About Me

My name is Binhang Qi (齐斌航). Currently, I am a postdoc at National University of Singapore, working with Prof. Jin-Song Dong and Prof. Yun Lin. Before joining NUS, I received my PhD degree from School of Computer Science and Engineering at Beihang University (BUAA), where I worked on software engineering, DNN modularization, model reuse, etc, supervised by Prof. Hailong Sun. I earned my bachelor’s degree at Software College of Northeastern University.

News

• [03/2026] Our paper Generalizing Test Cases for Comprehensive Test Scenario Coverage has been accepted by FSE 2026.

• [03/2026] I join the Program Commitee of ICSE’27, please consider to submit your work and attend the conference.

• [03/2026] I join the Program Commitee of ASE’26, please consider to submit your work and attend the conference.

• [10/2025] Our paper ModularEvo: Evolving Multi-Task Models via Neural Network Modularization and Composition has been accepted by ICSE 2026.

• [07/2025] Our paper NeMo: A Neuron-Level Modularizing-While-Training Approach for Decomposing DNN Models has been accepted by the ACM Transactions on Software Engineering and Methodology (TOSEM).

• [05/2025] Two papers are accepted by ICML 2025.

• [03/2025] I join the Program Commitee of ASE’25, please consider to submit your work and attend the conference.

• [04/2024] Our paper ModelFoundry: A Tool for DNN Modularization and On-demand Model Reuse has been accepted by the FSE’24 Demonstration track.

• [02/2024] Our ICSE’24 paper Modularizing while Training: A New Paradigm for Modularizing DNN Models has been selected for an ACM SIGSOFT Distinguished Paper Award.

• [02/2024] I joined National University of Singapore as a postdoc under the supervision of Prof. Jin-Song Dong.

• [12/2023] I have successfully defended my PhD thesis. Congrats to myself.

• [11/2023] Our paper Reusing Convolutional Neural Network Models through Modularization and Composition has been accepted by the TOSEM.

• [09/2023] I obtain China National Scholarship.

• [08/2023] Our paper AutoMRM: A Model Retrieval Method Based on Multimodal Query and Meta-learning has been accepted by the CIKM’23.

• [06/2023] Our paper Modularizing while Training: A New Paradigm for Modularizing DNN Models has been accepted by the ICSE’24 technical track.

• [12/2022] Our paper Reusing Deep Neural Network Models through Model Re-engineering has been accepted by the ICSE’23 technical track.

• [04/2022] Our paper Patching Weak Convolutional Neural Network Models through Modularization and Composition has been accepted by the ASE’22 research papers track.

Selected Publications

1. Generalizing Test Cases for Comprehensive Test Scenario Coverage (accepted)
   Binhang Qi, Yun Lin, Xinyi Weng, Chenyan Liu, Hailong Sun, Gordon Fraser, Jin Song Dong
   The ACM International Conference on the Foundations of Software Engineering (FSE), 2026

2. ModularEvo: Evolving Multi-Task Models via Neural Network Modularization and Composition
   Wenrui Long, Binhang Qi*, Hailong Sun, Zongzhen Yang, Ruobing Zhao, Xiang Gao.
   The 48th IEEE/ACM International Conference on Software Engineering (ICSE), 2026

3. NeMo: A Neuron-Level Modularizing-While-Training Approach for Decomposing DNN Models      
   Xiaohan Bi, Binhang Qi, Hailong Sun, Xiang Gao, Yue Yu, Xiaojun Liang
   ACM Transactions on Software Engineering and Methodology (TOSEM)

4. CABS: Conflict-Aware and Balanced Sparsification for Enhancing Model Merging      
   Zongzhen Yang, Binhang Qi, Hailong Sun, Wenrui Long, Ruobin Zhao, Xiang Gao.
   The 42nd International Conference on Machine Learning (ICML), 2025.

5. ModelFoundry: A Tool for DNN Modularization and On-demand Model Reuse
   Xiaohan Bi, Ruobing Zhao, Binhang Qi, Hailong Sun, Xiang Gao, Yue Yu, Xiaojun Liang
   The ACM International Conference on the Foundations of Software Engineering (FSE) - Demonstration track, 2024.

6. Modularizing while Training: A New Paradigm for Modularizing DNN Models      
   Binhang Qi, Hailong Sun, Hongyu Zhang, Ruobing Zhao, Xiang Gao
   The 46th International Conference on Software Engineering (ICSE), 2024.
   ACM SIGSOFT Distinguished Paper Award

7. Reusing Convolutional Neural Network Models through Modularization and Composition      
   Binhang Qi, Hailong Sun, Hongyu Zhang, Xiang Gao
   ACM Transactions on Software Engineering and Methodology (TOSEM).

8. Reusing Deep Neural Network Models through Model Re-engineering      
   Binhang Qi, Hailong Sun, Xiang Gao, Hongyu Zhang, Zhaotian Li, Xudong Liu
   The 45th International Conference on Software Engineering (ICSE), 2023.

9. AutoMRM: A Model Retrieval Method Based on Multimodal Query and Meta-learning
   Zhaotian Li, Binhang Qi, Hailong Sun, Xiang Gao
   The 32nd ACM International Conference on Information and Knowledge Management (CIKM), 2023.

10. Patching Weak Convolutional Neural Network Models through Modularization and Composition      
    Binhang Qi, Hailong Sun, Xiang Gao, Hongyu Zhang
    The 37th IEEE/ACM International Conference on Automated Software Engineering (ASE), 2022.

11. DreamLoc: A deep relevance matching-based framework for bug localization
    Binhang Qi, Hailong Sun, Wei Yuan, Hongyu Zhang, Xiangxin Meng
    IEEE Transactions on Reliability 71 (1), 2022:235-249.

Selected Awards

• [2024.02] ICSE’24 ACM SIGSOFT Distinguished Paper Award
• [2023.09] China National Scholarship.
• [2023.09] Beihang University First Prize Scholarship.
• [2023.04] Outstanding Academic Innovation Achievement Award (Received Twice).
• [2022.12] Outstanding Graduate Student.
• [2021.09] Beihang University First Prize Scholarship.