Update app.py

app.py

@@ -26,6 +26,16 @@ examples = [[data['image'], data['question']] for data in vqa_data]
 
 title = 'VQA with ALBEF'
 description = 'VQA with [ALBEF](https://arxiv.org/abs/2107.07651), adapted from the [torchmultimodal example notebook](https://github.com/facebookresearch/multimodal/blob/main/examples/albef/vqa_with_albef.ipynb).'
+article = '''```bibtex
+@article{li2021align,
+  title={Align before fuse: Vision and language representation learning with momentum distillation},
+  author={Li, Junnan and Selvaraju, Ramprasaath and Gotmare, Akhilesh and Joty, Shafiq and Xiong, Caiming and Hoi, Steven Chu Hong},
+  journal={Advances in neural information processing systems},
+  volume={34},
+  pages={9694--9705},
+  year={2021}
+}
+```'''
 
 def infer(image, question):
   images = [image]
@@ -57,7 +67,8 @@ demo = gr.Interface(
     outputs=gr.Text(label='answer'),
     examples=examples,
     title=title,
-    description=description
+    description=description,
+    article=article
 )
 
 demo.launch()