Zobrazeno 1 - 10
of 49
pro vyhledávání: '"Yu, Zhongxing"'
Autor:
Xue, Pengyu, Wu, Linhao, Yang, Zhen, Li, Xinyi, Yu, Zhongxing, Jin, Zhi, Li, Ge, Xiao, Yan, Wu, Jingwen
In recent years, Large language model-powered Automated Program Repair (LAPR) techniques have achieved state-of-the-art bug-fixing performance and have been pervasively applied and studied in both industry and academia. Nonetheless, LLMs were proved
Externí odkaz:
http://arxiv.org/abs/2410.07516
With the advancement of deep learning techniques, the performance of Automatic Program Repair(APR) techniques has reached a new level. Previous deep learning-based APR techniques essentially modified program sentences in the Autoregressive(AR) manner
Externí odkaz:
http://arxiv.org/abs/2406.16526
Autor:
Xue, Pengyu, Wu, Linhao, Yu, Zhongxing, Jin, Zhi, Yang, Zhen, Li, Xinyi, Yang, Zhenyu, Tan, Yue
Commit Message Generation (CMG) approaches aim to automatically generate commit messages based on given code diffs, which facilitate collaboration among developers and play a critical role in Open-Source Software (OSS). Very recently, Large Language
Externí odkaz:
http://arxiv.org/abs/2404.14824
Autor:
Yang, Zhen, Liu, Fang, Yu, Zhongxing, Keung, Jacky Wai, Li, Jia, Liu, Shuo, Hong, Yifan, Ma, Xiaoxue, Jin, Zhi, Li, Ge
Code translation tools (transpilers) are developed for automatic source-to-source translation. Although learning-based transpilers have shown impressive enhancement against rule-based counterparts, owing to their task-specific pre-training on extensi
Externí odkaz:
http://arxiv.org/abs/2404.14646
Writing logging messages is a well-established conventional programming practice, and it is of vital importance for a wide variety of software development activities. The logging mechanism in Solidity programming is enabled by the high-level event fe
Externí odkaz:
http://arxiv.org/abs/2308.12788
Autor:
Du, Yali, Yu, Zhongxing
Enlightened by the big success of pre-training in natural language processing, pre-trained models for programming languages have been widely used to promote code intelligence in recent years. In particular, BERT has been used for bug localization tas
Externí odkaz:
http://arxiv.org/abs/2308.12773
Autor:
Monperrus, Martin, Martinez, Matias, Ye, He, Madeiral, Fernanda, Durieux, Thomas, Yu, Zhongxing
This paper presents Megadiff, a dataset of source code diffs. It focuses on Java, with strict inclusion criteria based on commit message and diff size. Megadiff contains 663 029 Java diffs that can be used for research on commit comprehension, fault
Externí odkaz:
http://arxiv.org/abs/2108.04631
Autor:
Baudry, Benoit, Chen, Zimin, Etemadi, Khashayar, Fu, Han, Ginelli, Davide, Kommrusch, Steve, Martinez, Matias, Monperrus, Martin, Ron, Javier, Ye, He, Yu, Zhongxing
Publikováno v:
IEEE Software, 2021
Software bugs are common and correcting them accounts for a significant part of costs in the software development and maintenance process. This calls for automatic techniques to deal with them. One promising direction towards this goal is gaining rep
Externí odkaz:
http://arxiv.org/abs/2012.06824
Publikováno v:
IEEE Transactions on Software Engineering, 2023
To effectively guide the exploration of the code transform space for automated code evolution techniques, we present in this paper the first approach for structurally predicting code transforms at the level of AST nodes using conditional random field
Externí odkaz:
http://arxiv.org/abs/1907.09282
Publikováno v:
Proceedings of ICSE, Software Engineering in Practice, 2018
Program repair research has made tremendous progress over the last few years, and software development bots are now being invented to help developers gain productivity. In this paper, we investigate the concept of a " program repair bot " and present
Externí odkaz:
http://arxiv.org/abs/1811.09852