---

Biography

My research focuses on building trustworthy AI agents that can reason, learn, and adapt in complex real-world environments. I study how foundation models can acquire reliable reasoning capabilities, learn from experience, and improve through principled feedback and self-improvement mechanisms. My research spans three interconnected areas: (1) Trustworthy AI Agents, (2) Reliable Foundation Models, and (3) Robust Machine Learning. My long-term goal is to establish the foundations for intelligent systems that are both capable and dependable in real-world applications.

I am currently a Research Assistant Professor at the Hong Kong University of Science and Technology (HKUST), collaborating with Prof. Yike Guo (Fellow of IEEE and Royal Academy of Engineering). Prior to joining HKUST, I was a Postdoctoral Fellow at Hong Kong Baptist University (HKBU), working with Prof. Yiu-ming Cheung (IEEE Fellow) and Prof. Bo Han. I obtained my Ph.D. degree from the University of Science and Technology of China (USTC) in June 2022 under the supervision of Prof. Xinmei Tian.

---

Research Interests

My research interests center on:


• Trustworthy AI Agents: reliable reasoning, agent self-improvement, feedback-driven learning, and trustworthy agentic systems.


• Reliable Foundation Models: LLM reasoning and alignment, model adaptation, uncertainty, and reliability of foundation models.


• Robust Machine Learning: robustness under distribution shifts, adversarial robustness, and reliable learning in imperfect environments.

---

Selected News

• 2026: Our work Conditional Equivalence of DPO and RLHF: Implicit Assumption, Failure Modes, and Provable Alignment was selected as an ICML 2026 Spotlight.


• 2026: Our works on LLM self-improvement and knowledge-base question answering were accepted to ICLR 2026.


• 2026: I joined HKUST as a Research Assistant Professor.


• 2025: Our work Detecting Generated Images by Fitting Natural Image Distributions was selected as a NeurIPS 2025 Spotlight.

---

Research Experience

• Research Assistant Professor (Feb 2026 -- Present)

Hong Kong University of Science and Technology (HKUST)
Research: Trustworthy AI Agents, Reliable Foundation Models, and Robust Machine Learning

• Post-Doctoral Fellow (Jun 2025 -- Feb 2026)

Hong Kong University of Science and Technology (HKUST)
Advisor: Prof. Yike Guo (Fellow of IEEE and Royal Academy of Engineering)
Research: Trustworthy AI, Foundation Models, and Machine Reasoning

• Post-Doctoral Fellow (Aug 2022 -- Jun 2025)

Hong Kong Baptist University (HKBU)
Advisors: Prof. Yiu-ming Cheung (IEEE Fellow) and Prof. Bo Han
Research: Robust and Trustworthy Machine Learning

• Research Assistant (Dec 2020 -- Jul 2022)

University of Science and Technology of China (USTC)
Advisor: Prof. Bo Han
Research: Adversarial Robustness and Robust Machine Learning

---

Education

• Ph.D. in Information and Communication Engineering (Sep 2017 -- Jun 2022)

University of Science and Technology of China (USTC), China
Thesis: Adversarial Robustness of Deep Learning through the Lens of Data Distribution
Supervised by Prof. Xinmei Tian



• Bachelor of Electronic Information Engineering (Sep 2013 -- Jul 2017)

China University of Petroleum (East China), Qingdao, China
Thesis: Research on Adversarial Examples
Supervisors: Yanjiang Wang and Weifeng Liu