I’m Zeming Wei (魏泽明), a Ph.D. candidate at School of Mathematical Sciences @ Peking University, proudly supervised by Prof. Meng Sun, focusing on AI Safety and Interpretability research. I’m also a Full-time Research Consultant @ ByteDance Seed, working on foundation model safety and alignment. I obtained my Bachelor’s degree from Peking University in 2025 and visited UC Berkeley in Fall 2023, where I was also fortunate to be advised by Prof. Yisen Wang and Prof. David Wagner.

🔥 News

  • 2026.11:  🎉 1 Paper (as first author) accepted by EACL 2027 (Findings).
  • 2026.09:  🎉 1 Paper (as co-first author) accepted by NeurIPS 2026.
  • 2026.09:  🎉 1 Paper (as co-first author) accepted by NDSS 2027.
  • 2026.08:  💼 I serve as an Area Chair (Senior Program Committee) for AAAI 2027 AI Alignment Track.
  • 2026.08:  🎉 3 Papers (1 as corresponding author, 1 as co-first author) accepted by EMNLP 2026 (Main).
  • 2026.07:  🎉 1 Paper (as co-first author) accepted by ACM MM 2026.
  • 2026.06:  👨‍💻 I joined ByteDance Seed as a research intern.
  • 2026.04:  🎉 1 Paper (as corresponding author) accepted by ICML 2026.
  • 2026.04:  🎉 1 Paper (as co-first author) accepted by ACL 2026 (Findings).
  • 2026.03:  🎉 1 Paper (as first author) accepted by FSE 2026.
  • 2026.03:  🎉 1 Paper (as first author) accepted by Journal of Systems Architecture (JSA).
  • 2026.01:  🎉 1 Paper (as first author) accepted by Transactions on Pattern Analysis and Machine Intelligence (TPAMI).
  • 2025.10:  🏅 I received the Top Reviewer Award of NeurIPS 2025.
  • 2025.06:  🎊 I got my Bachelor of Science degree from Peking University and will start my Ph.D. studies in September 2025. Thank you to all my advisors and collaborators!
  • 2025.06:  🏅 I received the Outstanding Bachelor Dissertation Award by Peking University (Top 3%, pdf).
  • 2025.05:  🎉 1 Paper (as first author) accepted by ICML 2025.
  • 2024.12:  🎉 2 Papers (as corresponding author; 1 as Oral) accepted by ICASSP 2025.
  • 2024.12:  🏅 I received the Academic Rising Star Award (Top 5 undergraduates university-wide, blog) by School of Computer Science, Peking University.
  • 2024.11:  🏅 I received the May 4th Scholarship (五四奖学金, blog), which is the highest honor scholarship of Peking University (only 1 undergraduate awardee in School of Mathematical Sciences, Top 0.1%).
  • 2024.10:  💎 My research grant (as Principal Investigator) was approved by Beijing Natural Science Foundation.
  • 2024.05:  🎉 1 Paper (as corresponding author) accepted by ICML 2024.
  • 2023.12:  💯 I achieved a full GPA (4.0/4.0) during my studies at UC Berkeley (with 1 A and 2 A+ grades).
  • 2023.10:  🔗 I serve as a fellow of Berkeley AI Safety Initiative for Students (BASIS).
  • 2023.08:  🎉 1 Paper (as first author) accepted by Journal of Logical and Algebraic Methods in Programming (JLAMP).
  • 2023.05:  🥈 Won Second prize in Chinese Mathematics Competitions for Undergraduates (National final, Top 0.2%).
  • 2023.02:  🎉 1 Paper (as first author) accepted by CVPR 2023.
  • 2022.12:  🥇 Won First prize in Chinese Mathematics Competitions for Undergraduates (Beijing Division), and qualified for the finals.

📖 Experiences

  • 2026.11 - present, Full-time Research Consultant, ByteDance Seed
  • 2026.06 - 2026.11, Research Intern, ByteDance Seed
  • 2025.11 - 2026.05, Research Intern, Shanghai AI Lab
  • 2025.09 - 2027.06 (Expected), Ph.D. Candidate, School of Mathematical Sciences, Peking University
  • 2025.05 - 2025.10, Research Intern @ Somersault Cloud Talent Program (筋斗云人才计划), ByteDance Flow
  • 2023.08 - 2023.12, Visiting Student, University of California Berkeley
  • 2021.06 - 2025.06, Undergraduate Student, School of Mathematical Sciences, Peking University

✨ Selected Publications

(${}^{\boldsymbol\dagger}$: Corresponding Author; *: Equal Contribution)

  • Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations
    Zeming Wei, Yifei Wang, Ang Li, Yichuan Mo, Yisen Wang
    Transactions on Pattern Analysis and Machine Intelligence (Cited 500+ times)
    [pdf] [arxiv]

  • On Mutation Testing of In-context Learning Systems
    Zeming Wei, Guanzhang Yue, Yihao Zhang, Meng Sun
    Journal of Systems Architecture
    [pdf]

  • RAPO: Risk-Aware Preference Optimization for Generalizable Safe Reasoning
    Zeming Wei, An Wang, Qiaosheng Zhang, Xia Hu, Xingcheng Xu
    EACL 2027 Findings
    [pdf]

  • ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction
    Zeming Wei, Chengcan Wu, Meng Sun
    FSE 2026
    [pdf]

  • AgentWorm: Self-Propagating Attacks Across LLM Agent Ecosystems
    Yihao Zhang*, Zeming Wei*, Xiaokun Luan, Chengcan Wu, Zhixin Zhang, Jiangrong Wu, Haolin Wu, Huanran Chen, Jun Sun, Meng Sun
    NDSS 2027
    [pdf]

  • SMI: Statistical Membership Inference for Reliable Unlearned Model Auditing
    Jialong Sun*, Zeming Wei*, Jiaxuan Zou*, Jiacheng Gong, Jie Fu, Chengyang Dong, Heng Xu, Jialong Li, Bo Liu
    NeurIPS 2026
    [pdf]

  • Stabilizing Multi-Attack Adversarial Training via Bandit Optimization
    Rui Wang*, Zeming Wei*, Xiyue Zhang, Meng Sun
    ACM MM 2026
    [pdf]

  • Symbolic-Neural Soft-Logic Reasoning: Towards Robust and Verifiable Thinking Chains via Cooperative Evolution
    Rui Wang, Zeming Wei${}^{\boldsymbol\dagger}$, Yihao Zhang, Xiaokun Luan
    EMNLP 2026 (Oral)
    [pdf]

  • SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces
    Chang Jin*, An Wang*, Zeming Wei*, Kai Wang, Biaojie Zeng, Qiaosheng Zhang, Chao Yang, Jingjing Qu, Xia Hu, Xingcheng Xu
    EMNLP 2026
    [pdf]

  • False Sense of Security: Why Probing-based Malicious Input Detection Fails to Generalize
    Cheng Wang*, Zeming Wei*, Qin Liu, Wenxuan Zhou, Muhao Chen
    ACL 2026 Findings
    [pdf]

  • Securing Multi-Agent Systems Against Corruptions via Node Contribution Backpropagation
    Chengcan Wu*, Zhixin Zhang*, Mingqian Xu, Zeming Wei${}^{\boldsymbol\dagger}$, Meng Sun${}^{\dagger}$
    ICML 2026
    [pdf]

  • Boosting Jailbreak Attack with Momentum
    Yihao Zhang*, Zeming Wei*${}^{\boldsymbol\dagger}$
    ICASSP 2025 (Oral)
    [pdf] [arxiv] [code]

  • Identifying and Understanding Cross-Class Features in Adversarial Training
    Zeming Wei, Yiwen Guo, Yisen Wang
    ICML 2025
    [pdf] [arxiv] [code]

  • On the Duality Between Sharpness-Aware Minimization and Adversarial Training
    Yihao Zhang*, Hangzhou He*, Jingyu Zhu*, Huanran Chen, Yifei Wang, Zeming Wei${}^{\boldsymbol\dagger}$
    ICML 2024
    [pdf] [arxiv] [code]

  • CFA: Class-wise Calibrated Fair Adversarial Training
    Zeming Wei, Yifei Wang, Yiwen Guo, Yisen Wang
    CVPR 2023 (Cited 100+ times)
    [pdf] [arxiv] [code]

  • Weighted Automata Extraction and Explanation of Recurrent Neural Networks for Natural Language Tasks
    Zeming Wei, Xiyue Zhang, Yihao Zhang, Meng Sun
    Journal of Logical and Algebraic Methods in Programming
    [pdf] [arxiv] [code]

💎 Grants

  • Adversarial Safety Testing and Defense of AI Foundation Models
    Principal Investigator, Beijing Natural Science Foundation (Grant No. QY24035)
    2024.10 - 2026.09

🏅 Honors and Awards

  • Merit Student (Top 10%), Peking University, 2026
  • Best Paper Award, ICFEM, 2025
  • Top Reviewer Award, NeurIPS, 2025
  • Outstanding Bachelor Dissertation Award (Top 3%), Peking University, 2025
  • Excellent Graduate of Beijing Municipal (Top 5%), Beijing Municipal Education Commission, 2025
  • Excellent Graduate of Peking University, Peking University, 2025
  • May 4th Scholarship (五四奖学金, Top 0.1%) [blog], the highest honor scholarship of Peking University, 2024
  • Academic Rising Star Award (Top 5 undergraduates university-wide) [blog], School of Computer Science, Peking University, 2024
  • Merit Student (Top 10%), Peking University, 2024
  • Best Paper Award, 1st ICML Workshop on In-Context Learning, 2024
  • Exceptional Award for Academic Innovation (Top 0.1%), Peking University, 2023
  • Merit Student (Top 10%), Peking University, 2023
  • Second prize, Chinese Mathematics Competitions for Undergraduates (National Final, Top 0.2%), 2023
  • First prize, Chinese Mathematics Competitions for Undergraduates (Beijing Division), 2022
  • Merit Student (Top 10%), Peking University, 2022
  • Award for Contribution in Student Organizations, Peking University, 2021

(Alphabetical Order)