diff --git a/index.html b/index.html
index 7daef9e8a1..6658453336 100644
--- a/index.html
+++ b/index.html
@@ -76,27 +76,6 @@ <h2>Research</h2>
             </td>
 	    </tr> 
 
-        <tr onmouseout="ld_stop()" onmouseover="ld_start()">
-          <td style="padding:0px;width:25%;vertical-align:middle">
-            <img src="image/RaTEScore.png" width="320" height="120" style="border-style: none">
-          </td>
-          <td style="padding:10px;width:75%;vertical-align:middle">
-            <a href="https://www.medrxiv.org/content/medrxiv/early/2024/06/24/2024.06.24.24309405.full.pdf">
-              <papertitle>RaTEScore: A Metric for Radiology Report Generation</papertitle>
-            </a>
-            <br>
-            <a>Weike Zhao</a>,
-            <a>Chaoyi Wu</a>,
-            <strong>Xiaoman Zhang</strong>,
-            <a href="https://mediabrain.sjtu.edu.cn/yazhang/">Ya Zhang</a>,
-            <a href="https://mediabrain.sjtu.edu.cn/members/">Yanfeng Wang</a>,
-            <a href="https://weidixie.github.io/">Weidi Xie</a>,
-            <br>
-            <em>Technical Report, 2024.</em><br>
-            In this paper, we introduce a novel, entity-aware metric, termed as Radiological Report (Text) Evaluation (RaTEScore), to assess the quality of medical reports generated by AI models.
-          </td>
-      </tr>
-
       <tr onmouseout="ld_stop()" onmouseover="ld_start()" bgcolor="#ffffd0">
         <td style="padding:0px;width:40%;vertical-align:middle">
           <img src="image/RadGenome_ChestCT.png" width="320" height="180" style="border-style: none">
@@ -118,7 +97,28 @@ <h2>Research</h2>
           In this paper, we introduce RadGenome-Chest CT, a comprehensive, large-scale, region-guided 3D chest CT interpretation dataset based on CT-RATE.  It includes: Organ-level segmentation for 197 categories; 665K multi-granularity grounded reports; 1.3M grounded VQA pairs.
         </td>
     </tr> 
-    
+
+    <tr onmouseout="ld_stop()" onmouseover="ld_start()">
+      <td style="padding:0px;width:25%;vertical-align:middle">
+        <img src="image/RaTEScore.png" width="320" height="120" style="border-style: none">
+      </td>
+      <td style="padding:10px;width:75%;vertical-align:middle">
+        <a href="https://www.medrxiv.org/content/medrxiv/early/2024/06/24/2024.06.24.24309405.full.pdf">
+          <papertitle>RaTEScore: A Metric for Radiology Report Generation</papertitle>
+        </a>
+        <br>
+        <a>Weike Zhao</a>,
+        <a>Chaoyi Wu</a>,
+        <strong>Xiaoman Zhang</strong>,
+        <a href="https://mediabrain.sjtu.edu.cn/yazhang/">Ya Zhang</a>,
+        <a href="https://mediabrain.sjtu.edu.cn/members/">Yanfeng Wang</a>,
+        <a href="https://weidixie.github.io/">Weidi Xie</a>,
+        <br>
+        <em>Technical Report, 2024.</em><br>
+        In this paper, we introduce a novel, entity-aware metric, termed as Radiological Report (Text) Evaluation (RaTEScore), to assess the quality of medical reports generated by AI models. We developed a comprehensive medical NER dataset, RaTE-NER, and trained an NER model specifically for crucial medical entities.
+        purpose
+      </td>
+  </tr>
         <tr onmouseout="ld_stop()" onmouseover="ld_start()">
             <td style="padding:0px;width:25%;vertical-align:middle">
               <img src="image/KEP.png" width="320" height="120" style="border-style: none">