Minimalist Concept Erasure in Generative Models
Yang Zhang, Er Jin, Yanfei Dong, Yixuan Wu, Philip Torr, Ashkan Khakzar, Johannes Stegmaier, Kenji Kawaguchi
2025年份
6顶会引用
摘要
Figure 1 : Minimalist concept erasure results on FLUX, the latest rectified flow model with 12 billion parameters. We propose minimalist concept erasure, an approach that applies just enough changes to unwanted concepts, so they become unrecognizable. We can effectively remove inappropriate content like NSFW, weapons, and tackle copyright issues by removing protected IPs and art styles while maintaining the model performance.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了最后一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper6
- Closing the Safety Gap: Surgical Concept Erasure in Visual Autoregressive ModelsXinhao Zhong, Yimin Zhou, Zhiqi Zhang, Junhao Li 等ICLR 2026 · 被引用 7 次
- Prototype-Guided Concept Erasure in Diffusion ModelsYuze Cai, Jiahao Lu, Hongxiang Shi, Yichao Zhou 等CVPR 2026 · 被引用 3 次
- Z-Erase: Enabling Concept Erasure in Single Stream Diffusion TransformersNanxiang Jiang, Zhaoxin Fan, Baisen Wang, Daiheng Gao 等ICML 2026 · 被引用 2 次
- Where Concept Erasure Should Occur: Concept–Layer Alignment in Text-to-Video Diffusion ModelsYiwei Xie, Ping Liu, Zheng ZhangICML 2026
- Concept Removal for Frontier Image Generative ModelsAditya Kumar, Pierre Joly, Adam Dziedzic, Franziska BoenischICML 2026
它引用的顶会 Paper21
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 被引用 35,902 次
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
- Scalable Diffusion Models with TransformersWilliam Peebles, Saining XieICCV 2023 · 被引用 5,568 次
- SDXL: Improving Latent Diffusion Models for High-Resolution Image SynthesisDustin Podell, Zion English, Kyle Lacey, Andreas Blattmann 等ICLR 2024 · 被引用 4,569 次
- Scaling Rectified Flow Transformers for High-Resolution Image SynthesisPatrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari 等ICML 2024 · 被引用 3,620 次
相关 Paper
- Closed-Form Concept Erasure via Double ProjectionsChi Zhang, Jingpu Cheng, Zhixian Wang, Ping LiuCVPR 2026 · 被引用 5 次
- DuMo: Dual Encoder Modulation Network for Precise Concept ErasureFeng Han, Kai Chen, Chao Gong, Zhipeng Wei 等AAAI 2025 · 被引用 10 次
- ICE: Intercede Concept Erasure in Text-to-Image Diffusion ModelsYizhou Lin, Nisha Huang, Kaer Huang, Henglin Liu 等ACM MM 2025 · 被引用 1 次
- Erasing Concepts from Diffusion ModelsRohit Gandikota, Joanna Materzynska, Jaden Fiotto-Kaufman, David BauICCV 2023 · 被引用 536 次
- Erasing Undesirable Concepts in Diffusion Models with Adversarial PreservationAnh Bui, Tung-Long Vuong, Khanh Doan, Trung Le 等NeurIPS 2024 · 被引用 55 次
