Youngseok Hwang

Hi, I'm Youngseok Hwang. I'm an integrated Ph.D. student at the Graduate School of Data Science, Seoul National University, advised by Prof. Hyunwoo Park. I'm currently conducting research alongside my great colleagues at the Data Intelligence and Learning (DIAL) Lab.

I'm fortunate to collaborate with Dr. Wonhee Lee at KRISO on maritime AI (AI for Science) and with Dr. Jaeyeon Kim at A*STAR on 3D CAD reconstruction (AI for Engineering).

I'm always open to research collaborations. Feel free to reach out by email or LinkedIn.

Email / Google Scholar / GitHub / LinkedIn

Santa Monica, CA · NeurIPS 2025 trip

Research

I'm interested in solving real-world problems, particularly through AI for Science and AI for Engineering. I'm also interested in representation learning for graph and tabular data. My current research focuses on:

AI for Science: benchmarks and models for physical systems with scarce labels but rich domain knowledge.
AI for Engineering: solving engineering problems such as 3D CAD reconstruction with agentic frameworks.
Heterogeneous Graph Learning: quantifying the utility of graph structure in heterogeneous text-attributed graphs.

News

Aug 2026 Received the Best Paper Award at the KDMS 2026 Summer Conference.

Aug 2026 Received the Research Achievement Scholarship from SNU AI MED for our KDD 2026 paper.

May 2026 2 papers accepted at the ICML 2026 Workshop on AI for Science.

May 2026 1 paper accepted at KDD 2026 (AI for Sciences Track) as an oral presentation.

Dec 2025 Received the Best Poster Award at the NeurIPS 2025 Workshop on AI for Science.

Sep 2025 1 paper accepted at the NeurIPS 2025 Workshop on AI for Science.

Sep 2025 1 paper accepted at IEEE Access.

Aug 2025 Received the Best Paper Award at the KDMS 2025 Summer Conference.

Mar 2025 Started the integrated Ph.D. program at GSDS, SNU, in the DIAL Lab.

Dec 2024 1 paper accepted at the AAAI 2025 Workshop on Anomaly Detection in Scientific Domains.

Research Experience

SNU	Seoul National University, Graduate School of Data Science Research Intern, DIAL Lab Aug 2024 – Feb 2025 Advisor: Prof. Hyunwoo Park
KISTI	Korea Institute of Science and Technology Information (KISTI) Research Assistant, Technology Commercialization Research Center Feb 2024 – May 2024 Advisor: Dr. Yunjeong Choi
ETRI	Electronics and Telecommunications Research Institute (ETRI) Research Intern, Fiscal and Economic Policy Intelligence Research Center Jul 2023 – Aug 2023 Advisor: Dr. Yeonhee Lee

Publications

Some papers are highlighted. * denotes equal contribution, † denotes corresponding author.

