init

Author: zichuanlin

images/main_result.png

@@ -429,9 +429,17 @@ <h2 class="title is-3"><img id="painting_icon" width="3%" src="https://cdn-icons
 <div class="container is-max-desktop">
   <div class="columns is-centered">
     <div class="column is-full-width">
-      <h2 class="title is-4"><img id="painting_icon" width="4%" src="https://cdn-icons-png.flaticon.com/512/1698/1698535.png"> <span style="font-size: 100%;">Visual Search:</span> Mini-o3 achieves the state-of-the-art results among various benchmarks </h2>
+      <h2 class="title is-4"><img id="painting_icon" width="4%" src="https://cdn-icons-png.flaticon.com/512/1698/1698535.png"> AdaptVision achieves a sota-level accuracy-efficiency trade-off across multiple VQA benchmarks </h2>
       <div>
-<style>
+
+        <div class="columns is-centered">
+          <centering>
+            <div style="text-align: center;">
+              <img id="result" width="100%" src="images/main_result.png">
+            </div>
+          </centering>           
+        </div>
+<!-- <style>
   table.perf-table {
     border-collapse: collapse;
     width: 95%;
@@ -472,12 +480,14 @@ <h2 class="title is-4"><img id="painting_icon" width="4%" src="https://cdn-icons
     color: #444;
     margin-top: 6px;
   }
-</style>
+</style> -->
 
-<table class="perf-table">
+<!-- <table class="perf-table">
   <caption>
-    Performance comparisons among existing models and ours on visual search tasks. 
-    The sizes of all listed models are 7B. We report Avg@32 to reduce variance caused by randomness.
+    Performance comparison with previous efficient VLM methods. 
+    Vanilla denotes the Qwen2.5-VL-7B-Instruct model. Down-Sample uses a 1/4-resolution image as input to the Vanilla model. 
+    ``\#Token'' indicates the visual token consumption ratio relative to the vanilla model across all benchmarks. 
+    ``Avg.'' denotes the average performance relative to the vanilla model on all benchmarks.
   </caption>
   <thead>
     <tr>
@@ -589,7 +599,7 @@ <h2 class="title is-4"><img id="painting_icon" width="4%" src="https://cdn-icons
       <td>65.5</td>
     </tr>
   </tbody>
-</table>
+</table> -->
 
 <div class="table-notes">
   <div>† The models only report the metric of Avg@1 and the model weights are not available.</div>