Update README.md

README.md

@@ -1,4 +1,16 @@
-# 📌 Overview
+---
+pipeline_tag: image-text-to-text
+library_name: transformers
+license: mit
+---
+
+# Skywork-R1V4
+
+<div align="center">   
+  <img src="skywork-logo.png" alt="Introduction Image" width="500" height="400"> 
+</div>
+
+## 1. Model Introduction
 
 **Skywork-R1V4** is a 30B (A3B) multimodal agent that unifies:
 - Multimodal task planning
@@ -6,7 +18,7 @@
 - Deep multimodal search (text × image)
 - Interleaved tool-grounded reasoning
 
-Unlike traditional VLMs that treat visual operations and search as disjoint capabilities—or agent systems that rely heavily on costly RL—Skywork-R1V4 is trained **purely via supervised finetuning** on **< 30k high-quality, execution-consistent trajectories**.
+Skywork-R1V4 is trained **purely via supervised finetuning** on **< 30k high-quality, execution-consistent trajectories**.
 
 At inference time, the model exhibits **emergent long-horizon reasoning**, executing **10+ tool calls** across visual operations and web search to solve complex real-world tasks.
 
@@ -16,25 +28,28 @@ Skywork-R1V4 achieves **state-of-the-art performance** on multimodal search benc
 - **Beats Gemini 2.5 Flash on all 11 comparable metrics**
 
 
-# 🚀 Key Features
+## 2. Feature
+
+### 🔍 **“Thinking With Images”**  
+Skywork-R1V4 actively manipulates images through:
 
-### **“Thinking With Images”**
-Skywork-R1V4 actively manipulates images:
-- Multi-stage cropping  
-- Local detail extraction  
-- Region attention  
-- Visual clue refinement  
+&nbsp;&nbsp;&nbsp;&nbsp;• Multi-stage cropping  
+&nbsp;&nbsp;&nbsp;&nbsp;• Local detail extraction  
+&nbsp;&nbsp;&nbsp;&nbsp;• Region attention  
+&nbsp;&nbsp;&nbsp;&nbsp;• Visual clue refinement  
 
-### **Interleaved Reasoning**
+
+### 🔄 **Interleaved Reasoning**  
 The model alternates between:
-1. Visual reasoning  
-2. Image operation  
-3. Web search  
-4. Cross-evidence verification  
+
+&nbsp;&nbsp;&nbsp;&nbsp;1. Visual reasoning  
+&nbsp;&nbsp;&nbsp;&nbsp;2. Image operation  
+&nbsp;&nbsp;&nbsp;&nbsp;3. Web search  
+&nbsp;&nbsp;&nbsp;&nbsp;4. Cross-evidence verification
 
 ---
 
-# 🔗 Links
+## 3. Links
 
 - **Model Center**: https://platform.skyworkmodel.ai/#/model-center  
 - **API Documentation (R1V4)**: https://docs.skyworkmodel.ai/r1v4/api-reference/completions.html