Youngjin Shin

Youngjin Shin

Research Intern · KAIST AI

Focused on understanding and improving AI models through internal mechanisms and representations. Interested in representation learning, 3D visual understanding, and how models reason through structured analysis.

yeongjins916@gmail.com

Scroll

Interests

Representation Learning 3D Visual Understanding Vision-Language Models

Work Experience

Research Intern · Computer Vision Lab
KAIST AI, Seoul · Advisor: Seungryong Kim
2025.09 – Present
Research Intern · Multi-dimensional Insight Lab
Yonsei University, Seoul · Advisor: Sanghoon Lee
2025.01 – 2025.08

Publications

2026
MORPHOS teaser
MORPHOS: Autoregressive 4D Generation with Temporal Structured Latents
Minkyung Kwon, Jinhyeok Choi, Youngjin Shin, Jaeyeong Kim, JongMin Lee, Seungryong Kim
Project Paper Code
CORAL teaser
CORAL: Correspondence Alignment for Improved Virtual Try-On
Jiyoung Kim, Youngjin Shin, Siyoon Jin, Dahyun Chung, Jisu Nam, Tongmin Kim, Jongjae Park, Hyeonwoo Kang, Seungryong Kim
Project Paper Code
2025
YOTO teaser
You Only Touch Once: One-Touch System for Personalized 3D Music Video Generation
Kyungjune Lee, Youngjin Shin, Jungwoo Huh, Sanghoon Lee
Paper

Education

B.S. in Electrical and Electronic Engineering
Yonsei University
Mar 2020 – Mar 2026
  • GPA: 4.1 / 4.3
  • Military service leave: Nov 2021 – May 2023

Personal Playground

Feature Visualization playground
Feature Visualization · InceptionV1
An interactive playground reproducing the technique from Olah et al., “Feature Visualization” (Distill, 2017) — explore channels, neurons, layers, logits, probabilities, and joint optimizations.
Live Code