Master’s student @ KAIST EE
Seungjoo Lee
Weak-Supervised Learning, Mobile Sensing, Natural Language Processing
I am currently pursuing a Master’s degree at KAIST in Network & Mobile Systems Lab (NMSL) under the guidance of Professor Sung-Ju Lee. I received my B.S. degree in Computer Science from KAIST in 2022.
My research interest lies in the development of practical machine learning systems capable of real-world deployment, thereby benefiting individuals. For this, I am working on Federated Learning (FL) and ML-powered mobile sensing applications. My current research focuses on practical FL, particularly addressing label deficiency challenges.
News
• Dec 2023 | Participating EMNLP 2023 @ Singapore | |
• Oct 2023 | Paper accepted at EMNLP 2023 | |
• Aug 2022 | Graduated from KAIST with a bachelor's degree in Computer Science with honors | |
• Mar 2022 | Honorable Mention at ACM CHI 2022 | |
• Nov 2022 | Paper accepted at ACM CHI 2022 |
Publications
Conference papers
[EMNLP '23] FedTherapist: Mental Health Monitoring with User-Generated Linguistic Expressions on Smartphones via Federated Learning
Jaemin Shin, Hyungjun Yoon, Seungjoo Lee, Sungjoon Park, Yunxin Liu, Jinho D. Choi, Sung-Ju Lee
[CHI '22] MyDJ: Sensing Food Intakes with an Attachable on Your Eyeglass Frame
Jaemin Shin, Seungjoo Lee, Taesik Gong, Hyungjun Yoon, Hyunchul Roh, Andrea Bianchi, and Sung-Ju Lee
Best Paper Honorable Mention Award (Top 5%)
Demo/Workshop papers
[MobiSys '19 Demo] Accurate Eating Detection on a Daily Wearable Necklace
Jaemin Shin, Hyungjun Yoon, Seungjoo Lee, Sungjoon Park, Yunxin Liu, Jinho D. Choi, Sung-Ju Lee
Honors
KAIST 2023 Winner of the Graduate of the Year Award (KAIST Board of Trustee Chairperson's Prize)
2nd place out of 715 students, awarded to top 5 students (0.7%) who demonstrated outstanding performances in various activities as well as in grades. Awarded at the commencement ceremony, KAIST, Feb 2023
Summa Cum Laude
Awarded for achieving the highest academic performance among students, KAIST, Sep 2022
Engineering Innovator Award
Awarded to 5 students each semester, who showed outstanding performance in extracurricular activities, including academic publications, entrepreneurial activities, exhibitions, and inventions, KAIST college of engineering, Sep 2022
Honorable Mention Award
Awarded to top 5% of all submissions in CHI 2022, ACM SIGCHI, Mar 2022
U.S. Army Certificate of Appreciation
Awarded for exemplary service during military duty, serving as a role model for others, U.S. Army, Jul 2021
Dean's List
Awarded to top 3% among 2,900+ students in College of Engineering, KAIST, Fall 2019
Dean's List
Awarded to top 3% among 2,900+ students in College of Engineering, KAIST, Spring 2019
National excellence scholarship
National scholarship to students who showed excellence, Korea Student Aid Foundation, Fall 2018 - Fall 2019
Projects
Validating Labeling Functions in Domain Shift (Out of Domain Detection)
Course project in KAIST Advanced Big Data-AI Integration (EE616)
Domain shift detection using programmatic weak supervision
Will Overly Polite Sentences Harm Model Performance? Adversarial Pragmatic Perturbation for NLP
Course project in KAIST Bias and Ethics in Natural Language Processing course (AI620)
Adversarial attack on LLM model with tone perturbation and its defense
Rocket Recycling with Reinforcement Learning
Course project in KAIST Reinforcement Learning (EE488D)
Hovering & landing task with soft actor critic & curiosity-driven experience replay
Context-aware automatic video screen manipulation using trajectory tracking
Course project in KAIST Mobile Computing and Systems for Intelligent Living course (EE595)
Manipulating Youtube interface (rotate, zoom, relay from smartphone to laptop) using user head location & orientation.Implemented head tracking using Arduino & bluetooth connection between laptop, smartphone, and Arduino
Selected as interesting project and uploaded to the course website
GraspTraker: Tracking smartphone grab posture with inaudible sound
Course project in KAIST Mobile Computing and Applications course (CS442)
Detecting smartphone grasp posture using inaudible sound and FMCW modulation
SPADE-based Line Art Colorization
Course project in KAIST Introduction to Artificial Intelligence course (CS470)
SPADE-based model that colorizes a given line art image using a hint image
DeltaCNN: Efficient processing of CNN inference for continuous mobile vision
Course project in KAIST Operating System course (CS530)
Fast calculation of convolutional layers in continuous video streams using the fact that the video scene does not change significantly