Thank you for visiting! As a new beginning, I am maintaining my new homepage – still under construction and will be launched soon.

🐯 About Me

I am an incoming PhD student at UCLA starting in September 2025, under the supervision of Prof. Cho-Jui Hsieh.
I received my M.Phil. degree from The Hong Kong University of Science and Technology, supervised by Prof. Hao Liu and Prof. Hui Xiong. Prior to my MPhil, I received a Bachelor’s degree from the Department of Electronic Engineering at Tsinghua University, where I was fortunate to be advised by Prof. Yong LI.

My Research Interest

Previous Research Keywords: Urban Computing, Data Mining, Trustworthy Foundation Models.
Future: My primary research focus is on building and enhancing trustworthy foundation models (e.g., LLMs, VLMs). More specifically, (i) how to better develop FMs that maintain robust performance under varying conditions while ensuring harmless and reliable responses; (ii) how to further boost the performance of FMs without increasing model sizes or pre-training dataset sizes, particularly as the benefits from scaling laws begin to plateau.

Acknowledgment

I used to suffer from severe lumbar and heart disease from 2020 to 2022. Despite facing severe health issues, I persevered with the support of my family, friends, and supervisors, including Prof. Yong Li and Prof. Minghua Chen, as well as Dr. Junbo Zhang, Dr. Jie Feng, Dr. Yuanwei Fang, and Kai Zhao. I am deeply grateful for their help. After recovery, I am now determined and motivated to move on and make the best of each day.
I had a wonderful time at the USAIL group at HKUST, where I had the privilege of working with Prof. Hao Liu and Prof. Hui Xiong. I am deeply grateful for their guidance and support, which have been invaluable in shaping my research journey. I also sincerely appreciate the opportunity to be supervised by Prof. Bo Li during my internship. Under her mentorship, I learned how to conduct research more efficiently and effectively, and I am truly thankful for her generous encouragement, patience, and support.

Let’s Connect!

Feel free to reach out—whether it’s a quick question or something more in-depth! I’m always open to connecting and typically respond within 24 hours unless I’m on a tight deadline. You can reach me by email or on [Twitter/WeChat/LinkedIn—see the icons on the left]. If you’d like to schedule a quick call, you can simply click here to book a time on my Calendly. Looking forward to connecting!

Genius only means hard-working all one's life. (Mendeleev)

🔥 News

2025.05: I am honored to be recognized as an Outstanding Reviewer (Top 10%) for KDD 2025! I am grateful for the opportunity to contribute to the research community.
2025.04: 🎉🎉 Our work, LLMLight, received the 🏆 Special Grand Award & 🏆 Golden Medal (the highest award!!) at the 50th International Exhibition of Inventions Geneva. Many thanks to Siqi for his continuous dedication and to our advisors for their huge support!

Starting 2025.09, University of California, Los Angeles
Doctor of Philosophy, Department of Computer Science
2024.08 - 2024.12, The University of Chicago
Research Intern, Department of Computer Science
Supervisor: Prof. Bo Li
Project: Mitigating Hallucinations in LLMs through Collaborative Multi-Agent Systems.
2025 (Anticipated), The Hong Kong University of Science and Technology
Master of Philosophy, Department of Artificial Intelligence
Supervisor: Prof. Hao Liu Co-supervisor: Prof. Hui Xiong
Project: Jailbreak Defense, and Evaluation Strategies for Large Language Models; Applications of Foundation Models in Smart City Scenarios.
2022, Tsinghua University
Bachelor, Department of Electronic Engineering
Supervisor: Prof. Yong Li
2019.07 - 2019.10, Pennsylvania State University
Undergraduate Visiting Researcher, School of Electronic Engineering and Computer Science

^* indicates equal contribution, ^† indicates corresponding author.

NeurIPS 2024

“Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs”
[Github] [Media Coverage (🔥8k+ reads)] [1], [2], [3]
Zhao Xu, Fan Liu, Hao Liu^†
Annual Conference on Neural Information Processing Systems (NeurIPS), Vancouver, Canada, 2024

Arxiv 2024

KDD 2024

“Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Models”
[Github] , [Media Coverage (2k+ reads)]
Weijia Zhang, Jindong Han, Zhao Xu, Hang Ni, Hao Liu^†, Hui Xiong
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Barcelona, Spain, 2024

Arxiv 2024

“Large Language Models as Traffic Signal Control Agents: Capacity and Opportunity”
[Github] , [Project Page], [Demo], [Media Coverage (🔥14k+ reads)]
Siqi Lai, Zhao Xu, Weijia Zhang, Hao Liu^†, Hui Xiong
ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Toronto, Canada, 2025

TMC 2020 “DeepMM: Deep learning based map matching with data augmentation” (Extension of SIGSPATIAL 2019 Paper)
Jie Feng, Yong Li^†, Kai Zhao, Zhao Xu, Tong Xia, Lin Chen, Depeng Jin
IEEE Transactions on Mobile Computing (CCF A)
SIGSPATIAL 2019 “DeepMM: Deep learning based map matching with data augmentation”
Kai Zhao, Jie Feng, Zhao Xu, Tong Xia, Lin Chen, Funing Sun, Diansheng Guo, Depeng Jin, Yong Li^†
Proceedings of the 27th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (CORE Rank A, Acceptance Rate: 21%)

Outstanding Reviewer (Top 10%), KDD 2025
Special Grand Award & Golden Medal 2025 (Highest award), 50th International Exhibition of Inventions Geneva
Travel Grant for KDD 2024, HKUST
Postgraduate Scholarship (＄35,000 for stipend, ＄45,000 for HPC computing resource), HKUST
Scholarship for Outstanding Freshman (Full Tuition Waiver), Tsinghua University (Top 1%, 30 out of 3000)
Undergraduate Overseas Summer Research Scholarship, Tsinghua University
Outstanding Student in Work-Study Assistance, Tsinghua University

PC Member & Reviewer: NeurIPS’25, ACL ARR’25, KDD’25, COLING’25, ICLR’25, AI4Math@ICML’25, FM-Wild/SCI-FM@ICLR’25, MARW/AIGOV@AAAI’25, SafeGenAi@NeurIPS’24, LLMAgents@ICLR’24
External Reviewer: NeurIPS’23-25, KDD’24
Volunteer: KDD2024

2024.11: I’ll be presenting our latest work on benchmarking LLM jailbreaks at the AI Time Forum (in Chinese). If you’re interested in the topic, please join us at 3:30 PM on November 13. I will also serve as session chair for the afternoon session on November 19.

Last update: July 14, 2025