Perfection not required? Human-AI partnerships in code translation

JD Weisz, M Muller, S Houde, J Richards… - Proceedings of the 26th …, 2021 - dl.acm.org
Generative models have become adept at producing artifacts such as images, videos, and
prose at human-like levels of proficiency. New generative techniques, such as unsupervised …

Code completion by modeling flattened abstract syntax trees as graphs

Y Wang, H Li - Proceedings of the AAAI conference on artificial …, 2021 - ojs.aaai.org
Code completion has become an essential component of integrated development
environments. Contemporary code completion methods rely on the abstract syntax tree …

Seqtrans: automatic vulnerability fix via sequence to sequence learning

J Chi, Y Qu, T Liu, Q Zheng… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Software vulnerabilities are now reported unprecedentedly due to the recent development of
automated vulnerability hunting tools. However, fixing vulnerabilities still mainly depends on …

Setransformer: A transformer-based code semantic parser for code comment generation

Z Li, Y Wu, B Peng, X Chen, Z Sun… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
Automated code comment generation technologies can help developers understand code
intent, which can significantly reduce the cost of software maintenance and revision. The …

Learning to parallelize in a shared-memory environment with transformers

R Harel, Y Pinter, G Oren - Proceedings of the 28th ACM SIGPLAN …, 2023 - dl.acm.org
In past years, the world has switched to multi and many core shared memory architectures.
As a result, there is a growing need to utilize these architectures by introducing shared …

Hierarchical semantic-aware neural code representation

Y Jiang, X Su, C Treude, T Wang - Journal of Systems and Software, 2022 - Elsevier
Code representation is a fundamental problem in many software engineering tasks. Despite
the effort made by many researchers, it is still hard for existing methods to fully extract …

Regminer: towards constructing a large regression dataset from code evolution history

X Song, Y Lin, SH Ng, Y Wu, X Peng, JS Dong… - Proceedings of the 31st …, 2022 - dl.acm.org
Bug datasets lay significant empirical and experimental foundation for various SE/PL
researches such as fault localization, software testing, and program repair. Current well …

[PDF][PDF] How Data Scientists Improve Generated Code Documentation in Jupyter Notebooks.

MJ Muller, AY Wang, SI Ross, JD Weisz… - IUI …, 2021 - star.informatik.rwth-aachen.de
Generative AI models are capable of creating high-fidelity outputs, sometimes
indistinguishable from what could be produced by human effort. However, some domains …

Pragformer: data-driven parallel source code classification with transformers

R Harel, T Kadosh, N Hasabnis, T Mattson… - International Journal of …, 2025 - Springer
Multi-core shared memory architectures have become ubiquitous in computing hardware
nowadays. As a result, there is a growing need to fully utilize these architectures by …

PragFormer: Data-driven Parallel Source Code Classification with Transformers

T Kadosh, N Hasabnis, T Mattson, Y Pinter, G Oren - 2023 - researchsquare.com
Multi-core shared memory architectures have become ubiquitous in computing hardware
nowadays. As a result, there is a growing need to fully utilize these architectures by …