Výsledky vyhledávání - "Proceedings / International Conference on Software Engineering"

A Novel Neural Source Code Representation Based on Abstract Syntax Tree Autor Zhang, Jian, Wang, Xu, Zhang, Hongyu, Sun, Hailong, Wang, Kaixuan, Liu, Xudong

“…Exploiting machine learning techniques for analyzing programs has attracted much attention. One key problem is how to represent code fragments well for…”
Získat plný text

A Neural Model for Generating Natural Language Summaries of Program Subroutines Autor LeClair, Alexander, Jiang, Siyuan, McMillan, Collin

“…Source code summarization -- creating natural language descriptions of source code behavior -- is a rapidly-growing research topic with applications to…”
Získat plný text

Automated Program Repair in the Era of Large Pre-trained Language Models Autor Xia, Chunqiu Steven, Wei, Yuxiang, Zhang, Lingming

“…Automated Program Repair (APR) aims to help developers automatically patch software bugs. However, current state-of-the-art traditional and learning-based APR…”
Získat plný text

CodaMosa: Escaping Coverage Plateaus in Test Generation with Pre-trained Large Language Models Autor Lemieux, Caroline, Inala, Jeevana Priya, Lahiri, Shuvendu K., Sen, Siddhartha

“…Search-based software testing (SBST) generates high-coverage test cases for programs under test with a combination of test case generation and mutation. SBST's…”
Získat plný text

Automatically Learning Semantic Features for Defect Prediction Autor Song Wang, Taiyue Liu, Lin Tan

“…Software defect prediction, which predicts defective code regions, can help developers find bugs and prioritize their testing efforts. To build accurate…”
Získat plný text

Superion: Grammar-Aware Greybox Fuzzing Autor Wang, Junjie, Chen, Bihuan, Wei, Lei, Liu, Yang

“…In recent years, coverage-based greybox fuzzing has proven itself to be one of the most effective techniques for finding security bugs in practice…”
Získat plný text

Using an LLM to Help with Code Understanding Autor Nam, Daye, Macvean, Andrew, Hellendoorn, Vincent, Vasilescu, Bogdan, Myers, Brad

“…Understanding code is challenging, especially when working in new and complex development environments. Code comments and documentation can help, but are…”
Získat plný text

Automated Repair of Programs from Large Language Models Autor Fan, Zhiyu, Gao, Xiang, Mirchev, Martin, Roychoudhury, Abhik, Tan, Shin Hwei

“…Large language models such as Codex, have shown the capability to produce code for many programming tasks. However, the success rate of existing models is low,…”
Získat plný text

CURE: Code-Aware Neural Machine Translation for Automatic Program Repair Autor Jiang, Nan, Lutellier, Thibaud, Tan, Lin

“…Automatic program repair (APR) is crucial to improve software reliability. Recently, neural machine translation (NMT) techniques have been used to…”
Získat plný text

SourcererCC: Scaling Code Clone Detection to Big-Code Autor Sajnani, Hitesh, Saini, Vaibhav, Svajlenko, Jeffrey, Roy, Chanchal K., Lopes, Cristina V.

“…Despite a decade of active research, there has been a marked lack in clone detection techniques that scale to large repositories for detecting near-miss…”
Získat plný text

Retrieval-Based Prompt Selection for Code-Related Few-Shot Learning Autor Nashid, Noor, Sintaha, Mifta, Mesbah, Ali

“…Large language models trained on massive code corpora can generalize to new tasks without the need for task-specific fine-tuning. In few-shot learning, these…”
Získat plný text

Angelix: Scalable Multiline Program Patch Synthesis via Symbolic Analysis Autor Mechtaev, Sergey, Jooyong Yi, Roychoudhury, Abhik

“…Since debugging is a time-consuming activity, automated program repair tools such as GenProg have garnered interest. A recent study revealed that the majority…”
Získat plný text

Impact of Code Language Models on Automated Program Repair Autor Jiang, Nan, Liu, Kevin, Lutellier, Thibaud, Tan, Lin

“…Automated program repair (APR) aims to help developers improve software reliability by generating patches for buggy programs. Although many code language…”
Získat plný text

A Large-Scale Survey on the Usability of AI Programming Assistants: Successes and Challenges Autor Liang, Jenny T., Yang, Chenyang, Myers, Brad A.

“…The software engineering community recently has witnessed widespread deployment of AI programming assistants, such as GitHub Copilot. However, in practice,…”
Získat plný text

Large Language Models are Few-shot Testers: Exploring LLM-based General Bug Reproduction Autor Kang, Sungmin, Yoon, Juyeon, Yoo, Shin

“…Many automated test generation techniques have been developed to aid developers with writing tests. To facilitate full automation, most existing techniques aim…”
Získat plný text

Fuzz4ALL: Universal Fuzzing with Large Language Models Autor Xia, Chunqiu Steven, Paltenghi, Matteo, Tian, Jia Le, Pradel, Michael, Zhang, Lingming

“…Fuzzing has achieved tremendous success in discovering bugs and vulnerabilities in various software systems. Systems under test (SUTs) that take in programming…”
Získat plný text

Studying the Usage of Text-To-Text Transfer Transformer to Support Code-Related Tasks Autor Mastropaolo, Antonio, Scalabrino, Simone, Cooper, Nathan, Nader Palacio, David, Poshyvanyk, Denys, Oliveto, Rocco, Bavota, Gabriele

“…Deep learning (DL) techniques are gaining more and more attention in the software engineering community. They have been used to support several code-related…”
Získat plný text

Guiding Deep Learning System Testing Using Surprise Adequacy Autor Kim, Jinhan, Feldt, Robert, Yoo, Shin

“…Deep Learning (DL) systems are rapidly being adopted in safety and security critical domains, urgently calling for ways to test their correctness and…”
Získat plný text

On Learning Meaningful Code Changes Via Neural Machine Translation Autor Tufano, Michele, Pantiuchina, Jevgenija, Watson, Cody, Bavota, Gabriele, Poshyvanyk, Denys

“…Recent years have seen the rise of Deep Learning (DL) techniques applied to source code. Researchers have exploited DL to automate several development and…”
Získat plný text

Code Prediction by Feeding Trees to Transformers Autor Kim, Seohyun, Zhao, Jinman, Tian, Yuchi, Chandra, Satish

“…Code prediction, more specifically autocomplete, has become an essential feature in modern IDEs. Autocomplete is more effective when the desired next token is…”
Získat plný text