NOTE : Blog updates may occasionally not be reflected, so we recommend performing a FORCE RELOAD (Windows: Ctrl + Shift + R, Mac: Command (⌘) + Shift + R)
Topics I keep returning to across current projects, papers, and experiments.
Embodied Robot Intelligence and Robot Control & Manipulation
I am interested in robot intelligence across decision-making and control, focusing on physics-based simulation, trajectory optimization, and motion learning for interactive robotic systems.
Learning from Human Demonstrations, Vision-Language-Action model
I keep studying how human demonstrations, language, and perception can be aligned into robot policies.
Multimodal Foundation Models for Data-Efficient Medical Vision
I am interested in medical vision-language models for robust medical image understanding under limited supervision.
Nature-Inspired Technology and Cross-Domain Fusion
I enjoy experimenting with applying methodologies used in one task or domain to other areas.
Selected main projects and representative work.
Enhanced the tumor segmentation performance of the MedCLIP-SAM framework by integrating DPO-based optimization with diffusion-driven counterfactual image generation.
Build a custom robotics simulator based on MuJoCo to understand robot kinematics, dynamics, and control.
Developed an end-to-end pipeline to construct physically constrained EgoVLA training data represented through MANO hand meshes.
MuJoCo simulation demo for dVRK PSM teleoperation with RCM-aware control and surgical task targets.
A seminar session that introduces EgoVLA and EgoBridge through the lens of shared ideas and representation learning.
A seminar session that introduces the Olaf robot implementation process based on reinforcement learning and human-robot interaction principles.
Experiment with asymmetry-aware distance For SAR-Optical domain gap mitigation.
Community activity around AI/ML study, technical sessions, and collaborative growth through GDGoC.
Participated in the Korean translation of the PyTorch documentation and translated the Knowledge Distillation Tutorial document.
A demand forecasting project for restaurant menus using operational data and machine learning modeling.
A generative design project exploring efficient font creation for minority languages.
Development and deployment of Softie, a routine recommendation application for mental health improvement.
Experiments under active iteration, experimentation, and repeated attempts.
External activities, communities, and small projects.
Conducted an iOS frontend development study at UMC.