🔆 About Me | 个人简介
I am an algorithm researcher at the Feitian Lab of Alibaba Cloud, dedicated to deploying Qwen post-training into real-world business scenarios and creating tangible value. I received my Ph.D. from Zhejiang University in 2019, advised by Prof. Yaowu Chen, and my B.Eng. from Chu Kochen Honors College, Zhejiang University.
我目前在阿里云飞天实验室工作，致力于通过Qwen后训练，在实际业务场景中落地应用、创造价值。我 2019 年博士毕业于浙江大学，本科毕业于浙江大学竺可桢学院。
🎓️ Research Interest | 研究方向
My research focuses on LLM algorithm, building key components of the post-training pipeline to deeply optimize Planning & Tool-Use capabilities at both model and system levels, reducing hallucination and accurately completing user tasks. I lead a team that has delivered domain-specific LLM solutions across verticals including international sports events and education.
当前从事大语言模型算法研究，致力于通过构建后训练过程中的关键环节：Data/Trajectory Curation、Training Strategy、Reasoning Scaffolding、Fine-grained Benchmarking，深度优化模型和链路的Planning & ToolUse能力，降低幻觉并精准完成用户任务。
我带领团队在奥运会国际赛事、国内教育等场景均有行业化落地。米兰冬奥基于阿里千问打造奥运官方大模型，并在奥运会期间上线olympics.com官网，服务全球用户。
我们诚邀 LLM 研究及行业应用方向的 🎖️ 优秀实习生和正式员工加入，欢迎随时联系！详情请见 Internship 页面。
🔥 News | 动态
- Apr-2026 The Interact-RAG has been accepted by ICLR’26.
- Dec-2025 The Thinking Speed Control has been accepted by NeurIPS’25 Spotlight.
- May-2025 The StruXGPT2 has been accepted by ACL’25.
- May-2025 The ROPO has been accepted by ICML’25.
- Feb-2025 The ROUTE has been accepted by ICLR’25.
- Sep-2024 Three papers have been accepted by NeurIPS’24.
- StruXGPT on LLM Corpus Structurization.
- Thinking-Bias of LLM behaviors.
- ImOOD on Imbalanced OOD Detection.
- Feb-2024 Honored as the Outstanding Research Mentor 2024 in Alibaba Cloud.
- Congratulations to my intern Kai Liu for his excellent achievements!
- Jan-2024 The paper INSIDE on LLM hallucination has been accepted by ICLR’24.
📜 Professional Services | 学术服务
- Programme Committee: NeurIPS (2023–2025), ICLR (2023–2024), ICML (2023–2024), CVPR (2024), AAAI (2024), KDD (2023).
- Journal Reviewer: IEEE TIP, TCSVT.