👋 Hi there, my name is Junyao Yang. I am a graduate student at the School of Computing, National University of Singapore (NUS), where I am pursuing a specialization in Artificial Intelligence. My research interests lie in Natural Language Processing and Language Models. Here is my CV.

My research story revolves around the Underlying Principles and Understanding of LLMs, particularly focusing on how to enhance the “Robustness” and “Safety” of LLM-generated information, which connects to related areas such as Trustworthy LLM [PrivacyRestore, RewardDS], Reasoning Model Merging RCP-Merging and Malicious Attacks [PrivacyRestore], of LLMs and so on:

• Trustworthy Artificial Intelligence
• Large Language Models Reasoning

🔥 News

• [2025.08] 🚀🚀 Check out my latest work: RCP-Merging! This novel framework integrates long CoT capability into domain-specific LLMs without sacrificing their performance in the original domain!
• [2025.05] 🎉🎉 Successfully passed my undergraduate thesis defense!
• [2025.05] 🎉🎉 My first Co-First-Author paper PrivacyRestore has been accepted to ACL 2025 Main! Deeply grateful to my mentor Ziqian and collaborator Jianwei! See you in Vienna!
• [2025.02] 🚀🚀 Please check our newest papers: RewardDS and PrivacyRestore! Thanks to the help of other collaborators.
• [2024.07] I joined ZeroNLP as a Research Assistant, advised by Prof. Ziqian Zeng.
• [2024.07] I spent a wonderful time at Tencent as a machine learning intern!
• [2024.07] Contextless CS is available now, which reaches 20,000 DAU! Check my work here!
• [2024.04] I joined Tencent as a machine learning intern.
• [2024.03] I spent a wonderful time at ShenZhen Stock Exchange as a machine learning intern!

🧐 Research

RCP-Merging: Merging Long Chain-of-Thought Models with Domain-Specific Models by Considering Reasoning Capability as Prior
Junyao Yang, Jianwei Wang, Huiping Zhuang, Cen Chen, Ziqian Zeng^#
arXiv preprint, 2025.08

PrivacyRestore: Privacy-Preserving Inference in Large Language Models via Privacy Removal and Restoration
Ziqian Zeng^*#, Jianwei Wang^*, Junyao Yang^*, Zhengdong Lu, Haoran Li, Huiping Zhuang, Cen Chen
ACL 2025 Main

RewardDS: Privacy-Preserving Fine-Tuning for Large Language Models via Reward Driven Data Synthesis
Jianwei Wang, Junyao Yang, Haoran Li, Huiping Zhuang, Cen Chen, Ziqian Zeng^#
arXiv preprint, 2025.02

_{(^* co-author, ^# correspondence author)}

✏️ Education

• National University of Singapore, Singapore
  M.S. in Artificial Intelligence
  2025 ~ 2027 (expected)
  

• South China University of Technology, Guangzhou, China
  B.E. in Computer Science Union Class (top 30 students in undergraduates)
  2021 ~ 2025

• Shenzhen Experimental School, Shenzhen, China
  High School Diploma
  2018 ~ 2021

💻 Experience

• 2025.06 ~ Present, Research Intern, Shanghai AI Lab
  Supervisor: Dongrui Liu, Shanghai, China.
  Topics: Trustworthy Machine Learning & LLM Reasoning
  

• 2024.07 ~ Present, Research Intern, South China University of Technology
  Supervisor: Prof. Ziqian Zeng, Guangzhou, China.
  Topics: LLM Privacy & Reasoning
  

• 2024.04 ~ 2024.07, Machine Learning Intern, Tencent, Shenzhen, China.
  Topics: LLM Deployment & Fine-Tuning
  

• 2024.01 ~ 2024.04, Machine Learning Intern, SZSE, Shenzhen, China.
  Topics: LLM Acceleration & Memory Optimizing
  

• 2023.06 ~ 2024.08, Research Intern, South China University of Technology
  Supervisor: Prof. Guanglong Du, Guangzhou, China.
  Topics: Reinforcement Learning & UAV Navigation
  

🎖️ Honor and Awards

• [2024.10] Second-Class Scholarship of South China University of Technology
• [2024.11 & 2023.11 & 2022.11] Outstanding Student Leader
• [2024.11 & 2023.11 & 2022.11] Merit Student
• [2023.05] Outstanding Student Union Member
• [2022.10] Third-Class Scholarship of South China University of Technology
• [2022.09] Second-Class Award in CUMCM at Guangdong Province

📘 Patents

An Intelligent Obstacle Avoidance and Destination Landing Unmanned Aerial Vehicles Based on Multi-Layer Neural Networks
Guanglong Du, Xiaojian Qiu, Junyao Yang, Jiancheng Li, Xueqian Wang, Xiaojun Zhu (Student First Author)
2023.08 Publication Number: CN117170403A