Publications
[J22]Resource-efficient automatic software vulnerability assessment via knowledge distillation and particle swarm optimization
Chaoyang Gao, Xiang Chen💌, Jiyu Wang, Jibin Wang, Guang Yang
Engineering Applications of Artificial Intelligence 2025EAAI'25
A resource-efficient framework integrating particle swarm optimization and knowledge distillation.
[J21]Large Language Model for Verilog Code Generation: Literature Review and the Road Ahead
Guang Yang, Wei Zheng💌, Xiang Chen, Dong Liang, Peng Hu, Yukui Yang, Shaohua Peng, Zhenghan Li, Jiahui Feng, Xiao Wei, Kexin Sun, Deyuan Ma, Haotian Cheng, Yiheng Shen, Xing Hu💌, Terry Yue Zhuo, David Lo
Preprints 2025Preprints'25
A comprehensive literature review of LLMs for Verilog code generation, highlighting their strengths, limitations, and potential applications.
[C18]Evaluating and Improving Framework-based Parallel Code Completion with Large Language Models
Ke Liu, Qinglin Wang, Xiang Chen, Guang Yang, YiGui Feng, Gencheng Liu, Jie Liu💌
Proceedings of the 40th IEEE/ACM International Conference on Automated Software Engineering 2025ASE'25
A novel framework-based parallel code completion method for code generation, balancing accuracy, efficiency and explainability.
[C17]Code-DiTing: Automatic Evaluation of Code Generation without References or Test Cases
Guang Yang, Yu Zhou💌, Xiang Chen, Wei Zheng, Xing Hu, Xin Zhou, David Lo, Taolue Chen💌
Proceedings of the 40th IEEE/ACM International Conference on Automated Software Engineering 2025ASE'25
A novel LLM-as-Judge method for code evaluation, balancing accuracy, efficiency and explainability.
[C16]SE-Jury: An LLM-as-Ensemble-Judge Metric for Narrowing the Gap with Human Evaluation in SE
Xin Zhou, Kisub Kim, Ting Zhang, Martin Weyssow, Luis F. Gomes, Guang Yang, Kui Liu, Xin Xia, David Lo💌
Proceedings of the 40th IEEE/ACM International Conference on Automated Software Engineering 2025ASE'25
A novel LLM-as-Ensemble-Judge metric for SE, balancing accuracy, efficiency and explainability.
[J20]The Cream Rises to the Top: Efficient Reranking Method for Verilog Code Generation
Guang Yang, Wei Zheng💌, Xiang Chen, Yifan Sun, Fengji Zhang, Terry Yue Zhuo
arXiv 2025arXiv'25
A novel reranking method for Verilog code generation, highlighting their strengths, limitations, and potential applications.
[C15]Beyond Sequences: Two-dimensional Representation and Dependency Encoding for Code Generation
Xiangyu Zhang, Yu Zhou💌, Guang Yang, Wei Cheng, Taolue Chen💌
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics 2025ACL'25
A novel dependency encoding approach for code generation, highlighting its generalizability, context understanding and retrieval, as well as interpretability in code generation.
[J19]Anchor Attention, Small Cache: Code Generation With Large Language Models
Xiangyu Zhang, Yu Zhou💌, Guang Yang, Harald C. Gall, Taolue Chen💌
IEEE Transactions on Software Engineering 2025TSE'25
A novel attention mechanism and cache mechanism for code generation with LLMs, achieving significant reduction in KV cache requirements while preserving the majority of model's performance.
[J18]Less is More: DocString Compression in Code Generation
Guang Yang, Yu Zhou💌, Wei Cheng, Xiangyu Zhang, Xiang Chen, Terry Yue Zhuo, Ke Liu, Xin Zhou, David Lo, Taolue Chen💌
ACM Transactions on Software Engineering and Methodology 2025TOSEM'25
A novel DocString compression method for code generation, achieving significant reduction in token processing cost while preserving the quality of the generated code.
[J17]Assessing and improving syntactic adversarial robustness of pre-trained models for code translation
Guang Yang, Yu Zhou💌, Xiangyu Zhang, Xiang Chen, Tingting Han, Taolue Chen💌
Information and Software Technology 2025IST'25
A novel approach to assess and improve the syntactic adversarial robustness of PTMs in code translation, achieving significant reduction in syntactic adversarial robustness while preserving the majority of model's performance.
