Yoonjeon Kim

Ph.D student at Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST)

Hello, I am a Ph.D candidate at Machine Learning and Intelligence Lab (MLILAB) in KAIST, advised by Prof. Eunho Yang.

Currently my research interest lies in enhancing reasoning model in both language and multi-modal domains. More specifically, I am focusing on the thinking ability of diffusion-based large language models, in its natural way.

Publications

  • Meta-Awareness Enhances Reasoning Models: Self-Alignment Reinforcement Learning [paper] [code]
    Yoonjeon Kim*, Doohyuk Jang*, Eunho Yang (*equal contribution)
    Preprint

  • Reasoning Model is Stubborn: Diagnosing Instruction Overriding in Reasoning Models [paper] [code] [project page]
    Doohyuk Jang*, Yoonjeon Kim*, Chanjae Park, Hyun Ryu, Eunho Yang (*equal contribution)
    Preprint

  • Preserve or Modify? Context-Aware Evaluation for Balancing Preservation and Modification in Text-Guided Image Editing [paper] [code] [project page]
    Yoonjeon Kim*, Soohyun Ryu*, Yeonsung Jung, Hyunkoo Lee, Joowon Kim, June Yong Yang, Jaeryong Hwang, Eunho Yang (*equal contribution)
    CVPR 2025

  • Learning Input-agnostic Manipulation Directions in StyleGAN with Text Guidance [paper]
    Yoonjeon Kim, Hyunsu Kim, Junho Kim, Yunjey Choi, Eunho Yang
    ICLR 2023

  • Sequential targeting: A continual learning approach for data imbalance in text classification [paper]
    Joel Jang, Yoonjeon Kim, Kyoungho Choi, Sungho Suh
    Expert Systems with Applications 2021

Invited Talk

  • AI Technology Seminar hosted by KAIST AI Graduate School [link]

Work Experience

  • Research Intern, NAVER Cloud, July. 2023 - Oct. 2023

Education

  • Ph.D. in Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST), Mar. 2023 - Present

  • M.S. in Graduate School of AI, Korea Advanced Institute of Science and Technology (KAIST), Mar. 2021 - Feb. 2023

  • B.S. in Applied Statistics, Yonsei University, Mar. 2017 - Feb. 2021

Projects

  • A Study on Optimization and Network Interpretation Method for Large-Scale Machine Learning
    National Research Foundation of Korea (NRF), Mar.2024-Feb.2027

  • Efficient Foundation Models on Intel Systems
    Intel Corporation & NAVER, Sep.2024-Aug.2027

  • Naver-KAIST Hyper-Creative Center
    NAVER Cloud, Sep.2021-Aug.2023

Acamdeic Services

  • Conference Reviewer
    • International Conference on Learning Representations (ICLR)
    • Computer Vision and Pattern Recognition (CVPR)
    • Conference on Neural Information Processing Systems (NeurIPS)