8 papers
MOA: A Profiling-Guided LLM Framework for Memory-Optimization Automation at Codebase Scale
Jiaxi Liang, Yuanxiang Shi, Zezhou Yang +1
Modern large-scale software systems often suffer from pervasive memory inefficiencies (e.g., bloat, churn), leading to excessive resource costs and performance degradation. Existin…
Cascaded Code Editing: Large-Small Model Collaboration for Effective and Efficient Code Editing
Chaozheng Wang, Zezhou Yang, Shuzheng Gao +7
Code editing constitutes a fundamental practice in software development, wherein developers modify existing codebases according to natural language requirements. Accurate code edit…
A Roadmap on Modern Code Review: Challenges and Opportunities
Zezhou Yang, Cuiyun Gao, Zhaoqiang Guo +4
Over the past decade, modern code review (MCR) has been established as a cornerstone of software quality assurance and a vital channel for knowledge transfer within development tea…
Automated Prompt Generation for Code Intelligence: An Empirical study and Experience in WeChat
Kexing Ji, Shiyun Fu, Cuiyun Gao +4
Large Code Models (LCMs) show potential in code intelligence, but their effectiveness is greatly influenced by prompt quality. Current prompt design is mostly manual, which is time…
An Empirical Study of Knowledge Distillation for Code Understanding Tasks
Ruiqi Wang, Zezhou Yang, Cuiyun Gao +2
Pre-trained language models (PLMs) have emerged as powerful tools for code understanding. However, deploying these PLMs in large-scale applications faces practical challenges due t…
A Deep Dive into Retrieval-Augmented Generation for Code Completion: Experience on WeChat
Zezhou Yang, Ting Peng, Cuiyun Gao +3
Code completion, a crucial task in software engineering that enhances developer productivity, has seen substantial improvements with the rapid advancement of large language models…