[J16]Defending Code Language Models against Backdoor Attacks with Deceptive Cross-Entropy Loss
Guang Yang, Yu Zhou💌, Xiangyu Zhang, Xiang Chen, Terry Zhuo, David Lo, Taolue Chen💌
ACM Transactions on Software Engineering and Methodology 2025TOSEM'25
A general and effective loss function DeCE (Deceptive Cross-Entropy) to defend Code Language Models against backdoor attacks, preventing overfitting to backdoor triggers.
[J15]Less is More: Towards Green Code Large Language Models via Unified Structural Pruning
Guang Yang, Yu Zhou💌, Xiangyu Zhang, Wei Cheng, Ke Liu, Xiang Chen, Terry Yue Zhuo, Taolue Chen💌
Engineering Applications of Artificial Intelligence 2025EAAI'25
A novel unified structural pruning method for Code Large Language Models, achieving significant reduction in computational demands and energy consumption while preserving the majority of model's performance.
[C14]RegexExplainer: Automatic Description Generation for Regular Expressions via Transformer
Yun Wu, Shuangbo Cao, Tianyue Liu, Xiao Yang, Guang Yang
Proceedings of the 4th International Conference on Communication Technology and Information Technology 2024ICCTIT'24
A novel method to automatically generate functional descriptions for regular expressions, achieving significant improvement in performance compared to the state-of-the-art baselines.
[J14]Chain-of-Thought in Neural Code Generation: From and for Lightweight Language Models
Guang Yang, Yu Zhou💌, Xiang Chen, Xiangyu Zhang, Terry Yue Zhuo, Taolue Chen💌
IEEE Transactions on Software Engineering 2024TSE'24
A novel approach COTTON to automatically generate CoTs for code generation, achieving significant improvement in performance compared to the state-of-the-art baselines.
[J13]Context-aware code generation with synchronous bidirectional decoder
Xiangyu Zhang, Yu Zhou💌, Guang Yang, Tingting Han, Taolue Chen💌
Journal of Systems and Software 2024JSS'24
A novel context-sensitive model employing a bidirectional decoder to generate tokens in two different orders synchronously and interactively.
[J9]How important are good method names in neural code generation? a model robustness perspective
Guang Yang, Yu Zhou💌, Wenhua Yang, Tao Yue, Xiang Chen, Taolue Chen💌
ACM Transactions on Software Engineering and Methodology 2024TOSEM'24
A novel approach RADAR to enhance the performance of PCGMs from a model robustness perspective.
[J8]CodeScore-R：用于评估代码合成功能准确性的自动化鲁棒指标
Yang Guang, Zhou Yu💌, Chen Xiang, Zhang Xiangyu
计算机研究与发展 2024计算机研究与发展'24
A novel automated robust metric CodeScore-R for evaluating the functional accuracy of code synthesis, achieving significant improvement in performance compared to the state-of-the-art baselines.
[J7]A syntax-guided multi-task learning approach for Turducken-style code generation
Guang Yang, Yu Zhou, Xiang Chen, Xiangyu Zhang, Yiran Xu, Tingting Han, Taolue Chen
Empirical Software Engineering 2023EMSE'23
A novel syntax-guided multi-task learning approach for Turducken-style code generation.
[C12]EDP-BGCNN: Effective Defect Prediction via BERT-based Graph Convolutional Neural Network
Hao Shen, Xiaolin Ju, Xiang Chen, Guang Yang
Proceedings of the 47th Annual Computers, Software, and Applications Conference 2023COMPSAC'23
A novel BERT-based Graph Convolutional Neural Network for effective defect prediction.
[C11]An Empirical Study of Adversarial Training in Code Comment Generation
Yiheng Shen, Xiaolin Ju, Xiang Chen, Guang Yang
Proceedings of the 35th International Conference on Software Engineering and Knowledge Engineering 2023SEKE'23
An empirical study of adversarial training in code comment generation.
[C10]CCGRA: Smart Contract Code Comment Generation with Retrieval-enhanced Approach
Shizhan Chen Zhenhua Zhang
Proceedings of the 35th International Conference on Software Engineering and Knowledge Engineering 2023SEKE'23
A novel retrieval-enhanced approach CCGRA that leverages retrieval knowledge to generate high-quality comments for Solidity language code.
