Graduate students
Dahee Kwon
PhD student (22.09 ~ )
- PhD student, 2022 Fall – Present
- MS student, 2020 Fall Bachelor of Arts in Statistics from Yonsei University, 2020
- Research interest: Explainable AI, model Generalization, Computer VIsion
6 notes
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.
2025
Creative Concept Catalyst
C3 selectively amplifies features during denoising to improve creativity in Stable Diffusion-based models without additional training.
2025
Enhancing Creative Generation on Stable Diffusion-based Models
Recent text-to-image generative models, particularly Stable Diffusion and its distilled variants, have achieved impressive fidelity and strong text-image alignment. However, their creative capability remains constrained, as including `creative' in prompts seldom yields the desired results. In this paper, we introduce C3 (Creative Concept Catalyst), a training-free approach designed to enhance creativity in Stable Diffusion-based models. C3 selectively amplifies features during the denoising process to foster more creative outputs. We offer practical guidelines for choosing amplification factors based on two main aspects of creativity. C3 is the first study to enhance creativity in diffusion models without extensive computational costs. We demonstrate its effectiveness across various Stable Diffusion-based models.
2024
Relaxed Decision Regions
Principal neuron subsets reveal coherent distributed concepts in the intermediate representations of image classifiers.
2024
Understanding Distributed Representations of Concepts in Deep Neural Networks without Supervision
Understanding intermediate representations of the concepts learned by deep learning classifiers is indispensable for interpreting general model behaviors. In this paper, we propose a novel unsupervised method for discovering distributed representations of concepts by selecting a principal subset of neurons. Our empirical findings demonstrate that instances with similar neuron activation states tend to share coherent concepts. Based on the observations, the proposed method selects principal neurons that construct an interpretable region, namely a Relaxed Decision Region (RDR), encompassing instances with coherent concepts in the feature space.
5 papers
Publications
2026
- [113]
SPICE: Simple Polysemantic Feature Interpretation via Clustering-based Explanations
- [110]
Breaking the Lock-in: Diversifying Text-to-Image Generation via Representation Modulation