Giwon Lee

Hello! I am a first-year Ph.D. student in VILAB led by Prof. Kuk-Jin Yoon in the Department of Mechanical Engineering at KAIST. My research spans the full spectrum of planning — from high-level reasoning to low-level control — with the long-term goal of building a single, coherent framework that can be entrusted to act fully autonomously, end to end.

I think of this stack in three layers. At the high level, Agentic AI handles reasoning, decision-making, and long-horizon planning. As the bridge, Vision-Language-Action (VLA) and Vision-Language Navigation (VLN) models ground language and perception into embodied action. At the low level, Motion Planning and End-to-End Autonomous Driving turn intent into safe, executable behavior. My earlier research centered on this low level, primarily in autonomous driving; my current work moves up the stack to the high and bridge levels — these days on Agentic AI, VLA, and VLN — building toward connecting all three into one autonomous whole.

I am also eager to gain hands-on industry experience through internships, and I would be grateful to hear about any relevant opportunities. Please feel free to get in touch by email or on LinkedIn.