avatar

Hojun Choi

Ph.D. Candidate
KAIST AI
hchoi256@kaist.ac.kr


About Me

Hello. 👋

⠻⣷⣤⣄⣀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⣀⣠⣤⣾⠟
⠀⠀⠙⠻⢿⣿⣿⣿⣿⣿⣶⣶⣤⣀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⣀⣤⣶⣶⣿⣿⣿⣿⣿⡿⠟⠋⠀⠀
⢠⠀⠀⠀⠀⠀⠉⠛⠻⢿⣿⣿⣿⣿⣷⣤⣀⣀⣀⣀⣠⣤⣴⣶⣶⣾⡷⠀⠀⠀⠀⠀⠀⢾⣷⣶⣶⣦⣤⣄⣀⣀⣀⣀⣤⣾⣿⣿⣿⣿⡿⠟⠛⠉⠀⠀⠀⠀⠀⡄
⢸⡆⠀⠀⠀⠀⠀⠀⠀⠀⠉⢻⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⠃⠀⠀⠀⠀⠀⠀⠈⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⡟⠋⠀⠀⠀⠀⠀⠀⠀⠀⢰⡇
⠸⣿⡄⠀⠀⠀⠘⢦⡀⠀⠀⠀⢹⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⠃⠀⠀⠀⠀⠀⠀⠀⠀⠘⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⡏⠀⠀⠀⢀⡴⠃⠀⠀⠀⢀⣿⠇
⠀⢿⣷⡀⠀⠀⠀⠀⠻⣦⡀⠀⢸⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⡟⠁⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠈⢻⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⡇⠀⢀⣴⠟⠀⠀⠀⠀⢀⣾⡿⠀
⠀⠘⣿⣿⣄⠀⠀⠀⠀⠘⢿⣶⣾⣿⣿⣿⣿⣿⣿⣿⣿⣿⡟⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢻⣿⣿⣿⣿⣿⣿⣿⣿⣿⣷⣶⡿⠃⠀⠀⠀⠀⣠⣿⣿⠃⠀
⠀⠀⠈⢿⣿⣦⡀⠀⠀⠀⠀⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⠁⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠈⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⠀⠀⠀⠀⢀⣴⣿⡿⠃⠀⠀
⠀⠀⠀⠀⠙⢿⣿⣷⣦⣤⣾⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣷⣤⣴⣾⣿⡿⠋⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠙⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⡆⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢰⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⣿⠋⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠘⣿⣿⣿⣿⣿⣿⣿⣿⢿⣿⣿⣿⣿⣿⣿⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⣿⣿⣿⣿⣿⣿⡿⢿⣿⣿⣿⣿⣿⣿⣿⠇⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⣿⣿⣿⣿⣿⣿⣿⣶⣦⣄⠙⢿⣿⣿⣿⡇⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢸⣿⣿⣿⡿⠋⣠⣴⣶⣿⣿⣿⣿⣿⣿⣿⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⣿⣿⣿⣿⣿⣇⠀⣸⣿⣿⣇⠈⣿⣿⣿⣿⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⣿⣿⣿⣿⠁⣸⣿⣿⣏⠀⣸⣿⣿⣿⣿⣿⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⢹⣿⣿⣿⣿⣿⣿⣿⣿⣿⡏⢀⣿⣿⣿⡟⠀⠀⢀⣀⣀⣀⣀⣀⣀⡀⠀⠀⢻⣿⣿⣿⡀⢹⣿⣿⣿⣿⣿⣿⣿⣿⣿⡏⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⣿⣿⣿⣿⣿⣿⣿⠟⢋⣠⣾⣿⡿⠟⠀⠀⢰⣿⣿⣿⣿⣿⣿⣿⣿⡆⠀⠀⠛⢿⣿⣷⣄⡙⠻⣿⣿⣿⣿⣿⣿⣿⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⢸⣿⣿⣿⣿⣿⣿⣿⣿⠿⠛⠉⠀⠀⠀⠀⠘⣿⣿⣿⣿⣿⣿⣿⣿⠃⠀⠀⠀⠀⠉⠛⠿⢿⣿⣿⣿⣿⣿⣿⣿⡇⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⢸⣿⣿⣿⣿⡿⠛⠁⠀⠀⠀⠀⠀⠀⠀⠀⠀⠈⢿⣿⣿⣿⣿⡿⠁⠀⠀⠀⠀⠀⠀⠀⠀⠀⠈⠙⢿⣿⣿⣿⣿⣇⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⣿⣿⣿⣿⠋⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢸⣿⣿⣿⣿⡇⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠙⣿⣿⣿⣿⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠘⣿⣿⣿⡏⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢸⣿⣿⣿⣿⡇⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢹⣿⣿⣿⠃⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠘⣿⣿⣧⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⣼⣿⣿⣿⣿⣧⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⣼⣿⣿⠃⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠈⠻⣿⡄⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢀⣼⣿⣿⣿⣿⣿⣿⣧⡀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢠⣿⠟⠁⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠈⠳⠀⠀⠀⠀⠀⠀⠀⠀⠀⢀⣴⣿⣿⠿⠟⠛⠛⠻⠿⣿⣿⣦⡀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠞⠁⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⢀⣀⣀⣤⣴⣾⡿⢛⣩⣴⣶⣾⣿⣿⣷⣶⣦⣍⡛⢿⣷⣦⣤⣀⣀⣀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀
⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠈⠉⠉⢩⣴⣾⠿⠛⠋⠉⠀⠀⠀⠀⠉⠙⠛⠿⣷⣦⡍⠉⠉⠉⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀⠀

I am a first-year Ph.D. student at KAIST AI, advised by Prof. Hyunjung (Kate) Shim. Before joining KAIST, I conducted research with Prof. Bin Ran at the CAVH Research Group at the University of Wisconsin–Madison and with Prof. U Kang at the Data Mining Lab at Seoul National University. I also worked with Prof. Insik Shin at FLUIZ AI and Dr. Jinhan Lee at NAVER LABS.

