Junjie Wu 伍君杰
👋 Hi!
I am a Senior Researcher at the Hunyuan LLM Team, Tencent, focusing on post-training and evaluation for the Hunyuan foundation model series (e.g., Hy3 preview), with a particular interest in reward modeling stability and next-generation agentic evaluation pipelines. I obtained my Ph.D. in Artificial Intelligence from HKUST in January 2026, where I was supervised by Prof. Dit-Yan Yeung.
Previously, I was a Research Scientist Intern at GenAI, Meta, and a visiting Ph.D. student at Yale University with Prof. Arman Cohan. Throughout my research journey, I have also collaborated closely with Mo Yu and Lemao Liu at Tencent AI Lab and Wechat AI.
News
- [2026.04] 🔥 Hy3 preview is released! The most intelligent agentic model we've shipped so far. Happy to be part of the team!.
- [2026.04] 🎉 Happy to have two papers on situated embedding models and multi-task RL for MLLM-as-a-Judge accepted to ACL 2026 (Main Conference and Industry Track). See you at SD!
- [2026.03] 🏁 Wrapping up my internship at Meta with a new work on training better MLLM-as-a-Judge with multi-task RL.
- [2025.07] 🎉 One paper on Hallucination Evaluation for MLLMs accepted to TMLR 2025.
- [2025.06] 💼 Started my journey as a Research Scientist Intern at Meta.
- [2025.05] 🎉 One paper on the long context referencing capabilities of LLMs accepted to ACL 2025 (Main Conference).
- [2025.01] 🔥 Two papers on the intelligence of LLMs accepted to NAACL 2025 (Oral).
Education / Experience
- 2026/02 - Present: Senior Researcher at Hunyuan LLM Team, Tencent
- 2020/09 - 2026/01: Ph.D. at HKUST
- 2025/06 - 2026/01: Research Scientist Intern at GenAI, Meta
- 2024/09 - 2025/02: Visiting Ph.D. Student at Yale NLP, Yale University
- 2024/05 - 2025/05: Research Intern at WeChat AI, Tencent
- 2021/06 - 2024/01: Research Intern at NLP Group, Tencent AI Lab
- 2016/09 - 2020/06: B.S. in Statistics, Sun Yat-sen University (GPA: 3.8/4.0)
- 2019/07 - 2019/10: Visiting Student at the University of Michigan, Ann Arbor
Research
My current research interests lie in building more intelligent and reliable large (language/vision) models.
Specifically, here are some topics I currently focus on:
- Intelligence of Large (langauge/vision) Model: [NAACL'25 (1), NAACL'25 (2)]
- Long-Context Understanding Capability Investigation: [ACL'25, ACL'26, Preprint (2)]
- Post-training & Reward Modeling of Large Models. [ACL'26]
Publications (* Equal contribution)
Bo Pan, Xuan Kan, Kaitai Zhang, Yan Yan, Shunwen Tan, Zihao He, Zixin Ding, Junjie Wu, and Liang Zhao
[Paper]
Yuqing Li, Jiangnan Li, Zheng Lin, Ziyan Zhou, Junjie Wu, Weiping Wang, Jie Zhou, and Mo Yu
[Paper]
Junjie Wu and Dit-Yan Yeung
[Paper]
Junjie Wu, Jiangnan Li, Yuqing Li, Lemao Liu, Liyan Xu, Jiwei Li, Dit-Yan Yeung, Jie Zhou, and Mo Yu
ACL 2026
[Paper] [Model]
Junjie Wu, Xuan Kan, Zihao He, Shunwen Tan, Bo Pan, and Kaitai Zhang
ACL 2026 Industry Track
[Paper]
Junjie Wu*, Gefei Gu*, Yanan Zheng, Dit-Yan Yeung, and Arman Cohan
ACL 2025
[Paper] [Project] [Code]
Junjie Wu, Mo Yu, Lemao Liu, Dit-Yan Yeung, and Jie Zhou
NAACL 2025 (Oral)
[Paper] [Project] [Code]
Mo Yu*, Lemao Liu*, Junjie Wu*, Tsz Ting Chung*, Shunchi Zhang*, Jiangnan Li, Dit-Yan Yeung, and Jie Zhou
NAACL 2025 (Oral)
[Paper] [Project] [Code]
Junjie Wu*, Tsz Ting Chung*, Kai Chen*, and Dit-Yan Yeung
TMLR 2025
[Paper] [Project] [Code]
Junjie Wu, Lemao Liu, Wei Bi, and Dit-Yan Yeung
ICASSP 2024
[Paper] [Code]
Junjie Wu, Lemao Liu, and Dit-Yan Yeung
EMNLP 2023 Findings (Presented at the GenBench Workshop @EMNLP 2023)
[Paper] [Code]
Jiajun Bao*, Junjie Wu*, Yiming Zhang*, Eshwar Chandrasekharan, and David Jurgens
The Web Conference 2021
[Paper] [Code]
Junjie Wu and Hao Zhou
DeeLIO Workshop @ NAACL 2021
[Paper]