5 citations · 16 across the 10 of their papers we have counts for
5 papers · 1 filter
Standards-Guided and Dependency-Aware Code-Level Documentation Generation
Tingxu Han, Wei Song, Ziming Li +6
Automatically generating high-quality documentation for software repositories remains challenging: existing approaches largely treat documentation as unconstrained text generation,…
Enhancing and Reporting Robustness Boundary of Neural Code Models for Intelligent Code Understanding
Tingxu Han, Wei Song, Weisong Sun +6
With the development of deep learning, Neural Code Models (NCMs) such as CodeBERT and CodeLlama are widely used for code understanding tasks, including defect detection and code cl…
SWE-Skills-Bench: Do Agent Skills Actually Help in Real-World Software Engineering?
Tingxu Han, Yi Zhang, Wei Song +4
Agent skills, structured procedural knowledge packages injected at inference time, are increasingly used to augment LLM agents on software engineering tasks. However, their real ut…
Security of Language Models for Code: A Systematic Literature Review
Yuchen Chen, Weisong Sun, Chunrong Fang +7
Language models for code (CodeLMs) have emerged as powerful tools for code-related tasks, outperforming traditional methods and standard machine learning approaches. However, these…
An Extractive-and-Abstractive Framework for Source Code Summarization
Weisong Sun, Chunrong Fang, Yuchen Chen +6
(Source) Code summarization aims to automatically generate summaries/comments for a given code snippet in the form of natural language. Such summaries play a key role in helping de…