Inseok Kong profile photo

Inseok Kong

Hello! I am an Undergraduate Researcher in the Speech & Interactive AI Laboratory (SIA) at University of Seoul (UOS), advised by Prof. Heeseung Kim. I am also a senior undergraduate student in the Department of GeoInformatics & AI at UOS. Previously, I worked as an Undergraduate Research Intern in the Statistical Inference and Information Theory Lab (SIIT) at KAIST (advised by Prof. Junmo Kim) and the Robotics and Computer Vision Lab (RCV) at UOS (advised by Prof. Jiyoung Jung).

My research interests lie in Trustworthy Artificial Intelligence and Computer Vision. I have worked on Test-Time Adaptation (TTA), 3D adversarial defense, and Vision-Language Models (VLMs). Beyond these topics, I am eager to explore a broader spectrum of research areas to build reliable and robust visual AI systems.

Email  /  CV  /  Google Scholar  /  GitHub  /  LinkedIn

News

  • [2026.07] Thrilled to announce that our paper, MAMVI, will be presented as an Oral Presentation at ICPR 2026 in Lyon, France!

  • [2026.04] Our work on 3D test-time adaptation via masked multi-view point clouds, MAMVI, has been accepted to ICPR 2026!

  • [2026.03] Our work on transferable 3D point cloud adversarial defense, APC, has been accepted to CVPR 2026 Findings!

Publications & Preprints
APC Framework Diagram
APC: Transferable and Efficient Adversarial Point Counterattack for Robust 3D Point Cloud Recognition
Geunyoung Jung, Soohong Kim, Inseok Kong, Jiyoung Jung
IEEE/CVF Conference on Computer Vision and Pattern Recognition Findings (CVPR Findings)
Mar. 2026
paper
MAMVI Framework Diagram
MAMVI: 3D Test-Time Adaptation via Masked Multi-View Point Clouds
Inseok Kong, Geunyoung Jung, Jiyoung Jung
IEEE/IAPR International Conference on Pattern Recognition (ICPR)
(Oral Presentation)  Apr. 2026 (Accepted), Jul. 2026 (Oral Selected)
arXiv
Under Review
SATOR: Backpropagation-Free 3D Test-Time Adaptation via Sample-Adaptive Token Routing
Inseok Kong, Geunyoung Jung, Jiyoung Jung
Under Review
Under Review
Mitigating Feature Collapse for Test-Time Adaptation of 3D VLMs via Distribution-Guided Regularization
Geunyoung Jung, Inseok Kong, Jiyoung Jung
Under Review

Research Experience

  • Speech & Interactive AI Laboratory (SIA), University of Seoul - Seoul, S. Korea
    Undergraduate Research Student
    Aug. 2026 – Present
    • Advisor: Prof. Heeseung Kim
    • Research on Audio-Vision-Language Models (AVLLMs) and hallucination mitigation.

  • Statistical Inference and Information Theory Lab (SIIT), KAIST - Daejeon, S. Korea
    Undergraduate Research Student
    Jul. 2026 – Aug. 2026
    • Advisor: Prof. Junmo Kim
    • Research on Large Vision-Language Models (LVLMs), object hallucination mitigation, and uncertainty calibration.

  • Robotics and Computer Vision Lab (RCV), University of Seoul - Seoul, S. Korea
    Undergraduate Research Student
    Jul. 2025 – Jun. 2026
    • Advisor: Prof. Jiyoung Jung
    • Researched 3D Test-Time Adaptation (TTA) under severe domain shifts, point cloud robustness & adversarial defense, and cross-modal alignment in 3D VLMs.

Education

  • University of Seoul (UOS) - Seoul, S. Korea
    B.S. in GeoInformatics and Artificial Intelligence (Double Major)
    Mar. 2022 – Present
    • Cumulative GPA: 3.8 / 4.5
    • Relevant Coursework: Machine Learning, Deep Learning, Pattern Recognition, Data Structures, Algorithms.

Projects

  • LG Aimers 8th Cohort (LLM Compression Track)
    Jan. 2026 – Feb. 2026
    • Applied model compression & optimization techniques (pruning, quantization) on EXAONE LLMs.

  • Optimal Autonomous Shuttle Route Planning
    Capstone Design Project & Seoul Big Data Campus
    Oct. 2025 – Jan. 2026
    • Developed route optimization algorithms using mobility big data to support autonomous shuttle services for elderly citizens in Seoul.

  • Sportier (UOS Entrepreneurship Club)
    Lead Developer & President
    Mar. 2025 – Jul. 2025
    • Developed a sports matchmaking web application using React.js with location-based matching and competitive tier rankings.

  • Football Big Data Analytics
    Football Big Data Camp
    Feb. 2025
    • Investigated practical applications of LLMs and RAG in football performance analytics.

Honors & Awards
  • Creativity Award, K-DATA Science Conference & Hackathon (Sep 2026)
  • Excellence Award, Seoul RISE AI Competition (Project: SATOR) (Jun 2026)
  • Grand Prize (Seoul Mayor Award), Seoul Metropolitan Big Data Campus Competition (Oct 2025)
  • Excellence Award, UOS Capstone Design Project (Jan 2026)
  • Encouragement Award, AICOSS Industry-Academia Hackathon (Aug 2025)
  • Dean's Award of College of Engineering, AICOSS Deep Learning Bootcamp (Jan 2025)

Website template adapted from Jon Barron.