Enxin
/

VideoNSA

Video-Text-to-Text

video-understanding

sparse-attention

vision-language

Model card Files Files and versions

Enxin commited on Oct 2, 2025

Commit

48b726c

·

verified ·

1 Parent(s): 0576bfc

Update README.md

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -14,7 +14,7 @@ pipeline_tag: video-text-to-text
 # VideoNSA: Native Sparse Attention for Video Understanding
 <div align="center">
-  <img src="https://enxinsong.com/VideoNSA-web/assets/teaser.png" alt="VideoNSA Overview" width="100%">
 </div>
 ## Model Description

 # VideoNSA: Native Sparse Attention for Video Understanding
 <div align="center">
+  <img src="VideoNSA.png" alt="VideoNSA Overview" width="100%">
 </div>
 ## Model Description