BASE Lab - DGIST | 양방향 AI-소프트웨어 공학 연구실

Learning to Represent Code Changes

X. Tang, H. Tian, W. Pian, S. Ezzini, A. Kabore, A. Habib, K. Kim**, J. Klein, and T. Bissyandé

Empirical Software Engineering (EMSE), 2025 [Just Accepted]

Automating Requirement-to-Specification Traceability Recovery in Weapon Systems via Domain-Adapted Pretrained Models

T. Kim, K. Kim**, and K. Jo

The Journal of Software Systems (JSS), 2025 [Under Review]

Just-in-Time Detection of Silent Security Patches

D. Tang, K. Kim, S. Ezzini, Y. Song, H. Tian, J. Klein, and T. Bissyandé

ACM Transactions on Software Engineering and Methodology (TOSEM), 2025 [Just Accepted]

Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models

M. Weyssow, X. Zhou, K. Kim, D. Lo, and H. Sahraoui

ACM Transactions on Software Engineering and Methodology (TOSEM), 2025

How are We Detecting Inconsistent Method Names? An Empirical Study from Code Review Perspective

K. Kim, X. Zhou, D. Kim, J. Lawall, K. Liu, T. Bissyandé, J. Klein, J. Lee, and D. Lo

ACM Transactions on Software Engineering and Methodology (TOSEM), 2025

Temporal-Incremental Learning for Android Malware Detection

T. Sun, N. Daoudi, W. Pian, K. Kim**, K. Allix, T. Bissyandé, and J. Klein

ACM Transactions on Software Engineering and Methodology (TOSEM), 2025

SE-Jury - An LLM-as-Ensemble-Judge Metric for Narrowing the Gap with Human Evaluation in SE

X. Zhou, K. Kim**, T. Zhang, M. Weyssow, L. Gomes, G. Yang, K. Liu, X. Xia, and D. Lo

IEEE/ACM International Conference on Automated Software Engineering (ASE), 2025 [Just Accepted]

iCodeReviewer - Improving Secure Code Review with Mixture of Prompts

Y. Peng, K. Kim**, L. Meng, and K. Liu

IEEE/ACM International Conference on Automated Software Engineering (ASE), 2025 [Just Accepted]

Investigating sparsity of self-attention

M. Garaj, K. Kim**, and A. Stockinger

European Conference on Artificial Intelligence, 2025

RAML --- Toward Retrieval-augmented Localization of Malicious Payloads in Android Apps

T. Sun, M. Alecci, Y. Song, X. Tang, K. Kim, J. Samhi, T. Bissyandé, and J. Klein

IEEE/ACM International Conference on Automated Software Engineering, 2025 [Just Accepted]

Leveraging Large Language Model for Automatic Patch Correctness Assessment

X. Zhou, B. Xu, K. Kim, D. Han, T. Le Cong, J. He, B. Le, and D. Lo

Transactions on Software Engineering (TSE), 2024

Representation Learning for Stack Overflow Posts - How Far are We?

J. He, X. Zhou, B. Xu, T. Zhang, K. Kim**, Z. Yang, F. Thung, I. Clairine Irsan, and D. Lo

ACM Transactions on Software Engineering and Methodology (TOSEM), 2024

DataRecipe --- How to Cook the Data for CodeLLM?

K. Kim, J. Kim, B. Park, D. Kim, C. Chong, Y. Wang, T. Sun, D. Tang, J. Klein, and T. Bissyandé

IEEE/ACM International Conference on Automated Software Engineering (ASE), 2024 [Selected for IEEE Software, Practitioner's digest]

CodeAgent --- Autonomous Communicative Agents for Code Review

D. Tang, K. Kim, Y. Song, C. Lothritz, B. Li, S. Ezzini, H. Tian, J. Klein, and T. Bissyandé

The Conference on Empirical Methods in Natural Language Processing (EMNLP), 2024

Out of Sight, Out of Mind - Better Automatic Vulnerability Repair by Broadening Input Ranges and Sources

X. Zhou, K. Kim**, B. Xu, D. Han, and D. Lo

IEEE/ACM International Conference on Software Engineering (ICSE), 2024

Curiosity-Driven Testing for Sequential Decision-Making Process

J. He, Z. Yang, J. Shi, C. Yang, K. Kim, B. Xu, X. Zhou, and D. Lo

IEEE/ACM International Conference on Software Engineering (ICSE), 2024

DexBERT - Effective, Task-Agnostic and Fine-Grained Representation Learning of Android Bytecode

