Junhyun Park

News

• Feb 2026 Joined DEEPNOID AI Research Lab (Multimodal Team) as a researcher, working on medical foundation models for CXR, CT, and MRI.
• Dec 2025 Honored to receive the Talent Award of Korea from the Minister of Education — a national award given to 100 outstanding young talents annually.
• Jun 2025 Our paper OFF-CLIP: Improving Normal Detection Confidence in Radiology CLIP with Simple Off-Diagonal Term Auto-Adjustment has been early-accepted to MICCAI (top 9%). Our paper Vibration-Assisted Hysteresis Mitigation for Achieving High Compensation Efficiency has also been accepted to IEEE/RSJ IROS.
• Mar 2025 Attending IEEE ICRA 2025 to present Hysteresis Compensation of Flexible Continuum Manipulator Using RGBD Sensing and Temporal Convolutional Network. Happy to grab coffee and chat.

• Jan 2025 Received the Best Researcher Award (top 1%) from the Department of Robotics & Mechatronics Engineering, DGIST.
• May 2024 Our paper Hysteresis Compensation of Flexible Continuum Manipulator using RGBD Sensing and Temporal Convolutional Network has been accepted to IEEE RA-L.
• Apr 2024 Our paper Integrating ChatGPT into Secure Hospital Networks: A Case Study on Improving Radiology Report Analysis has been accepted to CHIL 2024.

Publications

^* denotes equal contribution.

Journal

Surgical Robotics Hysteresis Compensation

Hysteresis Compensation of Flexible Continuum Manipulator using RGBD Sensing and Temporal Convolutional Network

Junhyun Park^*, Seonghyeok Jang^*, Hyojae Park, Seongjun Bae, Minho Hwang

IEEE Robotics and Automation Letters (RA-L), vol. 9, no. 7, 2024

Paper · Video · arXiv

A data-driven TCN approach captures the nonlinear, history-dependent characteristics of cable actuation, enabling real-time hysteresis compensation. Reduces position error by 61.4% (13.7 → 5.29 mm) and orientation error by 64.0% (31.2° → 11.2°).

Surgical Robotics Hysteresis Compensation

SAM: Semi-Active Mechanism for Extensible Continuum Manipulator and Real-time Hysteresis Compensation Control Algorithm

Junhyun Park^*, Seonghyeok Jang^*, Myeongbo Park, Hyojae Park, Jeonghyeon Yoon, Minho Hwang

International Journal of Medical Robotics and Computer Assisted Surgery (IJMRCAS), 2024

Paper · Video · arXiv

An extensible cable-driven continuum manipulator with a semi-active mechanism (SAM) and a TCN-based real-time hysteresis compensation algorithm. SAM improves lesion access, while TCN-based compensation enhances accuracy.

Conference

Medical AI VLP

OFF-CLIP: Improving Normal Detection Confidence in Radiology CLIP with Simple Off-Diagonal Term Auto-Adjustment

Junhyun Park^*, Chanyu Moon^*, Donghwan Lee, Kyungsu Kim, Minho Hwang

International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2025

Early Accept — Top 9% · Acceptance rate 30%

arXiv

OFF-CLIP uses an off-diagonal loss and sentence-level text filtering to improve normal detection and reduce false negatives, enhancing both zero-shot classification and anomaly localization.

Surgical Robotics Hysteresis Compensation Tendon-Sheath Mechanism

Vibration-Assisted Hysteresis Mitigation for Achieving High Compensation Efficiency

Myeongbo Park^*, Chunggil An^*, Junhyun Park^*, Jonghyun Kang, Minho Hwang

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025

arXiv

Controlled vibration reduces friction and dead zones in tendon-sheath mechanisms, improving trajectory tracking. Combined with DL-based hysteresis compensation, achieves 85% reduction in hysteresis.

Surgical Robotics

Optimizing Base Placement of Surgical Robot: Kinematics Data-Driven Approach by Analyzing Working Pattern

Jeonghyeon Yoon^*, Junhyun Park^*, Hyojae Park, Hakyoon Lee, Sangwon Lee, Minho Hwang

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024

Paper · Video · arXiv

A machine learning approach to determine the optimal robot base pose based on a surgeon's working pattern. End-effector pose clustering identifies key positions, with scoring that accounts for joint limits and singularities.

Medical AI LLM

Integrating ChatGPT into Secure Hospital Networks: A Case Study on Improving Radiology Report Analysis

Kyungsu Kim^*, Junhyun Park^*, Saul Langarica, Adham Mahmoud Alkhadrawi, Synho Do

Conference on Health, Inference, and Learning (CHIL), 2024

Acceptance rate 34%

Paper · HuggingFace · arXiv · Code

The first in-hospital adaptation of a cloud-based LLM into a secure, on-premise model for radiology report analysis. A sentence-level contrastive knowledge distillation achieves >95% accuracy in anomaly detection while preserving patient privacy.

Preprints

Surgical Robotics Hysteresis Compensation Tendon-Sheath Mechanism

SSTL: Self-Sensing Tendon Loop for Hysteresis Modeling and Compensation in Tendon-Sheath Mechanisms

Myeongbo Park^*, Junhyun Park^*, Inayat Ullah, Chunggil An, Minho Hwang

arXiv preprint, arXiv:2605.16870, 2026

arXiv

Surgical Robotics Pose Estimation

Markerless 6D Pose Estimation and Position-Based Visual Servoing for Endoscopic Continuum Manipulators

Junhyun Park^*, Chunggil An^*, Myeongbo Park, Inayat Ullah, Seonghyun Park, Minho Hwang

arXiv preprint, arXiv:2602.16365, 2026

arXiv

Experience

Education

Honors & Awards

Professional Services

• Reviewer: MICCAI (2025); IEEE RA-L, IEEE/RSJ IROS (2024).
• Teaching Assistant: Undergraduate Research Group Project (2025); Artificial Intelligence Basics (2024).