HEEJI YOON

profile_img.jpg
profile_back.jpg

click my pic!

I am 1st year M.S student in CVLAB@KAIST AI under the advisement of Prof. Seungryong Kim.

My research interest lies in understanding real world at multiple levels through the visual information, with the goal of solving practical problems. In particular, my current research focuses on segmentation and multimodal large language models (MLLMs), while I also hold a strong interest in medical AI.

Before joining KAIST, I received my B.S in Life Science from Korea University, where I was particularly fascinated by neuroscience. I remain deeply intrigued by the analogies between the human neurobiological system and artificial intelligence, and I look forward to the synergy they will continue to create.

If you have any questions or would like to connect, feel free to reach out via email (hjyoon@kaist.ac.kr) or LinkedIn!

Education

Publications

Preprints
  2. arXiv
    viral_teaser.png
    Visual Representation Alignment for Multimodal Large Language Models
    Heeji Yoon*, Jaewoo Jung*, Junwan Kim*, Hyungyu Choi, Heeseong Shin, Sangbeom Lim, Honggyu An, Chaehyun Kim, Jisang Han, Donghyun Kim, Chanho Eom, Sunghwan Hong, Seungryong Kim
    arXiv preprint arXiv:2509.07979, 2025
    arXiv Project Page
  3. arXiv
    ureca_fig.png
    URECA: Unique Region Caption Anything
    Sangbeom Lim*, Junwan Kim*, Heeji Yoon, Jaewoo Jung, and Seungryong Kim†
    arXiv preprint arXiv:2504.05305, 2025
    arXiv Project Page
  4. arXiv
    sola_fig.png
    Referring Video Object Segmentation via Language-aligned Track Selection
    Seongchan Kim*, Woojeong Jin*, Sangbeom Lim*, Heeji Yoon*, Hyunwook Choi, and Seungryong Kim†
    arXiv preprint arXiv:2412.01136, 2024
    arXiv Project Page
International Conference
  1. NeurIPS
    seg4diff_teaser.png
    Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformers
    Chaehyun Kim, Heeseong Hin, Eunbeen Hong, Heeji Yoon, Anurag Arnab, Paul Hongsuck Seo, Sunghwan Hong†, Seungryong Kim†
    Neural Information Processing Systems (NeurIPS), 2025
    arXiv Project Page
  2. ICCVW
    talk3d.jpeg
    High-Fidelity Talking Portrait Synthesis via Personalized 3D Generative Prior
    Jaehoon Ko, Kyusun Cho, Joungbin Lee, Heeji Yoon, Sangmin Lee, Sangjun Ahn, and Seungryong Kim†
    1st Workshop on Generative AI for Audio-Visual Content Creation @ ICCV (ICCVW), 2025
    arXiv Project Page
  3. ICCV
    main_framework.png
    S⁴M: Boosting Semi-Supervised Instance Segmentation with SAM
    Heeji Yoon*, Heeseong Shin*, Eunbeen Hong, Hyunwook Choi, Hansang Cho, Daun Chung, and Seungryong Kim†
    IEEE International Conference on Computer Vision (ICCV), 2025
    arXiv Project Page
  4. ACMMM
    gstalker_framework.png
    GaussianTalker: Real-Time High-Fidelity Talking Head Synthesis with Audio-Driven 3D Gaussian Splatting
    Kyusun Cho*, Joungbin Lee*, Heeji Yoon*, Yeobin Hong, Jaehoon Ko, Sangjun Ahn, and Seungryong Kim†
    ACM Multimedia, 2024
    arXiv Project Page

Honors & Awards