About Me

I am a Ph.D. student (2025 cohort) at the Harbin Institute of Technology, Shenzhen, supervised by Prof. Li Jing. I graduated with an Honors Bachelor’s Degree from the YingCai Honors College of the University of Electronic Science and Technology of China (UESTC), majoring in Computer Science and Technology.我是哈尔滨工业大学（深圳）2025级博士研究生，师从李晶教授。本科毕业于电子科技大学英才实验学院（UESTC）计算机科学与技术专业，获荣誉工学学士学位。

My research interests include LLM Alignment, LLM Safety, and Reinforcement Learning. I have published 5 papers in international conferences, including ACL, KDD, and DASFAA.我的研究方向包括大模型对齐（LLM Alignment）、大模型安全（LLM Safety）与强化学习（Reinforcement Learning）。目前已在 ACL、KDD、DASFAA 等国际会议上发表 5 篇论文。

📖 Educations📖 教育经历

2021.09 - 2025.06, B.Eng. in Computer Science and Technology, YingCai Honors College, University of Electronic Science and Technology of China (UESTC).电子科技大学（UESTC）英才实验学院，计算机科学与技术专业，工学学士。
2025.09 - Present, Ph.D. student at Harbin Institute of Technology, Shenzhen, supervised by Prof. Li Jing.2025.09 - 至今，哈尔滨工业大学（深圳）博士研究生，导师：李晶教授。

🔥 News🔥 近期动态

2026.07: 🎉🎉 Our paper “Agent Reinforcement Learning via Pivotal-Aware Self-Feedback Retry” is now available on arXiv, with source code open-sourced on GitHub!🎉🎉 我们的论文 “Agent Reinforcement Learning via Pivotal-Aware Self-Feedback Retry” 已发布在 arXiv，源码已在 GitHub 开源！
2026.05: 🎉🎉 Two papers were accepted by ACL 2026! “Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward” (Main) and “E3-TIR: Enhanced Experience Exploitation for Tool-Integrated Reasoning” (Findings).🎉🎉 两篇论文被 ACL 2026 接收：“Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable Reward”（Main）与 “E3-TIR: Enhanced Experience Exploitation for Tool-Integrated Reasoning”（Findings）。
2025.05: 🎉🎉 Our paper “MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming” was accepted by ACL 2025!🎉🎉 论文 “MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teaming” 被 ACL 2025 接收！
2025.05: 🎉🎉 Our paper “LLMs are Noisy Oracles! LLM-based Noise-aware Graph Active Learning for Node Classification” was accepted by KDD 2025!🎉🎉 论文 “LLMs are Noisy Oracles! LLM-based Noise-aware Graph Active Learning for Node Classification” 被 KDD 2025 接收！
2023.12: 🎉🎉 Our paper “IntFair: Graph Neural Networks for Fair Recommendations with Interest Awareness” was accepted by DASFAA 2024!🎉🎉 论文 “IntFair: Graph Neural Networks for Fair Recommendations with Interest Awareness” 被 DASFAA 2024 接收！