Update README.md

README.md

@@ -5,10 +5,9 @@ language:
 base_model:
 - lmms-lab/llava-onevision-qwen2-7b-ov
 ---
+# ![https://github.com/leost123456/LLaVAShield/blob/main/figs/logo.png?raw=true] LLaVAShield: Safeguarding Multimodal Multi-Turn Dialogues in Vision-Language Models
 
-# 🛡️ LLaVAShield: Safeguarding Multimodal Multi-Turn Dialogues in Vision-Language Models
-
-[![Paper](https://img.shields.io/badge/Paper-arXiv-red)](https://arxiv.org/abs/2509.25896) [![Dataset](https://img.shields.io/badge/Dataset-MMDS-blue)](https://huggingface.co/datasets/leost233/MMDS) [![Code](https://img.shields.io/badge/Code-GitHub-black)](https://github.com/leost123456/LLaVAShield)
+[![Paper](https://img.shields.io/badge/Paper-arXiv-B31B1B?style=flat-square&logo=arxiv&logoColor=white)](https://arxiv.org/abs/2509.25896) [![Dataset](https://img.shields.io/badge/Dataset-MMDS-FFD21E?style=flat-square&logo=huggingface&logoColor=black)](https://huggingface.co/datasets/leost233/MMDS) [![Code](https://img.shields.io/badge/Code-GitHub-black?style=flat-square&logo=github&logoColor=white)](https://github.com/leost123456/LLaVAShield)
 
 ## 📢 News
 
@@ -20,9 +19,6 @@ As Vision-Language Models (VLMs) move into interactive, multi-turn use, safety c
 
 To address these limitations, we propose **LLaVAShield**, a content moderation model specifically designed for multimodal multi-turn dialogues. It jointly leverages dialogue context with cross-modal signals to assess the safety of both user inputs and assistant responses under specified policy dimensions. LLaVAShield is initialized from [LLaVA-OV-7B](https://huggingface.co/lmms-lab/llava-onevision-qwen2-7b-ov) and fine-tuned on the [MMDS](https://huggingface.co/datasets/leost233/MMDS) training set. The model supports a context length of **16K**.
 
-* 💻 **Code Repository:** [https://github.com/leost123456/LLaVAShield](https://github.com/leost123456/LLaVAShield)
-* 📖 **Paper:** [https://arxiv.org/abs/2509.25896](https://arxiv.org/abs/2509.25896)
-
 ---
 
 ## 🚀 Quick Start (Usage)