Bowen Xu

Bowen Xu

Assistant Professor

Department of Computer Science
College of Engineering

Office: Engineering Building II (EB2), Room 3261
Email: bxu22@ncsu.edu

Research Focus

My research interests span software engineering, machine learning, and program analysis. My primary research interests are:

Large Language Model of Code

Empirical Studies of Pre-trained Language Models of Code [SANER-22] [ICPC-22]
Code Representation Enhancement [SANER-22] [FSE-22] [ICSME-23]
Model Compression [ASE-22]

Software Text Analytics for Software Automation

Interconnected Software Data Prediction [ESEM-18] [ASE-16]
Representation Learning of Software Data [TSE-21]
Sentiment Analysis for Software Engineering [ICSME-20]
Biases in Bug Report Analytics [TOSEM-22]

Understand and Assist Software Practice

Code Reuse and Re-implementation [EMSE-19]
Automatic Code Review [PAKDD-19]
Automatic Answer Summarization Tool for Technical Query [ICSE-23] [ASE-22] [ESEC/FSE-19] [ASE-17]
Automatic Relevant Question Retrival Tool for Technical Query [ESEC/FSE-17] [EMSE-17] [MSR-16]

News

Research Track

Forge 2024

Representation Learning for Stack Overflow Posts: How Far are We?

Technical Track

The Devil is in the Tails: An Exploratory Study on Long-tailed

Are We Ready to Embrace Generative AI for Software Q&A?

Self-Supervised Code Change Representation Learning

Supporting Collateral Evolution in Software Ecosystems

Software Ecosystems: Tooling and Analytics

Multi-Granularity Detector for Vulnerability Fixes

NIER Track

Technical Track

Demonstrations Track

Generation-based Code Review Automation: How Far Are We?

TECHSUMBOT: A Stack Overflow Answer Summarization Tool for Technical Query

Curiosity-Driven and Victim-Aware Adversarial Policies

Duplicate Bug Report Detection: How Far Are We?

Compressing Pre-trained Models of Code into 3 MB

Answer Summarization for Technical Queries: Benchmark and New Approach

How to Better Utilize Code Graphs in Semantic Code Search?

[Call For Paper]

the 6th edition of the MaLTeSQuE

PTM4Tag: Sharpening Tag Recommendation of Stack Overflow with Pre-trained Models

Aspect-Based API Review Classification: How Far Can Pre-Trained Transformer Model Go?

Can Identifier Splitting Improve Open-Vocabulary Language Model of Code?

Post2Vec: Learning Distributed Representations of Stack Overflow Posts

Bio

Dr. Bowen Xu is an Assistant Professor in the Department of Computer Science at North Carolina State University (NCSU). Prior he joining NCSU, he was a post-doctoral researcher in the School of Computing and Information Systems (SCIS) at Singapore Management University (SMU). He received his PhD degree from SCIS at SMU. His research interests lie primarily in the fields of machine learning and software engineering. Particularly, he focuses on securing AI models for SE tasks from both model and data perspectives. He co-organized an ESEC/FSE workshop MaLTeS in 2022 and served as PC and referee for many high-quality SE conferences and Journals, such as ICSE, FSE, TSE, TOSEM, etc. His works won several research paper awards. Contact him at: bxu22@ncsu.edu. More info at: https://www.bowenxu.me.