Update README.md

README.md

@@ -22,7 +22,7 @@
 </p>
 
 <p>
-Visual State Space backbone fused with explicit spatio–frequency cues, bidirectional change guidance, and class-imbalance-aware loss—delivering robust, precise semantic change detection under tough illumination/seasonal shifts and severe long-tail labels.
+Official implementation for the paper https://huggingface.co/papers/2508.08232. Visual State Space backbone fused with explicit spatio–frequency cues, bidirectional change guidance, and class-imbalance-aware loss—delivering robust, precise semantic change detection under tough illumination/seasonal shifts and severe long-tail labels.
 </p>
 
 <p>
@@ -145,7 +145,7 @@ Plug-and-play support for **SECOND** and **Landsat-SCD**.
 
 ### SECOND Layout
 
-```
+```yaml
 /path/to/SECOND/
 ├── train/
 │   ├── A/          # T1 images