Avatar

Woo Jae Kim

Ph.D. Candidate

School of Computing, KAIST


CV | Google Scholar | GitHub


I am a Ph.D. candidate in Scalable Graphics, Vision, and Robotics (SGVR) Lab at KAIST advised by Prof. Sung-eui Yoon. I received my M.S. degree in Computer Science from KAIST and received my B.S. degree in Computer Science from KAIST in 2021 with minor in Electrical Engineering. I am also a recipient of the Qualcomm Innovation Fellowship 2023. I also work closely with Prof. Sooel Son and Kyle Min.

My research aims to build trustworthy and controllable AI systems that people can rely on in the real world. AI models are developed in ideal settings, but once deployed they often fail under non-ideal conditions such as adversarial attacks, unclear user instructions, and uncontrollable, non-transparent outputs. My work centers on failure localization, the idea of pinpointing where an AI system goes wrong and repairing only those parts. Guided by this idea, I have developed robust, secure, transparent, and controllable AI across computer vision, 3D vision, language models, and embodied agents. Going forward, I aim to build agentic and physical AI systems that can find and fix their own failures.

Contact

  • wkim97 [at] kaist.ac.kr

  • Bldg E3-1, Rm 3446, 291 Daehak-ro, Yuseong-gu, Daejeon, Korea, 34141

Education

  • Ph.D in Computer Science, KAIST

    - Advisor: Sung-eui Yoon

    Mar. 2023 - Feb. 2027 (Expected)

  • M.S. in Computer Science, KAIST

    - Advisor: Sung-eui Yoon

    Mar. 2021 - Feb. 2023

  • B.S. in Computer Science, KAIST

    - Minor in Electrical Engineering

    Sep. 2016 - Feb. 2021

Industry Experience

  • Research Intern, NAVER LABS

    - Mentor: Jinhan Lee

    - Collaborators: Kisung Kim, Daejung Kim

    - Topic: Vision-Language Navigation under imperfect user instructions

    Apr. 2026 - Oct. 2026

News

  • [Jun 2026] Two papers are accepted to ECCV 2026.
  • [Apr 2026] I started a research internship at NAVER LABS.
  • [Jan 2026] One paper is accepted to ICRA 2026.
  • [Jan 2026] Two papers are accepted to ICLR 2026.
  • [Sep 2025] Our paper is chosen as the best student paper at ICIP 2025!
  • [Aug 2025] Two papers are accepted to BMVC 2025.
  • [Jun 2025] One paper is accepted to ICIP 2025.
  • [Feb 2025] One paper is accepted to ICLR 2025.
  • [Sep 2024] One paper is accepted to NeurIPS 2024.
  • [Feb 2024] One paper is accepted to CVPR 2024.
  • [Jan 2024] Our work on adversarial defense is invited for a talk at Qualcomm Korea.
  • [Nov 2023] I received the Qualcomm Innovation Fellowship!
  • [Jul 2023] Our work on adversarial defense is invited for oral and poster presentations at KCCV 2023.
  • [Jul 2023] One paper is accepted to ICCV 2023.
  • [Feb 2023] One paper is accepted to CVPR 2023 as a highlights paper.
  • [Feb 2023] One paper is accepted to i3D 2023.
  • [Jun 2022] One paper is accepted to ICIP 2022 as an oral paper.
  • [Mar 2022] One paper is accepted to CVPR 2022.
  • [Jan 2022] One paper is accepted to ICASSP 2022.