T. Sun, K. Allix, K. Kim**, X. Zhou, D. Kim, D. Lo, T. Bissyandé, and J. Klein

Transactions on Software Engineering (TSE), 2023

Big Code Search - a Bibliography

K. Kim, S. Ghatpande, D. Kim, X. Zhou, K. Liu, T. Bissyandé, J. Klein, and Y. Le Traon

ACM Computing Surveys (CSUR), 2023

AutoConf - Automated Configuration of Unsupervised Learning Systems using Metamorphic Testing and Bayesian Optimization

S. Lwin Khin, A. Göknil, E. Johannes Husom, S. Sen, Y. Naing Tun, and K. Kim**

IEEE/ACM International Conference on Automated Software Engineering (ASE), 2023

The Devil is in the Tails - An Exploratory Study on Long-tailed Distributions in Software Engineering Datasets

X. Zhou, K. Kim**, B. Xu, J. Liu, D. Han, and D. Lo

IEEE/ACM International Conference on Automated Software Engineering (ASE), 2023

Are We Ready to Embrace Generative AI for Software Q&A?

B. Xu, T. Nguyen, T. Le-Cong, T. Hoang, J. Liu, K. Kim, C. Gong, C. Niu, C. Wang, B. Le, and D. Lo

IEEE/ACM International Conference on Automated Software Engineering (ASE), 2023

On the Usage of Continual Learning for Out-of-Distribution Generalization in Pre-trained Language Models of Code

M. Weyssow, Z. Xin, K. Kim**, D. Lo, and H. Sahraoui

The ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering (ESEC/FSE), 2023

APISENS- Sentiment Scoring Tool for APIs with Crowd-Knowledge

K. Kim, F. Thung, T. Zhang, I. Clairine Irsan, R. Widyasari, Z. Yang, and D. Lo

arXiv, 2023

APIHarvest - Harvesting API Information from Various Online Sources

F. Thung, K. Kim, T. Zhang, I. Clairine Irsan, R. Widyasari, Z. Yang, and D. Lo

arXiv, 2023

PICASO - Enhancing API Recommendations with Relevant Stack Overflow Posts

I. Irsan, T. Zhang, F. Thung, K. Kim, and D. Lo

Proceedings of the 20th International Conference on Mining Software Repositories (MSR), 2023

Generation-based Code Review Automation - How Far Are We?

X. Zhou, K. Kim**, B. Xu, D. Han, J. He, and D. Lo

The 31st IEEE/ACM International Conference on Program Comprehension (ICPC), 2023

Multi-modal API recommendation

I. Irsan, T. Zhang, F. Thung, K. Kim, and D. Lo

Proceedings of the 30th IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER), 2023

DigBug – Pre/Post-processing Operator Selection for Accurate Bug Localization

K. Kim, S. Ghatpande, K. Liu, A. Koyuncu, D. Kim, T. Bissyandé, J. Klein, and Y. Le Traon

The Journal of Software Systems (JSS), 2022

Where were the Repair Ingredients for Defects4j Bugs?

D. Yang, K. Liu, D. Kim, A. Koyuncu, K. Kim, H. Tian, Y. Lei, X. Mao, J. Klein, and T. Bissyandé

Empirical Software Engineering (EMSE), 2021

On the Efficiency of Test Suite based Program Repair - A Systematic Assessment of 16 Automated Repair Systems for Java Programs

K. Liu, S. Wang, A. Koyuncu, T. Bissyandé, D. Kim, P. Wu, J. Klein, X. Mao, and Y. Traon

Proceedings of the 42th International Conference on Software Engineering (ICSE), 2020

Learning to spot and refactor inconsistent method names

K. Liu, D. Kim, T. Bissyandé, T. Kim, K. Kim, A. Koyuncu, S. Kim, and Y. Traon

Proceedings of the 41th International Conference on Software Engineering (ICSE), 2019 [As one of the corresponding authors.]

