update

Author: AaronCIH

index.html

@@ -290,7 +290,7 @@ <h3 class="title is-4 has-text-centered">Preliminary</h3>
         <!-- VisRAG -->
         <div class="column is-half">
           <p class="content has-text-justified">
-            <b>Vision-based RAG (VisRAG):</b> Given a textual query $q$ (e.g., a question or instruction) and a visual corpus $V = {X_i}_{i=1}^{N}$,  
+            <b>Vision-based RAG (VisRAG):</b> Given a textual query \[q\] (e.g., a question or instruction) and a visual corpus \( \mathcal{V} = \{ X_i \}_{i=1}^{N} \),  
             VisRAG retrieves the top-$k$ most relevant document images and generates a response as follows:
           </p>
         </div>
@@ -299,7 +299,7 @@ <h3 class="title is-4 has-text-centered">Preliminary</h3>
         <div class="column is-half">
           <p class="content has-text-justified">
             <b>Structural Causal Model (SCM)</b> 
-            adapts restored encoder features for diverse recognition tasks by integrating them with diffusion features in the decoder. Instead of using separate adapters per task, TFA employs lightweight, learnable prompts that guide feature fusion at each layer. These prompts are dynamically updated, allowing efficient task adaptation without retraining the entire model. This design ensures scalability and enables seamless extension to new tasks with minimal overhead.
+            ABC
           </p>
         </div>
       </div>