1 code implementation • 5 Sep 2017 • Claire Le Goues, Yuriy Brun, Sven Apel, Emery Berger, Sarfraz Khurshid, Yannis Smaragdakis
Double-blind review relies on the authors' ability and willingness to effectively anonymize their submissions.
Digital Libraries General Literature Software Engineering
no code implementations • 15 Apr 2020 • Afsoon Afzal, Deborah S. Katz, Claire Le Goues, Christopher S. Timperley
We find that simulation is used by 85% of our participants for testing, and that many participants desire to use simulation as part of their test automation.
Robotics Software Engineering
no code implementations • 28 Sep 2021 • Alex Shypula, Pengcheng Yin, Jeremy Lacomis, Claire Le Goues, Edward Schwartz, Graham Neubig
We also report that SILO's rate of superoptimization on our test set is over five times that of a standard policy gradient approach and a model pre-trained on compiler optimization demonstration.
1 code implementation • 5 Dec 2021 • Qibin Chen, Jeremy Lacomis, Edward J. Schwartz, Graham Neubig, Bogdan Vasilescu, Claire Le Goues
Machine learning-based program analysis methods use variable name representations for a wide range of tasks, such as suggesting new variable names and bug detection.
1 code implementation • 28 Aug 2023 • Daniel Ramos, Hailie Mitchell, Inês Lynce, Vasco Manquinho, Ruben Martins, Claire Le Goues
By leveraging code examples mined from the library source and automatically generated code examples based on the pull requests, we infer transformation rules in \comby, a language for structural code search and replace.
2 code implementations • 2 Oct 2023 • Nikitha Rao, Kush Jain, Uri Alon, Claire Le Goues, Vincent J. Hellendoorn
We also drastically increase the maximum sequence length of inputs to 8, 192 tokens, 4x more than typical code generation models, to ensure that the code context is available to the model when generating test code.
1 code implementation • 3 Oct 2023 • Aidan Z. H. Yang, Ruben Martins, Claire Le Goues, Vincent J. Hellendoorn
Specifically, we propose to overcome the left-to-right nature of LLMs by fine-tuning a small set of bidirectional adapter layers on top of the representations learned by LLMs to produce LLMAO, the first language model based fault localization approach that locates buggy lines of code without any test coverage information.