My research interests include Multimodal Learning, World Models, and Agentic AI.

News

2026
Aug New preprint is out: MBA.
Jun OVBEVSeg is accepted to ECCV 2026 🇸🇪
Jun MSPL is accepted to ECCV 2026 🇸🇪
Jun CoT-PL is accepted to the 2nd Workshop on Multimodal Spatial Intelligence @ CVPR 2026.
Feb New award: Best Poster Award at IPIU 2026.
Jan Graduated from KAIST AI with an M.S. in Artificial Intelligence.
2025
May Joined NAVER LABS as a Research Intern.
Feb I-HallA is selected for an Oral Presentation at AAAI 2025.
Jan I-HallA is accepted to AAAI 2025 🇺🇸
Jan New award: Oral Presentation at IPIU 2025.

Publications

*: denotes equal contribution. †: denotes corresponding author.

  1. Preprint
    MBA: Multimodal Benchmark and Agents for Real-World Business Ideation
    Hojun Choi, Jaeyo Shin, Suin Lee, and Hyunjung Shim†
    🤗 Hugging Face Daily Paper
    Preprint, 2026.
    Demo PDF Code Project Page BibTex

  2. ECCV
    Open-Vocabulary BEV Segmentation with 3D-Aware Geometric Constraints
    Hojun Choi, Seulbin Hwang, Dae Jung Kim, Kisung Kim, Hyunjung Shim†, and Jinhan Lee†
    European Conference on Computer Vision (ECCV), 2026.
    PDF Project Page BibTex

  3. ECCV
    MSPL: Multi-Step Pseudo-Labeling for Open-Vocabulary Object Detection
    Hojun Choi, Youngsun Lim, Jaeyo Shin, and Hyunjung Shim†
    2nd Workshop on Multimodal Spatial Intelligence @ CVPR (CVPRW), 2026.
    European Conference on Computer Vision (ECCV), 2026.
    PDF Code Project Page BibTex

  4. Preprint
    SUPER-AD: Semantic Uncertainty-aware Planning for End-to-End Robust Autonomous Driving
    Wonjeong Ryu, Seungjun Yu, Seokha Moon, Hojun Choi, Junsung Park, Jinkyu Kim, and Hyunjung Shim†
    Preprint, 2025.
    PDF BibTex

  5. AAAI
    Evaluating Image Hallucination in Text-to-Image Generation with Question-Answering
    Youngsun Lim*, Hojun Choi*, and Hyunjung Shim†
    🎉 Oral Presentation
    AAAI Conference on Artificial Intelligence (AAAI), 2025.
    PDF Code Project Page BibTex

  6. Preprint
    Sampling Bag of Views for Open-Vocabulary Object Detection
    Hojun Choi, Junsuk Choe, and Hyunjung Shim†
    Preprint, 2024.
    PDF BibTex

  7. MobiCom
    MobileGPT: Augmenting LLM with Human-like App Memory for Mobile Task Automation
    Sunjae Lee, Junyoung Choi, Jungjae Lee, Munim Hasan Wasi, Hojun Choi, Steven Y. Ko, Sangeun Oh†, and Insik Shin†
    ACM International Conference on Mobile Computing and Networking (MobiCom), 2024.
    PDF Code BibTex

  8. ICLR
    Accurate Retraining-free Pruning for Pre-trained Encoder-based Language Models
    Seungcheol Park, Hojun Choi, and U Kang†
    International Conference on Learning Representations (ICLR), 2024.
    PDF Code BibTex

Education

KAIST AI
KAIST AI
Ph.D. in Artificial Intelligence
Jan. 2026 – Present
 
KAIST AI
KAIST AI
M.S. in Artificial Intelligence
Jan. 2024 – Dec. 2025
 
University of Wisconsin–Madison
University of Wisconsin–Madison
B.S. in Computer Science · B.S. in Data Science
Jan. 2017 – Dec. 2022
Dean's List Recipient

Research Experience

NAVER LABS
Research Intern, NAVER LABS Corp., South Korea, May 2025 – Nov. 2025
FLUIZ AI
Research Intern, FLUIZ AI, South Korea, Sep. 2023 – Feb. 2024
Data Mining Lab
Research Intern, Data Mining Lab, South Korea, Jan. 2023 – Jul. 2023
CAVH Research Group
Undergraduate Research Intern, CAVH Research Group, USA, Sep. 2022 – Dec. 2022

Awards


Powered by Jekyll and Minimal Light theme.