Qiyao Xue

PhD Student in Data Science, University of North Carolina at Chapel Hill

qiyao_xue_pic.png

Chapel Hill, North Carolina, US

Hi! I’m Qiyao Xue (薛琪耀), a first-year PhD student in Data Science at the University of North Carolina at Chapel Hill, starting in Fall 2026.

My future research will center on agentic and self-evolving AI, particularly for healthcare. I am interested in developing agents that can reason, plan, act, use tools, learn from feedback, and improve over time, while integrating multimodal evidence across complex environments. A central goal of my work is to understand how such increasingly autonomous AI systems can become reliable and trustworthy collaborators in clinical practice.

Previously, I was a PhD student in the Department of Electrical and Computer Engineering at the University of Pittsburgh, where I worked on multimodal generative AI — bridging language, vision, and audio toward world models capable of perceiving, reasoning, and generating across modalities. Before that, I obtained my bachelor’s degree with first class honours at the Hong Kong Polytechnic University, majoring in Electrical Engineering with a minor in Applied Mathematics.

Contact: qiyaoxue@unc.edu

news

Sep 11, 2026 Paper accepted to MobiCom’26: SpatialMind: Spatially Aware On-Device Embodied AI via Viewpoint Integration
Aug 25, 2026 Started as a first-year PhD student in Data Science at the University of North Carolina at Chapel Hill, after moving on from the ECE PhD program at the University of Pittsburgh. New focus: agentic and self-evolving AI, particularly for healthcare.
Jul 03, 2026 Paper accepted to BioNLP’26 @ ACL 2026: KGRxn-LLM: Knowledge Graph Enhanced Large Language Models for Molecular Reaction Reasoning
Jun 17, 2026 Paper accepted to ECCV’26: Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspective
May 21, 2026 New preprint: CLORE: Content-Level Optimization for Reasoning Efficiency

selected publications

  1. Phyt2v: Llm-guided iterative self-refinement for physics-grounded text-to-video generation
    Qiyao Xue, Xiangyu Yin, Boyuan Yang, and 1 more author
    In Proceedings of the Computer Vision and Pattern Recognition Conference, 2025
  2. AAAI
    mmbert.png
    MMBERT: Scaled Mixture-of-Experts Multimodal BERT for Robust Chinese Hate Speech Detection under Cloaking Perturbations
    Qiyao Xue, Yuchen Dou, Ryan Shi, and 2 more authors
    In Annual AAAI Conference on Artificial Intelligence, 2026
  3. InfiniBench: Infinite Benchmarking for Visual Spatial Reasoning with Customizable Scene Complexity
    Haoming Wang, Qiyao Xue, and Wei Gao
    In Proceedings of the Computer Vision and Pattern Recognition Conference, 2026
  4. ProGait: A Multi-Purpose Video Dataset and Benchmark for Transfemoral Prosthesis Users
    Xiangyu Yin, Boyuan Yang, Weichen Liu, and 4 more authors
    In Proceedings of the International Conference on Computer Vision, 2025
  5. Reasoning Path and Latent State Analysis for Multi-view Visual Spatial Reasoning: A Cognitive Science Perspective
    Qiyao Xue, Weichen Liu, Shiqi Wang, and 3 more authors
    In Proceedings of the European Conference on Computer Vision, 2026
  6. SpatialMind: Spatially Aware On-Device Embodied AI via Viewpoint Integration
    Haoming Wang, Qiyao Xue, Weichen Liu, and 3 more authors
    In Proceedings of the Annual International Conference on Mobile Computing and Networking, 2026
  7. KGRxn-LLM: Knowledge Graph Enhanced Large Language Models for Molecular Reaction Reasoning
    Weichen Liu, Qiyao Xue, Yuyang Wu, and 2 more authors
    In Proceedings of the Workshop on Biomedical Natural Language Processing (BioNLP), 2026