Update content and formatting

app.py

@@ -1,5 +1,4 @@
 import gradio as gr
-from gradio_leaderboard import Leaderboard, ColumnFilter, SelectColumns
 import pandas as pd
 
 # Static data
@@ -21,56 +20,37 @@ STATIC_DATA = [
 ]
 
 COLUMNS = ["Model Type", "Method", "Control Type", "Input Type", "#Param.", "Acc. ↑", "Mean Traj. ↓"]
-LEADERBOARD_DF = pd.DataFrame(STATIC_DATA, columns=COLUMNS)
 
-# Custom CSS (simplified)
-custom_css = """
-/* Add any custom styling here */
-.gradio-container {
-    max-width: 1200px !important;
-}
-"""
+def create_leaderboard():
+    df = pd.DataFrame(STATIC_DATA, columns=COLUMNS)
+    return df
 
-def init_leaderboard(dataframe):
-    if dataframe is None or dataframe.empty:
-        raise ValueError("Leaderboard DataFrame is empty or None.")
-    return Leaderboard(
-        value=dataframe,
-        datatype=["str", "str", "str", "str", "str", "number", "number"],
-        select_columns=SelectColumns(
-            default_selection=COLUMNS,
-            cant_deselect=["Model Type", "Method", "Acc. ↑"],
-            label="Select Columns to Display:",
-        ),
-        search_columns=["Model Type", "Method"],
-        hide_columns=[],
-        filter_columns=[
-            ColumnFilter("Model Type", type="checkboxgroup", label="Model types"),
-            ColumnFilter("Control Type", type="checkboxgroup", label="Control types"),
-            ColumnFilter("Input Type", type="checkboxgroup", label="Input types"),
-        ],
-        bool_checkboxgroup_label="Hide models",
-        interactive=False,
-    )
-
-demo = gr.Blocks(css=custom_css, title="Model Performance Leaderboard")
-with demo:
-    gr.HTML("<h1 style='text-align: center'>🏆 Model Performance Leaderboard</h1>")
+# Create the Gradio interface
+with gr.Blocks(title="World-in-World: Building a Closed-Loop World Interface to Evaluate World Models", theme=gr.themes.Soft()) as demo:
+    gr.HTML("<h1 style='text-align: center; margin-bottom: 1rem'>🏆 World-in-World: Building a Closed-Loop World Interface to Evaluate World Models</h1>")
+    
     gr.Markdown("""
     **Performance comparison across vision-language models, image generation, and video generation models.**
     
     📊 **Metrics:** Acc. ↑ (Accuracy - higher is better) | Mean Traj. ↓ (Mean Trajectory error - lower is better)
-    """, elem_classes="markdown-text")
-
-    with gr.Tabs(elem_classes="tab-buttons") as tabs:
-        with gr.TabItem("🏅 Leaderboard", elem_id="leaderboard-tab", id=0):
-            leaderboard = init_leaderboard(LEADERBOARD_DF)
-
-        with gr.TabItem("📝 About", elem_id="about-tab", id=1):
+    """)
+    
+    with gr.Tabs():
+        with gr.TabItem("📊 Leaderboard"):
+            leaderboard_table = gr.DataFrame(
+                value=create_leaderboard(),
+                headers=COLUMNS,
+                datatype=["str", "str", "str", "str", "str", "number", "number"],
+                interactive=False,
+                wrap=True,
+                height=600
+            )
+        
+        with gr.TabItem("📝 About"):
             gr.Markdown("""
-            # About This Leaderboard
+            # World-in-World: Building a Closed-Loop World Interface to Evaluate World Models
             
-            This leaderboard showcases performance metrics across different types of AI models:
+            This leaderboard showcases performance metrics across different types of AI models in world modeling tasks:
             
             ## Model Categories
             - **VLM**: Vision-Language Models
@@ -87,8 +67,8 @@ with demo:
             - XXX indicates results pending/unavailable
             - – indicates not applicable or not available
             
-            *Results may vary across different evaluation settings and benchmarks.*
-            """, elem_classes="markdown-text")
+            *Results represent performance on world modeling evaluation benchmarks and may vary across different evaluation settings.*
+            """)
 
 if __name__ == "__main__":
     demo.launch()