Hao Xu

My name is Hao Xu (许浩). I am a PhD student in the School of Mathematics and Statistics at the University of Sydney, Australia, supervised by Dr. Garth Tarr and Dr. Qiuzhuang Sun. My research interests include foundation models for decision-making, partially observable Markov decision processes (POMDPs), and AI/LLM applications in manufacturing and materials science. During my master’s studies, I worked on deep-learning-based anomaly detection in manufacturing scenarios and attention-based financial sentiment analysis.

Education:

• Ph.D. in Mathematics and Statistics, The University of Sydney
• MPhil in Smart Manufacturing, HKUST (Guangzhou)
• M.S. in Data Science, City University of Hong Kong
• B.Eng. in Materials Science and Engineering, Chongqing University

Selected Awards:

• Finalist in the Best Paper Competition at the 2025 INFORMS Conference on Quality, Statistics, and Reliability.

Papers: * indicates co-first authors. ^† indicates corresponding authors.

• FORGE: Fine-grained multimodal evaluation for manufacturing scenarios
  Xiangru Jian*, Hao Xu*^†, Wei Pang*, Xinjian Zhao, Chengyu Tao, Qixin Zhang, Xikun Zhang^†, Chao Zhang, Guanzhi Deng, Alex Xue, Juan Du, Tianshu Yu, Garth Tarr, Linqi Song, Qiuzhuang Sun, Dacheng Tao
  arXiv preprint arXiv:2604.07413.
• GraphOmni: A Comprehensive and Extendable Benchmark Framework for Large Language Models on Graph-theoretic Tasks
  Hao Xu*, Xiangru Jian*^†, Xinjian Zhao*, Wei Pang*, Chao Zhang, Suyucheng Wang, Qixin Zhang, Zhengyuan Dong, Joao Monteiro, Bang Liu, Qiuzhuang Sun, Tianshu Yu^†
  International Conference on Learning Representations (ICLR), 2026.
• F2PAD: A General Optimization Framework for Feature-Level to Pixel-Level Anomaly Detection
  C Tao, H Xu, J Du^†
  arXiv preprint arXiv:2407.06519.
• Ano-SuPs: Multi-size anomaly detection for manufactured products by identifying suspected patches
  H Xu, J Du^†, A Wang, YC Chen
  arXiv preprint arXiv:2309.11120.

Please find my full set of publications on my Google Scholar page.