Hyeongcheol Park

Ph.D. Student @ Korea University

broiron@korea.ac.kr / Google Scholar / LinkedIn / CV

Welcome to my website! I am a Ph.D. student in the Department of Artificial Intelligence at Korea University, advised by Prof. Sangpil Kim.

My research interests lie in multimodal retrieval-augmented generation, knowledge graphs, continual learning for large language models, and 3D scene understanding.

Multimodal Retrieval-Augmented Generation
Knowledge Graphs and Multimodal Reasoning
LLM Continual Learning and Domain Adaptation
3D Scene Editing and Gaussian Splatting

news

2026 Our paper M³KG-RAG has been accepted to CVPR 2026.

2026 Our paper CompMarkGS has been accepted to ICLR 2026.

2025 Our papers EditSplat and IKNE have been accepted to CVPR 2025.

2024 I started my Ph.D. in Artificial Intelligence at Korea University.

publications

Under Review 2026

SALUTE: Benchmarking and Adapting LLMs for the Defense Domain

Hyeongcheol Park, Sumin In, Suyeon Myeong, Hogun Park, Sangmin Kim, Moonhyun Lee, Daekyeong Park, Sangpil Kim

Under review, 2026

Paper

CVPR 2026

M³KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation

Hyeongcheol Park, Jiyoung Seo, Jaewon Mun, Hogun Park, Wonmin Byeon, Sung June Kim, Hyeonsoo Im, JeungSub Lee, Sangpil Kim

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2026

Project Paper

Under Review 2025

VAT-KG: Knowledge-Intensive Multimodal Knowledge Graph for Retrieval-Augmented Generation

Hyeongcheol Park, MinHyuk Jang, Ha Dam Baek, Gyusam Chang, Jiyoung Seo, Jiwan Park, Hogun Park, Sangpil Kim

Under review, 2025

Paper

ICLR 2026

CompMarkGS: Robust Watermarking for Compressed 3D Gaussian Splatting

Sumin In, Youngdong Jang, Utae Jeong, MinHyuk Jang, Hyeongcheol Park, Eunbyung Park, Sangpil Kim

International Conference on Learning Representations, 2026

Project Paper Code

CVPR 2025

EditSplat: Multi-View Fusion and Attention-Guided Optimization for View-Consistent 3D Scene Editing with 3D Gaussian Splatting

Dong In Lee, Hyeongcheol Park, Jiyoung Seo, Eunbyung Park, Hyunje Park, Ha Dam Baek, Sangheon Shin, Sangmin Kim, Sangpil Kim

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

Project Paper Code

CVPR 2025

Insightful Instance Features for 3D Instance Segmentation

Wonseok Roh, Hwanhee Jung, Giljoo Nam, Dong In Lee, Hyeongcheol Park, Sang Ho Yoon, Jungseock Joo, Sangpil Kim

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

Paper

CVM 2024

Audio-guided Implicit Neural Representation for Local Image Stylization

Seung Hyun Lee, Sieun Kim, Wonmin Byeon, Gyeongrok Oh, Sumin In, Hyeongcheol Park, Sang Ho Yoon, Sung-Hee Hong, Jinkyu Kim, Sangpil Kim

Computational Visual Media, 2024

Paper

HCIS 2024

A Survey of Generative Models for Image and Video with Diffusion Model

Byoung Soo Koh, Hyeongcheol Park, Jin Ho Park

Human-centric Computing and Information Sciences, 2024

Paper

ICIIT 2023

A Study on the Optimization of the CNNs for Adversarial Attacks

Jongweon Kim, Hyeongcheol Park

International Conference on Intelligent Information Technology, 2023

Paper

KIPS 2023

Developing the Deep Text-to-Ontology Generator based on Neuro-Symbolic Architecture

Hyeongcheol Park, Eunsu Yun, Minjeong Kim, Huijae Bae, Yujin Shin, Jeehang Lee

International Conference on Intelligent Information Technology, 2023

Paper

patents

2025

Method and Apparatus for Robust Watermarking Through Selective Anchor Augmenting and Pruning of High-Frequency Regions in Rendering Images Based on 3D Gaussian Splatting

Korean Patent Application No. 10-2025-0119554

2022

Event Detenting Method for Unmanned Store

Korean Patent Application No. 10-2022-0116622