Update README.md

README.md

@@ -275,11 +275,10 @@ Before using the MegaBeam-Mistral-7B-512k model, it is important to perform your
 If you find our work helpful, feel free to give us a cite.
 
 ```
-@misc{megabeam-mistral-7B-512k-2024,
-author = { {Chen Wu and Yin Song and Eden Duthie} },
-title = { {aws-prototyping/MegaBeam-Mistral-7B-512k} },
-year = 2024,
-url = { https://huggingface.co/aws-prototyping/MegaBeam-Mistral-7B-512k },
-publisher = { Hugging Face }
+@article{wu2025scaling,
+  title={Scaling Context, Not Parameters: Training a Compact 7B Language Model for Efficient Long-Context Processing},
+  author={Wu, Chen and Song, Yin},
+  journal={arXiv preprint arXiv:2505.08651},
+  year={2025}
 }
 ```