Hyunuk Shin

I am currently a research intern in the Computer Vision Lab at the POSTECH, advised by Prof. Suha Kwak. I will join the lab as a Master’s student this September.

My research broadly focuses on the computational challenges at the intersection of machine learning and physical world understanding. Ultimately, I aim to build intelligent systems that can perceive and interact with complex environments much like humans do. Specifically, my current interests include:

Vision-Language-Action Model (VLA)
World Action Model (WAM)
Multimodal Learning
3D Vision

I am always eager to exchange ideas and explore potential research collaborations. If my work aligns with your interests, please feel free to reach out to me!

news

May 12, 2026	I will join Postech Computer Vision Lab this September.
Jan 15, 2026	One paper is accepted to WWW 2026

selected publications

WWW 26

ReCon: Improving the Accuracy of Community Detection on Signed Networks via Community Refinement and Contrastive Learning

Hyunuk Shin^*, Hojin Kim^*, Chanyoung Lee^*, and 2 more authors

Short Paper, Dubai, UAE, Apr 2026 (h-index: 120, accept rate: 23%)

Abs arXiv Code

Community detection (CD) on signed networks is crucial for understanding how positive and negative relations jointly shape network structure. However, existing CD methods often yield inconsistent communities due to noisy or conflicting edge signs. In this paper, we propose ReCon, a model-agnostic post-processing framework that progressively refines community structures through four iterative steps: (1) structural refinement, (2) boundary refinement, (3) contrastive learning, and (4) clustering. Extensive experiments on eighteen synthetic and four real-world networks using four CD methods demonstrate that ReCon consistently enhances community detection accuracy, serving as an effective and easily integrable solution for reliable CD across diverse network properties.