徐博文｜宁波大学｜学者主页

2026

Cross-Provider Review as a Runtime Contract for Coding Agents: A Controlled Pilot and Fault-Injection Study

Bowen Xu, Boyu Chen

arXiv preprint

2026

What Does a Harness Repair? A Preregistered Study of Visibility, Baseline Adequacy and Evaluation Defects

Bowen Xu, Boyu Chen

arXiv preprint

2026

SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces

Rongxue Li, Meng Yang, Yiru Mao, Yongliang Tao, Lulu Hu, Bin Yang, Zhao Xu, Weihua Luo, Bowen Xu

arXiv preprint

2026

AEGIS: From Clues to Verdicts -- Graph-Guided Deep Vulnerability Reasoning via Dialectics and Meta-Auditing

Sen Fang, Weiyuan Ding, Zhezhen Cao, Zhou Yang, Bowen Xu

arXiv preprint

2026

Large Language Models for Code Generation from Multilingual Prompts: A Curated Benchmark and a Study on Code Quality

Saima Afrin, Alessandro Midolo, Camilo Escobar-Velásquez, Mario Linares-Vásquez, Weiyuan Ding, Bowen Xu, Massimiliano Di Penta, Antonio Mastropaolo

arXiv preprint

2026

How Do Developers Interact with AI? An Exploratory Study on Modeling Developer Programming Behavior

Yinan Wu, Ze Shi Li, Kathryn Thomasset Stolee, Bowen Xu

arXiv preprint

2025

EVALOOOP: A Self-Consistency-Centered Framework for Assessing Large Language Model Robustness in Programming

Sen Fang, Weiyuan Ding, Mengshi Zhang, Zihao Chen, Bowen Xu

arXiv preprint

2025

Curiosity-Driven Testing for Sequential Decision-Making Process

Junda He, Zhou Yang, Jieke Shi, Chengran Yang, Kisub Kim, Bowen Xu, Xin Zhou, David Lo

arXiv preprint

2025

Signature in Code Backdoor Detection, how far are we?

Quoc Hung Le, Thanh Le-Cong, Bach Le, Bowen Xu

arXiv preprint

2025

Smart Cuts: Enhance Active Learning for Vulnerability Detection by Pruning Hard-to-Learn Data

Xiang Lan, Tim Menzies, Bowen Xu

arXiv preprint

2025

Capturing the Effects of Quantization on Trojans in Code LLMs

Aftab Hussain, Sadegh AlMahdi Kazemi Zarkouei, Md Rafiqul Islam Rabin, Mohammad Amin Alipour, Sen Lin, Bowen Xu

arXiv preprint

2025

Understanding the Effectiveness of LLMs in Automated Self-Admitted Technical Debt Repayment

Mohammad Sadegh Sheikhaei, Yuan Tian, Shaowei Wang, Bowen Xu

arXiv preprint

2025

Secure or Suspect? Investigating Package Hallucinations of Shell Command in Original and Quantized LLMs

Md Nazmul Haque, Elizabeth Lin, Lawrence Arkoh, Biruk Tadesse, Bowen Xu

arXiv preprint

2025

Smaller = Weaker? Benchmarking Robustness of Quantized LLMs in Code Generation

Sen Fang, Weiyuan Ding, Antonio Mastropaolo, Bowen Xu

arXiv preprint

2025

How Quantization Impacts Privacy Risk on LLMs for Code?

Md Nazmul Haque, Hua Yang, Zhou Yang, Bowen Xu

arXiv preprint

2025

Understanding Privacy Risks in Code Models Through Training Dynamics: A Causal Approach

Hua Yang, Alejandro Velasco, Sen Fang, Bowen Xu, Denys Poshyvanyk

arXiv preprint

2025

Context-Enhanced Vulnerability Detection Based on Large Language Model

Yixin Yang, Bowen Xu, Xiang Gao, Hailong Sun

arXiv preprint

2025

Understanding Codebase like a Professional! Human-AI Collaboration for Code Comprehension

Jie Gao, Yue Xue, Xiaofei Xie, SoeMin Thant, Erika Lee, Bowen Xu

arXiv preprint

2025

How Do Semantically Equivalent Code Transformations Impact Membership Inference on LLMs for Code?

