Unprecedented code change automation: The fusion of llms and transformation by example

M Dilhara, A Bellur, T Bryksin, D Dig - Proceedings of the ACM on …, 2024 - dl.acm.org
Software developers often repeat the same code changes within a project or across different
projects. These repetitive changes are known as “code change patterns”(CPATs) …

The living review on automated program repair

M Monperrus - 2018 - hal.science
Concept This paper is a living review on automatic program repair 1. Compared to a
traditional survey, a living review evolves over time. I use a concise bullet-list style meant to …

Program repair

X Gao, Y Noller, A Roychoudhury - arxiv preprint arxiv:2211.12787, 2022 - arxiv.org
Automated program repair is an emerging technology which consists of a suite of techniques
to automatically fix bugs or vulnerabilities in programs. In this paper, we present a …

Neurosymbolic repair for low-code formula languages

R Bavishi, H Joshi, J Cambronero, A Fariha… - Proceedings of the …, 2022 - dl.acm.org
Most users of low-code platforms, such as Excel and PowerApps, write programs in domain-
specific formula languages to carry out nontrivial tasks. Often users can write most of the …

MELT: Mining Effective Lightweight Transformations from Pull Requests

D Ramos, H Mitchell, I Lynce… - 2023 38th IEEE/ACM …, 2023 - ieeexplore.ieee.org
Software developers often struggle to update APIs, leading to manual, time-consuming, and
error-prone processes. We introduce Melt, a new approach that generates lightweight API …

Pyevolve: Automating frequent code changes in python ml systems

M Dilhara, D Dig, A Ketkar - 2023 IEEE/ACM 45th International …, 2023 - ieeexplore.ieee.org
Because of the naturalness of software and the rapid evolution of Machine Learning (ML)
techniques, frequently repeated code change patterns (CPATs) occur often. They range from …

Synthesizing code quality rules from examples

P Garg, SH Sengamedu - Proceedings of the ACM on Programming …, 2022 - dl.acm.org
Static Analysis tools have rules for several code quality issues and these rules are created
by experts manually. In this paper, we address the problem of automatic synthesis of code …

Automated Deep Learning Optimization via DSL-Based Source Code Transformation

R Wang, M Lu, CH Yu, YH Lai, T Zhang - Proceedings of the 33rd ACM …, 2024 - dl.acm.org
As deep learning models become increasingly bigger and more complex, it is critical to
improve model training and inference efficiency. Though a variety of highly optimized …

API Misuse Detection via Probabilistic Graphical Model

Y Ma, W Tian, X Gao, H Sun, L Li - Proceedings of the 33rd ACM …, 2024 - dl.acm.org
API misuses can cause a range of issues in software development, including program
crashes, bugs, and vulnerabilities. Different approaches have been developed to …

Compiler-directed Migrating API Callsite of Client Code

H Zhong, N Meng - Proceedings of the IEEE/ACM 46th International …, 2024 - dl.acm.org
API developers evolve software libraries to fix bugs, add new features, or refactor code, but
the evolution can introduce API-breaking changes (eg, API renaming). To benefit from such …