I am currently a junior student at Xu Teli College, Beijing Institute of Technology (北京理工大学特立书院), majoring in the Elite Class of Computer Science (计算机科学拔尖班), advised by Chengliang Chai (柴成亮). I also collaborate with Kunpeng Ning (宁鲲鹏) and Jiayu Yao (姚佳雨) from Peking University closely.
I won the 2025 Sensetime Scholarship (30 candidates nationwide each year) and 2024 National Scholarship (top 10 students in the college). My research project was selected for the “Qi Yan” Program for Undergraduates from the Beijing Natural Science Foundation (one of the top 8 projects selected college-wide).
My research interest includes ai4data, ai agents and multimodal large language models. I have published 3 papers at the top international conferences such as SIGMOD, VLDB.
I am now working at Chatexcel
, leading the research on RAG and unstructured data retrieval. I am also a researcher at Edit Banana, where I lead the development of img2svg technology. If you are seeking any form of academic cooperation, please feel free to email me at zephyrzhong248@gmail.com.
🔥 News
- 2026.04: 💼 I join ChatExcel
to lead the research on RAG and unstructured data retrieval - 2026.01: 💼 I join Edit Banana to lead the research on img2svg
- 2025.08: 🏆 I won 1st Place in the Alibaba Tianchi LLM Evaluation Contest and the relevant technical report is accepted by CCL 2025
- 2025.08: 🎖️ I was awarded the Sensetime Scholarship

- 2025.07: 🚀 My research project was selected for the Beijing Natural Science Foundation Program

- 2025.07: 🎉 Two papers are accepted by VLDB 2025
- 2025.05: 🎉 My first paper is accepted by SIGMOD 2025
- 2024.10: 🎖️ I was awarded the National Scholarship(8/656)
- 2024.07: 💼 I join Alibaba Lingxi Interactive Entertainment
as an algorithm intern in Guangzhou - 2024.02: 🚀 I release a modern and responsive academic personal homepage template. Welcome to STAR!
📝 Publications
📊 AI-Native Data Systems

Doctopus: Budget-aware Structural Data Extraction from Documents
Yuanhao Zhong, Yuhao Deng, Chengliang Chai, et al.
Project | | Video Demo
- Doctopus is a framework designed to accurately extract structured data from large-scale unstructured documents under cost constraints.
- Impact: Doctopus improves accuracy by 11% under the same cost, or achieves a 2.7x cost reduction while maintaining precision.

DocDB: A Database for Unstructured Document Analysis
Zequn Li*, Yuanhao Zhong*, Chengliang Chai, Zhaoze Sun, Ye Yuan, Lei Cao
Project | | Video Demo
- DocDB is tailored for unstructured document analysis, enabling users to perform complex data filtering and joining via standard SQL queries.
- Performance: DocDB significantly outperforms existing systems in query accuracy, execution latency, and Token consumption cost.
VLDB 2025Budget-aware Structural Table Extraction from Unstructured Documents, Chengliang Chai, Jiajun Li, Yuhao Deng, Yuanhao Zhong, Ye Yuan, Lei Cao
💡 Others
CCL 2025Application of Macroscopic Pattern Prompting and Efficient Finetuning in Factivity Inference, Zequn Li*, Yuanhao Zhong*, et al.
🛠️ Projects

Edit Banana: High-fidelity Image-to-DrawIO System 
Project |
- High-Fidelity Reconstruction: Converts static diagrams into editable DrawIO vector files with 1:1 visual fidelity and full logical connectivity.
- Many video demos created by the Editbanana Community are released.
- EditBanana was introduced in a very popular video (16k+ likes) on Douyin and was reported in more than 20 media and forums, such as 搜狐, aitnt!
🎖 Honors and Awards
- 2026.01, First Prize, “Jingcai” Beijing College Students Entrepreneurship Competition (Top 5%).
- 2025.12, Special Prize, “Challenge Cup” Capital College Students’ Academic Works Competition (Top 1%).
- 2025.11, Special Prize, “Century Cup” Student Entrepreneurship Competition (Top 1%).
- 2025.10, School First-Class Scholarship, Beijing Institute of Technology (Top 5%).
- 2025.08, Beijing Natural Science Foundation “Qi Yan” Program (Top 8 projects in the college).
- 2025.08, Sensetime Scholarship (30 students in the nation each year)
- 2025.08, 1st Place, Alibaba Tianchi LLM Evaluation Contest.
- 2025.08, National 4th Place, National Industrial Internet Entrepreneurship Competition.
- 2025.03, School First-Class Scholarship, Beijing Institute of Technology (Top 5%).
- 2024.11, First Prize, National Mathematical Modeling Competition (Top 3%).
- 2024.11, First Prize, National Mathematics Competition for College Students (Top 3%).
- 2024.10, National Scholarship (Top 10 students in the college).
- 2024.03, School Second-Class Scholarship, Beijing Institute of Technology (Top 10%).
- 2024.03, School First-Class Scholarship, Beijing Institute of Technology (Top 5%).
- 2023.11, First Prize, BIT “Mingli Cup” Freshman Mathematics Competition (Top 1%).
📖 Educations
- 2023.09 - 2027.06, Undergraduate, Xu Teli College, Beijing Institude of Technology, Beijing.
- 2020.09 - 2023.06, Guangzhou No.2 High School, Guangzhou.
💬 Invited Talks
- 2025.11, Technical Talk at the 24th China National Conference on Computational Linguistics (CCL 2025).
- 2025.08, Accelerating Agent Deployment, Huawei Internal Talk.
💻 Internships
- 2026.03 - 2026.04, Chatexcel, Beijing.
- 2024.07 - 2024.08, Alibaba Lingxi Interactive Entertainment, Guangzhou.