Update README.md

README.md

@@ -6,24 +6,20 @@ base_model:
 - rhymes-ai/Aria
 ---
 
-<div style="display: flex; align-items: center; gap: 20px;">
-  <img src="assets/performance_spider.pdf" alt="Performance Spider Plot" width="400">
-  <!-- Text Section -->
-  <div>
-    <h2>Key Features of Aria-UI</h2>
-    <div style="font-weight: bold;">✨ Versatile Grounding Instruction Understanding:</div>
-    <div>Aria-UI handles diverse grounding instructions, excelling in interpreting varied formats, ensuring robust adaptability across dynamic scenarios or when paired with diverse planning agents.</div>
-    <div style="font-weight: bold; margin-top: 10px;">📝 Context-aware Grounding:</div>
-    <div>Aria-UI effectively leverages historical input, whether in pure text or text-image-interleaved formats, to improve grounding accuracy.</div>
-    <div style="font-weight: bold; margin-top: 10px;">⚡ Lightweight and Fast:</div>
-    <div>Aria-UI is a mixture-of-expert model with 3.9B activated parameters per token. It efficiently encodes GUI input of variable sizes and aspect ratios, with ultra-resolution support.</div>
-    <div style="font-weight: bold; margin-top: 10px;">🎉 Superior Performances:</div>
-    <div>
-      Aria-UI sets new state-of-the-art results on offline and online agent benchmarks. 
-      <div style="margin-top: 5px;">
-        <span style="font-weight: bold;">🏆 1st place</span> on <span style="font-weight: bold;">AndroidWorld</span> with <span style="font-weight: bold;">44.8%</span> task success rate and 
-        <span style="font-weight: bold;">🥉 3rd place</span> on <span style="font-weight: bold;">OSWorld</span> with <span style="font-weight: bold;">15.2%</span> task success rate (Dec. 2024).
-      </div>
-    </div>
-  </div>
-</div>
+## Key Features of Aria-UI
+
+✨ **Versatile Grounding Instruction Understanding:**  
+Aria-UI handles diverse grounding instructions, excelling in interpreting varied formats, ensuring robust adaptability across dynamic scenarios or when paired with diverse planning agents.
+
+📝 **Context-aware Grounding:**  
+Aria-UI effectively leverages historical input, whether in pure text or text-image-interleaved formats, to improve grounding accuracy.
+
+⚡ **Lightweight and Fast:**  
+Aria-UI is a mixture-of-expert model with 3.9B activated parameters per token. It efficiently encodes GUI input of variable sizes and aspect ratios, with ultra-resolution support.
+
+🎉 **Superior Performances:**  
+Aria-UI sets new state-of-the-art results on offline and online agent benchmarks.  
+🏆 **1st place** on **AndroidWorld** with **44.8%** task success rate and  
+🥉 **3rd place** on **OSWorld** with **15.2%** task success rate (Dec. 2024).
+
+![Performance Spider Plot](assets/performance_spider.pdf)