About Me

Hi, I’m Chanuk Lee, a junior undergraduate student at KAIST School of Computing, currently advised by Prof. Sung Ju Hwang at the KAIST MLAI Lab.

My research interests primarily lie in LLM post-training, including RLVR and distillation, but I am broadly interested in efficient and scalable learning for language models. Recently, my work has focused on exploration in LLM reinforcement learning.

Here is my CV.

News

• May 2026 NudgeRL is now on arXiv.
• May 2026 SAGE has been accepted to ICML 2026! 🎉

Selected Publications

* denotes equal contribution

@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}
}

@article{lee2026sage,
  title={SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs},
  author={Lee, Chanuk and Kang, Minki and Hwang, Sung Ju},
  journal={arXiv preprint arXiv:2605.18864},
  year={2026}
}

Full publication list →

Experience

• Oct 2025 – Present KAIST MLAI Lab — Undergraduate Research Intern

Education

• Mar 2022 – Present KAIST, School of Computing — B.S. in Computer Science, minor in Mathematics Expected graduation 2028; two years of mandatory military service in the ROK Air Force (2024–2025)
• Mar 2020 – Feb 2022 Hansung Science High School Early graduation (2 years)