Update README.md

README.md

@@ -11,16 +11,15 @@ pipeline_tag: text-generation
 
 ## Model Summary
 
-**Innovator-VL-8B-Instruct** is a multimodal instruction-following large language model designed for scientific understanding and reasoning.  
-The model integrates strong general-purpose vision-language capabilities with enhanced scientific multimodal alignment, while maintaining a fully transparent and reproducible training pipeline.
+**Innovator-VL-8B-Instruct** is a multimodal instruction-following large language model designed for scientific understanding and reasoning. The model integrates strong general-purpose vision-language capabilities with enhanced scientific multimodal alignment, while maintaining a fully transparent and reproducible training pipeline.
 
 Unlike approaches that rely on large-scale domain-specific pretraining, Innovator-VL-8B-Instruct achieves competitive scientific performance using high-quality instruction tuning, without additional scientific text continued pretraining.
 
----
+--
 
 ## Model Architecture
 
-![Innovator-VL Architecture](assets/innovator_vl_architecture.png)
+<img src="assets/innovator_vl_architecture.png" width="600"/>
 
 - **Vision Encoder**: RICE-ViT (region-aware visual representation)  
 - **Projector**: PatchMerger for visual token compression  
@@ -29,7 +28,6 @@ Unlike approaches that rely on large-scale domain-specific pretraining, Innovato
 
 The model supports native-resolution multi-image inputs and is suitable for complex scientific visual analysis.
 
-
 ## Training Overview
 
 - **Multimodal Alignment**: LLaVA-1.5 (558K)