Chanuk Lee

Hi, I’m Chanuk, a junior undergraduate at KAIST, advised by Prof. Sung Ju Hwang at the MLAI Lab.

My research focuses on building intelligent systems that make effective use of limited resources. I study how to improve reasoning performance while reducing the computation and supervision required for post-training [1, 2, 3], and how models can recognize when their own capabilities are insufficient and selectively leverage external resources at inference time [4].

More broadly, I am interested in learning and inference systems that allocate computation, information, and external resources where they are most useful. This includes efficient post-training, test-time scaling, tool-augmented reasoning, and self-improving agents that learn through interaction.

News

Sep 2026FlyBy and EAPO are now on arXiv.
Sep 2026NudgeRL has been accepted to the MATH-AI@NeurIPS 2026 workshop! 🎉
May 2026NudgeRL is now on arXiv.
May 2026SAGE has been accepted to ICML 2026! 🎉

Selected publications

All publications

* denotes equal contribution · † denotes corresponding authors / equal advising

arXiv2026

[S1] Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge

Chanuk Lee, Minki Kang, Sangwoo Park, Woongyeong Yeo, Jinheon Baek†, Sung Ju Hwang†

Paper Code

@misc{lee2026knowingthinkingenoughteaching,
  title={Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge},
  author={Chanuk Lee and Minki Kang and Sangwoo Park and Woongyeong Yeo and Jinheon Baek and Sung Ju Hwang},
  year={2026},
  eprint={2609.34327},
  archivePrefix={arXiv},
  primaryClass={cs.AI},
  url={https://arxiv.org/abs/2609.34327}
}

MATH-AI@NeurIPS2026

[S2] Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR

Chanuk Lee*, Sangwoo Park*, Minki Kang, Sung Ju Hwang

Paper Code

@article{lee2026nudging,
  title={Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR},
  author={Lee, Chanuk and Park, Sangwoo and Kang, Minki and Hwang, Sung Ju},
  journal={arXiv preprint arXiv:2605.15726},
  year={2026}
}

Experience

Oct 2025 — Present

KAIST MLAI Lab

Undergraduate Research Intern

Education

Mar 2022 — Present

KAIST

B.S. in Computer Science
Minor in Mathematics

Expected graduation 2028. Mandatory military service in the ROK Air Force, 2024–2025.

Mar 2020 — Feb 2022

Hansung Science High School

Early graduation (2 years)

Academic Service

Reviewer

MATH-AI@NeurIPS 2026