JiHyuk Byun profile photo

JiHyuk Byun

I am an M.S. student in Artificial Intelligence at Yonsei University, advised by Prof. Seon Joo Kim.

My research focuses on intelligent visual systems, especially agentic AI, 3D vision, vision-language models, and multimodal learning. I am interested in developing models and evaluations that connect visual understanding with practical decision-making.

Research interests: Agentic AI, 3D Vision, Vision-Language Models (VLMs), and Multimodal Learning.

CV

News

Aug 2026 🚀 Joined NAVER Cloud as a research intern in the HyperCLOVA X Omnimodal team!
Jul 2026 WebSTEP accepted to COLM 2026!
Dec 2025 3D-PAQA accepted to IPIU 2026!
May 2025 🙏 I was selected as a Gwanjeong Educational Foundation scholar. Grateful for their support.

Education

  • Yonsei University, M.S. in Artificial Intelligence Advisor: Prof. Seon Joo Kim · Mar. 2024 - Aug. 2026 (expected)
  • Yonsei University, B.S. in Electrical and Electronic Engineering Mar. 2018 - Aug. 2024

Blog

All posts →

Publications

  1. WebSTEP teaser
    Where Did It Go Wrong? Process-Level Evaluation of Web Agents with Semantic State Tracking
    Jiwan Chung, JiHyuk Byun, Vibhav Vineet, and Seon Joo Kim
    COLM, 2026
    A benchmark that enables process-aware evaluation of web agents through automatic semantic state tracking, revealing exactly where and why each agent fails.
    Project PDF
  2. 3D-PAQA teaser
    Towards Preference-Aligned 3D Quality Assessment
    JiHyuk Byun and Seon Joo Kim
    Workshops on Image Processing and Image Understanding (IPIU), 2026
    A large-scale, MLLM-annotated dataset and lightweight evaluator for human-aligned 3D asset quality — accurate enough to steer iterative asset refinement.
    Project PDF Code Huggingface

Awards & Honors