About Me

I am a Research Engineer at Nota AI specializing in advanced AI model compression (e.g., quantization) and hardware-aware model optimization methods. Previously, I was a Machine Learning Engineer at Xiaomi working on Large Language Model (LLM) acceleration and building large-scale recommender systems. I received a master's degree at Seoul National University in computer science, advised by Prof. U Kang where I conducted research related to NLP model compression. Here is a full Curriculum Vitae.

Experience

Research Engineer Jul. 2023 - Present

Nota AI Seoul, Republic of Korea


Machine Learning Engineer Oct. 2021 - Jun. 2023

Xiaomi AI Lab Beijing, China


Research Assistant Aug. 2019 - Aug. 2021

Data Mining Lab @ SNU Seoul, Republic of Korea

Education

Seoul National University , Republic of Korea
M.S. in Computer Science and Engineering
Aug. 2019 - Aug. 2021

Harbin Engineering University , China
B.Eng. in Computer Science and Technology
Aug. 2015 - June. 2019

Publications

•
EdgeFusion: On-Device Text-to-Image Generation
Thibault Castells, Hyoung-Kyu Song, Tairen Piao, Shinkook Choi, Bo-Kyeong Kim, Hanyoung Yim, Changgwun Lee, Jae Gon Kim, Tae-Ho Kim
CVPR 2024 EDGE Workshop | ArXiv | Code

•
SensiMix: Sensitivity-Aware 8-bit Index & 1-bit Value Mixed Precision Quantization for BERT Compression
Tairen Piao, Ikhyun Cho, and U Kang
PLOS ONE (2022) | Code

Teaching Experience

  • T.A. M1522.001400 Introduction to Data Mining @SNU Spring 2020
  • T.A. M1522.000900 Data Structure @SNU Fall 2020
  • T.A. SK-Univ @SK Aug 2020