update the link about DC-AE;

index.html

@@ -567,7 +567,8 @@ <h2>About Sana</h2>
           <h2>Several Core Design Details for Efficiency</h2>
           <p>
               &nbsp;&nbsp;&nbsp;&nbsp;&bull;&nbsp;&nbsp;  <strong style="font-size: 18px;">Deep Compression Autoencoder: </strong>
-              We introduce a new Autoencoder (AE) that aggressively increases the scaling factor to 32.
+              We introduce a new
+              <a rel="license" href="https://hanlab.mit.edu/projects/dc-ae" target="_blank" style="color: darkred; font-weight: bold">Deep Compressinon Autoencoder (DC-AE)</a> that aggressively increases the scaling factor to 32.
               Compared with AE-F8, our AE-F32 outputs 16× fewer latent tokens, which is crucial for efficient training
               and generating ultra-high-resolution images, such as 4K resolution.<br>
           </p>