Sewoong Lee is a PhD student at UIUC, advised by Professor Julia Hockenmaier. He received his Bachelor's degree from Seoul National University and his Master of Computer Science from UIUC. Before joining the PhD program, he worked as a Staff Engineer in Data Science at Samsung Electronics. Sewoong has been awarded the Pre-doctoral Fellowship from UIUC and the National Science and Engineering Scholarship from the Korea Student Aid Foundation. His research interests lie at the intersection of AI, NLP, and mechanistic interpretability.
Se as in seven, woo as in wood. You can also call me Sam.
Present
University of Illinois Urbana-ChampaignNatural Language Research Group, advised by Prof. Julia Hockenmaier.
2023–2024
Samsung ElectronicsMechatronics Research
2022–2023
University of Illinois Urbana-ChampaignGPA 4.0 / 4.0
2016–2023
Samsung ElectronicsMechatronics R&D Center
2009–2015
Seoul National UniversityCum laude
November 2025
Sparse Autoencoders: Discoveries, Limitations, and the Bridge between Experiment and Theory
Amazon-Illinois Center, UIUC NLP Large Group [Event] [Photo]
Teaching assistant, University of Illinois Urbana-Champaign.
Reviewer.
Boston Consulting GroupResearch Analyst (Intern)2014–2015
Bain & CompanyResearch Assistant (Intern)2014
Ernst & YoungSummer Intern2014
LG CNSSummer Intern2013
* Equal contribution.
MineCEraft: evaluating language models as construction engineers.
V-Steer: steering instruction hierarchies at inference time.
KR20240023791A
Filed August 16, 2022; granted September 10, 2025
Normal and abnormal sensor readings (Figure 5).
US20250079211A1
Filed May 2, 2024; published March 6, 2025
Input, hidden, and output layers (Figure 6).
Learning from equipment time series to detect faults without labeled anomalies.
Outstanding Paper, Bronze Award, Samsung P&P Fair
Samsung Mechatronics Research P&P Fair, 2023
Separating normal and faulty sequences (Figure 2)