About Me

데이터로 가치를 만드는 Data Scientist, 박소영입니다.

<aside>

I’m SoYoung, a data scientist dedicated to data-driven, data-informed, and data-inspired decision-making.

With five years of experience in data analysis and machine learning, I have worked on power data analysis at KEPRI, big data projects for NTS and KoROAD, and end-to-end data initiatives for government agencies such as MOLIT and MAFRA.

Currently, I am pursuing a Ph.D. in Computer Science and AI.

</aside>

Contact

<aside>

• 📧 Email: [email protected] | [email protected]
• 📱 Phone: +82 10-97**-14****
• 📍 Location: Daejeon & Sejong, Korea </aside>

Research

<aside>

• Ethical AI, Reliable AI, Machine Learning, Deep Learning
• Graph Neural Networks, Time-series Analysis, Robust Modeling
• Effective approach to achieving trustworthy AI </aside>

International Research Achievements (4 first authors, 3 co-authors, 1 co-corresponding†)

<aside>

• Soyoung Park, Hwanjun Song, and Sungsu Lim†. “Quantile-Free Uncertainty Quantification in Graph Neural Networks.” In ICML, 2026.
• Minkyung Song, Soyoung Park†, and Sungsu Lim†. “DisCoRec: Disentangled Conformity-aware Recommendation with LLM-Guided Multi-View Learning.” In SIGIR, 2026.
• Minkyung Song, Soyoung Park, and Sungsu Lim†. “MV-LLMRec: Multi-View Representation Learning with Large Language Models for Recommendation.” In AAAI, 2026.
• Seunghoon Han, Hyewon Lee, Soyoung Park, Jong-Ryul Lee†, and Sungsu Lim†. “MR-Pruner: Training-free Multi-resolution Visual Token Pruning for Multi-modal Large Language Models.” In WACV, 2026.
• Soyoung Park, Hyewon Lee, and Sungsu Lim†. “Dynamic Periodic Event Graphs for Multivariate Time Series.” PeerJ Computer Science, 2025.
• Soyoung Park and Sungsu Lim†. “FnRGNN: Distribution-aware Fairness in Graph Neural Network.” In CIKM, 2025.
• Soyoung Park, Hyewon Lee, Mingyu Choi, Seunhoon Han, Jong-Ryul Lee†, Sungsu Lim†, and Tae-Ho Kim†. “Zero-shot Industrial Anomaly Segmentation with Image-Aware Prompt Generation.” In PAKDD, 2025.
• Seunhoon Han, Mingyu Choi, Hyewon Lee, Soyoung Park, Jong-Ryul Lee†, Sungsu Lim†, and Tae-Ho Kim†. “Diverse Knowledge Selection for Enhanced Zero-shot Visual Question Answering.” In WWW, 2025. </aside>

Domestic Research Achievements (1 first Author, 3 co-author)

<aside>

• 송민경, 박소영, 임성수†. “대규모 언어 모델을 활용한 멀티 뷰 학습 기반의 추천 시스템.” In KDBC, 2025.
• 박소영, 임성수†. “비볼록 벌점화 분위수 회귀를 통한 그래프 신경망 신뢰성 향상.” In KSC, 2024.
• 이혜원, 박소영, 송민경, 임성수†. “도로 환경에서 LLM 기반 제로샷 이상 분할을 위한 방법론.” In KSC, 2024.
• 배은형, 박소영, 임성수†. “사전학습 언어 모델을 이용한 법인세 조세심판 결정 예측 모델 연구.” In KDBC, 2023. </aside>