You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
<b>Vision-based RAG (VisRAG):</b> Given a textual query \(q\) (e.g., a question or instruction) and a visual corpus \( \mathcal{V} = \{ X_i \}_{i=1}^{N} \),
293
+
<b>Vision-based RAG (VisRAG):</b>
294
+
Given a textual query \(q\) (e.g., a question or instruction) and a visual corpus \( \mathcal{V} = \{ X_i \}_{i=1}^{N} \),
294
295
VisRAG retrieves the top-\(k\) most relevant document images and generates a response as follows:
0 commit comments