Hi, I am a PhD student researching artificial intelligence at KAIST. I write posts about interesting problems or ideas after I think about them for a while. I also write educational posts, e.g. on physics.
I have a passion for building technology that can empower individuals, in particular by helping them better understand the world. From a reductionist point of view, this is a problem of influencing/controlling/assisting humans so that they achieve a certain mental state, namely one with a better understanding. Imbuing AIs with a strong theory of mind would therefore be extremely helpful. However, such technology poses some unique risks such as malicious usage, or strong reward tampering, which should be investigated in parallel. Some other directions I’m interested in are AIs that can predict the future very accurately, a.k.a. AI superforecasters [1][2][3][4][5][6], AIs that can enhance collective intelligence by facilitating communication between humans [7][8], and scalable oversight [9][10].
Education
Korea Advanced Institute of Science and Technology (KAIST)
Ph.D. in Graduate School of Artificial Intelligence
2025 - Present
Korea Advanced Institute of Science and Technology (KAIST)
M.S. in Graduate School of Artificial Intelligence
2023 - 2025
Korea Advanced Institute of Science and Technology (KAIST)
B.S. in Mathematics | Summa Cum Laude
2019 - 2023
Publications
- Yegon Kim, Seungyoo Lee, Chaeyun Jang, Hyungi Lee, Juho Lee,
Under review, Parallel Test-Time Scaling with Multi-Sequence Verifiers - Chaeyun Jang, Moonseok Choi, Yegon Kim, Hyungi Lee, Juho Lee,
ICML 2025 Workshop R2-FM, Verbalized Confidence Triggers Self-Verification: Emergent Behavior Without Explicit Reasoning Supervision - Yegon Kim, Hyunsu Kim, Gyeonghoon Ko, Juho Lee,
ICML 2025, Active Learning with Selective Time-Step Acquisition for PDEs - Hyunsu Kim, Yegon Kim, Hongseok Yang, Juho Lee,
ICML 2024, Variational Partial Group Convolutions for Input-Aware Partial Equivariance of Rotations and Color-Shifts