本课程教学团队的科研方向是智能软件工程，即研究如何构建代码大模型，以及基于代码大模型的代码自动生成、翻译、测试和缺陷修复，主持与参与了《基于编程现场大数据的软件智能开发方法和环境》、《大规模高质量软件缺陷库的自动构建与应用》、《面向低代码开发的模板挖掘方法与模板库技术》、《面向群体协同开发的软件工程关联数据挖掘》等多项国家自然科学基金项目和国家重点研发项目，发表了30多篇智能软件工程的相关学术论文。所取得的科研成果反哺到教学工作中，以研促教，以教驱研，引导学生参与智能软件工程的科研实践，指导学生进行科研创新，培养创新能力和实践能力。
2022年以来学生发表的智能软件工程论文如下：
| 智能开发任务 | 发表论文 |
| 代码注释生成 |
Shangbo Yun, Shuhuai Lin, Xiaodong Gu, Beijun Shen. Project-specific Code Summarization with In-Context Learning, Journal of Systems & Software (JSS), Volume 216, July 2024, 112149
|
| 变量名的语义表征 |
Yalan Lin, Chengcheng Wan, Shuwen Bai and Xiaodong Gu. VarGAN: Adversarial Learning of Variable Semantic Representations, IEEE Transactions on Software Engineering (TSE'24), 2024
|
| 代码翻译 |
Xuan Li, Shuai Yuan, Xiaodong Gu, Yuting Chen, Beijun Shen. Few-Shot Code Translation via Task-adapted Prompt Learning, Journal of Systems & Software (JSS), Volume 212, June 2024, 112002
|
| 代码翻译 |
Mingsheng Jiao, Tingrui Yu, Xuan Li, Guanjie Qiu, Xiaodong Gu, Beijun Shen. On the Evaluation of Neural Code Translation: Taxonomy and Benchmark, International Conference on Automated Software Engineering (ASE), Kirchberg, Luxembourg, Sept. 11-15, 2023
|
| 正则表达式生成 |
Shuai Zhang, Xiaodong Gu, Yuting Chen, Beijun Shen. InfeRE: Step-by-Step Regex Generation via Chain of Inference, International Conference on Automated Software Engineering (ASE), Kirchberg, Luxembourg, Sept. 11-15, 2023
|
| 代码搜索 |
Yuetian Mao, Chengcheng Wan, Yuze Jiang, Xiaodong Gu, Self-Supervised Query Reformulation for Code Search, 2023 ESEC/FSE, San Francisco, California, United States, 3-9 December 2023
|
| 代码问答 |
Tingrui Yu, Xiaodong Gu, Beijun Shen, Code Question Answering via Task-Adaptive Sequence-to-Sequence Pre-training, THE 29th Asia-Pacific Software Engineering Conference (APSEC), Virtual, Dec. 6-9, 2022
|
| 缺陷修复 |
Dangwei Wu, Beijun Shen, Yuting Chen, Jiang He, Lei Qiao, Automatically Repairing Tensor Shape Faults in Deep Learning Programs, Information and Software Technology (IST), Volume 151, November 2022, 107027
|
| 代码瘦身 |
Zhaowei Zhang, Hongyu Zhang, Beijun Shen, Xiaodong Gu, Diet Code is Healthy: Simplifying Programs for Pre-trained Code Models, ACM SIGSOFT Symposium on the Foundation of Software Engineering/European Software Engineering Conference (ESEC/FSE), Singapore, November 14-18, 2022
|
| 软件部署问答 |
Guanjie Qiu, Diwei Chen, Shuai Zhang, Yitian Chai, Xiaodong Gu, Beijun Shen. Answering Software Deployment Questions via Neural Machine Reading at Scale, The 37th IEEE/ACM International Conference on Automated Software Engineering (ASE), Tool demo, Ann Arbor, Michigan, USA, October 10-14, 2022
|
| 代码表征 |
Nan Cui, , Beijun Shen, Zero-Shot Program Representation Learning, The 30th IEEE/ACM International Conference on Program Comprehension (ICPC), Virtual, May 16-17, 2022
|
| 代码表征 |
Nan Cui, , Beijun Shen, Zero-Shot Program Representation Learning, The 30th IEEE/ACM International Conference on Program Comprehension (ICPC), Virtual, May 16-17, 2022
|
| 代码表征 |
Shouliang Yang, Xiaodong Gu, Beijun Shen, Self-Supervised Learning of Smart Contract Representations, The 30th IEEE/ACM International Conference on Program Comprehension (ICPC), Virtual, May 16-17, 2022
|
| 代码搜索 |
Yitian Chai, Hongyu Zhang, Beijun Shen, Xiaodong Gu, Cross-Domain Deep Code Search with Meta Learning, The 44th IEEE/ACM International Conference on Software Engineering (ICSE), Pittsburgh, Pennsylvania, USA, May 21-29, 2022
|