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 spent most of my childhood growing up in the United States, having graduated from Northview High School in Johns Creek, GA. I am also a recipient of the Qualcomm Innovation Fellowship 2023.
My research focuses on adversarial robustness, AI safety, and 3D computer vision. I develop robust AI systems that maintain performance under diverse real-world threats, with recent work on protecting intellectual property of neural radiance fields and building mixture-of-experts architectures for multi-threat defense. I also collaborate extensively on 3D vision problems and privacy-preserving machine learning. More recently, I am interested in building robust and safe Vision-Language-Action (VLA) systems that can operate reliably in the real world.
I am actively seeking for industrial internship positions. Please feel free to contact me for any potential opportunities!
wkim97 [at] kaist.ac.kr
Bldg E3-1, Rm 3446, 291 Daehak-ro, Yuseong-gu, Daejeon, Korea, 34141
B.S. in Computer Science, KAIST
- Minor in Electrical Engineering
Sep. 2016 - Feb. 2021
High School, Northview High School, Johns Creek, GA, USA
Sep. 2012 - May. 2016
Learning Event-guided Exposure-agnostic Video Frame Interpolation via Adaptive Feature Blending
BMVC 2025
Pose-free 3D Gaussian splatting via shape-ray estimation
ICIP 2025 Best student paper award (Top 0.16%)
Towards Content-based Pixel Retrieval in Revisited Oxford and Paris
ICCV 2023
Feature Separation and Recalibration for Adversarial Robustness
CVPR 2023 Highlights paper (~2.5% acceptance rate)
Diverse Generative Perturbations on Attention Space for Transferable Adversarial Attacks
ICIP 2022 Oral paper (~10% acceptance rate)