안녕하세요! 이곳은 제가 읽은 논문들을 리뷰하고 정리하는 공간입니다.
각 논문에 대한 핵심 아이디어와 주요 기여점을 간결하게 요약하여 공유합니다.
| 논문 제목 | 출판년도 | 학회/저널 | 작성일 |
|---|---|---|---|
| Unified Concept Editing in Diffusion Models | 2024 | WACV 2024 | 2025-04-18 |
| An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion | 2022 | ICLR 2023 | 2025-04-17 |
| Circumventing Concept Erasure Methods For Text-To-Image Generative Models | 2023 | ICLR 2024 | 2025-04-15 |
| Direct Unlearning Optimization for Robust and Safe Text-to-Image Models | 2024 | NIPS 2024 | 2025-04-15 |
| Probing Unlearned Diffusion Models: A Transferable Adversarial Attack Perspective | 2024 | Arxiv | 2025-04-14 |
| GuardT2I: Defending Text-to-Image Models from Adversarial Prompts | 2024 | NIPS 2024 | 2025-04-14 |
| SafetyDPO: Scalable Safety Alignment for Text-to-Image Generation | 2024 | Arxiv | 2025-04-11 |
| Latent Guard: A Safety Framework for Text-to-Image Generation | 2025 | ECCV 2024 | 2025-04-11 |
| MMA-Diffusion: MultiModal Attack on Diffusion Models | 2024 | CVPR 2024 | 2025-04-09 |
| Conflict-Averse Gradient Descent for Multi-task learning | 2021 | NIPS 2021 | 2025-04-09 |