POSTECH EPIC Lab

Welcome to EPIC LAB at POSTECH EE

Embedded Processor & Intelligent Computing (EPIC) LAB is a research group in the department of Electrical Engineering at Pohang University of Science and Technology (POSTECH), Pohang, Korea. With enthusiastic members, EPIC LAB enables the optimized HW/SW building blocks in modern application-specific embedded processors for various intelligent computing workloads. 

Our research interests cover cross-disciplinary topics including algorithms, architectures, and system-on-chip (SoC) designs. Currently, we are focusing on developing the advanced deep learning processor for on-device AI processing, the high-performance baseband processor for next-generation communications, and the energy-optimized IoT platform for human-centric applications.


Latest News

[2025/01] Our paper entitled "AMC: Adaptive mixed compression for ML models based on block-wise sensitivity," has been accepted for presentation at the 2025 IEEE International Symposium on Circuits and Systems (ISCAS 2025).

[2025/01] Our research on the ML-based demosaicing algorithm has recieved the Best Poster Award at the 7th Annual Winter Conference of ISE.

[2024/12] Our paper entitled "Energy-efficient flexible RNS-CKKS processor for FHE-based privacy-preserving computing" has been accepted for publication in the IEEE Journal of Solid-State Circuits.

[2024/11] Our paper entitled "High-performance and low-complexity multi-touch detection for variable ground states" has been accepted for publication in the IEEE Sensors Journal.

[2024/11] Our paper entitled "FIGLUT: An energy-efficient accelerator design for FP-INT GEMM using look-up tables" has been accepted for presentation at the 2025 IEEE International Symposium on High-Performance Computer Architecture (HPCA 2025).

[2024/11] Our paper entitled "Panacea: Novel DNN accelerator using accuracy-preserving asymmetric quantization and energy-saving bit-slice sparsity" has been accepted for presentation at the 2025 IEEE International Symposium on High-Performance Computer Architecture (HPCA 2025).

[2024/10] Our paper entitled "mDARTS: Searching ML-based ECG classifiers against membership inference attacks" has been accepted for publication in the IEEE Journal of Biomedical and Health Informatics.