AI Researcher · Korea University
I am an integrated M.S.–Ph.D. researcher in Artificial Intelligence at Korea University. My work connects neural signals, embodied systems, and interpretable machine learning to make human–AI collaboration more adaptive and trustworthy.
My research spans Physical AI, brain–computer interfaces, and explainable AI. I am particularly interested in systems that learn from implicit human feedback and translate it into safer real-world behavior.
Explore my research Discuss collaboration →
Embodied agents that learn to operate safely in dynamic environments with humans in the loop.
Robust neural decoding, cross-subject adaptation, and multimodal interfaces grounded in EEG.
Counterfactual methods that reveal why fine-grained models fail and how their decisions can improve.
14th International Winter Conference on Brain-Computer Interface (BCI), Accepted Paper
A compact language model adapted to clinical EEG reporting for polishing, summarization, terminology QA, and future EEG–language systems.
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
A counterfactual framework that explains fine-grained misclassification at both object and part levels using saliency partition.
Neural Networks
A semantic-prioritized counterfactual framework that improves the relevance and efficiency of region replacement.
13th International Winter Conference on Brain-Computer Interface (BCI)
A flexible representation-learning framework that fuses EEG with video and audio for affective brain–computer interfaces.
2026
A belief-aware, object-centric dynamics model that learns multiple plausible 3D futures from structured object-state histories.
View project →
2025
A closed-loop human–AI system that decodes implicit neural error signals and adapts multimodal cues for safer embodied autonomy.
View project →
2025
An immersive VR/AR platform for decoding multi-site tactile EEG and recognizing continuous tactile input in real time.
2023
A VR-based four-class motor-imagery BCI with real-time EEG decoding and robotic arm interaction across users.
NeuroLex was accepted to the International BCI Conference 2026.
Our work on fine-grained counterfactual explanations appeared at CVPR 2025.
GITGAN was published in Pattern Recognition.
I welcome conversations about neuroadaptive embodied systems, EEG representation learning, explainability, and international research collaboration. Email me or explore my work on Google Scholar.