JeongHyeon Kim

GitHubGoogle ScholarLinkedInEmail

jeonghyeonkim-pic.jpg

Hello! My name is Jeonghyeon Kim, and I am a Ph.D. student in Data Science at SeoulTech, advised by Prof. Sangheum Hwang of DAINTLAB.

🧗‍♂️I am dedicated to enhancing the reliability and interpretability of AI systems, particularly through:

  • Out-of-distribution detection (OoDD)
  • LLM unlearning
  • Energy based models (EBMs)

⭐️Research Focus

My research explores OoDD in vision-language models (VLMs) like CLIP, leveraging multi-modal fine-tuning (MMFT). In our work, we have addressed the modality gap between image and text embeddings through cross-modal alignment (CMA), enhancing the utilization of pretrained knowledge. Moving forward, we aim to extend this research to multi-modal pre-training and integrate large language models.

I am also interested in LLM unlearning, with a particular focus on preserving utility performance while effectively unlearning target knowledge. I have developing strategies for dataset sampling methods that optimize the balance between forgetting targeted information and maintaining model utility.

💥Ultimate Goal

To develop AI systems that are reliable, and interpretable, ensuring their trustworthy deployment in real-world applications.

News

Feb 26, 2025 “Enhanced OoD Detection through Cross-Modal Alignment of Multi-Modal Representations” has been accepted at CVPR 2025 !🔥

Publications

  1. VLM OoDD
    main.jpg
    Enhanced OoD Detection through Cross-Modal Alignment of Multi-Modal Representations
    Jeonghyeon Kim, and Sangheum Hwang
    In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025
  2. Unlearning
    unlearn.jpg
    Uncovering Hidden Vulnerabilities in Machine Unlearning: Adversarial Attack as a Probe and Pruning as a Solution
    Hwiyeong Lee Jeonghyeon Kim, and Sangheum Hwang
    In Korea Computer Congress 2024, 2024
  3. VLM OoDD
    Comparison_figure.jpg
    Comparison of Out-of-Distribution Detection Performance of CLIP-based Fine-Tuning Methods
    Jihyo Kim Jeonghyeon Kim, and Sangheum Hwang
    In 2024 International Conference on Electronics, Information, and Communication (ICEIC), 2024
  4. VLM OoDD
    KCC2023_figure_final.jpg
    Enhancing Out-of-Distribution Detection Performance of CLIP Based on Fine-tuning with Random Texts
    Jeonghyeon Kim Jihyo Kim, and Sangheum Hwang
    In Korea Computer Congress 2023, 2023
  5. Active Learning
    AL_figure.jpg
    Deep Active Learning with Contrastive Learning Under Realistic Data Pool Assumptions
    Jihyo Kim Jeonghyeon Kim, and Sangheum Hwang
    2023