Album: AI for Code

Awards

ACM SIGSOFT Impact Paper Award (2024) "For pioneering the use of machine learning to assist developers in generating code snippets, paving the way for today’s intelligent code assistance tools" in this 2009 paper (inventing the concept of Github Copilot).

Papers

• Galapagos: Automated N-Version Programming with LLMs (Javier Ron, Diogo Gaspar, Javier Cabrera-Arteaga, Benoit Baudry and Martin Monperrus), In ACM Transactions on Software Engineering and Methodology 2025, 2025. [github]
• Mokav: Execution-driven Differential Testing with LLMs (Khashayar Etemadi, Bardia Mohammadi, Zhendong Su and Martin Monperrus), In Journal of Systems and Software, 2025. [github]
• RepairBench: Leaderboard of Frontier Models for Program Repair (André Silva and Martin Monperrus), In Proceedings of the International Workshop on Large Language Models for Code (LLM4Code), 2025. [github]
• RepairLLaMA: Efficient Representations and Fine-Tuned Adapters for Program Repair (André Silva, Sen Fang and Martin Monperrus), In IEEE Transactions on Software Engineering, 2025. [github]
• UPPERCASE IS ALL YOU NEED (Vivi Andersson, Benoit Baudry, Sofia Bobadilla, Ludvig Christensen, Serena Cofano, Khashayar Etemadi, Raphina Liu, Martin Monperrus, Frank Reyes García, Javier Ron Arteaga, Aman Sharma, Deepika Tiwari and Tim Toady), In SIGBOVIK : A Record of the Proceedings of SIGBOVIK 2025, SIGBOVIK, 2025. [github]
• Gradient-Based Program Repair: Fixing Bugs in Continuous Program Spaces (André Silva, Gustav Thorén and Martin Monperrus), Technical report 2505.17703, arXiv, 2025. [github]
• FLAMES: Fine-tuning LLMs to Synthesize Invariants for Smart Contract Security (Mojtaba Eshghie, Gabriele Morello, Matteo Lauretano, Alexandre Bartel and Martin Monperrus), Technical report 2510.21401, arXiv, 2025.
• PoCo: Agentic Proof-of-Concept Exploit Generation for Smart Contracts (Vivi Andersson, Sofia Bobadilla, Harald Hobbelhagen and Martin Monperrus), Technical report 2511.02780, arXiv, 2025.
• Project Rachel: Can an AI Become a Scholarly Author? (Martin Monperrus, Benoit Baudry and Clément Vidal), Technical report 2511.14819, arXiv, 2025.

• Generative AI to Generate Test Data Generators (Benoit Baudry, Khashayar Etemadi, Sen Fang, Yogya Gamage, Yi Liu, Yuxin Liu, Martin Monperrus, Javier Ron, André Silva and Deepika Tiwari), In IEEE Software, 2024. [github]
• ITER: Iterative Neural Repair for Multi-Location Patches (He Ye and Martin Monperrus), In Proceedings of International Conference on Software Engineering, 2024. [github]
• Scoping Software Engineering for AI: The TSE Perspective (Sebastian Uchitel, Martin Monperrus and Hao Zhong), In IEEE Transactions on Software Engineering, Institute of Electrical and Electronics Engineers (IEEE), volume 50, 2024.
• Supersonic: Learning to Generate Source Code Optimizations in C/C++ (Zimin Chen, Sen Fang and Martin Monperrus), In IEEE Transactions on Software Engineering, 2024. [github]
• CigaR: Cost-efficient Program Repair with LLMs (Dávid Hidvégi, Khashayar Etemadi, Sofia Bobadilla and Martin Monperrus), Technical report 2402.06598, arXiv, 2024. [github]

• Human, What Must I Tell You? (Markus Borg, Emil Aasa, Khashayar Etemadi and Martin Monperrus), In IEEE Software, Institute of Electrical and Electronics Engineers (IEEE), volume 40, 2023.
• Learning the Relation between Code Features and Code Transforms with Structured Prediction (Zhongxing Yu, Matias Martinez, Zimin Chen, Tegawendé F. Bissyandé and Martin Monperrus), In IEEE Transactions on Software Engineering, 2023. [github]
• Self-Supervised Learning to Prove Equivalence Between Straight-Line Programs via Rewrite Rules (Steve Kommrusch, Martin Monperrus and Louis-Noël Pouchet), In IEEE Transactions on Software Engineering, 2023. [github]
• MUFIN: Improving Neural Repair Models with Back-Translation (André Silva, João F. Ferreira, He Ye and Martin Monperrus), Technical report 2304.02301, arXiv, 2023.

