Subin Kim

Research Interest

I am a Master student in MLML Lab. I am interested in reinforcement learning and cognitive AI (AGI). Currently, I am studying model-based, pixel-level zeroshot agent. This is an essay I wrote about the prospects of AI.

Education

KAIST, M.S., Computer Science, Mar 2023 – present

MLML Lab,

KAIST, B.S., Computer Science, Mar 2018 – Jan 2023

Work Experience

Research Intern, KAIST, DS Lab, (July 2022 – Jan 2022) Advisor: Sundong Kim

"인지 및 추론 연구를 위한 Mini-ARC 벤치마크 데이터"

KSC2022 (Best Paper Award)

"Playgrounds for Abstraction and Reasoning"

NeurIPS nCSI Workshop 2022

poster

KAIRI Intern, KAIST, DM Lab (Dec 2021 – June 2022) Advisor: Kijung Shin
SW Developer Intern, BankofWine (Jun 2022 - Aug 2022)

code

SW Developer Intern, RedWit (Jun 2021 - Aug 2021)

Demo

Research Intern, KAIST, PROSYS Lab, (June 2021 – Aug 2021) Advisor: Kihong Heo

Submitted as 2nd author

Poster

Research Intern, KAIST, CDSN Lab, (Jan 2021 – June 2021) Advisor: Dongman Lee, Sumin Han

"Spatio-Temporal Attention based Conditional Traffic Flow Prediction in Urban Areas",

Submitted as 2nd author to ECML-PKDD

"서울시의 토지 이용에 따른 도로의 차량 속도의 상관관계 분석"

KCC2020

Extracurricular activities & Experiences

Certified as Korean Red Cross lifeguard, Jan 2023
Participated as an instructor on Digital Warrior program 2nd, Hana bank, March 2022 - Present
Participated as an Assistant on HSS587, HSS590, Feb 2022 - Present
Participated as an instructor on Korean Camp, Jan 2022 - Feb 2022
Participated as an instructor on Digital Warrior program 1st, Hana bank, Oct 2021 - Dec 2021
Joined KAIST RUN team, 2021 - Present
Joined KAIST KAORIswimming club, Jun 2021 - Present
KAIST Buddy program, 2018
Joined KAIST pop band Sturgeon as a female drummer, 2018 - 2019

Projects/Courses

Deep Reinforcement Learning (Spring 2023) (A+)

NMix Q-learning: Investigating overestimation bias of Q-values
proposal(presentation) | presentation slides | final(presentation) | paper

CS470 Introduction to Artificial Intelligence (Spring 2022) (S)

Open Dialogue Generation based on knowledge graph
proposal(presentation) | progress report(presentation) | final(presentation) | paper

CS492 Special Topics in Computer Science<Graph Machine Learning and Mining> (Spring 2022) (S)

Movie recommender system based on emotion analysis
proposal(presentation) | proposal(video) | final presentation | paper

CS454 Artificial Intelligence Based Software Engineering (Fall 2021) (A+)

Improving Directed Greybox Fuzzing using Monte-Carlo Decision Tree and Ant Colony Optimization
final presentation | code | paper

CS376 Machine Learning (Fall 2021) (A-)

Basics of machine learning
projects

IE481 Special Topics in Industrial Engineering I<AI for Smart Life> (Spring 2020) (S)

Q&AI: An AI-Infused Question Answering System for Online Learning
final paper

CS270 Intelligent robot design and programming (Spring 2021) (A-)

Using Q-Learning(MDP) and Deep Q-Learning to solve grid-searching robots
Assignment

CoE202 Basics of Artificial Intelligence<Big data analsys and machine learning> (Fall 2019) (A+)

Semantic segmentation through state-of-the-art CNN models
paper | code

CS330 Operating Systems and Lab (Spring 2021) (A0)

Implement simple operating system framework pintos-kaist for x86-64
Lab1 100/100 (avg 90.3), Lab2 118.24/120 (avg 85.08), Lab3 104.17/115 (avg 68.55), Lab4 133/150 (avg 59.78)
code

CS341 Introduction to Computer Networks (Fall 2021) (A0)

Implement Ethernet, IP, TCP layer in KENSv3(KAIST Educational Network System)
PA1 7.19/8 (avg 6.57), PA2 7.5/8 (avg 6.62), PA3 6.95/8 (avg 5.18), PA4 9/9 (avg 7.17) + additional score, total 30/30 (avg 24.96)
code

CS473 Introduction to Social Computing (Fall 2021) (A+)

Implement social game streaming system that supports live stream, character movement, chatting, emoji, games, etc
Lo-fi prototype | Hi-fi prototype | Project pitch | Video | Final report | Frontend Code, Backend Code

Contact

Subin Kim
21supersoo (at) kaist.ac.kr
1st year, M.S.
KAIST
Daejeon, Republic of Korea

(Last Update: 2023/11/19)