Zhengyang Tang (唐正阳)

Ph.D. Candidate

School of Science and Engineering (SSE), CUHK-Shenzhen

Email | Google Scholar | GitHub | Twitter

About Me

I am a Ph.D. candidate at The Chinese University of Hong Kong, Shenzhen (CUHK-Shenzhen), advised by Prof. Benyou Wang. I've had the privilege of working with amazing teams at Alibaba (Qwen Team), Microsoft Research Asia (MSRA), and Tencent.

Research Interests: My research focuses on enhancing the reasoning capabilities of Large Language Models (LLMs), including areas like instruction tuning, critique model, tool-integrated reasoning, and dense retrieval.

I am actively seeking full-time research or engineering roles starting around July 2026. Feel free to reach out!

Selected Publications

• Qwen3 Technical Report Qwen Team (My Contribution: Tool-integrated Reasoning). Technical Report, 2025. [Paper] [Code]
• Enabling Scalable Oversight via Self-Evolving Critic (SCRIT) Zhengyang Tang*, Ziniu Li*, Zhenyang Xiao*, Tian Ding, Ruoyu Sun, Benyou Wang, Dayiheng Liu, Fei Huang, Tianyu Liu, Bowen Yu, Junyang Lin. The 2nd Conference on Language Modeling (COLM), 2025. [Paper]
• Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary Expansion Jianqing Zhu*, Huang Huang*, Zhihang Lin*, Juhao Liang*, Zhengyang Tang*, Khalid Almubarak, Abdulmohsen Alharthik, Bang An, Juncai He, Xiangbo Wu, Fei Yu, Junying Chen, Zhuoheng Ma, Yuhao Du, He Zhang, Emad A. Alghamdi, Lian Zhang, Ruoyu Sun, Haizhou Li, Benyou Wang, Jinchao Xu. The 63rd Annual Meeting of the Association for Computational Linguistics (ACL), 2025. (Oral & Panel) [Paper] [Model]
• ORLM: Training Large Language Models for Optimization Modeling Chenyu Huang*, Zhengyang Tang*, Shixi Hu, Ruoqing Jiang, Xin Zheng, Dongdong Ge, Benyou Wang, Zizhuo Wang. Operations Research (OR), 2025. [Paper] [Code] [Demo]
• Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models (GLAN) Haoran Li*, Qingxiu Dong*, Zhengyang Tang*, Chaojun Wang*, Xingxing Zhang, Haoyang Huang, Shaohan Huang, Xiaolong Huang, Zeqiang Huang, Dongdong Zhang, Yuxian Gu, Xin Cheng, Xun Wang, Si-Qing Chen, Li Dong, Wei Lu, Zhifang Sui, Benyou Wang, Wai Lam, Furu Wei. Transactions on Machine Learning Research (TMLR), 2025. [Paper]
• MathScale: Scaling Instruction Tuning for Mathematical Reasoning Zhengyang Tang, Xingxing Zhang, Benyou Wang, Furu Wei. The 41st International Conference on Machine Learning (ICML), 2024. [Paper] [Code]
• DPTDR: Deep Prompt Tuning for Dense Passage Retrieval Zhengyang Tang, Benyou Wang, Ting Yao. The 29th International Conference on Computational Linguistics (COLING), 2022. [Paper] [Code]

Experiences

• Oct 2024 - Present, Research Intern, Qwen Team, Alibaba.
  Mentor: Dayiheng Liu
• Jun 2023 - Dec 2023, Research Intern, Microsoft Research Asia (MSRA).
  Mentors: Xingxing Zhang; Furu Wei
• Jan 2023 - Present, Ph.D. Candidate, The Chinese University of Hong Kong, Shenzhen.
  Supervisor: Prof. Benyou Wang
• Aug 2020 - Jan 2023, Senior Researcher (T10), Tencent.
• May 2019 - Aug 2020, Algorithm Engineer II (P6), Alibaba Group.
• Jan 2018 - Jul 2019, Graduate Student (SCPD), Stanford University.
• Aug 2016 - May 2019, Algorithm Engineer, CreditX Technology.
  Mentor: Mingjie Zhu
• Sep 2012 - Jul 2016, Bachelor of Engineering, Tongji University.

Invited Talks & Media

• Media Coverage for ORLM: Featured by Cardinal-AI and CUHK-Shenzhen.
• Invited Talk at ICML 2024: "MathScale: Scaling Instruction Tuning for Mathematical Reasoning". [Slides]
• Invited Talk at Baidu Search (2022): "DPTDR: Deep Prompt Tuning for Dense Passage Retrieval".

Patents

• A kind of Default Probability Forecasting Methodology of the unstructured data based on deep learning. CN107992982A, 2018. [Link]

Honors & Awards

• Runner-up (2nd Place / 793), LIC 2022 Passage-Ranking Competition.
• Ranked 3rd, Official MS MARCO Passage Ranking Leaderboard, 2022.

Curriculum Vitae

• My CV is here