Publications

Trustworthy AI Domain

  • AdKnob: Ad Intensity Control and Labeling for LLM-Native Advertising

    Woo Jae Kim, Seongho Keum, Joonsung Jeon, Suhyeon Ha, Sooel Son, and Sung-eui Yoon

    Under review

  • EvBS: Event-guided Blur Synthesis for Domain-adaptive Motion Deblurring

    Junsik Jung, Seokryun Choi, Yoonki Cho, Woo Jae Kim, Andrew Jeong, and Sung-eui Yoon

    ACM MM 2026

    [Project] [Paper]

  • RoME: Robust Mixture of Low-Rank Experts against Multiple Adversarial Perturbations

    Woo Jae Kim, Kyle Min, Suhyeon Ha, Joonsung Jeon, and Sung-eui Yoon

    ECCV 2026

    [Project] [Paper] [Code]

  • APT: Anchor-aligned Perturbations for Tamper Localization in Fully Regenerated Images

    Suhyeon Ha, Woo Jae Kim, Joonsung Jeon, Sooel Son, and Sung-eui Yoon

    ECCV 2026

    [Project] [Paper]

  • Beyond the Patch: Exploring Vulnerabilities of Visuomotor Policies via Viewpoint-Consistent 3D Adversarial Object

    Chanmi Lee, Minsung Yoon, Woo Jae Kim, Sebin Lee, and Sung-eui Yoon

    ICRA 2026

    [Project] [Paper]

  • Radiometrically Consistent Gaussian Surfels for Inverse Rendering

    Kyubeom Han, Jaeyoon Kim, Woo Jae Kim, Jinhwan Seo, and Sung-eui Yoon

    ICLR 2026 Oral paper

    [Project] [Paper] [Code]

  • No Caption, No Problem: Caption-Free Membership Inference via Model-Fitted Embeddings

    Joonsung Jeon, Woo Jae Kim, Suhyeon Ha, Sooel Son, and Sung-eui Yoon

    ICLR 2026

    [Project] [Paper] [Code]

  • AegisRF: Adversarial Perturbations Guided with Sensitivity for Protecting Intellectual Property of Neural Radiance Fields

    Woo Jae Kim, Kyubeom Han, Yoonki Cho, Youngju Na, Junsik Jung, Sooel Son, and Sung-eui Yoon

    BMVC 2025

    [Project] [Paper] [Code]

  • Learning Event-guided Exposure-agnostic Video Frame Interpolation via Adaptive Feature Blending

    Junsik Jung, Yoonki Cho, Woo Jae Kim, Lin Wang, and Sung-eui Yoon

    BMVC 2025

    [Paper]

  • Pose-free 3D Gaussian splatting via shape-ray estimation

    Youngju Na*, Taeyeon Kim*, Jumin Lee, Kyubeom Han, Woo Jae Kim, and Sung-eui Yoon

    ICIP 2025 Best student paper award (Top 0.16%)

    [Paper]

  • AdvPaint: Protecting Images from Inpainting Manipulation via Adversarial Attention Disruption

    Joonsung Jeon, Woo Jae Kim, Suhyeon Ha, Sooel Son, and Sung-eui Yoon

    ICLR 2025

    [Project] [Paper] [Code]

  • Generalizable Person Re-identification via Balancing Alignment and Uniformity

    Yoonki Cho, Jaeyoon Kim, Woo Jae Kim, Junsik Jung, and Sung-eui Yoon

    NeurIPS 2024

    [Project] [Paper] [Code]

  • UFORecon: Generalizable Sparse-View Surface Reconstruction from Arbitrary and UnFavOrable Sets

    Youngju Na, Woo Jae Kim, Kyubeom Han, Suhyeon Ha, and Sung-eui Yoon

    CVPR 2024

    [Project] [Paper] [Code]

  • Towards Content-based Pixel Retrieval in Revisited Oxford and Paris

    Guoyuan An, Woo Jae Kim, Saelyne Yang, Rong Li, Yuchi Huo, and Sung-eui Yoon

    ICCV 2023

    [Project] [Paper] [Datasets and Code] [Interactive Tools]

  • Feature Separation and Recalibration for Adversarial Robustness

    Woo Jae Kim, Yoonki Cho, Junsik Jung, and Sung-eui Yoon

    CVPR 2023 Highlights paper (~2.5% acceptance rate)

    [Project] [Paper] [Code]

