6 papers
CAMGen: A Core Change-Aware Multi-View Framework for Commit Message Generation
Bo Xiong, Weisheng Chen, Zongen Ren +5
Commit messages help developers understand code changes and support software maintenance. Recent approaches use repository context to improve commit message generation (CMG) with l…
FeatLens: Feature-Guided Dynamic Code Graph Construction and Retrieval for Repository-Level Code Generation
Xutian Li, Bo Xiong, Yifeng Zhu +6
Recent code generation research has moved from isolated function completion toward repository-level generation in existing codebases. To implement a target function correctly, an L…
LLM-Enhanced Commit Message Generation via Issue Information: An Exploratory Study
Zongen Ren, Wei Shi, Bo Xiong +2
Commit messages help developers understand code changes, support collaboration, and improve long-term maintenance. However, the use of issue information alone as the external conte…
CoRaCMG: Contextual Retrieval-Augmented Framework for Commit Message Generation
Bo Xiong, Linghao Zhang, Zongen Ren +2
Commit messages play a key role in documenting the intent behind code changes. However, they are often low-quality, vague, or incomplete, limiting their usefulness. Commit Message…
Contextual Code Retrieval for Commit Message Generation: A Preliminary Study
Bo Xiong, Linghao Zhang, Chong Wang +1
A commit message describes the main code changes in a commit and plays a crucial role in software maintenance. Existing commit message generation (CMG) approaches typically frame i…
Geometric Relational Embeddings
Bo Xiong
Relational representation learning transforms relational data into continuous and low-dimensional vector representations. However, vector-based representations fall short in captur…