Update info in pp

Update info in pp

Author: MTDoven

index.html

@@ -55,12 +55,20 @@ <h1 class="title is-1 publication-title">Scaling Up Parameter Generation: A Recu
               <a href="https://scholar.google.com/citations?user=9lKm_5IAAAAJ" target="_blank">Dongwen Tang</a>,  </span>
             <span class="author-block">
               <a href="https://wangbo-zhao.github.io/" target="_blank">Wangbo Zhao</a>,  </span>
+            <span class="author-block">
+              <a href="https://kschuerholt.github.io/" target="_blank">Konstantin Schürholt</a>,  </span>
+            <span class="author-block">
+              <a href="https://www.vita-group.space/" target="_blank">Zhangyang Wang</a>,  </span>
             <span class="author-block">
               <a href="https://www.comp.nus.edu.sg/~youy/" target="_blank">Yang You</a>  </span>
           </div>
           <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="author-block">
+              <a href="https://www.unisg.ch/" target="_blank">University of St.Gallen</a>  </span>
+            <span class="author-block">
+              <a href="https://www.utexas.edu/" target="_blank">University of Texas at Austin</a>  </span>
             <span class="eql-cntrb"><small><br>Kai and Dongwen contributed equally to this work.</small>  </span>
           </div>
           <div class="column has-text-centered">
@@ -137,12 +145,12 @@ <h2 class="title is-3">Abstract</h2>
             a novel framework that generates full neural network parameters—up to <b>hundreds of millions</b>—on a <b>single GPU</b>. 
             Our approach first partitions a network’s parameters into non-overlapping ‘tokens’, each corresponding to a distinct portion of the model. 
             A recurrent mechanism then learns the inter-token relationships, 
-            producing ‘prototypes’ which serve as conditions for a diffusion process that ultimately synthesizes the full parameters. 
+            producing ‘prototypes’ which serve as conditions for a diffusion process that ultimately synthesizes the parameters. 
             Across a spectrum of architectures and tasks—including ResNets, ConvNeXts and ViTs on ImageNet-1K and COCO, 
             and even LoRA-based LLMs—RPG achieves performance on par with fully trained networks while avoiding excessive memory overhead. 
             Notably, it generalizes beyond its training set to generate valid parameters for previously unseen tasks, 
-            highlighting its flexibility in dynamic and open-ended scenarios. By overcoming the longstanding memory and scalability barriers, 
-            RPG serves as a critical advance in ‘AI generating AI’, potentially enabling efficient weight generation at scales previously deemed infeasible.
+            highlighting its flexibility in open-ended scenarios. By overcoming the longstanding memory and scalability barriers, 
+            RPG serves as a critical advance in ‘<b>AI generating AI</b>’, potentially enabling efficient weight generation at scales previously deemed infeasible.
           </p>
         </div>
       </div>