Minho Park

Researcher at Electronics and Telecommunications Research Institute (ETRI)

I’m Minho Park. I received my B.S. (2018) and M.S. (2020) degrees in Electrical Engineering from KAIST. Currently, I am a Ph.D. student at KAIST, advised by Prof. Yong Man Ro, and also work as a researcher at ETRI. My research focuses on the synergy between Generative AI and Multimodal Learning. I am particularly interested in advancing Scalable Generative Frameworks and Probabilistic Modeling. My current work involves developing robust Vision-Language Representation Models and ensuring AI Safety within Large Language and Vision Models (LLMs/VLMs).

Email: roger618 [at] etri.re.kr

[Google Scholar] [LinkedIn] [CV]

Education

Korea Advanced Institute of Science and Technology (KAIST), South Korea (Mar. 2024 - Present)

Ph.D in Electrical Engineering (Advisor: Prof. Yong Man Ro)

Korea Advanced Institute of Science and Technology (KAIST), South Korea (Mar. 2018 - Feb. 2020)

M.S in Electrical Engineering (Advisor: Prof. Yong Man Ro)

Korea Advanced Institute of Science and Technology (KAIST), South Korea (Mar. 2013 - Feb. 2018)

B.S in Electrical Engineering

Research Interests

Generative Model (Diffusion, Flow-matching)
Multi-modal AI (Vision-Language Representation Model)
AI Safety (LLM, VLM)

Experience

Electronics and Telecommunications Research Institute, South Korea (Mar. 2020 - Present)
- Senior Researcher at AI Safety Research Section

Publications

Focus Where It Matters: LLM-Guided Regional Identification for Instruction-based Image Editing

Minho Park, Young Joo Jo, Jae-Hyeok Lee, Ji Yong Lee, Dong-oh Kang, Yong Man Ro

ACM International Conference on Multimedia (ACM MM), 2025

LGD-BEV: Label-Guided Distillation for BEV 3D Object Detection

Ji-Yong Lee, Minho Park, Youngjoo Jo, Dong-Oh Kang

IEEE Access, 2025

UP-VTON: A Unified Virtual Try-On Framework Supporting Mask, Mask-Free, and Prompt-Driven Guidance

Young Joo Jo, Minho Park, Dong-Oh Kang

IEEE International Conference on Computer Vision Workshop (ICCV Workshop), 2025

SMIT: Style-based Multi-level Feature Fusion for Image-to-Image Translation

Narae Yi*, Minho Park*, Dong-Oh Kang

International Conference on Information and Communication Technology Convergence (ICTC), 2024

Network-Based Message Selection for Efficient Communication of Multi-Agent Collaboration

Seungjun Hyeon, Minho Park, Dong-oh Kang

International Conference on Information and Communication Technology Convergence (ICTC), 2024

Augmenting Features via Contrastive Learning-based Generative Model for Long-Tailed Classification

Minho Park, Hyung-Il Kim, Hwa Jeon Song, Dong-Oh Kang

IEEE International Conference on Computer Vision Workshop (ICCV Workshop), 2023

Context-aware Image-to-Image Translation for Autonomous Driving

Narae Yi, Minho Park, Dong-Oh Kang

IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia), 2023

Urban scene editing with diffusion model using segmentation mask

Minho Park, Dong-oh Kang

International Conference on Control, Automation and Systems (ICCAS), 2023

Complex Motion-aware Splatting for Video Frame Interpolation
Minho Park, Yuseok Bae

International Conference on Information and Communication Technology Convergence (ICTC), 2023

Learning to embed multi-modal contexts for situated conversational agents

Haeju Lee, Oh Joon Kwon, Yunseon Choi, Minho Park, Ran Han, Yoonhyung Kim, Jinhyeon Kim, Youngjune Lee, Haebin Shin, Kangwook Lee, Kee-Eung Kim

Findings of the Association for Computational Linguistics (NAACL), 2022

Imbalanced classification via feature dictionary-based minority oversampling

Minho Park, Hwa Jeon Song, Dong-Oh Kang

IEEE Access, 2022

Tackling situated multi-modal task-oriented dialogs with a single transformer model

Haeju Lee, Oh Joon Kwon, Yunseon Choi, Jinhyeon Kim, Youngjune Lee, Ran Han, Yoonhyung Kim, Minho Park, Kangwook Lee, Haebin Shin, Kee-Eung Kim

Association for the Advancement of Artificial Intelligence Workshop (AAAI Workshop), 2021

Visual comfort aware-reinforcement learning for depth adjustment of stereoscopic 3d images

Hak Gu Kim, Minho Park, Sangmin Lee, Seongyeop Kim, Yong Man Ro

Association for the Advancement of Artificial Intelligence (AAAI), 2021

Video frame interpolation via exceptional motion-aware synthesis

Minho Park, Sangmin Lee, Yong Man Ro

IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020

Robust video frame interpolation with exceptional motion map

Minho Park, Hak Gu Kim, Sangmin Lee, Yong Man Ro

IEEE Transactions on Circuits and Systems for Video Technology (TCSVT), 2020

Deep objective assessment model based on spatio-temporal perception of 360-degree video for VR sickness prediction

Kihyun Kim*, Sangmin Lee*, Hak Gu Kim, Minho Park, Yong Man Ro

IEEE International Conference on Image Processing (ICIP), 2019

Generative guiding block: Synthesizing realistic looking variants capable of even large change demands

Minho Park, Hak Gu Kim, Yong Man Ro

IEEE International Conference on Image Processing (ICIP), 2019

Photo-realistic facial emotion synthesis using multi-level critic networks with multi-level generative model

Minho Park, Hak Gu Kim, Yong Man Ro

International Conference on Multimedia Modeling (MMM), 2019

Professional Activities

Reviewer

• Conference on Computer Vision and Pattern Recognition (CVPR)

• International Conference on Computer Vision (ICCV)

• Conference on Association for the Advancement of Artificial Intelligence (AAAI)

• ACM International Conference on Multimedia (ACM MM)

Invited Talk

• Top Conference Session @ The 6th Korea Artificial Intelligence Conference (Sep. 24, 2025)

– Title: LLM-Guided Regional Identification for Instruction-based Image Editing