Hailong Sun, Beihang University

Hailong Sun

Professor, School of Software, Beihang University

Visiting Professor, University of Toronto, 2015.8~2016.8 (Prof. Ding Yuan's Group)
Exchange Scholar, AT&T Shannon Laboratory, New Jersey, 2008.7-2008.12 (working with Dr. Yih-Farn Robin Chen)
Ph.D. , Beihang University, 2001.9-2008.1
B. S. , Northern JiaoTong University (now Beijing JiaoTong University),1997.9-2001.7

Email: sunhl[AT]buaa[DOT]edu[DOT]cn

Research Interests

Intelligent Software Engineering, Artificial Intelligence, Open Source Software and Ecosystems, Distributed Systems.

I am looking for highly self-motivated students to work with me in the broad areas of computer software and artificial intelligence. Please send me an email if you are interested. We also have postdoc positions available.

Publication Records: @DBLP @Google Scholar

Selected Publications:

NEW! Xiaohan Bi, Ruobing Zhao, Binhang Qi, Hailong Sun, Xiang Gao, Yue Yu, Xiaojun Liang. ModelFoundry: A Tool for DNN Modularization and On-demand Model Reuse. The ACM International Conference on the Foundations of Software Engineering (FSE 2024) - Demonstration track (accepted).
NEW! Wenling Zhang, Yixiao Li, Zhaotian Li, Hailong Sun, Xiang Gao, Xudong Liu. ModelGalaxy: A Versatile Model Retrieval Platform. The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2024) - Demonstration track (accepted).
NEW! Yunlong Ma, Wentong Tian, Xiang Gao, Hailong Sun, Li Li. API Misuse Detection via Probabilistic Graphical Model. The ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2024) (accepted).
NEW! Lei Chai, Lu Qi, Hailong Sun, Jingzheng Li. RA³: Human-in-the-loop Framework for Interpreting and Improving Image Captioning with Relation-Aware Attribution Analysis. The 40th IEEE International Conference on Data Engineering (ICDE 2024) (accepted).
Binhang Qi, Hailong Sun, Hongyu Zhang, Xiang Gao. Reusing Convolutional Neural Network Models through Modularization and Composition. ACM Transactions on Software Engineering and Methodology (TOSEM), 33(3), 2024: 1-39.
Binhang Qi, Hailong Sun, Hongyu Zhang, Ruobin Zhao, Xiang Gao. Modularizing while Training: a New Paradigm for Modularizing DNN Models. The 46th IEEE/ACM International Conference on Software Engineering (ICSE 2024, ACM SIGSOFT Distinguished Paper Award).
Shuo Hong, Hailong Sun, Xiang Gao, Shin Hwei Tan. Investigating and Detecting Silent Bugs in PyTorch Programs. The 31st IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER 2024, IEEE Computer Society TCSE Distinguished Paper Award).
Zhaotian Li, Binhang Qi, Hailong Sun, Xiang Gao. AutoMRM: A Model Retrieval Method Based on Multimodal Query and Meta-learning. The 32nd ACM International Conference on Information and Knowledge Management (CIKM 2023).
Jingzheng Li, Hailong Sun. LiFT: Transfer Learning in Vision-Language Models for Downstream Adaptation and Generalization. The 31st ACM International Conference on Multimedia (MM 2023) .
Zhijun Chen, Hailong Sun, Wanhao Zhang, Chunyi Xu, Pengpeng Chen. Neural-Hidden-CRF: A Robust Weakly-Supervised Sequence Labeler. The 29th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2023).
Pengpeng Chen, Yongqiang Yang, Dingqi Yang, Hailong Sun, Zhijun Chen, Peng Lin. Black-Box Data Poisoning Attacks on Crowdsourcing. The 32nd International Joint Conference on Artificial Intelligence (IJCAI 2023).
Binhang Qi, Hailong Sun, Xiang Gao, Hongyu Zhang, Zhaotian Li, Xudong Liu. Reusing Deep Neural Network Models through Model Re-engineering. The 45th IEEE/ACM International Conference on Software Engineering (ICSE 2023).
Xiangxin Meng, Xu Wang, Hongyu Zhang, Hailong Sun, Xudong Liu, Chunming Hu. Template-based Neural Program Repair. The 45th IEEE/ACM International Conference on Software Engineering (ICSE 2023).
Zhijun Chen, Hailong Sun, Haoqian He, Pengpeng Chen. Learning from Noisy Crowd Labels with Logics. The 39th IEEE International Conference on Data Engineering (ICDE 2023).
Binhang Qi, Hailong Sun, Xiang Gao, Hongyu Zhang. Patching Weak Convolutional Neural Network Models through Modularization and Composition. The 37th IEEE/ACM International Conference on Automated Software Engineering (ASE 2022).
Jingzheng Li, Hailong Sun. Correct Twice at Once: Learning to Correct Noisy Labels for Robust Deep Learning. The 30th ACM International Conference on Multimedia (MM 2022) .
Xiangxin Meng, Xu Wang, Hongyu Zhang, Hailong Sun, Xudong Liu. Improving fault localization and program repair with deep semantic features and transferred knowledge. The 44th International Conference on Software Engineering (ICSE 2022).
Pengpeng Chen, Hailong Sun,Yongqiang Yang, Zhijun Chen. Adversarial Learning from Crowds. The Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI 2022).
