Jacky Keung

Delving into Parameter-Efficient Fine-Tuning in Code Change Learning: An Empirical Study

2024

Compared to Full-Model Fine-Tuning (FMFT), Parameter Efficient Fine-Tuning (PEFT) has demonstrated superior performance and lower computational overhead in several code understanding tasks, such as code summarization and code search. This advantage can be attributed to …

Improving Learning Efficacy in Basic Programming Practice Based on Three-Stage Thinking

2025

Basic Programming Practice (BPP), as an introductory course for computer science majors, aims to enable students to have basic programming skills and lay a foundation for subsequent advanced course learning. This article draws on the …