
I’m a CS Ph.D. student at Stanford, advised by Chelsea Finn and part of the IRIS Lab. My research is supported by the KFAS Doctoral Fellowship.
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.
My research interest is in developing models capable of learning and decision-making in changing environments. To do so, I believe we should go beyond the independent and identically distributed (i.i.d.) paradigm and account for the variability of real-world conditions in our learning procedures. Two alternative problem formulations of interest to me are meta-learning and distribution-shift robustness, which encode the non-static nature of data generating processes through notions of tasks and domains.
My publications grouped by topic:
- Robustness [NeurIPS22, ICLR23a, ICLR23b, pre23]
- Meta-learning [ICML18, NeurIPS20a, NeurIPS20b, Entropy22, NeurIPS22]
- Attention [ICML19, NeurIPS19, NeurIPS19-W, arxiv21]
- Distillation [UAI21, NeurIPS21]