Binhang Qi, Hailong Sun, Wei Yuan, Hongyu Zhang, Xiangxin Meng. DreamLoc: A deep relevance matching-based framework for bug localization. IEEE Transactions on Reliability 71 (1), 2022:235-249.
Zizhe Wang, Hailong Sun. Teaching Active Human Learners. The Thirty-Fifth AAAI Conference on Artificial Intelligence (AAAI 2021).
Zhijun Chen, Huimin Wang, Hailong Sun, Pengpeng Chen, Tao Han, Xudong Liu, Jie Yang. Structured Probabilistic End-to-End Learning from Crowds. The 29th International Joint Conference on Artificial Intelligence(IJCAI 2020).
Jian Zhang, Xu Wang, Hongyu Zhang, Hailong Sun,Yanjun Pu, Xudong Liu. Learning to Handle Exceptions. The 35th IEEE/ACM International Conference on Automated Software Engineering (ASE 2020).
Jian Zhang, Xu Wang, Hongyu Zhang, Hailong Sun, Xudong Liu. Retrieval-based Neural Source Code Summarization. The 42nd International Conference on Software Engineering (ICSE 2020).
Jian Zhang, Xu Wang, Hongyu Zhang, Hailong Sun, Xudong Liu. A Novel Neural Source Code Representation based on Abstract Syntax Tree. The 41st International Conference on Software Engineering (ICSE 2019).
Luting Ye, Hailong Sun, Xu Wang, Jiaruijue Wang. Personalized Teammate Recommendation for Crowdsourced Software Developers. The 33rd IEEE/ACM International Conference on Automated Software Engineering (ASE 2018).
Yili Fang, Hailong Sun, Pengpeng Chen and Jinpeng Huai. On the Cost Complexity of Crowdsourcing. The 27th International Joint Conference on Artificial Intelligence (IJCAI 2018).
Jian Zhang, Hailong Sun, Yanfei Tian and Xudong Liu. Semantically Enhanced Tag Recommendation for Software CQAs via Deep Learning. The 40th International Conference on Software Engineering (ICSE 2018).
Shujie Wu, Hailong Sun, Pengpeng Chen and Xudong Liu. Service4Crowd: A Service Oriented Process Management Platform for Crowdsourcing. The 21st ACM Conference on Computer-Supported Cooperative Work and Social Computing (CSCW 2018)-demonstration.
Zizhe Wang, Hailong Sun, Yang Fu and Luting Ye. Recommending Crowdsourced Software Developers in Consideration of Skill Improvement. The 32nd IEEE/ACM International Conference on Automated Software Engineering (ASE 2017).
Tao Han, Hailong Sun, Yangqiu Song, Zizhe Wang and Xudong Liu. Budgeted Task Scheduling for Crowdsourced Knowledge Acquisition. The 26th ACM International Conference on Information and Knowledge Management (CIKM 2017).
Yili Fang, Pengpeng Chen, Kai Sun and Hailong Sun. A Decision Tree Based Quality Control Framework for Multi-phase Tasks in Crowdsourcing. In Proceedings of the 12th Chinese Conference on Computer Supported Cooperative Work and Social Computing (ChineseCSCW '17, Best Paper Award).
Tao Han, Hailong Sun, Yangqiu Song, Yili Fang, Xudong Liu. Incorporating External Knowledge into Crowd Intelligence for More Specific Knowledge Acquisition. The 25th International Joint Conference on Artificial Intelligence(IJCAI 2016).
David Lion, Adrian Chiu, Hailong Sun, Xin Zhuang, Nikola Grcevski, and Ding Yuan. Don't Get Caught In the Cold, Warm-up Your JVM: Understand and Eliminate JVM Warm-up Overhead In Data-parallel Systems. Proceedings of the 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 2016), November 2016, Savannah, GA.
Heting Wu, Hailong Sun, Yili Fang, Kefan Hu, Yongqing Xie, Yangqiu Song, Xudong Liu. Combining Machine Learning and Crowdsourcing for Better Understanding Commodity Reviews. The 29th AAAI Conference on Artificial Intelligence (AAAI 2015) (poster).
Yangqiu Song, Chenguang Wang, Ming Zhang, Hailong Sun, Qiang Yang. Spectral Label Refinement for Noisy and Missing Text Labels. The 29th AAAI Conference on Artificial Intelligence (AAAI 2015).
Wancai Zhang, Hailong Sun, Xudong Liu and Xiaohui Guo. Temporal QoS-Aware Web Service Recommendation via Non-negative Tensor Factorization. The 23rd International World Wide Web Conference (WWW 2014).
Yili Fang, Hailong Sun, Richong Zhang, JingpengHuai, Yongyi Mao. A Model for Aggregating Contributions of Synergistic Crowdsourcing Workflows. The 28th AAAI Conference on Artificial Intelligence (AAAI 2014).
Chune Li, Richong Zhang, Jinpeng Huai, Xiaohui Guo and Hailong Sun. A Probabilistic Approach for Web Service Discovery. IEEE SCC 2013 (Best Student Paper Award).

Teaching

Operating Systems, Spring, 2013-2014/2017-2024.
Introduction to Open Source Software Development, Fall, 2022-2023.
Code LLMs: Research and Applications, Spring, 2024.
Principles of Information Retrieval, Fall, 2010-2016.
Information Retrieval (for part-time graduate students), Fall, 2009-2016.
Foundations of Service Computing, Fall, 2011-2014/2016.
Artificial Intelligence and Application (for international graduate students), Fall, 2010-2012.