Wonhyeok Choi

Hi, I'm Wonhyeok Choi, a M.S.-Ph.D. integrated course student at the Department of Electrical Engineering & Computer Sciences (EECS) at DGIST, South Korea. I am conducting my research under the supervision of Prof. Sunghoon Im at the DGIST Computer Vision Lab.

Previously, I earned a B.S. degree from the Department of School of Undergraduate Studies, DGIST, in 2022, and I was fortunate to have the opportunity to study as an exchange student at UC Berkeley during my undergraduate years and later visit Stanford as a visiting scholar during my Ph.D. program.

My research interests lie at the intersection of Computer Vision, Deep Learning, and Physical AI. In the realm of Computer Vision, I focus on Scene Understanding and 3D perception tasks, aiming to bridge the gap between 2D observations and 3D spatial intelligence. My Deep Learning research explores fundamental optimization challenges, specifically in Multi-task learning, optimization strategies, and metric learning, to build robust and generalizable representations.

Recently, I have expanded my focus toward Physical AI, investigating how embodied agents can interact with the real world. Specifically, I am interested in leveraging Reinforcement Learning (RL) and Diffusion-based Policies to develop sophisticated decision-making and control systems for complex robotic tasks.


Email  /  Google Scholar  /  Github  /  OpenReview  /  📄Curriculum Vitae

profile photo
News

2026

  • 2026-03: One paper accepted to SPL 2026.
  • 2026-02: Two paper accepted to CVPR 2026.
  • 2025

  • 2025-11: One paper accepted to RA-L 2025 & ICRA 2026.
  • 2025-11: One paper accepted to AAAI 2025.
  • 2025-01: One paper accepted to ICLR 2025.
  • 2024

  • 2024-12: One paper accepted to AAAI 2025.
  • 2024-11: Our team received the Top Prize from the 16th Electronics Newspaper ICT Paper Contest.
  • 2024-08: I am going to serve as Visiting Scholar at CNSLab in Stanford University for four months.
  • 2024-01: One paper accepted to ICRA 2024.
  • 2024-01: Our team received the 3rd Prize from the 30th Samsung Human-Tech Paper Award.
  • 2023

  • 2023-12: I received the Outstanding Researcher Award from the DGIST.
  • 2023-12: Our team received the Excellence Prize from the 15th Electronics Newspaper ICT Paper Contest.
  • 2023-10: I received the Outstanding Researcher Award from the EECS of DGIST.
  • 2023-10: Our team received the Top Prize from the Autonomous Driving AI Development Challenge 2023.
  • 2023-09: One paper accepted to NeurIPS 2023.
  • 2023-02: One paper accepted to CVPR 2023.
  • 2022

  • 2022-03: One paper accepted to CVPR 2022.
  • 2022-03: I join in DGIST CVLab as a M.S.-Ph.D Integrated Course Student.
  • 2022-02: Our team received the Participation Prize from the 28th Samsung Human-Tech Paper Award.
  • Publications

    * indicates equal contribution
    † indicates the corresponding author



    dise CascadeOcc: Rethinking 3D Occupancy World Models with Cascaded VQ Representations
    Kyumin Hwang*, Wonhyeok Choi*, Jaeyeul Kim, Jihun Park, Daehee Park†, and Sunghoon Im†
    IEEE Signal Processing Letters (SPL), 2026
    [Paper]
    dise TaskForce: Cooperative Multi-agent Reinforcement Learning for Multi-task Optimization
    Wonhyeok Choi, Kyumin Hwang, Jihun Park, Kyoungmin Lee, Seunghun Lee, Jaeyeul Kim, Minwoo Choi, and Sunghoon Im†
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
    [Paper]
    dise A Training-Free Style-Personalization via SVD-Based Feature Decomposition
    Kyoungmin Lee, Jihun Park, Jongmin Gim, Wonhyeok Choi, Kyumin Hwang, Jaeyeul Kim, and Sunghoon Im†
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2026
    [Paper]
    dise Scale-invariant and View-relational Representation Learning for Full Surround Monocular Depth (Oral) (Collaborated with Hyundai Motor Group)
    Kyumin Hwang*, Wonhyeok Choi*, Kiljoon Han, Wonjoon Choi, Minwoo Choi, Yongcheon Na, Minwoo Park, and Sunghoon Im†
    IEEE Robotics and Automation Letters (RA-L), 2025
    IEEE International Conference on Robotics and Automation (ICRA), 2026
    [Paper]
    dise Infinite-Story: A Training-Free Consistent Text-to-Image Generation (Oral)
    Jihun Park*, Kyoungmin Lee*, Jongmin Gim*, Hyeonseo Jo, Minseok Oh, Wonhyeok Choi, Kyumin Hwang, Jaeyeul Kim, Minwoo Choi, and Sunghoon Im†
    The Fortieth Annual AAAI Conference on Artificial Intelligence (AAAI), 2026
    [Paper]
    dise Self-supervised Monocular Depth Estimation Robust to Reflective Surface Leveraged by Triplet Mining (Top Prize in ICT Paper Contest)
    Wonhyeok Choi*, Kyumin Hwang*, Wei Peng, Minwoo Choi, and Sunghoon Im†
    International Conference on Learning Representations (ICLR), 2025
    [Paper] | [Openreview]
    dise Intrinsic Image Decomposition for Robust Self-supervised Monocular Depth Estimation on Reflective Surfaces
    Wonhyeok Choi*, Kyumin Hwang*, Minwoo Choi, Kiljoon Han, Wonjoon Choi, Mingyu Shin, and Sunghoon Im†
    The Thirty-Ninth Annual AAAI Conference on Artificial Intelligence (AAAI), 2025
    [Paper]
    dise Multi-task Learning for Real-time Autonomous Driving leveraging Task-wise Attention Generator (Oral) (Collaborated with Hyundai Motor Group) (Excellence Prize in ICT Paper Contest)
    Wonhyeok Choi*, Mingyu Shin*, Hyukzae Lee, Jaehoon Cho, Jaehyeon Park, and Sunghoon Im†
    IEEE International Conference on Robotics and Automation (ICRA), 2024
    [Paper]
    dise Depth-discriminative Metric Learning for Monocular 3D Object Detection
    (3rd Prize in Samsung Human-Tech Paper Award)
    Wonhyeok Choi*, Mingyu Shin*, and Sunghoon Im†
    Neural Information Processing Systems (NeurIPS), 2023
    [Paper] | [OpenReview]
    dise Dynamic Neural Network for Multi-Task Learning Searching across Diverse Network Topologies
    Wonhyeok Choi, and Sunghoon Im†
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023
    [Paper]
    dise ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic Segmentation
    (Participation Prize in Samsung Human-Tech Paper Award)
    Seunghun Lee, Wonhyeok Choi, Changjae Kim, Minwoo Choi, and Sunghoon Im†
    IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
    [Paper]
    Education


