggingface.co/spaces/yuhangzang/ContextDet-Demo?duplicate=true">
 <img style="margin-top: 0em; margin-bottom: 0em" src="https://bit.ly/3gLdBN6" alt="Duplicate Space"></a>
 <p/>
@@ -34,7 +34,11 @@ We would be grateful if you consider star our <a href="https://github.com/yuhang
 📝 **Citation**
 We would be grateful if you consider citing our work if you find it useful:
 ```bibtex
-@article{
+@article{zang2023contextual,
+  author = {Zang, Yuhang and Li, Wei and Han, Jun, and Zhou, Kaiyang and Loy, Chen Change},
+  title = {Contextual Object Detection with Multimodal Large Language Models},
+  journal = {arXiv preprint arXiv:2305.18279},
+  year = {2023}
 }
 ```