I’m a third-year CS Ph.D. student at Stanford, advised by Chelsea Finn and part of the IRIS lab. I am affiliated with SAIL, CRFM, and the ML Group. My research is partly supported by KFAS.
Previously, as alternative military service for the South Korean army, I worked as a research scientist at Kakao and AITRICS, working with Juho Lee. Before that, I completed my master’s (CS, advised by Seungjin Choi) and undergraduate (math) degrees at POSTECH.
Real-world conditions are nonstationary rather than static. My research interest is in building reliable machine learning systems that can navigate and make sound decisions in such perpetually changing environments. Here are some key questions that guide my research:
- Better teaching: Is there a more efficient and robust way to teach machines, beyond passive observation or imitation, so that they more easily “understand” the underlying concepts? What should we do when we want a machine to perform a task that humans cannot do well?
- Underspecification: No dataset fully specifies its intended task. How can we make models recognize and represent the multitude of possible realities consistent with given data?
- Understanding fine-tuning: How can we better conceptualize fine-tuning as applied in practice? What knowledge is present in foundation models, and what factors influence how much knowledge is preserved during fine-tuning?
- De-risking errors: What strategies can we employ to handle the reality of machine learning systems generating potentially erroneous outputs?
Selected Papers
NeurIPS 2023 workshops XAIA, ICBINB
NeurIPS 2023 workshop DistShift
ICLR 2024 (spotlight)
ICML 2023 (long oral)