Jan 2026 — present
Researcher · KETI
3D vision & physical AI.
Supervisor: Dr. Min-Gyu Park.
Researcher · Optimization for Efficiency & Robustness
Seonghwan Park 박성환
I'm a researcher at the Korea Electronics Technology Institute (KETI), working with Dr. Min-Gyu Park. Before this, I received my M.S. from POSTECH under Prof. Namhoon Lee.
My research studies model efficiency and robustness through the lens of optimization. I now bring this perspective to 3D vision and physical AI.
Research Interests
- ◆ Optimization
- △ 3D Vision
- ○ Physical AI
- ▽ Robustness
- ◇ Efficiency
01 News
Joined the Korea Electronics Technology Institute (KETI) as a researcher, working on 3D vision and physical AI under Dr. Min-Gyu Park.
Our paper on robust concept bottleneck models was accepted to NeurIPS 2025.
Completed my M.S. in AI at POSTECH, advised by Prof. Namhoon Lee.
Our paper on black-box prompt tuning was accepted to ICLR 2025.
Started a project with Samsung Advanced Institute of Technology (SAIT) on visual prompting for MMFM-based VQA.
Our paper on backprop-free federated learning was presented at the ICML 2023 Federated Learning Workshop.
Started my M.S. in AI at POSTECH, joining the Computational Optimization Lab under Prof. Namhoon Lee.
02 Publications
Year
Topic
-
In review 2026
Physically Plausible 3D Human-Object Interaction (Tentative)
-
In review 2026
Efficient Out-of-Distribution Detection Method (Tentative)
-
In review 2026
3D Reconstruction from Monocular Video (Tentative)
-
NeurIPS 2025
-
CKAIA 2025
OAIG: Object-Centric Visual Prompting for Vision-Language Models
-
ICLR 2025
-
ICML-W 2023
-
ICML-W 2023
No publications match this filter.
03 Experience
Aug 2025 — Dec 2025
Research Assistant · Computational Optimization Lab, POSTECH
Efficiency & robustness through optimization.
Supervisor: Prof. Namhoon Lee.
Jun 2025 — Nov 2025
Samsung Research Project
MMFM for anomaly detection.
Jun 2024 — May 2025
Samsung Advanced Institute of Technology Project
Visual prompting for MMFM-based VQA.
Jan 2022 — Dec 2022
Undergraduate Research Intern · ML Lab, Hanyang Univ.
Large language models.
Supervisor: Prof. Eun-Sol Kim.
04 Education
Mar 2023 — Aug 2025
M.S. in Artificial Intelligence · POSTECH
GPA 3.9 / 4.0 (4.0 / 4.3).
Advised by Prof. Namhoon Lee.
Mar 2017 — Feb 2023
B.S. in Computer Science & Engineering · Hanyang University
GPA 3.86 / 4.0 (4.12 / 4.5).
summa cum laude.
05 Teaching, Awards & Service
Teaching
-
POSTECH · TA
Introduction to Artificial Intelligence
-
POSCO AI Fellowship · TA
Deep Learning
Honors & Awards
- CKAIA Best Paper Finalist
- HYU Academic Excellence · top 3%
Service
- Reviewer · ICLR, ECCV, TMLR
- ROKAF Logistics Command · Sergeant