Update README.md

README.md

@@ -16,6 +16,12 @@ base_model:
 </div>
 </div>
 
+<!-- [![Paper](https://img.shields.io/badge/ArXiv-Paper-brown)](https://www.arxiv.org/abs/2510.15110)
+[![Code](https://img.shields.io/badge/GitHub-Link-blue)](https://github.com/NVlabs/DLER)
+[![Model](https://img.shields.io/badge/HuggingFace-Model-yellow)](https://huggingface.co/nvidia/omnivinci)
+[![Website](https://img.shields.io/badge/Web-Page-orange)](https://nvlabs.github.io/OmniVinci)
+
+ -->
 ![Comparison between Llama-3.1-Nemotron-Nano-8B-v1 and DLER-Llama-Nemotron-8B-Merge](./asset/latency_8b.png)
 
 ### Description: