Graduate students

Sehyun Lee

PhD student (20.03 ~ )

Ph.D student at KAIST, 2020 - present MS student at UNIST, 2019 – 2020 BS in Computer Science and Engineering, and System Design and Business Administration from UNIST, 2018

Ph.D student at KAIST, 2020 - present
MS student at UNIST, 2019 – 2020
BS in Computer Science and Engineering, and System Design and Business Administration from UNIST, 2018
Research interest: Polysemantic neurons, neural network verification, representation learning, computer vision
sehyun.lee (at) kaist.ac.kr

2 notes

Research

All research

2025
Granular Concept Circuits
GCC discovers fine-grained circuits tied to specific visual concepts by assessing functional dependencies and semantic alignment between neurons.
2025
Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations
Deep vision models have achieved remarkable classification performance by leveraging a hierarchical architecture in which human-interpretable concepts emerge through the composition of individual neurons across layers. Given the distributed nature of representations, pinpointing where specific visual concepts are encoded within a model remains a crucial yet challenging task. In this paper, we introduce an effective circuit discovery method, called Granular Concept Circuit (GCC), in which each circuit represents a concept relevant to a given query. To construct each circuit, our method iteratively assesses inter-neuron connectivity, focusing on both functional dependencies and semantic alignment. By automatically discovering multiple circuits, each capturing specific concepts within that query, our approach offers a profound, concept-wise interpretation of models and is the first to identify circuits tied to specific visual concepts at a fine-grained level. We validate the versatility and effectiveness of GCCs across various deep image classification models.

4 papers

Publications

Full record

2026

[113]
SPICE: Simple Polysemantic Feature Interpretation via Clustering-based Explanations
Sehyun Lee, Dahee Kwon, Damin Lee, and Jaesik Choi
European Conference on Computer Vision (ECCV) 2026.Computer vision Explainable AI
[105]
Towards Transparent Time Series Analysis: Exploring Methods and Enhancing Interpretability
Youngjin Park, Anh Tong, Sehyun Lee, Jihyeon Seong, Qin Xie and Jaesik Choi
ACM Computing Surveys, 2026.Explainable AI Time series
Paper

2025

[99]
Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations
Dahee Kwon*, Sehyun Lee* and Jaesik Choi
International Conference on Computer Vision (ICCV), 2025.Explainable AI
Paper

2023

[76]
Implicit Contrastive Representation Learning with Guided Stop-gradient
Byeongchan Lee* and Sehyun Lee*
Conference on Neural Information Processing Systems (NeurIPS), 2023 (* contributed equally).Other
Paper

Sehyun Lee

Research

Granular Concept Circuits

Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations

Publications

2026

SPICE: Simple Polysemantic Feature Interpretation via Clustering-based Explanations

Towards Transparent Time Series Analysis: Exploring Methods and Enhancing Interpretability

2025

Granular Concept Circuits: Toward a Fine-Grained Circuit Discovery for Concept Representations

2023

Implicit Contrastive Representation Learning with Guided Stop-gradient