🇰🇷 🇺🇸 🇦🇺 🇸🇬 🇯🇵 🇲🇳 🇨🇳 🇲🇾 🇶🇦 🇷🇼 🇰🇪 🇻🇳 🇫🇷 🇮🇹 🇨🇭 🇩🇪 🇬🇧
- Safeguard Text-to-Image Diffusion Models with Human Feedback Inversion [paper] [code]
Sanghyun Kim, Seohyeon Jung, Balhae Kim, Moonseok Choi, Jinwoo Shin, Juho Lee
ECCV 2024 (Acceptance rate: 27.9%) - Slot-Mixup with Subsampling: A Simple Regularization for WSI Classification [arXiv]
Seongho Keum, Sanghyun Kim, Soojeong Lee, Juho Lee
ariXiv preprint. - Towards safe self-distillation of Internet-scale text-to-image diffusion models [paper] [code]
Sanghyun Kim, Seohyeon Jung, Balhae Kim, Moonseok Choi, Jinwoo Shin, Juho Lee
ICML 2023 Workshop on Challenges of Deploying Generative AI - Modeling uplift from observational time-series in continual scenarios [paper] [code] [PMLR]
Sanghyun Kim, Jungwon Choi, NamHee Kim, Jaesung Ryu, Juho Lee
AAAI 2023 Bridge on Continual Casality (oral presentation), 2023 - A simple yet powerful deep active learning with snapshot ensembles [paper] [code]
Seohyeon Jung*, Sanghyun Kim*, Juho Lee
(*: Equal Contribution)
ICLR 2023 (Acceptance rate: 24.3%)