ICML '26 Workshop	Domain-Prior-Regularized Graph Modeling for Anomaly Detection in Cyber-Physical Systems Youngseok Hwang, Joonsung Kwon, Geonwoo Lee, Hyunwoo Park† ICML Workshop on AI for Science, 2026 paper Using an LLM to extract physical sensor couplings from system documentation and fixing them as a graph prior beats learned topologies in data-scarce cyber-physical systems.
ICML '26 Workshop	AISFlow: Boundary-Informed Flow Matching for Long-Term AIS Trajectory Imputation Sungho Bae, Youngseok Hwang*, Geonwoo Lee, Jaeeun Seo, Dohun Lee, Hyunwoo Park† ICML Workshop on AI for Science*, 2026 paper Starting flow matching from the vessel states on both sides of a gap, instead of Gaussian noise, fills long AIS gaps more accurately and up to 317× faster than diffusion models.
KDD '26	Redefining Maritime Anomaly Detection via Equation-Grounded Synthetic Anomalies Youngseok Hwang, Sungho Bae, Dohun Lee, Jaeeun Seo, Jeehong Kim, Wonhee Lee, Hyunwoo Park† KDD (AI for Sciences Track), 2026 (Oral Presentation) paper / arXiv / code Grounding maritime anomalies in kinematic equations, rather than statistical rarity, lets an LLM-guided pipeline synthesize labeled anomalies, including inter-vessel close approaches, for systematic benchmarking.
IEEE Access	STGVAD: Spatio-Temporal Graph-based Vessel Behavior Anomaly Detection Jeehong Kim, Minchan Kim, Youngseok Hwang, Sungho Bae, Deuk Jae Cho, Wonhee Lee†, Hyunwoo Park† IEEE Access, 2026 paper / code Representing each timestamped vessel state as a node and linking nearby ships via clustering lets a GNN jointly model vessel dynamics and interactions, outperforming time-series baselines especially when anomalies are scarce.
NeurIPS '25 Workshop	Spatio-Temporal Graphs Beyond Grids: Benchmark for Maritime Anomaly Detection Jeehong Kim, Youngseok Hwang*, Minchan Kim, Sungho Bae, Hyunwoo Park† NeurIPS Workshop on AI for Science*, 2025 (Best Poster Award) arXiv Turning an open maritime traffic dataset into a graph benchmark enables node-, edge-, and graph-level anomaly detection in spatio-temporal systems without fixed spatial anchors.
AAAI '25 Workshop	Adaptive Sparsified Graph Learning Framework for Vessel Behavior Anomalies Jeehong Kim, Minchan Kim, Jaeseong Ju, Youngseok Hwang, Wonhee Lee, Hyunwoo Park† AAAI Workshop on Anomaly Detection in Scientific Domains, 2025 arXiv Modeling each timestamp as a node yields sparse multi-ship graphs on which forecasting and graph reconstruction jointly flag anomalous vessel behavior.

Awards & Honors

Best Paper Award, KDMS Summer Conference 2026

Research Achievement Scholarship, Medical AI Talent Program (SNU AI MED), SNU 2026

Best Poster Award, NeurIPS Workshop on AI for Science 2025

Medical AI Talent Program (SNU AI MED), SNU 2025–present

Best Paper Award, KDMS Summer Conference 2025

Commendation Prize, NH Investment & Securities Big Data Competition 2024

Outstanding Project Award, Google for Developers Machine Learning Bootcamp 2024

Top 2.8% of 2,400 participants, LG Aimers 5th Cohort (LG AI Research) 2024

Top 0.7% of 3,400 participants, LG Aimers 4th Cohort (LG AI Research) 2024

Research Grant, LG AI Talent Pool (LG AI Research) 2024

Encouragement Prize, Automobile Environmental Big Data Competition (K-ECO) 2024

Excellence Prize, Student Thesis Competition (NABO) 2023

Top Prize, Start-up Idea Pitching Competition (CTIA) 2023

Top Prize, CCF ChatGPT Competition (CICI) 2023

Excellence Prize, GetGPT Idea Competition (Wordbricks) 2023

Encouragement Prize, ChatGPT AI Service Hackathon (Maum.AI) 2023

Excellence Prize, MODUIDEALAB Idea Contest (Modulabs) 2023

Top Prize, AI Service Idea Hackathon (Maum.AI) 2022

Excellence Prize, Cloud Idea Competition (BIPA) 2022

Excellence Prize, AI Content Convergence Idea Competition (GICON) 2022

Dean's Award (Outstanding Project), Korea University Intelligent Information SW Academy 2022

Teaching Experience

Teaching Assistant, Special Topics in Data Science (Vibe Coding), GSDS, SNU Fall 2026

Instructor: Prof. Hyunwoo Park

Teaching Assistant, Mathematics and Data Science for Understanding Social Systems, SNU College Spring 2026

Instructor: Prof. Hyejin Youn

Teaching Assistant, AI Career Path Program, SNU GSDS & Korea Sanhak Foundation 2025–2026

Instructors: Prof. Hyunwoo Park and Prof. Taesup Kim

Teaching Assistant, Big Data & AI CEO Program (1st, 2nd, 4th cohorts), SNU & KDT 2025–2026

Instructor: Prof. Hyunwoo Park

Teaching Assistant, Advanced Training Program in Big Data, AI & Fintech (11th cohort), SNU & KDT 2025

Instructor: Prof. Hyunwoo Park

Service

President, Graduate Student Council, Graduate School of Data Science, SNU 2026

Mentor, Google-sponsored ExploreCSR SNU Data Science Career Workshop 2025