• I am a third-year PhD student in Computer Science department at Rutgers University. I am fortunate to be advised by Prof. Yongfeng Zhang.
• My research interests lie at language agent, LLM-served system.

News

• [2024-09] 1 paper is accepted to EMNLP 2024 (Findings).
• [2024-09] I am invited as a reviewer of ICLR 2025.
• [2024-06] I am invited as a reviewer of ARR 2024 (Jun Cycle).
• [2024-05] I am invited as a reviewer of NeurIPS 2024.
• [2024-01] I am invited as a reviewer of ARR 2024 (Feb Cycle).
• [2023-09] 1 paper is accepted to NeurIPS 2023 (Dataset and Benchmark Track).
• [2023-09] I am invited as a reviewer of ICLR 2024.
• [2023-06] 1 paper is accepted to TSE 2023.
• [2023-05] 1 paper is accepted to ACL 2023.
• [2023-03] I am invited as a reviewer of NeurIPS 2023.
• [2023-01] 1 paper is selected as the spotlight by ICLR 2023.
• [2022-12] I am invited as a reviewer of ICLR 2023 BANDS.
• [2022-09] 1 paper is accepted to NeurIPS 2022.

Open-sourced Projects

• AIOS: LLM Agent Operating System (2.8k stars)
  Role: Maintainer

• OpenAGI: When LLM Meets Domain Experts (1.8k stars)
  Role: Maintainer

Preprints

• AIOS: LLM Agent Operating System
  Kai Mei, Zelong Li, Shuyuan Xu, Ruosong Ye, Yingqiang Ge, Yongfeng Zhang

• LightLM: A Lightweight Deep and Narrow Language Model for Generative Recommendation
  Kai Mei, Shuyuan Xu, Yongfeng Zhang

• War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars
  Wenyue Hua, Lizhou Fan, Lingyao Li, Kai Mei, Jianchao Ji, Yingqiang Ge, Libby Hemphill, Yongfeng Zhang

Selected Publications

• NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models
  Kai Mei, Zheng Li, Zhenting Wang, Yang Zhang, Shiqing Ma
  ACL 2023

• OpenAGI: When LLM Meets Domain Experts
  Yingqiang Ge, Wenyue Hua, Kai Mei, Jianchao Ji, Juntao Tan, Shuyuan Xu, Zelong Li, Yongfeng Zhang
  NeurIPS 2023 (Dataset and Benchmark Track)

• UNICORN: A Unified Backdoor Trigger Inversion Framework
  Zhenting Wang, Kai Mei, Juan Zhai, Shiqing Ma
  ICLR 2023

• Rethinking the Reverse-engineering of Trojan Triggers
  Zhenting Wang, Hailun Ding, Kai Mei, Juan Zhai, Shiqing Ma
  NeurIPS 2022

Service

• Reviewer, NeurIPS 2023, ICLR 2024, ARR 2024 (Feb Cycle, Jun Cycle), NeurIPS 2024
• Sub-Reviewer, CIKM 2023, KDD 2023, RecSys 2023, SIGIR 2024