I am a Ph.D. candidate at the Intelligent Computational Imaging Lab (advised by Prof. Se Young Chun) in the Department of Electrical and Computer Engineering at Seoul National University. I received my B.S. in Electrical Engineering from UNIST.
My research focuses on selective knowledge updates for deep visual and foundation models toward agentic/physical AI — how to add new knowledge or remove unwanted knowledge while preserving existing capabilities. I have studied this through continual learning, unlearning, and reinforcement learning, which are essential for agentic/physical AI, vertical-AI, and visual generative AI. I am currently extending these ideas to multimodal LLMs, omnimodal models, vision-language-action models, and domain-specialized models, aiming at adaptive and reliable knowledge updates that efficiently scale to real-world settings. Additionally, I am interested in model acceleration, image restoration, and histopathology analysis.
* denotes equal contribution.
Scales selective concept erasure to 2,000+ concepts while preserving the remaining ones, via optimal transport and mixture-of-experts updates.
Memory-free continual learning for gigapixel pathology slides, preserving both diagnosis and localization across a stream of organs.
Training-free, spatially localized concept erasure that removes only the target while keeping the rest of the image intact.
A residual attention gate that erases target concepts from diffusion models while preserving the generation of remaining concepts.
Future-aware online continual learning that improves stability and plasticity through doubly perturbed training.
Hierarchy-aware memory management for online continual learning under streaming, label-expanding data.