update project page

Author: MTDoven

index.html

@@ -61,7 +61,7 @@ <h1 class="title is-1 publication-title">Recurrent Diffusion for Large-Scale Par
           <div class="is-size-5 publication-authors">
             <span class="author-block">
               <a href="https://www.nus.edu.sg/" target="_blank">National University of Singapore</a>  </span>
-            <span class="eql-cntrb"><small><br>Kai Wang and Dongwen Tang contributed equally to this work.</small>  </span>
+            <span class="eql-cntrb"><small><br>Kai and Dongwen contributed equally to this work.</small>  </span>
           </div>
           <div class="column has-text-centered">
             <div class="publication-links">
@@ -103,6 +103,18 @@ <h1 class="title is-1 publication-title">Recurrent Diffusion for Large-Scale Par
               </span>
             </div>
           </div>
+          <div class="has-text-centered mt-6">
+            <h2 class="title is-4">Generating models with prompts in minutes!</h2>
+          </div>
+
+          <div class="container is-max-desktop mt-6">
+            <video class="video" autoplay controls muted loop playsinline style="width: 100%; border-radius: 8px; box-shadow: 0 4px 10px rgba(0, 0, 0, 0.2);">
+              <source src="videos/demo.mp4" type="video/mp4">
+              Your browser does not support the video tag.
+            </video>
+          </div>
+
+
         </div>
       </div>
     </div>
@@ -373,6 +385,27 @@ <h2 class="title is-3">Text-Driven Parameter Generation</h2>
 
 
 
+
+<section class="section hero is-light">
+  <div class="container is-max-desktop">
+    <div class="columns is-centered has-text-centered">
+      <div class="column is-four-fifths">
+        <h2 class="title is-3">Conclusion</h2>
+        <div class="content has-text-justified">
+          <p>
+            Our approach demonstrates promising results in large-scale parameter generation across various vision and language
+tasks. However, we acknowledge that achieving true ‘AI creating AI’ remains a distant goal. Firstly, while our
+method shows potential in generating models for unseen tasks, it currently faces limitations in generating parameters for novel model architectures. Secondly, our approach
+is constrained by modeling parameter relationships within a single task, potentially limiting its practical applicability.
+More importantly, future work should focus on simultaneously modeling parameter relationships across diverse architectures and tasks. Such an approach could yield a more
+powerful and versatile parameter generator, potentially advancing us closer to the ‘AI creating AI’ era. We hope our approach will inspire future research in this field.
+          </p>
+        </div>
+      </div>
+    </div>
+  </div>
+</section>
+
 <!--BibTex citation -->
 <section class="section" id="BibTeX">
 
@@ -382,8 +415,10 @@ <h2 class="title">Acknowledgments</h2>
       <a href="https://jerryliang24.github.io/" target="_blank">Zhiyuan Liang</a>,
       <a href="https://liuzhuang13.github.io/" target="_blank">Zhuang Liu</a>,
       <a href="https://fangggf.github.io/" target="_blank">Gongfan Fang</a>,
+      <a href="https://oahzxl.github.io/" target="_blank">Xuanlei Zhao</a>,
       <a href="https://zhengzangw.github.io/" target="_blank">Zangwei Zheng</a>,
-      <a href="https://tianlong-chen.github.io/" target="_blank">Tianlong Chen</a>,
+      <a href="https://henryqin1997.github.io/ziheng_qin/" target="_blank">Ziheng Qin</a>,
+      <a href="https://tianlong-chen.github.io/" target="_blank">Tianlong Chen</a>, and
       <a href="https://www.ece.utexas.edu/people/faculty/atlas-wang" target="_blank">Zhangyang Wang</a>,
       for valuable discussions and feedbacks.
       This research is supported by the National Research Foundation,
@@ -392,9 +427,9 @@ <h2 class="title">Acknowledgments</h2>
 
   <div class="container is-max-desktop content">
     <h2 class="title">BibTeX</h2>
-    <pre><code>@misc{wang2024RPG,
+    <pre><code>@misc{wang2025recurrent,
       title={Recurrent Diffusion for Large-Scale Parameter Generation},
-      author={Kai Wang and Dongwen Tang and Wangbo Zhao and Yang You},
+      author={Wang, Kai and Tang, Dongwen and Zhao, Wangbo and You, Yang},
       year={2025},
 }</code></pre>
   </div>