Kibum Kim
Ph.D candidate majoring Machine Learning
Hello, I’m Kibum Kim!
Currently, I’m a fourth-year Ph.D Candidate in Industrial & Systems Engineering at KAIST, where i am fortunate to be advised by Prof. Chanyoung Park. I recently completed a visiting scholarship at University of California San Diego (UCSD) under the guidance of Prof. Julian McAuley and am currently a research intern at Huawei R&D London, hosted by Zhensong Zhang, where I work on applications of Video Multimodal Large Language Models.
My current research focuses on accelerating the inference of Video Multimodal Large Language Models (MLLMs) while preserving fine-grained visual cues, as well as their downstream applications. Previously, I explored scene understanding in the image and video domains, tackling challenges such as long-tailed distributions, data scarcity, and recommender systems.
If you are interested or have any question, please don’t hesitate to reach out to me at kb.kim@kaist.ac.kr email.
News
| Sep 4, 2026 | Won 2nd Place in the EgoLongQA Challenge at the ECCV 2026 Wearable AI Workshop. |
|---|---|
| Jun 18, 2026 | Two papers got accepted at ECCV 2026. |
| May 14, 2026 | I was selected as as a Gold Reviewer (top reviewer) at ICML 2026. |
| Mar 16, 2026 | I started my research internship at Huawei R&D London, hosted by Principal Researcher: Zhensong Zhang. |
Educations
- Korea Advanced Institute of Science and Technology (link)Sep. 2023 - Present
- Ph.d in Industrial and Systems Engineering
- Research interest: Scene Understanding, Recommender Systems, Graph Neural Networks
- Advisor: Chanyoung Park
- Korea Advanced Institute of Science and Technology (link)Sep. 2021 - Jul. 2023
- M.S in Industrial and Systems Engineering
- Research interest: Scene Understanding, Recommender Systems, Graph Neural Networks
- Advisor: Chanyoung Park
- Hanyang University (link) Mar. 2015 - Aug. 2021
- B.S., Industrial Engineering (major) & Computer Science (minor)
Lead Project
- Development of a Foundation Model for Electromyography (EMG) Dec. 2025 - Present
-
- Collaboration with Seoul National University College of Medicine
- Visual Intelligence Technique Development (ETRI) Jun. 2021 - Present
-
- Scene graph generation for reasoning the visual context
- AI Development for reasoning, extraction, understanding of Common-sense Jun. 2022 - May. 2026
-
- Reasoning the visual context based on common-sense
- NAVER-Intel-KAIST (NIK) AI Collaboration Project Jul. 2024 - July. 2025
-
- Building a new AI ecosystem for increasing usability and applicability of Gaudi-v2 (link)
Teaching Experience
- KSE801: Recommender System and Graph Machine Learning Fall 2022
-
- Teaching Assistant Review session
- KSE527: Machine Learning for Knowledge Service Spring 2022
-
- Teaching Assistant