Hyunwoo Kang

I'm a M.S. student in ALIN-LAB@KAIST, advised by Prof. Jinwoo Shin. Before my M.S., I received a B.S. in Computer Science and Physics (minor) at KAIST.

My research goal is to build generalizable, interpretable, and sample-efficient deep learning systems via using structured rules or human inductive biases. Specifically, I have been focused on robust representation learning. I also have an interest in the neuro-symbolic approach for deep learning.

Email: hyunwookang [at] kaist.ac.kr
Google scholar / Github / Twitter

Publications

Object-aware Contrastive Learning for Debiased Scene Representation
Sangwoo Mo*, Hyunwoo Kang*, Kihyuk Sohn, Chun-Liang Li, Jinwoo Shin
Neural Information Processing Systems (NeurIPS), 2021
paper / slide / poster / code
Qualcomm Innovation Fellowship Korea, 2021

Work Experience

Research Experience

External Collaborator, Google AI, Sunnyvale, CA (remote) - with Dr. Kihyuk Sohn and Dr. Chun-Liang Li, April 2021 - August 2021
Under-graduate research Intern, NMSL@KAIST, Dajeon, Korea, December 2018 - February 2019

Business Experience

Business Intern, VoyagerX (start-up), Seoul, Korea, March 2019 - July 2019

Education
Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea
M.S. in Electrical Engineering (advisor: Prof. Jinwoo Shin), September 2020 - present

Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Korea
B.S. in School of Computing & Department of Physics (minor) (Summa Cum Laude), March 2016 - August 2020

Selective Honors

Qualcomm Innovation Fellowship Korea, 2021 ($4,000)
LINE Scholarship, 2017
Dean's List, 2017 Spring

Projects

Interpretable learning for object detection, ADD, 2020

Teaching

TA, Data Structures and Algorithms (EE205), KAIST, Fall 2021
TA, Computer Networks (EE323), KAIST, Spring 2021
TA, Samsung DS AI Expert Program (Instructor: Jinwoo Shin), 2020
TA, CS101 Introduction to Programming, KAIST, Fall 2018