doc: add readme

Author: VinciGit00

assets/README.zh-CN.md

@@ -1,6 +1,10 @@
+<p align="center">
+  <img src="toonify.png" alt="Toonify Logo" width="400">
+</p>
+
 # TOON（面向Token的对象表示法）
 
-[English](../README.md) | [中文](README.zh-CN.md)
+[English](../README.md) | [中文](README.zh-CN.md) | [한국어](README.ko.md)
 
 一种紧凑、人类可读的序列化格式，专为向大型语言模型传递结构化数据而设计，显著减少Token使用量。
 
@@ -427,7 +431,7 @@ python examples/advanced_features.py
 
 **💰 成本影响：** 按GPT-4定价计算，TOON每百万次API请求**节省$2,147**，每十亿Token**节省$5,408**。
 
-**[📊 查看完整基准测试结果 →](benchmark/RESULTS.md)**
+**[📊 查看完整基准测试结果 →](../benchmark/RESULTS.md)**
 
 ## 贡献
 

benchmark/README.md

@@ -2,6 +2,8 @@
 
 This benchmark suite demonstrates the **MASSIVE memory and token savings** achieved by using TOON (Token-Oriented Object Notation) compared to JSON for structured data.
 
+**NEW:** TOON now supports direct conversion from [Pydantic models](../examples/pydantic_usage.py) with `encode_pydantic()` and `decode_to_pydantic()` functions!
+
 ## 🚀 HEADLINE RESULTS
 
 **Tested across 50 diverse, real-world datasets:**
@@ -116,6 +118,9 @@ pip install -e .
 
 # tiktoken is required for token counting
 pip install tiktoken
+
+# Pydantic is optional but recommended for model validation
+pip install pydantic
 ```
 
 ### Run All Benchmarks
@@ -301,7 +306,8 @@ All benchmark code is open source and can be reviewed in this directory.
 ## 📚 Additional Resources
 
 - [TOON Format Specification](https://github.com/toon-format/toon)
-- [Main README](../README.md)
+- [Main README](../README.md) - Includes Pydantic integration documentation
+- [Pydantic Examples](../examples/pydantic_usage.py) - Direct conversion from Pydantic models
 - [Python Package](https://pypi.org/project/toonify/)
 
 ## 🤝 Contributing