Upload README.md with huggingface_hub

README.md

@@ -22,7 +22,7 @@ size_categories:
 # LOGOS: Language of Generative Objects in Science
 
 <p align="center">
-  <img src="pics/logos.png" alt="LOGOS" height="120">
+  <img src="pics/logos.png" alt="LOGOS" height="90">
 </p>
 
 <p align="center">
@@ -44,7 +44,7 @@ size_categories:
 Unlike approaches that rely on natural language as an intermediary or require explicit 3D geometric networks, LOGOS operates directly on domain-native representations. Key spatial relationships (e.g., protein pocket–ligand contacts) are discretized and tokenized into the shared grammar, allowing the model to learn complex structural interactions in a purely sequential manner.
 
 <p align="center">
-  <img src="pics/LOGOS-mainfigure.png" alt="LOGOS Framework Overview" width="90%">
+  <img src="pics/LOGOS-mainfigure.png" alt="LOGOS Framework Overview" width="100%">
 </p>
 
 ### Key Features
@@ -55,7 +55,7 @@ Unlike approaches that rely on natural language as an intermediary or require ex
 * **Pre-training & Downstream Alignment**: The grammar space ensures formal consistency between continued pre-training objectives and downstream task goals.
 
 <p align="center">
-  <img src="pics/logos-data-process.png" alt="Data Construction in LOGOS" width="90%">
+  <img src="pics/logos-data-process.png" alt="Data Construction in LOGOS" width="100%">
 </p>
 
 ## Supported Tasks
@@ -72,7 +72,7 @@ LOGOS achieves competitive or state-of-the-art performance across six representa
 | Antibody CDR Design | Immunology | Design complementarity-determining regions for antibody engineering |
 
 <p align="center">
-  <img src="pics/bench_comparison.png" alt="Benchmark Comparison" width="90%">
+  <img src="pics/bench_comparison.png" alt="Benchmark Comparison" width="100%">
 </p>
 
 ## Model Architecture