init stamo

Author: MingyuLau

StaMo/index.html

@@ -272,7 +272,7 @@ <h2 class="title is-3 has-text-centered">Interpolation</h2>
           <img src="./static/images/interpolation-1.png" alt="Omni-R1 Model Architecture"
             style="width: 100%; max-width: 1200px;" />
           <p class="has-text-grey">
-            <b>Reconstruction, Motion Interpolation and Motion Transfer.</b>
+            <b>Visual reconstruction results from the same episode..</b>The first and last frames are reconstructed from ground-truth images using the StaMo encoder, while the intermediate frames are generated by linearly interpolating between the latent state tokens of the two endpoints. The transitions show that both the robotic arm and the objects move in a continuous and smooth manner.
           </p>
         </div>
       </div>
@@ -289,7 +289,7 @@ <h2 class="title is-3 has-text-centered">Motion Transfer</h2>
           <img src="./static/images/appen-1.png" alt="Omni-R1 Model Architecture"
             style="width: 100%; max-width: 1200px;" />
           <p class="has-text-grey">
-            <b>Reconstruction, Motion Interpolation and Motion Transfer.</b>
+            <b>Transfer linear interpolation experiment with the StaMo encoder.</b>The left and right panels illustrate different task scenarios, where reconstructions are obtained by tokens(3) + tokens(2) – tokens(1), demonstrating the linear interpolation property of latent representations during transfer.
           </p>
         </div>
       </div>

StaMo/static/css/index.css

@@ -115,10 +115,10 @@ body {
 }
 
 .results-carousel .item {
-  margin: 5px;
+  margin: 2px;
   overflow: hidden;
   border: 1px solid #bbb;
-  border-radius: 7px;
+  border-radius: 5px;
   padding: 0;
   font-size: 0;
 }