Augmenting and Structuring User Queries to Support Efficient Free-Form Code Search

R. Sirres, T. Bissyandé, D. Kim, D. Lo, J. Klein, K. Kim, and Y. Le Traon

Empirical Software Engineering (EMSE), 2018

FaCoY - A Code-to-Code Search Engine

K. Kim, D. Kim, T. Bissyandé, E. Choi, L. Li, J. Klein, and Y. Traon

Proceedings of the 40th International Conference on Software Engineering (ICSE), 2018

LSRepair - Live Search of Fix Ingredients for Automated Program Repair

K. Liu, D. Kim, L. Li, A. Koyuncu, K. Kim, and T. Bissyandé

Proceedings of the 25th Asia-Pacific Software Engineering Conference (APSEC), 2018

Extracting the Source Code Context to Predict Import Changes using GPES

J. Lee, K. Kim, Y. Lee, J. Hong, Y. Seo, B. Yang, and W. Jung

KSII Transactions on Internet and Information Systems (KSII), 2017

Design and Implementation of a Data Extraction Tool for Analyzing Software Changes

Y. Lee, K. Kim, J. Lee, and W. Jung

Journal of The Korea Society of Computer and Information (KSCI), 2016

A Distributed Survey Automation Based on a Customizable Form Template

J. Lee, K. Kim, and W. Jung

Proceedings of the 11th KIPS International Conference on Ubiquitous Information Technologies and Applications (CUTE), 2016

GPES - Supporting Source Code Analysis by Extracting the Evolutionary History of Software Structure and Quality

J. Lee, Y. Lee, K. Kim, J. Hong, and W. Jung

Proceedings of the 11th Asia Pacific International Conference on Information Science and Technology (APIC-IST), 2016

Identifying a Component Co-usability using Similarity Metric

J. Lee, K. Kim, and W. Jung

Proceedings of the 18th Korea Conference on Software Engineering (KCSE), 2016

Analyzing Developer’s Share of Code Based on Abstract Syntax Tree

Y. Lee, J. Lee, K. Kim, and W. Jung

Proceedings of the Korean Society of Computer Information Conference (KSCI), 2015

출판물

Learning to Represent Code Changes

Automating Requirement-to-Specification Traceability Recovery in Weapon Systems via Domain-Adapted Pretrained Models

Just-in-Time Detection of Silent Security Patches

Exploring Parameter-Efficient Fine-Tuning Techniques for Code Generation with Large Language Models

How are We Detecting Inconsistent Method Names? An Empirical Study from Code Review Perspective

Temporal-Incremental Learning for Android Malware Detection

SE-Jury - An LLM-as-Ensemble-Judge Metric for Narrowing the Gap with Human Evaluation in SE

iCodeReviewer - Improving Secure Code Review with Mixture of Prompts

Investigating sparsity of self-attention

RAML --- Toward Retrieval-augmented Localization of Malicious Payloads in Android Apps

Leveraging Large Language Model for Automatic Patch Correctness Assessment

Representation Learning for Stack Overflow Posts - How Far are We?

DataRecipe --- How to Cook the Data for CodeLLM?

CodeAgent --- Autonomous Communicative Agents for Code Review

Out of Sight, Out of Mind - Better Automatic Vulnerability Repair by Broadening Input Ranges and Sources

Curiosity-Driven Testing for Sequential Decision-Making Process

DexBERT - Effective, Task-Agnostic and Fine-Grained Representation Learning of Android Bytecode

Big Code Search - a Bibliography

AutoConf - Automated Configuration of Unsupervised Learning Systems using Metamorphic Testing and Bayesian Optimization

The Devil is in the Tails - An Exploratory Study on Long-tailed Distributions in Software Engineering Datasets

Are We Ready to Embrace Generative AI for Software Q&A?

On the Usage of Continual Learning for Out-of-Distribution Generalization in Pre-trained Language Models of Code

APISENS- Sentiment Scoring Tool for APIs with Crowd-Knowledge

APIHarvest - Harvesting API Information from Various Online Sources

PICASO - Enhancing API Recommendations with Relevant Stack Overflow Posts

Generation-based Code Review Automation - How Far Are We?

Multi-modal API recommendation

DigBug – Pre/Post-processing Operator Selection for Accurate Bug Localization

Where were the Repair Ingredients for Defects4j Bugs?

On the Efficiency of Test Suite based Program Repair - A Systematic Assessment of 16 Automated Repair Systems for Java Programs

Learning to spot and refactor inconsistent method names

Augmenting and Structuring User Queries to Support Efficient Free-Form Code Search

FaCoY - A Code-to-Code Search Engine

LSRepair - Live Search of Fix Ingredients for Automated Program Repair

Extracting the Source Code Context to Predict Import Changes using GPES

Design and Implementation of a Data Extraction Tool for Analyzing Software Changes

A Distributed Survey Automation Based on a Customizable Form Template

GPES - Supporting Source Code Analysis by Extracting the Evolutionary History of Software Structure and Quality

Identifying a Component Co-usability using Similarity Metric

Analyzing Developer’s Share of Code Based on Abstract Syntax Tree