Ying Zhou
Assistant Professor
School of Artificial Intelligence, Shandong University
Email: yingzhou@sdu.edu.cn
I am currently an Assistant Professor in the School of Artificial Intelligence at the Shandong University (SDU), Jinan, China. I received my PhD in 2025 from the Institute of Software, Chinese Academy of Sciences (ISCAS), where I worked in the Chinese Information Processing Laboratory under the supervision of Prof. Ben He. Prior to that, I obtained my bachelor’s degree in Software Engineering from Shandong University in 2020.
My recent research focuses on the generation and understanding mechanisms of large language models, with particular interests in AI-generated text detection and safety, LLM interpretability, and generative information retrieval.
I am actively looking for master students, research assistants, and visiting students. Please feel free to contact me if you are interested in collaborating (yingzhou@sdu.edu.cn).
研究聚焦于信息检索、大语言模型、可解释性等。现招收硕士研究生和科研助理,欢迎对人工智能和大模型研究有热情的同学加入团队!
News
| Dec, 2025 | Awarded with Young Scholar Future Program by Shandong University |
|---|---|
| Jul, 2025 | I joined School of Artificial Intelligence, Shandong University |
Selected publications
- DRIVE: Distributional and Retrieval-Augmented Bidding with Value EvaluationForty-third International Conference on Machine Learning (CCF-A, CORE Rank A*), 2026
- From Traits to Roles: Consensus-Guided Composition of Orthogonal Experts for Cooperative MARL35th International Joint Conference on Artificial Intelligence (CCF-A, CORE Rank A*), 2026
- Spectral Characterization and Mitigation of Sequential Knowledge Editing Collapsethe 64nd Annual Meeting of the Association for Computational Linguistics (CCF-A, CORE Rank A*), 2026
- Identifying and Transferring Reasoning-Critical Neurons: Improving LLM Inference Reliability via Activation SteeringarXiv, 2025
- DiffLM: Controllable Synthetic Data Generation via Diffusion Language ModelsFindings of the Association for Computational Linguistics (CCF-A, CORE Rank A*), 2025
- Navigating the Shadows: Unveiling Effective Disturbances for Modern AI Content DetectorsAnnual Meeting of the Association for Computational Linguistics (CCF-A, CORE Rank A*), 2024
- Humanizing Machine-Generated Content: Evading AI-Text Detection through Adversarial AttackJoint International Conference on Computational Linguistics, Language Resources and Evaluation (CCF-B, CORE Rank B), 2024
- Hidding the Ghostwriters: An Adversarial Evaluation of AI-Generated Student Essay DetectionConference on Empirical Methods in Natural Language Processing (CCF-B, CORE Rank A*), 2023
- Re-Thinking Knowledge Graph Completion Evaluation from an Information Retrieval PerspectiveInternational ACM SIGIR Conference on Research and Development in Information Retrieval (CCF-A, CORE Rank A*), 2022