Publications

Selected and recent work across brain–computer interfaces, Physical AI, multimodal learning, and explainable AI. For citation metrics and the latest indexing status, see my Google Scholar profile.

2026

NeuroLex: A Lightweight Domain Language Model for EEG Report Understanding and Generation

Kang Yin, Hye-Bin Shin

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.

2025

Towards Fine-Grained Interpretability: Counterfactual Explanations for Misclassification with Saliency Partition

Lintong Zhang*, Kang Yin*, Seong-Whan Lee

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.

2025

Semantic Prioritization in Visual Counterfactual Explanations with Weighted Segmentation and Auto-Adaptive Region Selection

Lintong Zhang, Kang Yin, Seong-Whan Lee

Neural Networks

A semantic-prioritized counterfactual framework that improves the relevance and efficiency of region replacement.

2025

Towards a Network Expansion Approach for Reliable Brain-Computer Interface

Byeong-Hoo Lee, Kang Yin

13th International Winter Conference on Brain-Computer Interface (BCI)

An expandable EEG network that increases capacity when needed to improve personalized, session-to-session BCI reliability.

2025

EEG-based Multimodal Representation Learning for Emotion Recognition

Kang Yin, Hye-Bin Shin, Dan Li, Seong-Whan Lee

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.

2024

Domain-Incremental Learning Framework for Continual Motor Imagery EEG Classification Task

Dan Li, Hye-Bin Shin, Kang Yin, Seong-Whan Lee

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

A continual-learning framework that separates invariant and subject-specific features to reduce catastrophic forgetting across EEG domains.

2024

Baseline-Guided Representation Learning for Noise-Robust EEG Signal Classification

Elissa Yanting Lim, Kang Yin, Hye-Bin Shin, Seong-Whan Lee

46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

A baseline-guided representation strategy for improving EEG classification robustness under noisy recording conditions.

2024

GITGAN: Generative Inter-subject Transfer for EEG Motor Imagery Analysis

Kang Yin, Elissa Yanting Lim, Seong-Whan Lee

Pattern Recognition

An unsupervised subject-adaptation framework that prioritizes high-quality source EEG data while preserving the target distribution.