Chujie Zheng 郑楚杰

I am a researcher in the Qwen Team. My work since joining the team has been dedicated to building AI systems that can tackle complex, long-horizon real-world problems. Currently, I am focusing on data curation and RL scaling to improve the agentic coding capability of Qwen models. I also led research of large-scale stable RL training recipes for Qwen models. Notably, I proposed the Routing Replay and Group Sequence Policy Optimization (GSPO) algorithms for large-scale MoE RL training.

Prior to entering the industry, I received my doctoral degree in Computer Science and Technology at Tsinghua University in 2025, and my bachelor degree in Mathematics and Physics at Tsinghua University in 2020.

You can find my CV here.

News

[02/2026] Release the Qwen3.5 series foundation models [blog] [model]
[01/2026] One paper accepted to ICLR 2026
[12/2025] Release the paper of large-scale stable RL training recipes [paper]
[10/2025] Selected for the 2025 CIPS Doctoral Dissertation Incentive Program (中国中文信息学会博士学位论文激励计划)
[09/2025] Two papers accepted to NeurIPS 2025
[07/2025] The ProcessBench paper wins the ACL 2025 SAC Award
[07/2025] Selected as Spotlight Recipient of the 2025 WAIC Yunfan Award (云帆奖·明日之星)
[07/2025] Release the Group Sequence Policy Optimization (GSPO) algorithm for large-scale MoE RL training [paper]
[07/2025] Release the Qwen3-2507 series updates
[05/2025] Release the Qwen3 technical report [paper]
[05/2025] Three papers accepted to ACL 2025
[04/2025] Release the Qwen3 series foundation models [blog] [model]
[03/2025] Release the QwQ-32B reasoning model [blog] [model]
[02/2025] Release the SuperGPQA benchmark for comprehensive LLM evaluation [paper] [data]
[01/2025] Release the Qwen2.5-Math-PRM models for process supervision in mathematical reasoning [paper] [model]
[12/2024] Release the ProcessBench benchmark for process supervision in mathematical reasoning [paper] [repo] [data]
[12/2024] Release the Yi-Lightning technical report [paper]
[11/2024] Release the QwQ-32B-Preview reasoning model [blog] [model]
[10/2024] Release the Yi-Lightning foundation model
[05/2024] One paper accpeted to ICML 2024
[01/2024] One paper accpeted to ICLR 2024 (Spotlight, 5%)

Recent Projects

You can find my full paper list on Google Scholar.

Qwen3.5: Towards Native Multimodal Agents
Qwen Team
[blog] [model]
Stabilizing Reinforcement Learning with LLMs: Formulation and Practices
Chujie Zheng, Kai Dang, Bowen Yu, Mingze Li, Huiqiang Jiang, Junrong Lin, Yuqiong Liu, Hao Lin, Chencan Wu, Feng Hu, An Yang, Jingren Zhou, Junyang Lin
[paper]
Group Sequence Policy Optimization
Chujie Zheng, Shixuan Liu, Mingze Li, Xiong-Hui Chen, Bowen Yu, Chang Gao, Kai Dang, Yuqiong Liu, Rui Men, An Yang, Jingren Zhou, Junyang Lin
[paper]
Qwen3: Think Deeper, Act Faster
Qwen Team
[blog] [model]
QwQ-32B: Embracing the Power of Reinforcement Learning
Qwen Team
[blog] [model]
QwQ: Reflect Deeply on the Boundaries of the Unknown
Qwen Team
[blog] [model]

Education

Aug 2020 – Jun 2025. Ph.D in Computer Science and Technology, Tsinghua University. Advisor: Minlie Huang
Nov 2023 – Jun 2024. Visiting Researcher. University of California, Los Angeles. Host: Nanyun Peng
Aug 2016 – Jul 2020. B.Sc. in Mathematics and Physics, Tsinghua University

Work Experiences

Oct 2024 – Present. Researcher. Qwen Team, Alibaba Group
Jul 2024 – Oct 2024. Research Intern. 01.AI

Services

Area Chair: ACL (24/25), EMNLP (24/25), NAACL (25), ACL Rolling Review (24/25)
Reviewer: ICLR (25), NeurIPS (24/25), ICML (24), COLM (24/25), ACL (22/23), EMNLP (21/22), NAACL (24), EACL (23), ACL Rolling Review (21/22/23), CogSci (24), AAAI (22/23)

Awards and Honors

CIPS Doctoral Dissertation Incentive Program (中国中文信息学会博士学位论文激励计划, Top 10 in China), 2025
ACL SAC Award, 2025
Spotlight Recipient of the 2025 WAIC Yunfan Award (云帆奖·明日之星), 2025
Outstanding Graduete, DCST, Tsinghua University, 2025
Outstanding Undergraduate, Tsinghua University, 2020
National Scholarship (Top 2/100), Ministry of Education of China, 2019