I am an AI Research Engineer at Samsung Research, working in the Agentic Model Part, where I focus on developing multimodal large language models (MLLMs) to build next-generation AI agents for practical applications.
Before joining Samsung Research, I completed my Ph.D. in Electrical Engineering at KAIST in 2025, where I had the honor of being advised by Prof. Jaekyun Moon throughout my graduate studies.
If you have any questions about my research or would like to discuss potential collaborations, please feel free to contact me via email.
Email: savertm9@gmail.com | Curriculum Vitae / Google Scholar / LinkedIn
(Top AI/ML conferences)
[C9] Beyond Uniform Detection: Adaptive Hallucination Detection for RAG Across Response Regimes
Jungwuk Park*, Sejong Ryu*, Jy-yong Sohn, Jaekyun Moon (* = equal contribution)
NeurIPS 2026
[C8] Why Act Without Asking? Evaluating Mobile GUI Agents under Ambiguous Instructions
Yeongjae Cho, Jungwuk Park, Tae-Min Choi, Chiyoun Park, Mincheol Kim, Kookhoi Kim
EMNLP 2026 (Main Conference)
[C7] ProLoG: Hybrid Prompt and LoRA Based Adaptation of Vision-Language Models for OOD Generalization
Jungwuk Park, Dong-Jun Han and Jaekyun Moon
AAAI 2026 (Oral Presentation)
[C6] Adaptive Energy Alignment for Accelerating Test-Time Adaptation
Wonjeong Choi, Do-Yeon Kim, Jungwuk Park, Jungmoon Lee, Younghyun Park, Dong-Jun Han and Jaekyun Moon
ICLR 2025
[C5] Consistency-Guided Temperature Scaling using Styles and Contents for Out-of-Domain Calibration
Wonjeong Choi, Jungwuk Park, Dong-Jun Han, Younghyun Park, Jaekyun Moon
AAAI 2024
[C4] StableFDG: Style and Attention Based Learning for Federated Domain Generalization
Jungwuk Park*, Dong-Jun Han*, Jinho Kim, Shiqiang Wang, Christopher Brinton and
Jaekyun Moon (* = equal contribution)
NeurIPS 2023
[C3] NEO-KD: Knowledge Distillation based Adversarial Training for Robust Multi-Exit Neural Network
Seokil Ham, Jungwuk Park, Dong-Jun Han and Jaekyun Moon
NeurIPS 2023
[C2] Test-Time Style Shifting: Handling Arbitrary Styles in Domain Generalization
Jungwuk Park*, Dong-Jun Han*, Soyeong Kim and Jaekyun Moon (* = equal contribution)
ICML 2023
[C1] Sageflow: Robust Federated Learning against Stragglers and Adversaries
Jungwuk Park*, Dong-Jun Han*, Minseok Choi and Jaekyun Moon (* = equal contribution)
NeurIPS 2021
(Journal)
[J3] Deep Learning of Read References in NAND Flash Memory
Sunyoung Jo, Jungwuk Park†, Younghyun Park, Sangho Yoon and Jaekyun Moon († =
corresponding author)
IEEE Access, 2026
[J2] Improving Low-Latency Predictions in Multi-Exit Architectures via Block-Dependent Losses
Dong-Jun Han*, Jungwuk Park*, Seokil Ham, Namjin Lee and Jaekyun Moon (* = equal
contribution)
IEEE Transactions on Neural Networks and Learning Systems (TNNLS), 2023
[J1] FedMes: Speeding Up Federated Learning with Multiple Edge Servers
Dong-Jun Han, Minseok Choi, Jungwuk Park and Jaekyun Moon
IEEE Journal on Selected Areas in Communications (JSAC) - Special Issue on Distributed
Learning over Wireless Edge Networks, 2021
Samsung Research, Seoul | Sep.2025 - Present
Agentic Model Part - AI Research Engineer
Postdoctoral Researcher in Electrical Engineering, KAIST | Mar. 2025 - August. 2025
Ph.D. in Electrical Engineering, KAIST | Mar. 2021 - Feb. 2025
Master in Electrical Engineering, KAIST | Mar. 2019 - Feb. 2021
B.S. in Electrical Engineering, Yonsei University | Mar. 2013 - Feb. 2019