update README

README.md

@@ -5,4 +5,11 @@ metrics:
 base_model:
 - xtuner/llava-phi-3-mini-hf
 pipeline_tag: image-text-to-text
----
+---
+
+@article{zhong2024compositional,
+  title={Compositional Image Retrieval via Instruction-Aware Contrastive Learning},
+  author={Zhong, Wenliang and An, Weizhi and Jiang, Feng and Ma, Hehuan and Guo, Yuzhi and Huang, Junzhou},
+  journal={arXiv preprint arXiv:2412.05756},
+  year={2024}
+}