Boqi (Percy) Chen
PhD Candidate, McGill University

email: boqi⚫chen@mail⚫mcgill⚫ca
I am a PhD candidate in the Department of Electrical and Computer Engineering (ece) at McGill University, supervised by Prof. Daniel Varro and Prof. Gunter Mussbacher. Additionally, I work as an R&D engineer at Aggregate Intellect through a Mitacs grant. My research focuses on applying model-based techniques to enhance the reliability and robustness of machine learning systems. I am also actively involved in projects evaluating the quality and properties of machine learning models for various software engineering tasks, such as model generation, bug detection, and code summarization. With the rapid advancements in large language models, I am exploring their potential in software engineering applications and to further improve their robustness and reliability.
Currently, I’m a part-time research associate at Huawei Waterloo Research Center. Besides I’m also an active contributor to the open-source project Sherpa that aims to build a robust and easy-to-use large language model framework.
I also organize a bi-weekly (sometimes weekly) discussion group on graph neural networks and their applications. You can find the scedules here. If you are interested in joining, please subscribe to this calendar. We are also actively looking for new speakers, so if you are interested in presenting your work or any topics you are interested in, please feel free to reach out to me.
news
Jan 14, 2025 | The paper I’ve contributed to “An adaptive language-agnostic pruning method for greener language models for code” has been accepted by FSE 2025 Research Paper Track! |
---|---|
Dec 17, 2024 | I will participate in the ICSE 2025 Student Research Competition with the paper ““Consistent Graph Model Generation with Large Language Models”, consisting of work I’ve done during my internship at Huawei Waterloo Research Center. |
Dec 07, 2024 | Our paper “Exploring Large Language Models for Requirements on String Values” has been accepted by 2nd Workshop on Multi-disciplinary, Open, and integRatEd Requirements Engineering at ICSE 2025 |
selected publications
- MODELS-CPrompting or Fine-tuning? A Comparative Study of Large Language Models for Taxonomy ConstructionIn 2023 ACM/IEEE International Conference on Model Driven Engineering Languages and Systems Companion (MODELS-C) , 2023
- REWOn the use of GPT-4 for creating goal models: an exploratory studyIn 2023 IEEE 31st International Requirements Engineering Conference Workshops (REW) , 2023
- ASEConsistent scene graph generation by constraint optimizationIn Proceedings of the 37th IEEE/ACM International Conference on Automated Software Engineering , 2022