Hoseok Kim

Interests

Energy-efficient Edge Computing, NPU Architecture

Ph.D. in Electrical and Computer Engineering, 2025 –
Purdue University
Advisor: Professor Vijay Raghunathan

M.S. in Computer Science and Engineering, 2025
Korea University
Advisor: Professor Sung Woo Chung

B.S. in Computer Science and Engineering, 2023
Korea University

2026

BIDENT: Heterogeneous Operator-level Mapping for Efficient Edge Inference

H. Kim, A. Das, S. Ghosh, A. Raha, V. Raghunathan

arXiv preprint, 2026

MOSAIC: A Workload-Driven Simulation and Design-Space Exploration Framework for Heterogeneous NPUs

A. Das*, H. Kim*, S. Lee, A. Raha, D. Mathaikutty, V. Raghunathan

arXiv preprint, 2026

*Equal contribution

2024

Sparrow ECC: A Lightweight ECC Approach for HBM Refresh Reduction towards Energy-efficient DNN Inference

H. Kim, S.H. Choi, Y.-H. Gong, J. Kong, S.W. Chung

ACM/IEEE International Symposium on Low Power Electronics and Design (ISLPED), 2024

Best Paper Award DOI Code