Update README.md

README.md

@@ -2,7 +2,7 @@
 
 ## **Introduction**
 
-**AutoNeural** is a next-generation, **NPU-native multimodal vision–language model** co-designed from the ground up for real-time, on-device inference. Instead of adapting GPU-first architectures, AutoNeural redesigns both **vision encoding** and **language modeling** for the constraints and capabilities of NPUs—achieving **14× faster latency**, **7× lower quantization error**, and **real-time automotive performance** even under aggressive low-precision settings.
+**AutoNeural** is an **NPU-native multimodal vision–language model** co-designed from the ground up for real-time, on-device inference on NPU. Instead of adapting GPU-first architectures, AutoNeural redesigns both **vision encoding** and **language modeling** for the constraints and capabilities of NPUs—achieving **14× faster latency**, **3× higher input resolution**, **7× lower quantization error**, and **real-time automotive performance** even under aggressive low-precision settings.
 
 AutoNeural integrates:
 
@@ -11,13 +11,13 @@ AutoNeural integrates:
 * A **normalization-free MLP connector** tailored for quantization stability.
 * Mixed-precision **W8A16 (vision)** and **W4A16 (language)** inference validated on real Qualcomm NPUs.
 
-AutoNeural powers real-time cockpit intelligence including **in-cabin safety**, **out-of-cabin awareness**, **HMI understanding**, and **visual + conversational function calls**.
-
 ---
 
 ## Use Cases
 
+AutoNeural powers real-time cockpit intelligence including **in-cabin detection**, **out-cabin awareness**, **HMI understanding**, and **visual + conversational function calls**.
 
+![Use_Cases](https://cdn-uploads.huggingface.co/production/uploads/6851901ea43b4824f79e27a9/hBbX11v67NNsZ7XLsm_RD.png)
 
 ---
 
@@ -33,6 +33,8 @@ Validated on **Qualcomm SA8295P NPU**:
 | **Decode Throughput**     | 15 tok/s               | **44 tok/s**      |
 | **Context Length**        | 1024                   | **4096**          |
 
+
+
 ---
 
 # **How to Use**
@@ -70,6 +72,8 @@ Multiple images can be processed with a single query.
 
 ## **Key Features**
 
+![Model Architecture](https://cdn-uploads.huggingface.co/production/uploads/6851901ea43b4824f79e27a9/eHNdopWWaoir2IP3Cu_AF.png)
+
 ### 🔍 **MobileNetV5 Vision Encoder (300M)**
 
 Optimized for edge hardware, with: