Publications

Concept Erasure	Localized Concept Erasure in Text-to-Image Diffusion Models via High-Level Representation Misdirection Uichan Lee, Jeonghyeon Kim and Sangheum Hwang International Conference on Learning Representations (ICLR), 2026 paper
Unlearning	Parameter-Efficient LLM Unlearning through Sparse Attention Head Updates Deokyong Lee, Jeonghyeon Kim and Sangheum Hwang Korean Institute of Industrial Engineers, (KIIE), 2025 paper
VLM-OoDD	Enhanced OoD Detection through Cross-Modal Alignment of Multi-Modal Representations Jeonghyeon Kim and Sangheum Hwang IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2025 paper code
Unlearning	Uncovering Hidden Vulnerabilities in Machine Unlearning: Adversarial Attack Hwiyeong Lee, Jeonghyeon Kim, Sangheum Hwang Korea Computer Congress (KCC), 2024 paper
VLM-OoDD	Uniformity Reduction Regularization: Multimodal Fine-tuning to Enhance Out-of-Distribution Detection Performance Jeonghyeon Kim, Jihyo Kim, Sangheum Hwang Korea Computer Congress (KCC), 2024 paper Oral
VLM-OoDD	Comparison of Out-of-Distribution Detection Performance of CLIP-based Fine-Tuning Methods Jeonghyeon Kim, Jihyo Kim, Sangheum Hwang International Conference on Electronics, Information, and Communication (ICEIC), 2024 paper Oral Best Paper Award
VLM-OoDD	Enhancing Out-of-Distribution Detection Performance of CLIP Based on Fine-tuning with Random Texts Jeonghyeon Kim, Jihyo Kim, Sangheum Hwang Korea Computer Congress (KCC), 2023 paper Oral Best Paper Award
Active-Learning	Deep Active Learning with Contrastive Learning Under Realistic Data Pool Assumptions Jihyo Kim, Jeonghyeon Kim, Sangheum Hwang AAAI Workshop on Practical Deep Learning in the Wild, 2023 paper

* Equal contribution