guanghan's personal webpage

Author: s-sahoo

index.html

@@ -65,7 +65,7 @@ <h1 class="title is-1 publication-title">The Diffusion Duality</h1>
                   <span class="author-block">
                     <a href="https://skylion007.github.io" target="_blank">Aaron Gokaslan<sup>1</sup></a>,</span>
                       <span class="author-block">
-                        <a href="https://tech.cornell.edu/people/guanghan-wang/" target="_blank">Guanghan Wang<sup>1</sup></a>,</span>
+                        <a href="https://www.guanghanwang.com" target="_blank">Guanghan Wang<sup>1</sup></a>,</span>
                         <span class="author-block">
                           <a href="https://justinchiu.netlify.app" target="_blank">Justin Chiu<sup>3</sup></a>,</span>
                             <span class="author-block">
@@ -201,26 +201,24 @@ <h4 class="subtitle has-text-centered">
 <!-- Paper abstract -->
 <section class="section hero is-light">
   <div class="container is-max-desktop">
-    <div class="columns is-centered has-text-centered">
+    <div class="columns is-centered">
       <div class="column is-four-fifths">
-        <h2 class="title is-3">Our Contributions</h2>
-        <div class="content has-text-justified">
-            <ol>
-              <li>
-                We show that <b>uniform-state discrete diffusion emerges from Gaussian diffusion</b>,
-                enabling the transfer of techniques from continuous to discrete domains.
-              </li>
-              <li>
-                Building on this insight, we propose the DUO framework,
-                which improves training through a low-variance curriculum.
-              </li>
-              <li>
-                We further introduce Discrete Consistency Distillation, adapting consistency
-                distillation to the discrete setting and accelerating DUO sampling
-                by <b>two orders</b> of magnitude.
-              </li>
-            </ol>
-        </div>
+        <h2 class="title is-3">Key Innovations</h2>
+        <ol>
+          <li>
+            We show that <b>uniform-state discrete diffusion emerges from Gaussian diffusion</b>,
+            enabling the transfer of techniques from continuous to discrete domains.
+          </li>
+          <li>
+            Building on this insight, we propose the DUO framework,
+            which improves training through a low-variance curriculum.
+          </li>
+          <li>
+            We further introduce Discrete Consistency Distillation, adapting consistency
+            distillation to the discrete setting and accelerating DUO sampling
+            by <b>two orders</b> of magnitude.
+          </li>
+        </ol>
       </div>
     </div>
   </div>