Hi there! I am a researcher at Parallel Distributed Computing Laboratory, 2012 Labs, Huawei Technologies Co., Ltd., focusing on Reinforcement Learning Post Training for Large Language Models (LLMs). Prior to joining Huawei, I obtained my Ph.D. degree from Zhejiang University, supervised by Prof. Jinming Xu. Previously, I received my B.S. degree from China University of Petroleum (East China). I was a visiting Ph.D. student with the A*STAR Centre for Frontier AI Research (CFAR), Singapore, supervised by Prof. Joey Tianyi Zhou. My research interests include Distributed Machine Learning, LLMs, Security and Privacy.

Education Background

2020.09—2025.09: Ph.D. Student
Zhejiang University

2024.06—2025.01: Visiting Ph.D. Student
A*STAR Centre for Frontier AI Research (CFAR), Singapore

2016.09—2020.06: B.S. Student
China University of Petroleum (East China)

Recent News

• Dec. 2025: Our paper, DP-CSGP: Differentially Private Stochastic Gradient Push with Compressed Communication, is online !
• Dec. 2025: Our paper, Bandwidth-Aware Network Topology Optimization for Decentralized Learning, is online !
• Oct. 2025: I have joined Huawei 2012 Labs as a researcher, working on Large Language Models (LLMs) !
• Sep. 2025: I have successfully completed my Ph.D. defense and received my doctoral degree !
• Apr. 2025: Our paper, Dyn-D²P: Dynamic Differentially Private Decentralized Learning with Provable Utility Guarantee, has been accepted by the 34th International Joint Conference on Artificial Intelligence (IJCAI 2025) !
• Jun. 2024: Our paper, R-FAST: Robust Fully-Asynchronous Stochastic Gradient Tracking over General Topology, has been accepted for publication in IEEE Transactions on Signal and Information Processing over Networks (IEEE TSIPN) as Regular Paper !
• May. 2024: Our paper, PerfTop: Towards Performance Prediction of Distributed Learning over General Topology, has been accepted for publication in Journal of Parallel and Distributed Computing (JPDC) as Regular Paper !
• Apr. 2024: Our paper, PrivSGP-VR: Differentially Private Variance-Reduced Stochastic Gradient Push with Tight Utility Bounds, has been accepted by the 33rd International Joint Conference on Artificial Intelligence (IJCAI 2024) !