squaresLab logo

squaresLab

Software QUAlity in Real Evolving Systems*

We research automated techniques to reason about, assure, measure, and improve the quality of real, messy, ever-changing software.

Carnegie Mellon University, School of Computer Science

squaresLab on GitHub  ·  clegoues@cs.cmu.edu

*We apologize, sort of, for the egregious backronym.

Team

Claire Le Goues Claire
Andrea Miller Andrea
Cláudia Mamede Cláudia
HG
Harrison
Kaia Newman Kaia
Luke Dramko Luke
+2 more →
View full team →

Recent Publications

ACM Trans. Softw. Eng. Methodol.

When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair

Wenqiang Luo, Jacky W. Keung, Boyang Yang, He Ye, Claire Le Goues, Tegawendé F. Bissyandé, Haoye Tian, Bach Le

ACM Trans. Softw. Eng. Methodol.

MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-Tuning

Boyang Yang, Haoye Tian, Jiadong Ren, Hongyu Zhang, Jacques Klein, Tegawendé F. Bissyandé, Claire Le Goues, Shunfu Jin

Proceedings of the Network and Distributed System Security Symposium (NDSS)

Idioms: A Simple and Effective Framework for Turbo-Charging Local Neural Decompilation with Well-Defined Types

Luke Dramko, Claire Le Goues, Edward J. Schwartz

Proceedings of the 40th IEEE/ACM International Conference on Automated Software Engineering (ASE)

Interpretable Vulnerability Detection Reports

Cláudia Mamede, José Campos, Claire Le Goues, Rui Abreu

Proc. ACM Softw. Eng. 2.ISSTA

AdverIntent-Agent: Adversarial Reasoning for Repair Based on Inferred Program Intent

He Ye, Aidan Z. H. Yang, Chang Hu, Yanlin Wang, Tao Zhang, Claire Le Goues

View all 118 publications →

Highlights

2026-01
Idioms: A Simple and Effective Framework for Turbo-Charging Local Neural Decompilation with Well-Defined Types

Proceedings of the Network and Distributed System Security Symposium (NDSS) 2026

2025-01
Interpretable Vulnerability Detection Reports

Proceedings of the 40th IEEE/ACM International Conference on Automated Software Engineering (ASE) 2025