[J5]ExploitGen: Template-augmented exploit code generation based on CodeBERT
Guang Yang, Yu Zhou💌, Xiang Chen, Xiangyu Zhang, Tingting Han, Taolue Chen💌
Journal of Systems and Software 2023JSS'23
A novel template-augmented exploit code generation approach ExploitGen based on CodeBERT.
[C9]BashExplainer: Retrieval-Augmented Bash Code Comment Generation based on Fine-tuned CodeBERT
Chi Yu, Guang Yang, Xiang Chen, Ke Liu, Yanlin Zhou
Proceedings of the 2022 IEEE International Conference on Software Maintenance and Evolution 2022ICSME'22
A novel retrieval-augmented Bash code comment generation method BASHEXPLAINER based on fine-tuned CodeBERT.
[C8]BUG-T5: A Transformer-based Automatic Title Generation Method for Bug Reports
Xinyi Tian, Jingkun Wu, Guang Yang
Proceedings of the 3rd International Conference on Big Data & Artificial Intelligence & Software Engineering 2022ICBASE'22
A novel Transformer-based automatic title generation method for bug reports.
[C7]EL-CodeBert: Better Exploiting CodeBert to Support Source Code-Related Classification Tasks
Ke Liu, Guang Yang, Xiang Chen, Yanlin Zhou
Proceedings of the 13th Asia-Pacific Symposium on Internetware 2022Internetware'22
A novel approach EL-CodeBert to better exploit CodeBert for source code-related classification tasks.
[C6]SOTitle: A Transformer-based Post Title Generation Approach for Stack Overflow
Ke Liu, Guang Yang, Xiang Chen, Chi Yu
2022 IEEE International Conference on Software Analysis, Evolution and Reengineering 2022SANER'22
A novel Transformer-based post title generation approach SOTitle for Stack Overflow.
[C5]DualSC: Automatic Generation and Summarization of Shellcode via Transformer and Dual Learning
Guang Yang, Xiang Chen, Yanlin Zhou, Chi Yu
2022 IEEE International Conference on Software Analysis, Evolution and Reengineering 2022SANER'22
A novel approach DualSC to solve the automatic shellcode generation and summarization tasks.
[C4]Fine-grained Pseudo-code Generation Method via Code Feature Extraction and Transformer
Guang Yang, Yanlin Zhou, Xiang Chen, Chi Yu
Proceedings of the 28th Asia-Pacific Software Engineering Conference 2021APSEC'21
A novel deep pseudo-code generation method DeepPseudo via code feature extraction and Transformer.
[C3]EKD-BSP: Bug Report Severity Prediction by Extracting Keywords from Description
Yanxin Jia, Xiang Chen, Shuyuan Xu, Guang Yang, Jinxin Cao
Proceedings of the 8th International Conference on Dependable Systems and Their Applications 2021DSA'21
A novel method EKD-BSP to predict the severity of bug reports by extracting keywords from the description.
[C2]ComFormer: Code Comment Generation via Transformer and Fusion Method-based Hybrid Code Representation
Guang Yang, Xiang Chen, Jinxin Cao, Shuyuan Xu, Zhanqi Cui, Chi Yu, Ke Liu
Proceedings of the 8th International Conference on Dependable Systems and Their Applications 2021DSA'21
A novel method ComFormer to generate code comments via Transformer and fusion method-based hybrid code representation.
[C1]DeepSCC: Source Code Classification Based on Fine-Tuned RoBERTa (S)
Guang Yang, Yanlin Zhou, Chi Yu, Xiang Chen
Proceedings of the 33rd International Conference on Software Engineering and Knowledge Engineering 2021SEKE'21
A novel source code classification method DeepSCC based on fine-tuned RoBERTa.
[J3]基于深度学习的 Stack Overflow 问题帖分类方法
Guang Yang, Yanxin Jia, Xiang Chen, Shuyuan Xu
吉林大学学报 (理学版) 2021吉林大学学报 (理学版)'21
A deep learning-based classification methods for question post on Stack Overflow.
[J2]ORESP:基于有序回归的软件缺陷严重程度预测方法
Yanxin Jia, Xiang Chen, Hao Lu, Guang Yang, Hao Lin
计算机应用研究 2021计算机应用研究'21
A novel method ORESP to predict the severity of software defects based on ordered regression.
[J1]代码注释自动生成方法综述
Xiang Chen, Guang Yang, Zhanqi Cui, Guozhu Meng, Zan Wang
软件学报 2021软件学报'21
A review of automatic code comment generation methods.