    dise M.S.-Ph.D. Integrated Course (Advisor: Sunghoon Im)
    Department of Electrical Engineering & Computer Sciences (EECS), DGIST, South Korea
    (Mar. 2022 - Present)
    dise Visiting Scholar (Advisor: Prof. Kilian M. Pohl)
    Department of Psychiatry and Behavioral Sciences (PBS), Stanford University, CA, USA
    (Sep. 2024 - Dec. 2024)
    dise Bachelor's Degree
    Department of Electrical Engineering & Computer Sciences (EECS), DGIST, South Korea
    (Mar. 2018 - Feb. 2022)
    dise Exchange Student (8 Credits)
    UC Berkeley, CA, USA (Supported by DGIST Freshmen Global Leadership Program, FGLP)
    (Jun. 2018 - Aug. 2018)
    dise Hansung Science High School, South Korea
    (Mar. 2016 - Feb. 2018)
    Academic Activities

    Honors & Awards

  • Top Prize, 16th ICT Paper Competition and Grand Exhibition, Electronic News, Dec. 2024
  • 3rd Prize, 30th HumanTech Paper Award, Samsung Electronics Co., Ltd, Feb. 2024
  • Outstanding Researcher Award, Electronic Engineering & Computer Sciences (EECS), DGIST, Dec. 2023
  • Excellence Prize, 15th ICT Paper Competition and Grand Exhibition, Electronic News, Dec. 2023
  • Hwang Gyuyoung Outstanding Researcher Award, Electronic Engineering & Computer Sciences (EECS), DGIST, Oct. 2023
  • Top Prize, Autonomous Driving AI Development Challenge 2023, Ministry of Land, Infrastructure and Transport, Oct. 2023
  • Participation Prize, 28th HumanTech Paper Award, Samsung Electronics Co., Ltd, Feb. 2022.
  • Teaching Experience

  • Invited Speaker of Specialized Seminar (50+ attendees), The 9th Daegu AI Researchers Forum (DARF), Dec. 2025
  • Invited Speaker of Online Tutorial Session (100+ attendees), Korea Conference on Computer Vision (KCCV), Aug. 2025
  • Teaching Assistant of AI Basics (100+ undergraduate students), DGIST, Aug. 2022 - Dec. 2022
  • Reviewer

  • IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023 - 2026
  • IEEE/CVF International Conference on Computer Vision (ICCV), 2023 - 2025
  • The European Conference on Computer Vision (ECCV), 2024 - 2026
  • Neural Information Processing Systems (NeurIPS), 2024 - 2025
  • IEEE Robotics and Automation Letters (RA-L), 2024 - 2025
  • IEEE International Conference on Robotics and Automation (ICRA), 2024 - 2025
  • International Conference on Learning Representations (ICLR), 2025 - 2026
  • International Conference on Machine Learning (ICML), 2025 - 2026
  • The Association for the Advancement of Artificial Intelligence (AAAI), 2025 - 2026
  • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2025
  • IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025
  • International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2025

  • Website Template


    © Wonhyeok Choi | Last updated: Feb 23, 2026