Seguir
Sungmin Kang
Sungmin Kang
Email confirmado em kaist.ac.kr - Página inicial
Título
Citado por
Citado por
Ano
Large language models are few-shot testers: Exploring llm-based general bug reproduction
S Kang, J Yoon, S Yoo
2023 IEEE/ACM 45th International Conference on Software Engineering (ICSE …, 2023
1942023
An ultra-high-density bin map facilitates high-throughput QTL mapping of horticultural traits in pepper (Capsicum annuum)
K Han, HJ Jeong, HB Yang, SM Kang, JK Kwon, S Kim, D Choi, BC Kang
DNA Research 23 (2), 81-91, 2016
1202016
Arachne: Search-Based Repair of Deep Neural Networks
J Sohn, S Kang, S Yoo
ACM Transactions on Software Engineering and Methodology 32 (4), 1-26, 2023
107*2023
A quantitative and qualitative evaluation of LLM-based explainable fault localization
S Kang, G An, S Yoo
Proceedings of the ACM on Software Engineering 1 (FSE), 1424-1446, 2024
76*2024
Towards autonomous testing agents via conversational large language models
R Feldt, S Kang, J Yoon, S Yoo
2023 38th IEEE/ACM International Conference on Automated Software …, 2023
522023
Explainable automated debugging via large language model-driven scientific debugging
S Kang, B Chen, S Yoo, JG Lou
Empirical Software Engineering 30 (2), 1-28, 2025
452025
Sinvad: Search-based image space navigation for dnn image classifier test input generation
S Kang, R Feldt, S Yoo
Proceedings of the IEEE/ACM 42nd International Conference on Software …, 2020
322020
Language models can prioritize patches for practical program patching
S Kang, S Yoo
Proceedings of the Third International Workshop on Automated Program Repair …, 2022
152022
Consistent comic colorization with pixel-wise background classification
S Kang, J Choo, J Chang
Proceedings of the NIPS 17, 2017
152017
Towards objective-tailored genetic improvement through large language models
S Kang, S Yoo
2023 IEEE/ACM International Workshop on Genetic Improvement (GI), 19-20, 2023
142023
Evaluating diverse large language models for automatic and general bug reproduction
S Kang, J Yoon, N Askarbekkyzy, S Yoo
IEEE Transactions on Software Engineering, 2024
122024
The github recent bugs dataset for evaluating llm-based debugging applications
JY Lee, S Kang, J Yoon, S Yoo
2024 IEEE Conference on Software Testing, Verification and Validation (ICST …, 2024
122024
Deceiving humans and machines alike: Search-based test input generation for dnns using variational autoencoders
S Kang, R Feldt, S Yoo
ACM Transactions on Software Engineering and Methodology 33 (4), 1-24, 2024
52024
Glad: Neural predicate synthesis to repair omission faults
S Kang, S Yoo
2023 IEEE/ACM 45th International Conference on Software Engineering …, 2023
42023
Identifying inaccurate descriptions in llm-generated code comments via test execution
S Kang, L Milliken, S Yoo
arXiv preprint arXiv:2406.14836, 2024
22024
Microcellular sensing media with ternary transparency states for fast and intuitive identification of unknown liquids
KM Song, S Kim, S Kang, TW Nam, GY Kim, H Lim, EN Cho, KH Kim, ...
Science Advances 7 (38), eabg8013, 2021
22021
Beyond pip install: Evaluating LLM Agents for the Automated Installation of Python Projects
L Milliken, S Kang, S Yoo
arXiv preprint arXiv:2412.06294, 2024
12024
COSMosFL: Ensemble of Small Language Models for Fault Localisation
H Cho, S Kang, G An, S Yoo
arXiv preprint arXiv:2502.02908, 2025
2025
Can We Predict the Effect of Prompts?
JY Lee, S Kang, S Yoo
arXiv preprint arXiv:2501.18883, 2025
2025
Lachesis: Predicting LLM Inference Accuracy using Structural Properties of Reasoning Paths
N Kim, S Kang, G An, S Yoo
arXiv preprint arXiv:2412.08281, 2024
2024
O sistema não pode efectuar a operação agora. Tente mais tarde.
Artigos 1–20