Byungwoo Bang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Byungwoo Bang has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Junyeon Lee
Korea University, Seoul, South Korea
3 shared publications - Uiseok Song
Korea University, Seoul, South Korea
3 shared publications - Jaehoon Kim
Korea University
2 shared publications - Changwook Chu1 shared publication
- Hansam Cho
Korea University
1 shared publication - Hanum Ko
Sungkyunkwan University, Suwon, Republic of Korea
1 shared publication
Latest Publications
- 3 February 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 312
CATS-RAG: Contextual Augmented Triplet Synthesis for RAG in Technical QA
- 3 February 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 312
CATS-RAG: Contextual Augmented Triplet Synthesis for RAG in Technical QA
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (9) , 1-14
DieCARE: Diekill-Correct ECC for HBM Reliability without Additional Dies
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 75 (9) , 1-14
DieCARE: Diekill-Correct ECC for HBM Reliability without Additional Dies
- 20 September 2025
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81 (15) , 1-30
HAMS: an AI-driven framework for real-time failure detection in HPC system logs
- 20 September 2025
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 81 (15) , 1-30
HAMS: an AI-driven framework for real-time failure detection in HPC system logs
- 2 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22 (1) , 279-291
FALL: Prior Failure Detection in Large Scale System Based on Language Model
As the scale of high-performance computing systems (HPC) continues to expand, the frequency of failures within the system also increases. The follow-up steps in the event of a failure are necessary because efficient prevention measures are absent. These actions, however, result in decreased operating efficiency as the system normalizes. To solve this problem, recent research has utilized deep learning to predict failures in advance by examining log messages. One common method uses log ID extracted from log messages as input data. However, these methods could lead to information loss in log messages and may not accurately capture log message properties. In this study, we propose the prior failure detection in large-scale systems using language models (FALL) that reflects the properties of log messages. The FALL uses log messages as text data and only uses normal data for training. The FALL makes use of sharpening, which concentrates on the minimal lexical change between normal and abnormal log messages. In addition, by leveraging the characteristics of log messages with limited vocabularies, the FALL utilizes only some tokens for anomaly detection. The experiments' results from log data from real industry-based HPC systems show that the FALL achieves superior performance in early failure detection.
- 2 May 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 22 (1) , 279-291
FALL: Prior Failure Detection in Large Scale System Based on Language Model
As the scale of high-performance computing systems (HPC) continues to expand, the frequency of failures within the system also increases. The follow-up steps in the event of a failure are necessary because efficient prevention measures are absent. These actions, however, result in decreased operating efficiency as the system normalizes. To solve this problem, recent research has utilized deep learning to predict failures in advance by examining log messages. One common method uses log ID extracted from log messages as input data. However, these methods could lead to information loss in log messages and may not accurately capture log message properties. In this study, we propose the prior failure detection in large-scale systems using language models (FALL) that reflects the properties of log messages. The FALL uses log messages as text data and only uses normal data for training. The FALL makes use of sharpening, which concentrates on the minimal lexical change between normal and abnormal log messages. In addition, by leveraging the characteristics of log messages with limited vocabularies, the FALL utilizes only some tokens for anomaly detection. The experiments' results from log data from real industry-based HPC systems show that the FALL achieves superior performance in early failure detection.