  • Pixel-wise Guidance for Utilizing Auxiliary Features in Monte Carlo Denoising

    Kyubeom Han, Olivia G. Odenthal, Woo Jae Kim, and Sung-eui Yoon

    i3D 2023

    also published at Proceedings of the ACM on Computer Graphics and Interactive Techniques (PACMCGIT)

    [Project] [Paper] [Code]

  • Diverse Generative Perturbations on Attention Space for Transferable Adversarial Attacks

    Woo Jae Kim, Seunghoon Hong, and Sung-eui Yoon

    ICIP 2022 Oral paper (~10% acceptance rate)

    [Project] [Paper] [Code]

  • Part-based Pseudo Label Refinement for Unsupervised Person Re-identification

    Yoonki Cho, Woo Jae Kim, Seunghoon Hong, and Sung-eui Yoon

    CVPR 2022

    [Project] [Paper] [Code]

  • Deep Video Inpainting Guided by Audio-Visual Self-Supervision

    Kyuyeon Kim, Junsik Jung*, Woo Jae Kim*, and Sung-eui Yoon (* equal contributions)

    ICASSP 2022

    [Project] [Paper] [Code]

Patents

  • Method and System for Separating and Recalibrating Feature for Adversarial Robustness
    Sung-eui Yoon, Woo Jae Kim, Yoonki Cho, and Junsik Jung
    Selected as a strategic technology by the KAIST Technology Licensing Center
    • US Patent Granted (Patent No. 12,694,655), Jul. 2026
    • Japan Patent Granted (Patent No. 7628350), Jan. 2025
    • Korea Patent Pending (Application No. 10-2024-0002170), Filed Jan. 2024
  • Method and Computer Device for Generalizable Sparse-View Surface Reconstruction from Arbitrary and Unfavorable Sets
    Sung-eui Yoon, Youngju Na, Woo Jae Kim, Kyubeom Han, and Suhyeon Ha
    • Korea Patent Pending (Application No. 10-2024-0071859), Filed May 2024
  • Pixel-wise Guidance for Utilizing Auxiliary Features in Monte Carlo Denoising
    Sung-eui Yoon, Kyubeom Han, and Woo Jae Kim
    • Korea Patent Pending (Application No. 10-2023-0190779), Filed Dec. 2023

Research Grants

  • College of Engineering Master's and Ph.D. Venture Research Program, KAIST, 2024 ($10,000)
    - Topic: Building a proactive defense against intellectual property theft of radiance fields (NeRF, 3DGS)
    - Selected as one of 12 out of 73 proposals

Awards & Honors

  • Best Student Paper Award (as co-author), International Conference on Image Processing (ICIP), 2025
  • Research Impact Award, SGVR Lab, KAIST, 2025
  • Recipient, Qualcomm Innovation Fellowship, 2023
  • Paper Award, 34th Workshop on Image Processing and Image Understanding (IPIU), 2022
  • Best Teaching Assistant Award, School of Computing, KAIST, 2022 & 2023
  • Grand Prix Award (1st place), Undergraduate Research Program (URP), KAIST, 2021
  • National Government Fellowship, South Korea Government, 2016 - Present

Invited Talks & Presentations

  • Invited Talk on adversarial robustness, Qualcomm Korea, 2024
  • Invited Presentation on adversarial robustness, Korean Conference on Computer Vision (KCCV), 2023

Experiences

Teaching Experience

  • Teaching Assistant, CS588: Deep Learning based Image Search, KAIST (2024)
  • Teaching Assistant, AI Expert Program, Samsung Electronics (2023, 2025)
  • Teaching Assistant, CS101: Introduction to Programming, KAIST (2018-2019, 2021-2023)
  • Teaching Assistant, CS206: Data Structure, KAIST (2021, 2023)

Reviewer

  • CVPR (2023-2026)
  • ICCV (2023-2025)
  • ECCV (2024-2026)
  • NeurIPS (2025-2026)
  • ACM MM (2025)
  • WACV (2025-2026)
  • ACCV (2024)