Hua Yang, Alejandro Velasco, Thanh Le-Cong, Md Nazmul Haque, Bowen Xu, Denys Poshyvanyk

arXiv preprint

DOI

2025

Is Quantization a Deal-breaker? Empirical Insights from Large Code Models

Saima Afrin, Bowen Xu, Antonio Mastropaolo

arXiv preprint

2024

Towards Agentic Runtime Healing

Zhensu Sun, Haotian Zhu, Bowen Xu, Xiaoning Du, Li Li, David Lo

arXiv preprint

2024

A Case Study of LLM for Automated Vulnerability Repair: Assessing Impact of Reasoning and Patch Validation Feedback

Ummay Kulsum, Haotian Zhu, Bowen Xu, Marcelo d'Amorim

arXiv preprint

2024

Trojans in Large Language Models of Code: A Critical Review through a Trigger-Based Taxonomy

Aftab Hussain, Md Rafiqul Islam Rabin, Toufique Ahmed, Bowen Xu, Premkumar Devanbu, Mohammad Amin Alipour

arXiv preprint

2024

AI Tool Use and Adoption in Software Development by Individuals and Organizations: A Grounded Theory Study

Ze Shi Li, Nowshin Nawar Arony, Ahmed Musa Awon, Daniela Damian, Bowen Xu

arXiv preprint

2024

An Empirical Study on the Effectiveness of Large Language Models for SATD Identification and Classification

Mohammad Sadegh Sheikhaei, Yuan Tian, Shaowei Wang, Bowen Xu

arXiv preprint

2024

Finding Safety Violations of AI-Enabled Control Systems through the Lens of Synthesized Proxy Programs

Jieke Shi, Zhou Yang, Junda He, Bowen Xu, Dongsun Kim, DongGyun Han, David Lo

arXiv preprint

2024

Multi-LLM Collaboration + Data-Centric Innovation = 2x Better Vulnerability Repair

Xin Zhou, Kisub Kim, Bowen Xu, DongGyun Han, David Lo

arXiv preprint

2023

Stealthy Backdoor Attack for Code Models

Zhou Yang, Bowen Xu, Jie M. Zhang, Hong Jin Kang, Jieke Shi, Junda He, David Lo

arXiv preprint

2023

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

Bowen Xu, Thanh-Dat Nguyen, Thanh Le-Cong, Thong Hoang, Jiakun Liu, Kisub Kim, Chen Gong, Changan Niu, Chenyu Wang, Bach Le, David Lo

arXiv preprint

2023

Prioritizing Speech Test Cases

Zhou Yang, Jieke Shi, Muhammad Hilmi Asyrofi, Bowen Xu, Xin Zhou, DongGyun Han, David Lo

arXiv preprint

2023

CCBERT: Self-Supervised Code Change Representation Learning

Xin Zhou, Bowen Xu, DongGyun Han, Zhou Yang, Junda He, David Lo

arXiv preprint

2023

Automated DevOps Pipeline Generation for Code Repositories using Large Language Models

Deep Mehta, Kartik Rawool, Subodh Gujar, Bowen Xu

arXiv preprint

2023

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

Xin Zhou, Kisub Kim, Bowen Xu, DongGyun Han, Junda He, David Lo

arXiv preprint

2023

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

Junda He, Zhou Xin, Bowen Xu, Ting Zhang, Kisub Kim, Zhou Yang, Ferdian Thung, Ivana Irsan, David Lo

arXiv preprint

2023

Greening Large Language Models of Code

Jieke Shi, Zhou Yang, Hong Jin Kang, Bowen Xu, Junda He, David Lo

arXiv preprint

DOI

2023

A Survey of Trojans in Neural Models of Source Code: Taxonomy and Techniques

Aftab Hussain, Md Rafiqul Islam Rabin, Toufique Ahmed, Navid Ayoobi, Bowen Xu, Prem Devanbu, Mohammad Amin Alipour

