Add files via upload

index.html

@@ -294,7 +294,7 @@ <h2 class="title is-3">Overview</h2>
           SEEACT leverages an LMM like GPT-4V to visually perceive websites and generate plans in textual forms (Action Generation). The textual plans are then grounded onto the HTML elements and operations to act on the website (Action Grounding).
           </p>
         <div class="content has-text-centered">
-          <img src="static/images/teaser_figure.png" alt="algebraic reasoning" class="center" style="width: 50%; height: auto;">
+          <img src="static/images/teaser_figure.png" alt="algebraic reasoning" class="center" style="width: 90%; height: auto;">
         </div>
         </div>
 
@@ -305,7 +305,7 @@ <h2 class="title is-3">Action Grounding</h2>
             In this action step, the model needs to click the "Find Your Truck" button to perform a search.
           </p>
         <div class="content has-text-centered">
-          <img src="static/images/action_grounding.png" alt="algebraic reasoning" class="center" style="width: 50%; height: auto;">
+          <img src="static/images/action_grounding.png" alt="algebraic reasoning" class="center" style="width: 90%; height: auto;">
         </div>
           <p>
             We explore three methods for action grounding.