Martin Weyssow's Homepage

Short Bio

I am a Research Scientist at Singapore Management University (SMU), where I focus on advancing large language models (LLMs) for software vulnerability detection. I am a member of the Centre for Research on Intelligent Software Engineering (RISE).

I earned my Ph.D. in Computer Science from DIRO, University of Montreal, under the supervision of Prof. Houari Sahraoui. During my Ph.D. studies, I was awarded two prestigious scholarships through competitive selection: a Google Scholarship for Excellence and the FRQ Merit Scholarship for Foreign Students in Canada. My research during this time focused on understanding and fine-tuning LLMs for code generation and analysis. I also spent time as a visiting researcher at SMU, collaborating with Prof. David Lo on topics related to lifelong learning for code LLMs. My academic foundation includes a master’s degree in data science and a bachelor’s degree in computer science and mathematics from the University of Namur.

My expertise is situated at the intersection of deep learning, natural language processing, and software engineering, with a special emphasis on LLMs for code analysis. My work aims to better understand how LLMs process and generalize from code, uncovering insights into their emergent capabilities and improving their adaptability to dynamic coding environments.

News

[Jan. 2025] Our paper on harnessing LLMs for curated code reviews has been accepted for publication at MSR 2025.
[Jan. 2025] Our paper on a reference architecture for LLM-integrated systems has been accepted for publication at ICSA 2025.
[Jan. 2025] Our paper on parameter-efficient fine-tuning for code generation with LLMs has been accepted for publication at ACM Transactions on Software Engineering and Methodology (TOSEM).
[Oct. 2024] I am starting a new position as a Research Scientist (postdoc) at Singapore Management University (SMU) where I'll be working on vulnerability detection with LLMs.
[Sept. 2024] I have succesfully defended my Ph.D dissertation "Aligning Language Models to Code: Exploring Efficient, Temporal, and Preference Alignment for Code Generation at DIRO, University of Montreal. I received the highest distinction with an exceptional mention.
[Feb. 2024] Our paper featuring a lifelong learning dataset for language models of code is accepted at MSR 2024.
[May. 2023] Our paper on continual learning and out-of-distribution generalization for PLMs of code is accepted at FSE 2023.
[Oct. 2022] I am starting a new visiting Ph.D. researcher position at SCIS, Singapore Management University under the supervision of Prof. David Lo.
[Jul. 2022] Our paper on syntax probing for pre-trained language models of code is accepted at ASE 2022.
[May 2022] I was awarded a prestigious FRQ Merit Scholarship for Foreign Students (PBEEE) issued by the Government of Quebec to fund my Ph.D.
[Mar. 2022] I am serving as a PC member of the Deep Learning for Code workshop at ICLR 2022.
[Dec. 2021] Our paper about multimodal learning with concept graphs for code is accepted at ICSE-NIER 2022.
Dec. 2021 Our paper about pre-trained language models for MDE is accepted to SOSYM journal AI-MDE theme issue.
[May 2021] I am recipient of a Google Scholarship for Excellence offered by DIRO, University of Montreal funding 1-year of full-time research.
[Sep. 2020] I am officially starting my Ph.D. program under the supervision of Prof. Houari Sahraoui.

Selected Publications [Google Scholar]

Under review

CleanVul: Automatic Function-Level Vulnerability Detection in Code Commits Using LLM Heuristics

Yikun Li, Ting Zhang, Ratnadira Widyasari, Yan Naing Tun, Huu Hung Nguyen, Tan Bui, Ivana Clairine Irsan, Yiran Cheng, Xiang Lan, Han Wei Ang, Frank Liauw, Martin Weyssow, Hong Jin Kang, Eng Lieh Ouh, Lwin Khin Shar, and David Lo

Under review

PDF

Under review

CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences

Martin Weyssow, Aton Kamanda, and Houari Sahraoui

Under review

PDF Code

MSR

CodeLL: A Lifelong Learning Dataset to Support the Co-Evolution of Data and Language Models of Code

Martin Weyssow, Claudio Di Sipio, Davide Di Ruscio, and Houari Sahraoui

International Conference on Mining Software Repositories, Data and Tool Showcase, 2024.

PDF Code

TOSEM

Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models

Martin Weyssow, Xin Zhou, Kisub Kim, David Lo, and Houari Sahraoui

ACM Transactions on Software Engineering and Methodology

PDF Code

ESEC/FSE

On the Usage of Continual Learning for Out-of-Distribution Generalization in Pre-trained Language Models of Code

Martin Weyssow, Xin Zhou, Kisub Kim, David Lo, and Houari Sahraoui

ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2023.

PDF Code

ASE

AST-Probe: Recovering abstract syntax trees from hidden representations of pre-trained language models

José Antonio Hernández López*, Martin Weyssow*, Jesús Sánchez Cuadrado, and Houari Sahraoui (*Equal contributions)

International Conference on Automated Software Engineering, 2022.

PDF Code

ICSE-NIER

Better modeling the programming world with code concept graphs-augmented multi-modal learning

Martin Weyssow, Houari Sahraoui, and Bang Liu

International Conference on Software Engineering, New Ideas and Emerging Results, 2022.

PDF

SOSYM

Recommending metamodel concepts during modeling activities with pre-trained language models

Martin Weyssow, Houari Sahraoui, and Eugene Syriani

Software and Systems Modeling, 2022.

PDF Code

Students Supervision

Aton Kamanda, MSc. at the University of Montreal, 2021-2023.
Adaptive computation strategies for deep neural networks
Lucas Maes, MSc. at the University of Montreal, 2021-2023.
Self-supervised learning for code representation learning.

Services

Program Committee

Conference Reviewer

Journal Reviewer

Contact

Email: mweyssow (at) smu.edu.sg