arXiv preprint

2023

Multi-Granularity Detector for Vulnerability Fixes

Truong Giang Nguyen, Thanh Le-Cong, Hong Jin Kang, Ratnadira Widyasari, Chengran Yang, Zhipeng Zhao, Bowen Xu, Jiayuan Zhou, Xin Xia, Ahmed E. Hassan, Xuan-Bach D. Le, David Lo

arXiv preprint

2023

The Devil is in the Tails: How Long-Tailed Code Distributions Impact Large Language Models

Xin Zhou, Kisub Kim, Bowen Xu, Jiakun Liu, DongGyun Han, David Lo

arXiv preprint

2023

Occlusion-based Detection of Trojan-triggering Inputs in Large Language Models of Code

Aftab Hussain, Md Rafiqul Islam Rabin, Toufique Ahmed, Mohammad Amin Alipour, Bowen Xu

arXiv preprint

2023

Unveiling Inclusiveness-Related User Feedback in Mobile Applications

Nowshin Nawar Arony, Ze Shi Li, Daniela Damian, Bowen Xu

arXiv preprint

2023

APIDocBooster: An Extract-Then-Abstract Framework Leveraging Large Language Models for Augmenting API Documentation

Chengran Yang, Jiakun Liu, Bowen Xu, Christoph Treude, Yunbo Lyu, Junda He, Ming Li, David Lo

arXiv preprint

2023

PatchZero: Zero-Shot Automatic Patch Correctness Assessment

Xin Zhou, Bowen Xu, Kisub Kim, DongGyun Han, Thanh Le-Cong, Junda He, Bach Le, David Lo

arXiv preprint

2023

A Study of Variable-Role-based Feature Enrichment in Neural Models of Code

Aftab Hussain, Md Rafiqul Islam Rabin, Bowen Xu, David Lo, Mohammad Amin Alipour

arXiv preprint

2022

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

Jieke Shi, Zhou Yang, Junda He, Bowen Xu, David Lo

arXiv preprint

2022

Compressing Pre-trained Models of Code into 3 MB

Jieke Shi, Zhou Yang, Bowen Xu, Hong Jin Kang, David Lo

arXiv preprint

2022

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

Junda He, Bowen Xu, Zhou Yang, DongGyun Han, Chengran Yang, David Lo

arXiv preprint

DOI

2022

Duplicate Bug Report Detection: How Far Are We?

Ting Zhang, DongGyun Han, Venkatesh Vinayakarao, Ivana Clairine Irsan, Bowen Xu, Ferdian Thung, David Lo, Lingxiao Jiang

arXiv preprint

DOI

2022

BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets

Chen Gong, Zhou Yang, Yunpeng Bai, Junda He, Jieke Shi, Kecen Li, Arunesh Sinha, Bowen Xu, Xinwen Hou, David Lo, Tianhao Wang

arXiv preprint

2022

Answer Summarization for Technical Queries: Benchmark and New Approach

Yang Chengran, Bowen Xu, Ferdian Thung, Yucen Shi, Ting Zhang, Zhou Yang, Xin Zhou, Jieke Shi, Junda He, DongGyun Han, David Lo

arXiv preprint

2022

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

chengran Yang, Bowen Xu, Junaed younus Khan, Gias Uddin, Donggyun Han, Zhou Yang, David Lo

arXiv preprint

2019

Question Relatedness on Stack Overflow: The Task, Dataset, and Corpus-inspired Models

Amirreza Shirani, Bowen Xu, David Lo, Thamar Solorio, Amin Alipour

arXiv preprint

2019

Ques-Chain: an Ethereum Based E-Voting System

Qixuan Zhang, Bowen Xu, Haotian Jing, Zeyu Zheng

arXiv preprint

精选作品

期刊论文

API-GRPO: Multi-task Fine-Tuning with Group Relative Policy Optimization for Security-Sensitive API Misuse Analysis