• Neural Program Repair with Execution-based Backpropagation (He Ye, Matias Martinez and Martin Monperrus), In Proceedings of the International Conference on Software Engineering, 2022. [RewardRepair github]
• Neural Transfer Learning for Repairing Security Vulnerabilities in C Code (Zimin Chen, Steve Kommrusch and Martin Monperrus), In IEEE Transactions on Software Engineering, 2022. [vrepair github]
• SelfAPR: Self-supervised Program Repair with Test Execution Diagnostics (He Ye, Matias Martinez, Xiapu Luo, Tao Zhang and Martin Monperrus), In Proceedings of ASE, 2022. [github]
• Styler: learning formatting conventions to repair Checkstyle violations (Benjamin Loriot, Fernanda Madeiral and Martin Monperrus), In Empirical Software Engineering, 2022. [github]

• Automated Classification of Overfitting Patches with Statically Extracted Code Features (He Ye, Jian Gu, Matias Martinez, Thomas Durieux and Martin Monperrus), In IEEE Transactions on Software Engineering, 2021. [github]
• Multimodal Representation for Neural Code Search (Jian Gu, Zimin Chen and Martin Monperrus), In Proceedings of International Conference on Software Maintenance and Evolution, 2021. [github]

• On the Relevance of Cross-project Learning with Nearest Neighbours for Commit Message Generation (Khashayar Etemadi and Martin Monperrus), In Proceedings of the IEEE/ACM 42nd International Conference on Software Engineering Workshops 2020, 2020. [github]

• SequenceR: Sequence-to-Sequence Learning for End-to-End Program Repair (Zimin Chen, Steve Kommrusch, Michele Tufano, Louis-Noël Pouchet, Denys Poshyvanyk and Martin Monperrus), In IEEE Transactions on Software Engineering, 2019. [github]
• Sorting and Transforming Program Repair Ingredients via Deep Learning Code Similarities (Martin White, Michele Tufano, Matias Martinez, Martin Monperrus and Denys Poshyvanyk), In Proceedings of the IEEE International Conference on Software Analysis, Evolution and Reengineering, 2019. [DeepRepair github]
• A Literature Study of Embeddings on Source Code (Zimin Chen and Martin Monperrus), Technical report 1904.03061, arXiv, 2019.

• The CodRep Machine Learning on Source Code Competition (Zimin Chen and Martin Monperrus), Technical report 1807.03200, arXiv, 2018. [github]

• A Learning Algorithm for Change Impact Prediction (Vincenzo Musco, Antonin Carette, Martin Monperrus and Philippe Preux), In 5th International Workshop on Realizing Artificial Intelligence Synergies in Software Engineering, 2016.
• Mutation-Based Graph Inference for Fault Localization (Vincenzo Musco, Martin Monperrus and Philippe Preux), In International Working Conference on Source Code Analysis and Manipulation, 2016.
• BanditRepair: Speculative Exploration of Runtime Patches (Thomas Durieux, Youssef Hamadi and Martin Monperrus), Technical report 1603.07631, arXiv, 2016.

• A Recommender System of Buggy App Checkers for App Store Moderators (Maria Gomez, Romain Rouvoy, Martin Monperrus and Lionel Seinturier), In 2nd ACM International Conference on Mobile Software Engineering and Systems, IEEE, 2015. [zenodo]
• Software that Learns from its Own Failures (Martin Monperrus), Technical report 1502.00821, arXiv, 2015.

• Learning to Combine Multiple Ranking Metrics for Fault Localization (Jifeng Xuan and Martin Monperrus), In ICSME - 30th International Conference on Software Maintenance and Evolution, 2014.

• Detecting Missing Method Calls as Violations of the Majority Rule (Martin Monperrus and Mira Mezini), In ACM Transactions on Software Engineering and Methodology, 2013. [data on Zenodo]

• Semi-Automatically Extracting FAQs to Improve Accessibility of Software Development Knowledge (Stefan Henß, Martin Monperrus and Mira Mezini), In ICSE - 34th International Conference on Software Engineering, 2012.

• Querying Source Code with Natural Language (Markus Kimmig, Martin Monperrus and Mira Mezini), In 26th IEEE/ACM International Conference On Automated Software Engineering, 2011. [data on Zenodo]

• Detecting Missing Method Calls in Object-Oriented Software (Martin Monperrus, Marcel Bruch and Mira Mezini), In Proceedings of the 24th European Conference on Object-Oriented Programming, 2010.
• Mining Subclassing Directives to Improve Framework Reuse (Marcel Bruch, Mira Mezini and Martin Monperrus), In Proceedings of the 7th IEEE Working Conference on Mining Software Repositories, 2010.

• Learning from Examples to Improve Code Completion Systems (Marcel Bruch, Martin Monperrus and Mira Mezini), In Proceedings of the 7th joint meeting of the European Software Engineering Conference and the ACM Symposium on the Foundations of Software Engineering , 2009.

Other publications by Martin Monperrus