Youngsik Yoon

POSTECH. ML Lab.

ysyoon_profile.jpg

I am a Ph.D. candidate in Computer Science and Engineering at POSTECH, advised by Prof. Jungseul Ok, and expect to graduate in February 2027. I study how to spend computation where it matters: which experts a mixture-of-experts language model should route to, when an LLM should plan at test time, and where a reinforcement learning agent should explore. Previously, I was a research intern at Microsoft Research Asia, mentored by Wei Chen and Siwei Wang.

You can reach me at    

Education

  • M.S./Ph.D. Integrated Program in Computer Science and Engineering, POSTECH
    2021.03 – 2027.02 (expected)
  • B.S. in Computer Science and Engineering & Mathematics, POSTECH
    2016.03 – 2021.02

Selected Publications

  • When Are Experts Misrouted? Counterfactual Routing Analysis in Mixture-of-Experts Language Models
    Youngsik Yoon, Siwei Wang, Wei Chen, Jungseul Ok
    Preprint
  • PaT: Planning-after-Trial for Efficient Test-Time Code Generation
    Youngsik Yoon, Sungjae Lee, Seockbean Song, Siwei Wang, Wei Chen, Jungseul Ok
    ACL 2026
  • Combinatorial Rising Bandits
    Seockbean Song*, Youngsik Yoon*, Siwei Wang, Wei Chen, Jungseul Ok
    ICLR 2026
  • Breadth-first Exploration on Adaptive Grid for Reinforcement Learning
    Youngsik Yoon, Gangbok Lee, Sungsoo Ahn, Jungseul Ok
    ICML 2024
  • Few-shot Unlearning
    Youngsik Yoon*, Jinhwan Nam*, Hyojeong Yun, Jaeho Lee, Dongwoo Kim, Jungseul Ok
    IEEE S&P 2024

Experience

  • Research Intern, Microsoft Research Asia (MSRA)
    2024.09 – 2025.03   ·   Mentored by Wei Chen and Siwei Wang
  • President of the Graduate Student Association, Dept. of Computer Science and Engineering
    2021.03 – 2022.02