Jaewon Kim

Welcome! I am an undergraduate student in Semiconductor Engineering at Korea University, working as a researcher at Complex Data Analytics Lab (CDAL) under Prof. Junhee Seok’s guidance.

What excites me most about AI research is diving deep into the mathematical foundations that make these systems work. Rather than just implementing existing solutions, I love breaking down complex problems into their basic components and building them back up – it’s like solving a puzzle where each piece has its own mathematical beauty.

Right now, my work focuses on making generative models and reinforcement learning more efficient by really understanding what’s happening under the hood. This approach has led to some exciting projects: DiffOptics, where we’re using diffusion models to generate optical designs, and OpticalGAN, which lets us precisely control the generation process.

I share my thoughts and findings about AI and Deep Learning on my tech blog, where I try to break down complex concepts into their fundamental building blocks. If you’re interested in collaborative research that combines deep learning with mathematical precision, I’d love to hear from you!

Research Interests:

• Generative Models: Diffusion models, GANs, with focus on precise control and optimization
• Reinforcement Learning: Model-based and model-free approaches, sample efficiency
• 3D Vision & Rendering: Neural rendering, 3D reconstruction, environmental modeling
• Deep Learning: Advanced optimization techniques, efficient sampling strategies
• Applications: Optical design generation, 3D space modeling, computer vision