fixed grammatical bugsgit add .

index.html

@@ -178,7 +178,7 @@ <h1 class="title is-1 publication-title">GraPE: A Generate-Plan-Edit Framework f
   <div class="hero-body">
     <div class="container is-centered">
       <h2 class="subtitle has-text-centered">
-        GraPE is a unifying and generic framework for improving semantic alignemt of T2I models<br> by post-hoc alignment of generated images via iterating editing.
+        GraPE is an unifying and generic framework for improving semantic alignemt of T2I models<br> by post-hoc alignment of generated images via iterating editing.
       <img src="assets/Teaser_updated_with_new.png" alt="teaser" style="display: block; margin-left: auto; margin-right: auto; margin-top: 50px;margin-bottom: 5px;width: 50%; height: auto;">      <h2 class="subtitle has-text-centered">
         &nbsp;
     </div>
@@ -226,23 +226,21 @@ <h2 class="title is-3 has-text-centered">GraPE Framework</h2>
             textual instruction. In the task of T2I synthesis, given an
             instruction <strong>T</strong>, our goal is to be able to generate an image
             <strong>I<sub>o</sub></strong> which satisfies various requirements expressed via the
-            instruction <strong>T</strong>. While most existing techniques take the ap-
-            proach of directly generating <strong>I<sub>o</sub></strong> via <strong>T</strong> , they often result in
+            instruction <strong>T</strong>. While most existing techniques take the approach of directly generating <strong>I<sub>o</sub></strong> via <strong>T</strong> , they often result in
             various kinds of inaccuracies, due to the complexity of the
             instruction. We are motivated by the observation that the
             task of T2I synthesis can be broken down into simpler steps
             of first generation, followed by identification of errors, and
             a sequence of corrective edits, each of which is simple and
-            object specific in nature. Accordingly, we propose the fol-
-            lowing generation pipeline
+            object specific in nature. Accordingly, we propose the following generation pipeline
           </p>
         </div>
         <div class="content has-text-centered">
           <div style="display: flex; justify-content: space-between;">
             <img src="./assets/cvpr_pipeline_15_nov.drawio.png" alt="Data Construction" style="display: block; margin-left: auto; margin-right: auto; margin-bottom: 30px;margin-top: 30px; width: 100%; height: auto;">
           </div>
           <div>
-            Proposed GraPE framework, a given text prompt is used to generate an initial image from T2I model, Ig which is then fed into
+            Proposed GraPE framework, a given text prompt is used to generate an initial image from T2I model, I<sub>g</sub> which is then fed into
             a MLLM based planner along with the text prompt which identifies the objects that are misaligned in the image and outputs a set of edit
             plans guided by few-shot prompting. The plans are executed as a series of edits over the initial image to produce the final image
           </div>
@@ -263,7 +261,7 @@ <h2 class="title is-3 has-text-centered">Results</h2>
 
         <div class="content has-text-justified">
           <p>
-            Iterative results by applying GraPE. on images generated by SD3.5 and SDXL, these images are edited via the proposed PixEdit
+            Iterative results by applying GraPE on images generated by SD3.5 Large and SDXL, these images are edited via the proposed PixEdit
 editing model.           
           </p>