CV

General Information

Full Name Hayeon Kim
Languages English, Korean

Education

  • 2023-(2025)
    Ph.D. Student in Electrical and Computer Engineering
    Seoul National University
    • Multimodal Generative AI (Text, Image, 3D), High- Dimensional Generative AI (<8K images, Video, 3D, 4D), Low-level Vision using pre-trained model (restoration, segmentation)
  • 2018–2023
    B.S. in Electrical and Computer Engineering
    Seoul National University

Publications

  • 2025
    RoMaP: Robust 3D-Masked Part-level Editing in 3D Gaussian Splatting with Regularized Score Distillation Sampling
    • Authors: Hayeon Kim*, Ji Ha Jang*, Se Young Chun

    • Venue: ICCV 2025

    • Paper   Project
  • 2025
    CDAM: Class Distribution-induced Attention Map for Open-vocabulary Semantic Segmentations
    • Authors: Dong Un Kang, Hayeon Kim, Se Young Chun

    • Venue: ICLR 2025

    • Paper   Project
  • 2024
    BeyondScene: Higher-Resolution Human-Centric Scene Generation With Pretrained Diffusion
    • Authors: Gwanghyun Kim*, Hayeon Kim*, Hoigi Seo*, Dong Un Kang*, Se Young Chun

    • Venue: ECCV 2024

    • Paper   Project
  • 2024
    Contribution-based Low-Rank Adaptation with Pre-training Model for Real Image Restoration
    • Authors: Dongwon Park, Hayeon Kim, Se Young Chun

    • Venue: ECCV 2024

    • Paper   Project
  • 2023
    DITTO-NeRF: Diffusion-based Iterative Text To Omni-directional 3D Model
    • Authors: Hoigi Seo*, Hayeon Kim*, Gwanghyun Kim*, Se Young Chun

    • Venue: arXiv 2023

    • Paper   Project

Work Experience

  • 2021
    BlueSignum Inc.
    • DailyBean App iOS development and involved in planning the detailed concept of the app.
    • Impact - The App ``DailyBean" is selected as the App of the day in the global AppStore.
    • Your Counseling Center App Product management

Additional Experience

  • 2022
    Metaverse Developer Competition -- Ministry of Science and ICT, Korea
    • vocAR App development
    • Developed and designed a comprehensive mobile application utilizing cutting-edge AI techniques, including image classification, text recognition, and augmented reality.
  • 2021
    Beyond Limit - Samsung Industrial Research Project
    • Develop Variational quantum linear solver - Improvement in Variational Quantum Algorithms by measurement simplification using Python & Mathematica
    • Refactoring naive quantum simulator - Refactoring the whole structure of naive quantum simulator by using Python
  • 2020
    XCORPS - Practical Issue Research Contest
    • Speech Split - Developed specific code to decomposed the input speech into pitch, identity, rhythm and content using PyTorch, and optimized them for voice personalization.
    • Creating Homepage - Designed the overall homepage and implemented responsive website with JavaScript, HTML and CSS5.

Academic Interests

  • Multimodal Generative AI.
    • Text, Image, 3D Point Cloud generation
  • High-dimensional Generative AI.
    • ~8K images, Video, 3D, 4D
  • Low-level Vision using pre-trained model.
    • Image restoration with fine-tuning, Image segmentation using CLIP