Bio

Pilsung Kang received his PhD in computer science from Virginia Tech in 2010 under the supervision of professors Srinidhi Varadarajan and Naren Ramakrishnan. He worked at Samsung Electronics on software for flash-based storage systems from 2010 to 2016.  He switched to academia in 2016, and is now a member at Dankook University, South Korea.

Recent Publications

Preprints

• "Interaction as Interference: A Quantum-Inspired Aggregation Approach", arXiv:2511.10018 (submitted to Applied Soft Computing)

• "Quantum Causality: Resolving Simpson's Paradox with DO-Calculus", arXiv:2509.00744 (submitted to IOP Quantum Science and Technology)

• "Quantum Entanglement as Super-Confounding: From Bell's Theorem to Robust Machine Learning", arXiv:2508.19327 (submitted to IEEE TETC)

• "Emergent Bifurcations in Quantum Circuit Stability from Hidden Parameter Statistics", arXiv:2508.00484 (submitted to IEEE TQE)

• "QFFN-BERT: An Empirical Study of Depth, Performance, and Data Efficiency in Hybrid Quantum-Classical Transformers",  arXiv:2507.02364 (submitted to IEEE TETC)

Published Papers

• "Performance Evaluation of Modern GPU Accelerator-Based Edge Systems: A Holistic Approach", H. Lee, P. Kang, IEEE Internet of Things Journal. 12(23), pp. 51716-51729 (2025)

• "Evaluating Coding Proficiency of Large Language Models: An Investigation Through Machine Learning Problems", E. Ko, P. Kang, IEEE Access. 13, pp. 52925-52938 (2025) 

• "Evolving Scientific Code Adaptations with Modularization Frameworks", P. Kang, Automated Software Engineering. 30, article no. 24 (2023) 

• "Programming for High-Performance Computing on Edge Accelerators", P. Kang, Mathematics. 11(4):1055 (2023)

Projects at High-Performance Computing Lab (HPCL)

• Quantum Causal Inference for Trustworthy AI

  • Develop a unified framework that integrates quantum principles with causal inference to ensure fairness, explainability, and robustness in AI systems

• Implementing High-Performance Computing (HPC) on Edge Accelerators

  • Leverage GPU-based edge systems for HPC applications