Update README.md
Browse files
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.
|