Xu Hu

Google Scholar · GitHub · Richardson, TX, USA

Las Vegas, NV

I'm a Ph.D. student in Computer Science at the University of Texas at Dallas (UT Dallas) since fall 2025. My research focuses on computer-use agents and AI safety — building agents that automate computer work and understanding how to make them trustworthy and reliable.

Before UT Dallas, I earned my B.S. in Statistics from Anhui University in 2025, where I ranked 1st in my major. I've been fortunate to do research at the TReNDS Lab at Georgia Tech (ECE) with Vince D. Calhoun, at NC State (ISE) with Xiaolei Fang and Shu-Cherng Fang, and at HKUST (Guangzhou) with Yuxuan Liang and Zhengyang Zhou.

News

Jul 30, 2026 Our paper Small Updates, Big Doubts, on hallucination detection, was accepted for publication in Transactions on Machine Learning Research (TMLR). This is the first paper from my Ph.D. research!
Jun 2026 New preprint: No Hidden Prompts Needed! — gaming AI peer review with presentation-only revisions.
May 2026 New preprint: LEAD — length-efficient adaptive and dynamic reasoning for LLMs.
2026 New survey: Toward Trustworthy Computer-Use Agents — risk propagation, evaluation gaps, and human governance.
Feb 2026 Two new preprints: Small Updates, Big Doubts (hallucination detection) and Anatomy of Agentic Memory.
Oct 2025 Paper at IEEE MASS 2025: Can Large Language Models Be Trusted Paper Reviewers?
Sep 2025 GM-LDM accepted to the PRIME 2025 workshop at MICCAI 2025.
Aug 2025 Started my Ph.D. in Computer Science at UT Dallas.

Older news

2025 Graduated with a B.S. in Statistics from Anhui University (rank 1/103).
Aug 2024 Research intern at NC State (ISE, Edward P. Fitts Dept.) with Xiaolei Fang and Shu-Cherng Fang.
Jun 2024 Research intern at the TReNDS Lab (GSU / Georgia Tech / Emory) with Vince D. Calhoun, and at HKUST (Guangzhou) with Yuxuan Liang and Zhengyang Zhou.
Feb 2023 Finalist, ICM (Interdisciplinary Contest in Modeling).

Academic Service

Reviewer for the Journal of Data Science and Analysis, KDD, NeurIPS, and Frontiers.