Kibum Kim

Hello, I’m Kibum Kim!

Currently, I’m a Ph.D student in Industrial & Systems Engineering at KAIST, where i am fortunate to be advised by Prof. Chanyoung Park.

I’m actively on research with my best teammates at DSAIL@KAIST.

Nowadays, machine learning has advanced significantly and is being applied across various domains. However, despite these advancements, fundamental challenges still arise, which compromise the model’s generalizability. In this regard, I focus on addressing the challenges of machine learning that occur across diverse domains, thereby improving the generalization power. The fundamental challenges of interest, but are not limited, are as follows:

• Long-tailedness: The challenge of predicting tail classes
• Data Scarcity: The challenge of collecting large-scale datasets
• Adversarial Attacks: The challenge of preserving model’s robustness under attacks

Since fundamental challenges arise across diverse domain, my research areas are diverse and include the following: Scene Understanding, Recommender Systems, and Graph Neural Networks.

If you are interested or have any question, please don’t hesitate to reach out to me at kb.kim@kaist.ac.kr email.