Wenxuan Zhou 周文轩

I’m a research scientist at Google Deepmind. My research focuses on natural language processing and machine learning, with a particular emphasis on the post-training of large language models. I am especially interested in instruction tuning, preference modeling, and reinforcement learning from human feedback. I earned my Ph.D. from the University of Southern California under the mentorship of Prof. Muhao Chen. Prior to that, I obtained my Bachelor’s degree in Computer Science and Applied Mathematics from HKUST in 2018.

Email: A [at] B, where A=wenxuan.zhou.usc and B is gmail.com

Preprints

  1. Wenjie Jacky Mo, Qin Liu, Xiaofei Wen, Wenxuan Zhou, Zhe Zhao, Muhao Chen. DEBUGLM: Learning Traceable Training Data Provenance for LLMs. Arxiv 2026. [paper]

  2. Zhenyu Zhang, Shujian Zhang, John Lambert, Wenxuan Zhou, Zhangyang Wang, Mingqing Chen, Andrew Hard, Rajiv Mathews, Lun Wang. Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process. Arxiv 2025. [paper]

  3. Bangzheng Li, Fei Wang, Wenxuan Zhou, Nan Xu, Ben Zhou, Sheng Zhang, Hoifung Poon, Muhao Chen, Semantic-Clipping: Efficient Vision-Language Modeling with Semantic-Guidedd Visual Selection. Arxiv 2025. [paper]

  4. Wenzhe Li, Shujian Zhang, Wenxuan Zhou, John Lambert, Chi Jin, Andrew Hard, Rajiv Mathews, Lun Wang. MUSIC: MUlti-Step Instruction Contrast for Multi-Turn Reward Models. Arxiv 2025. [paper]

Publication

[Organized by Area] [Full List by Year]

RLHF

  1. Wenxuan Zhou, Ravi Agrawal, Shujian Zhang, Sathish Reddy Indurthi, Sanqiang Zhao, Kaiqiang Song, Silei Xu, Chenguang Zhu. WPO: Enhancing RLHF with Weighted Preference Optimization. EMNLP 2024. [paper] [code] [model]

  2. Fei Wang, Wenxuan Zhou, James Y. Huang, Nan Xu, Sheng Zhang, Hoifung Poon, Muhao Chen. mDPO: Conditional Preference Optimization for Multimodal Large Language Models. EMNLP 2024. [paper] [code]

LM Safety and Faithfulness

  1. Wenjie Jacky Mo, Qin Liu, Xiaofei Wen, Wenxuan Zhou, Zhe Zhao, Muhao Chen. DEBUGLM: Learning Traceable Training Data Provenance for LLMs. Arxiv 2026. [paper]

  2. Zhenyu Zhang, Shujian Zhang, John Lambert, Wenxuan Zhou, Zhangyang Wang, Mingqing Chen, Andrew Hard, Rajiv Mathews, Lun Wang. Fantastic Reasoning Behaviors and Where to Find Them: Unsupervised Discovery of the Reasoning Process. Arxiv 2025. [paper]

  3. Wenjie Jacky Mo, Qin Liu, Xiaofei Wen, Dongwon Jung, Hadi Askari, Wenxuan Zhou, Zhe Zhao, Muhao Chen. RedCoder: Automated Multi-Turn Red Teaming for Code LLMs. ACL 2026. [paper]

  4. Tong Wu, Shujian Zhang, Kaiqiang Song, Silei Xu, Sanqiang Zhao, Ravi Agrawal, Sathish Reddy Indurthi, Chong Xiang, Prateek Mittal, Wenxuan Zhou. Instructional Segment Embedding: Improving LLM Safety with Instruction Hierarchy. ICLR 2025. [paper]

Information Extraction

  1. Wenxuan Zhou*, Sheng Zhang*, Yu Gu, Muhao Chen, Hoifung Poon. UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition. ICLR 2024. [paper] [project page] [model]

  2. Wenxuan Zhou and Muhao Chen. Learning from Noisy Labels for Entity-Centric Information Extraction. EMNLP 2021. [paper] [code] [slides]

  3. Wenxuan Zhou, Kevin Huang, Tengyu Ma, Jing Huang. Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling. AAAI 2021. [paper] [code] [slides]

  4. Wenxuan Zhou, Hongtao Lin, Bill Yuchen Lin, Ziqi Wang, Junyi Du, Leonardo Neves, Xiang Ren. NERO: A Neural Rule Grounding Framework for Label-Efficient Relation Extraction (Honorable Mention Paper). WWW 2020. [paper] [code] [slides]

Service