Yoonki Cho

Yoonki Cho
Ph.D. Candidate @ KAIST

About

I am a Ph.D. candidate at the Scalable Graphics, Vision, and Robotics (SGVR) Lab @ KAIST, advised by Prof. Sung-Eui Yoon. Before joining SGVR Lab, I received my B.S. degree in Computer Science from Korea University.

My research interest spans computer vision and machine learning, with a particular focus on developing efficient and robust representation learning for visual retrieval systems.

CV / Email / Google Scholar / LinkedIn / GitHub

Education

Mar. 2021 - Current: Ph.D. Candidate in Computer Science, KAIST (Advisor: Sung-Eui Yoon)

Mar. 2019 - Feb. 2021: M.S. in Computer Science, KAIST (Advisor: Sung-Eui Yoon)

Mar. 2015 - Feb. 2019: B.S. in Computer Science, Korea University

Research

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, Sung-Eui Yoon
British Machine Vision Conference (BMVC), 2025.
Paper / Code

Learning Event-guided Exposure-agnostic Video Frame Interpolation via Adaptive Feature Blending
Junsik Jung, Yoonki Cho, Woo Jae Kim, Lin Wang, Sung-Eui Yoon
British Machine Vision Conference (BMVC), 2025.
Paper

Pinpointing Trigger Moment for Grounded Video QA: Enhancing Spatio-temporal Grounding in Multimodal Large Language Models
Jinhwan Seo, Yoonki Cho, Junhyug Noh, Sung-Eui Yoon
Technical Report, The 3rd Perception Test Challenge @ ICCV, 2025. (Winner - Track 4: Grounded VideoQA)
Paper / Talk Slides

Towards Robustness of Person Search against Corruptions
Woojung Son, Yoonki Cho, Guoyuan An, Chanmi Lee, Sung-Eui Yoon
IEEE/CVF International Conference on Computer Vision (ICCV), 2025.
Paper / Code

Enhancing Visual Re-ranking through Denoising Nearest Neighbor Graph via Continuous CRF
Jaeyoon Kim, Yoonki Cho, Taeyoung Kim, Sung-Eui Yoon
IEEE International Conference on Image Processing (ICIP), 2025. (Spotlight)
Paper

Generalizable Person Re-identification via Balancing Alignment and Uniformity
Yoonki Cho, Jaeyoon Kim, Woo Jae Kim, Junsik Jung, Sung-Eui Yoon
Conference on Neural Information Processing Systems (NeurIPS), 2024.
Paper / Project / Code

Feature Separation and Recalibration for Adversarial Robustness
Woo Jae Kim, Yoonki Cho, Junsik Jung, Sung-Eui Yoon
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023. (Highlight)
Paper / Project / Code / Video

Part-based Pseudo Label Refinement for Unsupervised Person Re-identification
Yoonki Cho, Woo Jae Kim, Seunghoon Hong, Sung-Eui Yoon
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.
Paper / Project / Code / Video

RCIK: Real-Time Collision-Free Inverse Kinematics Using a Collision-Cost Prediction Network
Mincheul Kang, Yoonki Cho, Sung-Eui Yoon
IEEE Robotics and Automation Letters (RA-L), 2022.
Paper / Project / Code / Video

Experience

Research Assistant, National Forensic Service, Korea (Jul. 2017 - Dec. 2017)

Awards & Honors

Winner (1st Place), Track 4: Grounded VideoQA, Perception Test Challenge @ ICCV 2025
Cheongho Scholarship (full funding), Cheongho Cultural Foundation, 2017-2018
Science Talent Scholarship (full funding), Korea University, 2015-2016

Teaching

Teaching Assistant

AI Expert Course (Vision & Algorithm), Samsung Electronics, Summer 2023 & Summer 2024
[CS341] Introduction to Computer Networks, KAIST, Fall 2019
[CS576] Computer Vision, KAIST, Spring 2020
[CS360] Introduction to Database, KAIST, Spring 2021
[CS492(I)] Introduction to Deep Learning, KAIST, Fall 2022
[CS230] System Programming, KAIST, Spring 2023
[CS206] Data Structure, KAIST, Fall 2023

Academic Activities

Reviewer

CVPR (2023-2025), ICCV(2025), AAAI(2025-2026), NeurIPS(2025), TNNLS, etc