Eunji Kim

Google Scholar / LinkedIn / Github / CV / E-mail

Eunji is a Ph.D. candidate in the Department of Electrical and Computer Engineering at Seoul National University, working with Professor Sungroh Yoon. She has previously interned at Microsoft Research, Qualcomm AI Research, and Naver CLOVA. Her research has been supported by the Google PhD Fellowship.

Her current research areas include Responsible AI, Explainable AI (XAI), Efficient Learning, and Multimodality. Specifically, her research aims to build trustworthy models and prediction processes.

Publications


C: Conference, J: Journal, W: Workshop, P: Preprint / * Equal contribution


[W2] Exploring Intrinsic Fairness in Stable Diffusion

Eunji Kim*, Siwon Kim*, Rahim Entezari, Robin Rombach, Sungroh Yoon.

Conference on Neural Information Processing Systems (NeurIPS) workshop on Responsibly Building the Next Generation of Multimodal Foundational Models, 2024.


[C11] Semantic Token Reweighting for Interpretable and Controllable Text Embeddings in CLIP

Eunji Kim, Kyuhong Shim, Simyung Chang, Sungroh Yoon

Empirical Methods in Natural Language (EMNLP) findings, 2024.


[P3] Unlocking Intrinsic Fairness in Stable Diffusion

Eunji Kim*, Siwon Kim*, Rahim Entezari, Sungroh Yoon.

ArXiv Preprint, 2024.


[C10] Probabilistic Concept Bottleneck Models

Eunji Kim, Dahuin Jung, Sangha Park, Siwon Kim, Sungroh Yoon.

International Conference on Machine Learning (ICML), 2023.


[C9] Improving Visual Prompt Tuning for Self-supervised Vision Transformers

Seungryong Yoo, Eunji Kim, Dahuin Jung, Jungbeom Lee, Sungroh Yoon.

International Conference on Machine Learning (ICML), 2023.


[W1] De-stereotyping Text-to-image Models through Prompt Tuning

Eunji Kim*, Siwon Kim*, Chaehun Shin, Sungroh Yoon.

International Conference on Machine Learning (ICML) workshop on Deployment Challenges for Generative AI, 2023.


[C8] Bridging the Gap between Classification and Localization for Weakly Supervised Object Localization

Eunji Kim, Siwon Kim, Jungbeom Lee, Hyunwoo Kim, Sungroh Yoon.

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.


[C7] Weakly Supervised Semantic Segmentation using Out-of-Distribution Data

Jungbeom Lee, Seong Joon Oh, Sangdoo Yun, Junsuk Choe, Eunji Kim, Sungroh Yoon.

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2022.


[J4] Anti-Adversarially Manipulated Attributions for Weakly Supervised Semantic Segmentation and Object Localization

Jungbeom Lee, Eunji Kim, Jisoo Mok, Sungroh Yoon.

IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), in press. (Impact Factor: 16.389)


[J3] Silent Speech Recognition with Strain Sensors and Deep Learning Analysis of Directional Facial Muscle Movement

Hyunjun Yoo*, Eunji Kim*, Jong Won Chung*, Hyeon Cho, Sujin Jeong, Heeseung Kim, Dongju Jang, Hayun Kim, Jinsu Yoon, Gae Hwang Lee, Hyunbum Kang, Joo-Young Kim, Youngjun Yun, Sungroh Yoon, and Yongtaek Hong.

In ACS Appl. Mater. Interfaces, vol. 14, November 2022. (Impact Factor: 10.383)


[C6] XProtoNet: Diagnosis in Chest Radiography with Global and Local Explanations 

Eunji Kim, Siwon Kim, Minji Seo, Sungroh Yoon. 

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.

Oral presentation


[C5] Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentation 

Jungbeom Lee, Eunji Kim, Sungroh Yoon. 

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021.


[J2] Improving generalization performance of electrocardiogram classification models

Hyeongrok Han, Seongjae Park, Seonwoo Min, Eunji Kim, HyunGi Kim, Sangha Park, Jinkook Kim, Junsang Park, Junho An, Kwanglo Lee, Wonsun Jeong, Sangil Chon, Kwonwoo Ha, Myungkyu Han, Hyun-Soo Choi, Sungroh Yoon

In Physiological Measurement, vol. 44, May 2023.


[C4] Towards High Generalization Performance on Electrocardiogram Classification

Hyeongrok Han, Seongjae Park, Seonwoo Min, Hyun-Soo Choi, Eunji Kim, Hyunki Kim, Sangha Park, Jinkook Kim, Junsang Park, Junho An, Kwanglo Lee, Wonsun Jeong, Sangil Chon, Kwonwoo Ha, Myungkyu Han, Sungroh Yoon

Computing in Cardiology (CinC), 2021.


[J1] Robust End-to-End Focal Liver Lesion Detection using Unregistered Multiphase Computed Tomography Images 

Sang-gil Lee*, Eunji Kim*, Jae Seok Bae*, Jung Hoon Kim, Sungroh Yoon. 

IEEE Transactions on Emerging Topics in Computational Intelligence (TETCI), vol. 7, April 2023.


[C3] Interpretation of NLP models through input marginalization 

Siwon Kim, Jihun Yi, Eunji Kim, Sungroh Yoon. 

Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020.


[P2] Variational Saliency Maps for Explaining Model's Behavior

Jae Myung Kim, Eunji Kim, Seokhyeon Ha, Sungroh Yoon, Jungwoo Lee.

OpenReview, 2020.


[P1] Information-theoretic visual explanation for black-box classifiers

Jihun Yi, Eunji Kim,  Siwon Kim, Sungroh Yoon.

ArXiv preprint, 2020.


[C2] Frame-to-Frame Aggregation of Active Regions in Web Videos for Weakly Supervised Semantic Segmentation 

Jungbeom Lee, Eunji Kim, Sungmin Lee, Jangho Lee, Sungroh Yoon. 

IEEE International Conference on Computer Visio (ICCV), 2019.


[C1] FickleNet: Weakly and Semi-supervised Semantic Image Segmentation using Stochastic Inference 

Jungbeom Lee, Eunji Kim, Sungmin Lee, Jangho Lee, Sungroh Yoon. 

IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019.


Education


Seoul National University, Seoul, Korea


Seoul National University, Seoul, Korea

Exchange Student in Hamburg University of Technology, Hamburg, Germany Spring 2016

Work Experience


Microsoft Research, Redmond, USA


Qualcomm, Korea


Naver AI Lab, Korea

Honors & Awards


Academic Servicies