Juho Jung

I am a Research Scientist (Alternative Military Service) at VUNO Inc. My research focuses on uncertainty aware multimodal LLMs adaptation in medical image and improving uncertainty quantification of LLMs and hallucinations in real world environments.

Before joining VUNO I obtained my Master's from the Graduate School of Applied Artificial Intelligence at SKKU (Full Academic Excellence Scholarship), under the supervision of Prof. Jinyoung Han, where I researched uncertainty-aware Multitask Learning in Medical image and Multimodal Feature Alignment in complex and unknown modality. I completed my bachelor's degree (Magna Cum Laude) in Applied Artificial Intelligence at the SKKU. I had the privilege of working with Zhi-Qi Cheng, Alexander Hauptmann, and David Mortensen as a Visiting Scholar in the School of Computer Science Intensive Program in AI at Carnegie Mellon University.

Email  |  CV  |  Google Scholar  |  Github  |  LinkedIn

profile photo

Research Interests

I am interested in advancing uncertainty-aware multimodal learning for medical imaging. My work explores how to adapt large vision-language models to clinical data, quantify and calibrate their uncertainty, and mitigate hallucinations in real-world medical settings. My current research emphasizes:

Vision-Language Models for medical imaging
Uncertainty Quantification in multimodal learning
Hallucination detection and mitigation
Representation Learning for medical images

Selected Publications

(Equal contributions are denoted by *)

Automated Structured Radiology Report Generation with Rich Clinical Context
Seongjae Kang*, Dong Bok Lee*, Juho Jung, Dongseop Kim, Won Hwa Kim, Sunghoon Joo
Under Review, arXiv, 2025

Incorporating clinical context into automated structured radiology report generation improves report quality by addressing temporal hallucinations and utilizing comprehensive patient data.

CAMEL: Confidence-Aware Multi-Task Ensemble Learning with Spatial Information for Retina OCT Image Classification and Segmentation
Juho Jung*, Migyeong Yang*, Hyunseon Won, Jiwon Kim, Jeong Mo Han, Joon Seo Hwang, Daniel Duck-Jin Hwang, Jinyoung Han
WACV, 2025

A novel framework designed to reduce task-specific uncertainty in multi-task learning for retinal OCT image analysis through confidence-aware ensemble learning.

HiQuE: Hierarchical Question Embedding Network for Multimodal Depression Detection
Juho Jung, Chaewon Kang, Jeewoo Yoon, Seungbae Kim, Jinyoung Han
CIKM, 2024 (Oral)

A hierarchical question embedding network for multimodal depression detection using structured question-answer pairs.

Enhancing Temporal Action Localization: Advanced s6 Modeling with Recurrent Mechanism
Sangyoun Lee, Juho Jung, Changdae Oh, Sunghee Yun
arXiv, 2024

Advanced s6 modeling with recurrent mechanism for enhanced temporal action localization.

Prediction of neovascular age-related macular degeneration recurrence using optical coherence tomography images with a deep neural network
Juho Jung, Jinyoung Han, Jeong Mo Han, Junseo Ko, Jeewoo Yoon, Joon Seo Hwang, Ji In Park, Gyudeok Hwang, Jae Ho Jung, Daniel Duck-Jin Hwang
Scientific Reports, 2024

Deep neural network-based prediction of neovascular age-related macular degeneration recurrence using OCT images.

SAFE: Sequential Attentive Face Embedding with Contrastive Learning for Deepfake Video Detection
Juho Jung, Chaewon Kang, Jeewoo Yoon, Simon S Woo, Jinyoung Han
CIKM, 2024

Sequential attentive face embedding with contrastive learning for deepfake video detection.

For more publications, please visit my Google Scholar profile.

Selected Projects

LUNA25 Challenge
March 2025 - September 2025

Participating in the LUNA25 AI Challenge for lung nodule analysis and detection using advanced deep learning techniques.

Explainable AI for Audio-Visual Deepfake Video Detection
Carnegie Mellon University, Institute of Information & communications Technology Planning & Evaluation (IITP)
September 2023 - February 2024

Developed explainable AI models for detecting deepfake videos using audio-visual features with attention mechanisms and gradient-based explanations.

Heterogeneous Graph Neural Network for Electronic Health Records
Carnegie Mellon University, Institute of Information & communications Technology Planning & Evaluation (IITP)
September 2023 - December 2023

Implemented heterogeneous graph neural networks for modeling complex relationships in electronic health records using MIMIC dataset.

Clinical Decision Support System for Retinal Disease Detection with Explainable AI
National Research Foundation of Korea (KRF)
March 2023 - February 2024

Developed explainable AI systems for retinal disease detection using OCT images with clinical decision support and recurrence prediction capabilities.

Study on Self-Driving B5G Networks towards Federated Private-5G
National Research Foundation (NRF) of Korea Grant funded by the Korean Government (MSIT)
June 2021 - August 2024

Researched self-driving networks and federated learning approaches for private 5G networks with autonomous network management capabilities.

Pet Healthcare Platform with AI and LLMs
Lifet, February 2022 - September 2023

Developed an AI model for single-image disease detection and segmentation, deployed and optimized AI models in web, mobile, and LLM adaptation with customer community.

For more projects, please see my CV.


Template by Jon Barron.