AI SOC Lab.
Prof. 박준석
Research VLSI Design, Hardware–Software Co-design, Deep Learning/Deep Neural Network Accelerator
TEL +82-2-888-8476
FAX -
About the Laboratory & Research Area
Our research investigates specialized hardware systems for next-generation computing. The work covers VLSI design, hardware–software co-design, and processing-in-memory architectures.
We take a holistic, system-level approach to improve performance, efficiency, and scalability. Our current focus is the development of high-performance computing platforms designed to support future AI-driven applications.
We take a holistic, system-level approach to improve performance, efficiency, and scalability. Our current focus is the development of high-performance computing platforms designed to support future AI-driven applications.
Research Interests & Projects
Development of next-generation AI SoCs for emerging on-device AI applications, Deep Learning / Deep Neural Network Accelerator, AI System-on-Chip
Journals & Patents
Jun-Seok Park et al., “An On-Device Generative AI Focused Neural Processing Unit in 4nm Flagship Mobile SoC with Fan-Out Wafer-Level Package,” 2025 IEEE International Solid-State Circuits Conference (ISSCC)
Jun-Seok Park et al., “A Multi-Mode 8K-MAC HW-Utilization-Aware Neural Processing Unit with a Unified Multi-Precision Datapath in 4nm Flagship Mobile SoC,” 2022 IEEE International Solid-State Circuits Conference (ISSCC)
Jun-Seok Park et al., “A 6k-MAC Feature-Map-Sparsity-aware Neural Processing Unit in 5nm Flagship Mobile SoC,” 2021 IEEE International Solid-State Circuits Conference (ISSCC)
Jun-Seok Park et al., “A Multi-Mode 8K-MAC HW-Utilization-Aware Neural Processing Unit with a Unified Multi-Precision Datapath in 4nm Flagship Mobile SoC,” 2022 IEEE International Solid-State Circuits Conference (ISSCC)
Jun-Seok Park et al., “A 6k-MAC Feature-Map-Sparsity-aware Neural Processing Unit in 5nm Flagship Mobile SoC,” 2021 IEEE International Solid-State Circuits Conference (ISSCC)
