The ExRAIL Lab (Trustworthy AI Exploration Lab) at HKUST(GZ), directed by Prof. Sihong Xie, conducts research on trustworthy machine learning — explainability, uncertainty quantification, fairness, robustness, and reliability — with applications in graph learning, language models, multi-agent systems, and robotics.
Prof. Xie is a tenured Associate Professor, recipient of the NSF CAREER Award (2022) and 国家自然科学基金优秀青年科学基金项目（海外） (2024). He is the Executive Deputy Director of the HKUST(GZ)-Guangdong Unicom Joint Computing Lab, and serves on the executive committees of ACM SIGSPATIAL China, CCF-AI, and CCF-BigData. He has published 130+ papers (NeurIPS, ICML, ICLR, AAAI, IJCAI, KDD, ACL, CVPR, CIKM) with 3,200+ citations and an h-index of 24.
What this means for you: Prof. Xie serves as an Area Chair / Senior PC member for NeurIPS 2026 (also WWW 2025–2026, CIKM 2026, AAAI, SDM) and as a PC member for ICML (2023–2026), ICLR (2022–2026), KDD, ACL, ECCV, COLM, and UAI — you get first-hand exposure to how these venues judge a paper. He received his Ph.D. from the University of Illinois at Chicago under Prof. Philip S. Yu (IEEE Fellow). Research is supported by NSF (including a CAREER award), NSFC, the Tencent Rhino-bird Program, the HKUST(GZ)-Guangdong Unicom Joint Computing Lab, and industry collaborations — compute, data, and conference travel are covered.
Uncertainty quantification (conformal prediction, evidential learning) and explainability for graphs, LLMs, and agents — robust, calibrated models whose trustworthiness can be assessed and certified.
LLM interpretability (information flow, steering), faithfulness, VLM reasoning, knowledge-intensive LLM, and uncertainty attribution for AI agents across intent, tool use, and outcomes.
Safe RL, distributionally robust RL, scene graph navigation, and autonomous path-planning.
3D scene graphs, VLA (vision-language-action), retrieval-augmented 3D understanding, and efficient scene representation.
Uncertainty-aware and explainable AI for medical imaging, clinical data, and ICU/EHR — and for dispatch, forecasting, and decision-making in power systems and electricity markets.
Medical ImagingICU / EHREnergy Trading
What you can expect as a member of ExRAIL:
We welcome students with strong backgrounds in ML, math, and programming. Here’s how your interests map to our current work:
| Your Background | Research Topics | Current Members |
|---|---|---|
| LLM / NLP | LLM interpretability, steering, faithfulness, VLM reasoning | Rui Xu, Yazheng Liu, Xiaqiang Tang |
| RL / Robotics | Safe RL, distributionally robust RL, navigation, autonomous driving | Zhaofan Zhang, Rufeng Chen |
| CV / 3D Vision | 3D scene graphs, VLA, embodied AI, multi-modal learning | Yue Chang |
Funding (HKUST(GZ) standard — see the official site for the latest figures). Ph.D.: full scholarship, stipend ¥15,000/month (about ¥180,000/year) with tuition waived. MPhil: ¥10,000/month. RA: competitive salary plus project bonus. Conference travel is supported by the advisor’s grants. Guangzhou costs far less than Hong Kong (rent roughly ¥2,000–5,000 vs HK$8,000–15,000 per month), so the stipend goes further.
Email the following to sihongxie@hkust-gz.edu.cn with subject line: Prospective Student – Your Name – Expected Start (e.g., 2026 Fall)
Official application portal: HKUST(GZ) Fok Ying Tung Graduate School