People › Dr. Xiao Yu
Dr. Xiao Yu
余嘯 PhD Graduate (2021) 2021Now Research Fellow, State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China
Personal website ↗About
Dr. Xiao Yu is a PhD graduate in the Department of Computer Science, City University of Hong Kong.
Now Research Fellow, State Key Laboratory of Blockchain and Data Security, Zhejiang University, Hangzhou, China.
Research Interests
Publications (38)
- R2ComSync: improving code-comment synchronization with in-context learning and reranking.
- HumanEval-V: Systematic Evaluation of Visual Reasoning in Large Multimodal Models for Code Generation
- An Empirical Study of Perceptions of General LLMs and Multimodal LLMs on Hugging Face.
- Towards Understanding Bugs in Distributed Training and Inference Frameworks for Large Language Models.
- RealisticCodeBench: Towards More Realistic Evaluation of Large Language Models for Code Generation.
- Practitioners' Expectations on Log Anomaly Detection.
- On the Influence of Data Resampling for Deep Learning-Based Log Anomaly Detection: Insights and Recommendations.
- NegCPARBP: Enhancing Privacy Protection for Cross-Project Aging-Related Bug Prediction Based on Negative Database.
- Lightweight Model Editing for LLMs to Correct Deprecated API Recommendations.
- Less Is More: Unlocking Semi-Supervised Deep Learning for Vulnerability Detection.
- Large language model ChatGPT versus small deep learning models for self-admitted technical debt detection: Why not together?
- Where Are Large Language Models for Code Generation on GitHub?
- Practitioners' Expectations on Automated Test Generation.
- Improving the undersampling technique by optimizing the termination condition for software defect prediction.
- Improving effort-aware defect prediction by directly learning to rank software modules.
- HumanEval-V: Evaluating Visual Understanding and Reasoning Abilities of Large Multimodal Models Through Coding Tasks.
- Fight Fire with Fire: How Much Can We Trust ChatGPT on Source Code-Related Tasks?
- Data preparation for Deep Learning based Code Smell Detection: A systematic literature review.
- A multi-objective effort-aware defect prediction approach based on NSGA-II.
- A Semisupervised Approach for Industrial Anomaly Detection via Self-Adaptive Clustering.