Update README.md

README.md

@@ -5,24 +5,29 @@ language:
 base_model:
 - lmms-lab/llava-onevision-qwen2-7b-ov
 ---
-<p align="center">
-  <img src="https://github.com/leost123456/LLaVAShield/blob/main/figs/logo.png?raw=true" width="100">
-</p>
-
-<h1 align="center">LLaVAShield: Safeguarding Multimodal Multi-Turn Dialogues in Vision-Language Models</h1>
-
-<p align="center">
-  <a href="https://arxiv.org/abs/2509.25896">
-    <img src="https://img.shields.io/badge/Paper-arXiv-B31B1B?style=flat-square&logo=arxiv&logoColor=white" alt="Paper">
-  </a>
-  <a href="https://huggingface.co/datasets/leost233/MMDS">
-    <img src="https://img.shields.io/badge/Dataset-MMDS-FFD21E?style=flat-square&logo=huggingface&logoColor=black" alt="Dataset">
-  </a>
-  <a href="https://github.com/leost123456/LLaVAShield">
-    <img src="https://img.shields.io/badge/Code-GitHub-black?style=flat-square&logo=github&logoColor=white" alt="Code">
-  </a>
-</p>
+<div align="center">
 
+  <img src="https://github.com/leost123456/LLaVAShield/raw/main/figs/logo.png" width="130" alt="LLaVAShield Logo">
+
+  <h1>LLaVAShield</h1>
+
+  <h3>Safeguarding Multimodal Multi-Turn Dialogues in Vision-Language Models</h3>
+
+  <p>
+    <a href="https://arxiv.org/abs/2509.25896">
+      <img src="https://img.shields.io/badge/Paper-arXiv_2509.25896-B31B1B?logo=arxiv&logoColor=white" alt="arXiv">
+    </a>
+    <a href="https://huggingface.co/datasets/leost233/MMDS">
+      <img src="https://img.shields.io/badge/Dataset-HuggingFace_MMDS-FFD21E?logo=huggingface&logoColor=000000" alt="Dataset">
+    </a>
+    <a href="https://github.com/leost123456/LLaVAShield">
+      <img src="https://img.shields.io/badge/Code-GitHub-181717?logo=github&logoColor=white" alt="GitHub">
+    </a>
+  </p>
+
+</div>
+
+<br>
 ## 📢 News
 
 * **[03/2026]** 🚀 We officially release the **LLaVAShield** model and the **MMDS dataset** to the Hugging Face community!