Computing for Embedded Lightweight Learning

EE Department @ POSTECH

We design the future learning technology and platform.

slider-image
About Us
Primary Research Theme

Efficient AI Technology

We focus on how to redesign AI and learning technologies towards superior computing efficiency for IoT/Big Data/edge computing. We explore alternative computing solutions for future learning technology, including near data computing to push computation beyond traditional processors, and brain-inspired hyperdimensional computing that closely models the ultimate efficient processor - the human brain.

Latest News

Accepted Paper at PACT 2025

Research on scalable RAG retrieval, presented in our paper “Bit-Level Semantics: Scalable RAG Retrieval with Neurosymbolic Hyperdimensional Computing,” will appear at PACT 2025.

Accepted Paper at DAC 2025, ISCA 2025, SIGMETRICS 2025

3 papers accepted: DiTTO, a novel diffusion-based framework for generating realistic, configurable, and diverse multi-device storage traces (DAC 2025); FlexNeRFer, an energy-efficient NeRF accelerator (ISCA 2025); and a diffusion-based generative-AI surrogate framework for system optimization (SIGMETRICS 2025).

Accepted Paper at ICRA 2025, DATE 2025

3 papers accepted: Research on a dynamic-encoding, oversampling HD federated learning framework for mobile robots (ICRA 2025); an HD framework designed with fine-grained feature encoding and a robust training scheme to effectively capture complex data patterns (DATE 2025); and a dynamic pruning framework for large language models enabling real-time adaptation with competitive accuracy and improved efficiency (DATE 2025).

Address

LG Research Building #301, 77 Cheongam-Ro, Namgu, Pohang (Postal code: 37673), REPUBLIC OF KOREA

Email

yeseongkim@postech.ac.kr

Phone

(+82) 054-279-2218