Update README.md

README.md

@@ -24,7 +24,7 @@ language:
 # WeMM-Embedding-9B
 
 [![Hugging Face](https://img.shields.io/badge/🤗-Hugging%20Face-yellow)](https://huggingface.co/collections/tencent/wemm-embedding)
-[![Technical Report](https://img.shields.io/badge/📄-Technical%20Report-red)](https://github.com/Tencent/WeMM-Embedding/blob/main/assets/WeMM_Embedding_tech_report.pdf)
+[![Technical Report](https://img.shields.io/badge/📄-Technical%20Report-red)](https://arxiv.org/abs/2608.24053)
 [![GitHub](https://img.shields.io/badge/GitHub-WeMM--Embedding-black?logo=github)](https://github.com/Tencent/WeMM-Embedding)
 
 WeMM-Embedding-9B is a universal multimodal embedding model built on Qwen3.5. It accepts text, images, videos, visual documents, and interleaved multimodal inputs, and returns a 4,096-dimensional L2-normalized embedding. Audio input is not supported.
@@ -208,13 +208,16 @@ Results on all 190 tasks from Table 2 of the [technical report](https://github.c
 Text results use NDCG@5; agent, MCMR, and audio results use Hit@1.
 
 ## Citation
-
+If you find this repository useful, please consider giving a star ⭐ and citation
 ```bibtex
-@techreport{wemm_embedding_2026,
-  title       = {WeMM-Embedding: WeChat Multi-Modal Embedding Technical Report},
-  author      = {{WeChat Vision}},
-  institution = {Tencent Inc.},
-  year        = {2026}
+@article{wemm-embedding,
+      title={WeMM-Embedding: WeChat Multi-Modal Embedding Technical Report}, 
+      author={Junjie Zhou and Ke Mei and Lei Li and Tianyi Wang and Fengyun Rao and Jing Lyu},
+      year={2026},
+      eprint={2608.24053},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV},
+      url={https://arxiv.org/abs/2608.24053}, 
 }
 ```