基于幻方变换的HEVC熵编码加密方案

Web实时会话劫持攻击与防范研究

预印本

Cross-Provider Review as a Runtime Contract for Coding Agents: A Controlled Pilot and Fault-Injection Study

What Does a Harness Repair? A Preregistered Study of Visibility, Baseline Adequacy and Evaluation Defects

SpatialOPSD: Self-Distilling Spatial Intelligence from Verified Coding Agent Traces

AEGIS: From Clues to Verdicts -- Graph-Guided Deep Vulnerability Reasoning via Dialectics and Meta-Auditing

Large Language Models for Code Generation from Multilingual Prompts: A Curated Benchmark and a Study on Code Quality

How Do Developers Interact with AI? An Exploratory Study on Modeling Developer Programming Behavior

EVALOOOP: A Self-Consistency-Centered Framework for Assessing Large Language Model Robustness in Programming

Curiosity-Driven Testing for Sequential Decision-Making Process

Signature in Code Backdoor Detection, how far are we?

Smart Cuts: Enhance Active Learning for Vulnerability Detection by Pruning Hard-to-Learn Data

Capturing the Effects of Quantization on Trojans in Code LLMs

Understanding the Effectiveness of LLMs in Automated Self-Admitted Technical Debt Repayment

Secure or Suspect? Investigating Package Hallucinations of Shell Command in Original and Quantized LLMs

Smaller = Weaker? Benchmarking Robustness of Quantized LLMs in Code Generation

How Quantization Impacts Privacy Risk on LLMs for Code?

Understanding Privacy Risks in Code Models Through Training Dynamics: A Causal Approach

Context-Enhanced Vulnerability Detection Based on Large Language Model

Understanding Codebase like a Professional! Human-AI Collaboration for Code Comprehension

How Do Semantically Equivalent Code Transformations Impact Membership Inference on LLMs for Code?

Is Quantization a Deal-breaker? Empirical Insights from Large Code Models

Towards Agentic Runtime Healing

A Case Study of LLM for Automated Vulnerability Repair: Assessing Impact of Reasoning and Patch Validation Feedback

Trojans in Large Language Models of Code: A Critical Review through a Trigger-Based Taxonomy

AI Tool Use and Adoption in Software Development by Individuals and Organizations: A Grounded Theory Study

An Empirical Study on the Effectiveness of Large Language Models for SATD Identification and Classification

Finding Safety Violations of AI-Enabled Control Systems through the Lens of Synthesized Proxy Programs

Multi-LLM Collaboration + Data-Centric Innovation = 2x Better Vulnerability Repair

Stealthy Backdoor Attack for Code Models

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

Prioritizing Speech Test Cases

CCBERT: Self-Supervised Code Change Representation Learning

Automated DevOps Pipeline Generation for Code Repositories using Large Language Models

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

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

Greening Large Language Models of Code

A Survey of Trojans in Neural Models of Source Code: Taxonomy and Techniques

Multi-Granularity Detector for Vulnerability Fixes

The Devil is in the Tails: How Long-Tailed Code Distributions Impact Large Language Models

Occlusion-based Detection of Trojan-triggering Inputs in Large Language Models of Code

Unveiling Inclusiveness-Related User Feedback in Mobile Applications

APIDocBooster: An Extract-Then-Abstract Framework Leveraging Large Language Models for Augmenting API Documentation

PatchZero: Zero-Shot Automatic Patch Correctness Assessment

A Study of Variable-Role-based Feature Enrichment in Neural Models of Code

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

Compressing Pre-trained Models of Code into 3 MB

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

Duplicate Bug Report Detection: How Far Are We?

BAFFLE: Hiding Backdoors in Offline Reinforcement Learning Datasets

Answer Summarization for Technical Queries: Benchmark and New Approach

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

Question Relatedness on Stack Overflow: The Task, Dataset, and Corpus-inspired Models

Ques-Chain: an Ethereum Based E-Voting System

研究方向