👋 I am Yudong Han (韩 宇栋), a Ph.D. candidate at the School of Computer Science, Peking University. My research interests lie in the fields of efficient neural rendering (3DGS), computer graphics, agentic software engineering, AI for Science (AI4S), software/browser testing, and high-performance computing on the web (WebGPU).

Currently, I am passionate about building AI agents for SE tasks, AI4S, and optimizing web graphics pipelines.

🔗 Check out my Blog for technical notes and writings.

📢 News

• [Dec. 2025] Our paper “Characterizing GPU-accelerated Web Applications in Browsers” was accepted by ICSE 2026. 🎉
• [Mar. 2025] Our paper “WebANNS” was accepted by SIGIR 2025.
• [Jan. 2025] Our paper “GL2GPU” was accepted by TheWebConf 2025 (WWW ‘25). 🎉
• [Apr. 2025] Honored to receive “The Web Conference Travel Award”. 🏅
• [Jan. 2024] Our paper “FusionRender” was accepted by TheWebConf 2024 (WWW ‘24).
• [May 2023] Our paper “Who Judges the Judge” was accepted by ISSTA 2023.

📑 Publications

• Characterizing GPU-accelerated Web Applications in Browsers [Paper]
  • Yudong Han, Weichen Bi, Haiyang Shen, Mugeng Liu, Ruibo An, Yun Ma
  • The 48th International Conference on Software Engineering (ICSE ‘26), CCF-A
• GL2GPU: Accelerating WebGL Applications via Dynamic API Translation to WebGPU [Demo] [Paper]
  • Yudong Han, Weichen Bi, Ruibo An, Deyu Tian, Qi Yang, Yun Ma
  • The Web Conference 2025 (TheWebConf ‘25), CCF-A
• DegaFL: Decentralized Gradient Aggregation for Cross-Silo Federated Learning [Code] [Paper]
  • Jialiang Han, Yudong Han, Xiang Jing, Gang Huang, Yun Ma
  • IEEE Transactions on Parallel and Distributed Systems (TPDS ‘25), CCF-A
• WebANNS: Fast and Efficient Approximate Nearest Neighbor Search in Web Browsers [Paper]
  • Mugeng Liu, Siqi Zhong, Qi Yang, Yudong Han, Xuanzhe Liu, Yun Ma
  • The 48th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR ‘25), CCF-A
• LLM-Powered Test Case Generation for Detecting Bugs in Plausible Programs [Paper] [Code]
  • Kaibo Liu, Zhenpeng Chen, Yiyang Liu, Jie Zhang, Mark Harman, Yudong Han, Yun Ma, Yihong Dong, Ge Li, Gang Huang
  • The 63rd Annual Meeting of the Association for Computational Linguistics (ACL 2025), CCF-A
• FusionRender: Harnessing WebGPU’s Power for Enhanced Graphics Performance on Web Browsers [Paper]
  • Weichen Bi, Yun Ma, Yudong Han, Yifan Chen, Deyu Tian, Jiaqi Du
  • The Web Conference 2024 (TheWebConf ‘24), CCF-A
• WPIA: Accelerating DNN Warm-up in Web Browsers by Precompiling WebGL Programs [Paper]
  • Deyu Tian, Yun Ma, Yudong Han, Qi Yang, Haochen Yang, Gang Huang
  • Frontiers Comput. Sci. 2024, CCF-B
• TrickyBugs: A Dataset of Corner-case Bugs in Plausible Programs [Paper]
  • Kaibo Liu, Yudong Han, Yiyang Liu, Jie M. Zhang, Zhenpeng Chen, Federica Sarro, Gang Huang, Yun Ma
  • the 21st International Conference on Mining Software Repositories (MSR 2024), CCF-C
• Web-Based Al Assistant for Medical Imaging: A Case Study on Predicting Spontaneous Preterm Birth via Ultrasound Images [Paper]
  • Weichen Bi, Zijian Shao, Yudong Han, Jiaqi Du, Yuan Wei, Lijuan Guo, Tianchen Wu, Shuang Li, Yun Ma
  • The International Web Information Systems Engineering conference (WISE 2024), CCF-C
• Who Judges the Judge: An Empirical Study on Online Judge Tests [Paper]
  • Kaibo Liu, Yudong Han, Jie M. Zhang, Zhenpeng Chen, Federica Sarro, Mark Harman, Gang Huang, Yun Ma
  • The 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA ‘23), CCF-A

🏗️ Projects

• Decentralized Federated Learning for Healthcare Data (Sep 2024 - Present)
  • An industrial implementation of our research paper, “DegaFL,” in collaboration with Peking University Third Hospital.
  • My Role: Algorithm Design, System Development in Rust, and coordination with third-party testing.
• Medical Imaging Recognition Project (Sep 2022 - Sep 2023)
  • Developed a system for disease prediction based on multimodal data from hospital imaging.
  • Subsequent results were published at the WISE 2024 conference.

Experience

• Research Intern - Alibaba Tongyi Lab (通义实验室) (Jul. 2025 - Present) 👨‍💻
• President - Peking University Martial Arts Association (Feb. 2025 - Present) 🧑‍💼
  • Designed and taught a 10-week Historical European Martial Arts (HEMA) saber program.
  • Organized weekly training for over 100 members and secured development funds for the association.
• Teaching Assistant - Introduction to Computing (Python 🐍) (Sep. 2021 - Sep. 2024) 🧑‍🏫
  • Instructed over 480 undergraduate students across four semesters at Peking University.
  • Developed a browser-based Python IDE to provide a zero-installation, privacy-first coding environment for beginners.
  • Created a “Cyber TA” powered by LLMs to offer students 24/7 automated debugging support.

🏆 Honors and Awards

• Dean’s Scholarship, Institute for Artificial Intelligence, Peking University (2025)
• School Scholarship, Excellent Research Award, Peking University (2025)
• Lingyun Linghang’s Scholarship (2025)
• The Web Conference Travel Award (2025) 🛫
• Fourth Place, 2nd Beijing University Student Historical Fencing Open Competition (2025) 🤺
• Second Prize, EDAthon - International EDA Algorithm Competition (2022) 🥈
• Silver Medal, National Olympiad in Informatics (NOI) (2017) 🥈

🔧 Technical Skills

• Languages: Rust, Python, TypeScript/JavaScript, C++, Java
• Web Technologies: WebGPU, WebGL, Web App Optimization, Web-based LLM/RAG
• Systems: Linux Server Maintenance, AWS, LLM Deployment with Edge Computing, Docker, CI/CD

🥋 Beyond Academia

Me in a HEMA saber bout, Beijing, April 2025.

When I’m not debugging WebGPU shaders or training AI agents, you’ll find me wielding a longsword or saber in HEMA (Historical European Martial Arts) tournaments. As the current president of Peking University Martial Arts Association, I balance my research pursuits with a passion for reconstructing sword combat techniques.