text style changes

app.py

@@ -97,9 +97,9 @@ css = """
 with gr.Blocks(css=css) as demo:
     gr.Markdown(
         """
-        # 🚀 POSEIDON: Foundation Models for PDEs 🌊🔬
+        # POSEIDON: Foundation Models for PDEs 🌊🔬
 
-        POSEIDON is a **foundation model** for solving **Partial Differential Equations (PDEs)** efficiently. Instead of training a separate model for each PDE, POSEIDON **learns a general solution operator**—allowing it to **generalize across different physics** with minimal data. Think of it as the **GPT-4 for PDEs**, trained on a diverse set of **fluid dynamics equations** and capable of adapting to **new, unseen physical systems**. 🌍⚡
+        POSEIDON is a **foundation model** for solving **Partial Differential Equations (PDEs)** efficiently. Instead of training a separate model for each PDE, POSEIDON **learns a general solution operator**—allowing it to **generalize across different physics** with minimal data. Think of it as the **GPT-4 for PDEs**, trained on a diverse set of **fluid dynamics equations** and capable of adapting to **new, unseen physical systems**.
 
         # **Dataset Explorer**
         POSEIDON provides solutions to a variety of fluid dynamics problems. Below are a few datasets you can explore:
@@ -116,7 +116,7 @@ with gr.Blocks(css=css) as demo:
         - Models shock interactions across uncertain boundaries, crucial for hypersonic flows and uncertainty quantification.
         - Helps in high-speed aerodynamics and robust PDE solvers.
 
-        Explore these datasets to visualize fluid behavior and analyze dynamic flow evolution! 🚀
+        Explore these datasets to visualize fluid behavior and analyze dynamic flow evolution!
         """
     )
 
@@ -157,44 +157,44 @@ with gr.Blocks(css=css) as demo:
 
     gr.Markdown(
         """
-        ## 🔥 Key Innovations
-        ### 🔹 **Multiscale Operator Transformer (scOT) 🧠**  
+        ## Key Innovations
+        ### • **Multiscale Operator Transformer (scOT)**  
         A hierarchical transformer-based architecture that captures PDE solution dynamics across multiple spatial and temporal scales. It uses shifted-window attention (SwinV2) to efficiently process large solution spaces.
 
-        ### 🔹 **Continuous-in-Time Learning ⏳**  
+        ### • **Continuous-in-Time Learning**  
         Instead of learning PDE solutions at discrete time steps, POSEIDON uses time-conditioned layer normalization, enabling predictions at **any arbitrary time**—like a **true continuous function**.
 
-        ### 🔹 **All2All Training Strategy 📈**  
+        ### • **All2All Training Strategy**  
         By leveraging the semi-group property of PDEs, POSEIDON scales training data quadratically without additional simulations. Every time step becomes a learning opportunity!
 
-        ### 🔹 **Pretrained on Fluid Dynamics, Generalizes to New Physics 🌊**  
-        Trained on compressible Euler and Navier-Stokes equations, POSEIDON transfers its knowledge to unseen wave, diffusion, and reaction-diffusion PDEs—a huge step for scientific machine learning! 💡
+        ### • **Pretrained on Fluid Dynamics, Generalizes to New Physics**  
+        Trained on compressible Euler and Navier-Stokes equations, POSEIDON transfers its knowledge to unseen wave, diffusion, and reaction-diffusion PDEs—a huge step for scientific machine learning!
 
-        ### 🔹 **Outperforms FNO & Neural Operators 🚀**  
-        POSEIDON achieves the same accuracy as an FNO trained on 1024 samples—using only 20 samples. That's a 50x efficiency boost in sample efficiency. 📉
+        ### • **Outperforms FNO & Neural Operators**  
+        POSEIDON achieves the same accuracy as an FNO trained on 1024 samples—using only 20 samples. That's a 50x efficiency boost in sample efficiency.
 
         ---
 
-        ## 🎯 Why Does This Matter?
-        Traditional PDE solvers are computationally expensive 🖥️💰. POSEIDON is a general-purpose neural PDE solver that:  
+        ## Why Does This Matter?  
+        Traditional PDE solvers are computationally expensive. POSEIDON is a general-purpose neural PDE solver that:  
 
-        ✅ Works across multiple physics domains  
-        ✅ Requires fewer training samples
-        ✅ Enables real-time simulation & forecasting 
+        • Works across multiple physics domains  
+        • Requires fewer training samples  
+        • Enables real-time simulation & forecasting  
 
-        It's a step towards universal scientific models, just like foundation models transformed NLP and vision. 🚀
+        It's a step towards universal scientific models, just like foundation models transformed NLP and vision.
 
         ---
 
-        ## 🌟 Try POSEIDON Now!
+        ## Try POSEIDON Now!  
 
         You can experiment and empower your research with POSEIDON-T (21M parameters), POSEIDON-B (158M parameters), and POSEIDON-L (629M parameters).
 
-        🔗 **Pretrained models & datasets**: [Hugging Face Hub](https://huggingface.co/camlab-ethz)  
-        📜 **Code & Paper**: [GitHub](https://github.com/camlab-ethz/poseidon) | [arXiv](https://arxiv.org/abs/2405.19101)  
-        💬 **Join the Discussion**: [Hugging Face Forums](https://discuss.huggingface.co/)  
+        • **Pretrained models & datasets**: [Hugging Face Hub](https://huggingface.co/camlab-ethz)  
+        • **Code & Paper**: [GitHub](https://github.com/camlab-ethz/poseidon) | [arXiv](https://arxiv.org/abs/2405.19101)  
+        • **Join the Discussion**: [Hugging Face Forums](https://discuss.huggingface.co/)  
 
-        Let's reshape the future of PDE solving—one foundation model at a time! 🚀🔬
+        Let's reshape the future of PDE solving—one foundation model at a time!
 
         ---
 
@@ -209,7 +209,6 @@ with gr.Blocks(css=css) as demo:
             primaryClass={cs.LG}
         }
         ```
-
         """
     )