OmarSamir commited on
Commit
f56f884
·
verified ·
1 Parent(s): fd64a39

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +5 -0
README.md CHANGED
@@ -37,6 +37,11 @@ Built on the **Qwen2.5-VL** foundation, DriveFusion-V0.2 adds specialized MLP he
37
 
38
  DriveFusion-V0.2 extends the Qwen2.5-VL architecture with a modular "Driving Intelligence" layer.
39
 
 
 
 
 
 
40
  ### Technical Specifications
41
  - **Text Encoder**: Qwen2.5-VL (36 Transformer layers).
42
  - **Vision Encoder**: 32-layer ViT with configurable patch sizes.
 
37
 
38
  DriveFusion-V0.2 extends the Qwen2.5-VL architecture with a modular "Driving Intelligence" layer.
39
 
40
+ <div align="left">
41
+ <img src="drivefusion_architectures.png" alt="DriveFusion Architecture" width="700"/>
42
+ <p><i>The DriveFusion-V0.2 Architecture: Integrating visual tokens with telemetry-encoded tokens for dual-head output.</i></p>
43
+ </div>
44
+
45
  ### Technical Specifications
46
  - **Text Encoder**: Qwen2.5-VL (36 Transformer layers).
47
  - **Vision Encoder**: 32-layer ViT with configurable patch sizes.