Chejian Xu

CS Ph.D. Candidate · University of Illinois Urbana-Champaign

I am a fourth-year CS Ph.D. candidate at UIUC, advised by Prof. Bo Li. I received my B.S. in CS from Zhejiang University.

My research makes AI systems safe, scalable, and interpretable. I work on red-teaming that uncovers realistic agent failures, interpretability analysis of reasoning and hallucinations, and efficient post-training for reliable deployment.

Email Google Scholar GitHub LinkedIn
Portrait of Chejian Xu

Selected Publications

Full publication list available on my Google Scholar.

MAStrike: Shapley-Guided Collusive Red-Teaming on Multi-Agent Systems

Chejian Xu, Zhaorun Chen, Jingyang Zhang, Freddy Lecue, Avni Kothari, Sarah Tan, Wenbo Guo, Bo Li

Preprint 2026

PDF

From 128K to 4M: Efficient Training of Ultra-Long Context Large Language Models

Chejian Xu, Wei Ping, Peng Xu, Zihan Liu, Boxin Wang, Mohammad Shoeybi, Bo Li, Bryan Catanzaro

ACL 2026 (Findings)

PDF Website Model Weights 🤗

AdvAgent: Controllable Blackbox Red-teaming on Web Agents

Chejian Xu, Mintong Kang, Jiawei Zhang, Zeyi Liao, Lingbo Mo, Mengqi Yuan, Huan Sun, Bo Li

ICML 2025

PDF Code Website

MMDT: Decoding the Trustworthiness and Safety of Multimodal Foundation Models

Chejian Xu, Jiawei Zhang, Zhaorun Chen, Chulin Xie, Mintong Kang, Zhuowen Yuan, et al. (show all)

ICLR 2025

PDF Code Website T2I Dataset 🤗 I2T Dataset 🤗

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

Boxin Wang, Weixin Chen, Hengzhi Pei, Chulin Xie, Mintong Kang, …, Chejian Xu, et al. (show all)

NeurIPS 2023 · Outstanding Paper

PDF Code Website

SafeBench: A Benchmarking Platform for Safety Evaluation of Autonomous Vehicles

Chejian Xu*, Wenhao Ding*, Weijie Lyu, Zuxin Liu, Shuai Wang, Yihan He, Hanjiang Hu, Ding Zhao, Bo Li

NeurIPS 2022

PDF Code Leaderboard

Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models

Boxin Wang*, Chejian Xu*, Shuohang Wang, Zhe Gan, Yu Cheng, Jianfeng Gao, et al. (show all)

NeurIPS 2021 (Oral)

PDF Leaderboard Dataset

Experience

Service