講師

Gina Yu

PhD Candidate (Computer Science), MSc (Electronic Commerce and Internet Computing)

專業領域

AI
Education
Insurance

簡介

PhD Candidate in Computer Science at City University of Hong Kong, specializing in LLM-driven educational systems, InsurTech technologies, and AI-enabled software engineering. Research interests include insurance technology innovation, fraud detection and risk analytics, automated student feedback generation, scalable question-answering systems, and anomaly detection frameworks for complex data environments.

詳情

Education

  • PhD Candidate (Computer Science), City University of Hong Kong (CityU)
  • Master of Science in Electronic Commerce and Internet Computing, The University of Hong Kong (HKU)

Published Papers / Research Outputs

  • Yu, H. K.(and co-authors)(2025). Building Bridges to Student Growth: An LLM-Powered Feedback Generation System for Holistic Development.In Proceedings of the International Conference on Technology in Education (ICTE 2025), pp. 108–120.
  • Yu, H. K. (and co-authors) (2025). Towards Lightweight LLM Software Solutions for InsurTech: A Framework for Scalable Question Answering Systems, In Proceedings of the 32nd Asia-Pacific Software Engineering Conference (APSEC 2025).
  • Sun, Y.; Yu, H. K.; Keung, J.; Cao, Y.; Liao, Y. (2025). StuLAC: An Adaptive LLM-Driven Framework for Scalable Student Feedback Analysis in Software-Driven Educational Systems. In Proceedings of the IEEE 49th Annual International Computers, Software, and Applications Conference (COMPSAC 2025), pp. 121–130.
  • Sun, Y.; Yang, H.; Yu, H. K.; Suen, R. Boon or Bane? Evaluating AI-driven Learning Assistance in Higher Education Professional Coursework. Education and Information Technologies, online first, 34 pages.
  • Sun, Y.; Keung, J. W.; Yang, Z.; Liu, S.; Yu, H. K. SemiRALD: A Semi-supervised Hybrid Language Model for Robust Anomalous Log Detection. Information and Software Technology, Vol. 183, Article 107743, 19 pages.
  • Sun, Y.; Keung, J.; Yang, Z.; Liu, S.; Yu, H. K. Improving Anomaly Detection in Software Logs through Hybrid Language Modeling and Reduced Reliance on Parser. Automated Software Engineering, Vol. 33, No. 1, Article 12.
  • Sun, Y.; Keung, J.; Yu, H. K.; Liu, S.; Liao, Y.; Zhang, J. Beyond Log Parsers: A Scalable AI-Driven Framework for Efficient Log Anomaly Detection in Software Engineering.
  • Sun, Y.; Keung, J.; Zhang, J.; Yu, H. K.; Luo, W.; Liu, S. (2024). Unveiling Hidden Anomalies: Leveraging SMAC-LSTM for Enhanced Software Log Analysis. In Proceedings of the IEEE 48th Annual International Computers, Software, and Applications Conference (COMPSAC 2024), pp. 1178–1183.

Licenses & certifications

  • Google AI
  • Gemini Certified Educator
  • AWS Certified AI Practitioner