Update app.py

app.py

@@ -42,14 +42,15 @@ training.
   <img src="figs/framework.png" width="80%" />
 </p>
     """)
-gr.Markdown(
+    gr.Markdown(
     """
 **Main Takeaways**
 1. ✂️ Thinking + Solution are explicitly separated with independent budgets — boosting reliability under tight compute constraints.
 2. 🧠 Budget-Constrained Rollout: We train models to handle truncated reasoning using GRPO.
 3. 📈 Flexible scalability: Robust performance across diverse inference budgets on reasoning benchmarks like AIME and LiveCodeBench.
 4. ⚙️ Better performance with fewer tokens: Our trained model generates outputs that are 30% shorter while maintaining (or even improving) accuracy.
-
+    """)
+    gr.HTML("""
 <p align="center">
   <img src="figs/aime.png" width="46%" />
     <img src="figs/livecode.png" width="48%" />
@@ -59,7 +60,7 @@ gr.Markdown(
   <img src="figs/codetable.png" width="90%" />
 </p>
     """)
-gr.Markdown(
+    gr.Markdown(
     """
 ## Citation