English
Related papers

Related papers: Minimalist Concept Erasure in Generative Models

200 papers

Diffusion models that are based on iterative denoising have been recently proposed and leveraged in various generation tasks like image generation. Whereas, as a way inherently built for continuous data, existing diffusion models still have…

Computation and Language · Computer Science 2023-04-11 Jiaao Chen , Aston Zhang , Mu Li , Alex Smola , Diyi Yang

Concept erasure techniques for text-to-video (T2V) diffusion models report substantial suppression of sensitive content, yet current evaluation is limited to checking whether the target concept is absent from generated frames, treating…

Computer Vision and Pattern Recognition · Computer Science 2026-03-24 Yiwei Xie , Zheng Zhang , Ping Liu

Machine unlearning has emerged as a new paradigm to deliberately forget data samples from a given model in order to adhere to stringent regulations. However, existing machine unlearning methods have been primarily focused on classification…

Machine Learning · Computer Science 2024-02-05 Guihong Li , Hsiang Hsu , Chun-Fu Chen , Radu Marculescu

Two-dimensional array-based datasets are pervasive in a variety of domains. Current approaches for generative modeling have typically been limited to conventional image datasets and performed in the pixel domain which do not explicitly…

Machine Learning · Computer Science 2021-07-12 Hoda Shajari , Jaemoon Lee , Sanjay Ranka , Anand Rangarajan

Many generative models have to combat $\textit{missing modes}$. The conventional wisdom to this end is by reducing through training a statistical distance (such as $f$-divergence) between the generated distribution and provided data…

Machine Learning · Statistics 2019-10-28 Peilin Zhong , Yuchen Mo , Chang Xiao , Pengyu Chen , Changxi Zheng

Large-scale text-to-image diffusion models can generate high-fidelity images with powerful compositional ability. However, these models are typically trained on an enormous amount of Internet data, often containing copyrighted material,…

Computer Vision and Pattern Recognition · Computer Science 2023-08-17 Nupur Kumari , Bingliang Zhang , Sheng-Yu Wang , Eli Shechtman , Richard Zhang , Jun-Yan Zhu

Recent advancements in multi-modal large language models have propelled the development of joint probabilistic models capable of both image understanding and generation. However, we have identified that recent methods suffer from loss of…

Computer Vision and Pattern Recognition · Computer Science 2025-06-05 Jian Yang , Dacheng Yin , Yizhou Zhou , Fengyun Rao , Wei Zhai , Yang Cao , Zheng-Jun Zha

Recent advances in text-to-video (T2V) diffusion models have significantly enhanced the quality of generated videos. However, their capability to produce explicit or harmful content introduces new challenges related to misuse and potential…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Xiaoyu Ye , Songjie Cheng , Yongtao Wang , Yajiao Xiong , Yishen Li

Text-to-image generative models have achieved impressive fidelity and diversity, but can inadvertently produce unsafe or undesirable content due to implicit biases embedded in large-scale training datasets. Existing concept erasure methods,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-20 Jun Li , Lizhi Xiong , Ziqiang Li , Weiwei Jiang , Zhangjie Fu , Yong Li , Guo-Sen Xie

Fine-tuning based concept erasing has demonstrated promising results in preventing generation of harmful contents from text-to-image diffusion models by removing target concepts while preserving remaining concepts. To maintain the…

Computer Vision and Pattern Recognition · Computer Science 2025-07-11 Byung Hyun Lee , Sungjin Lim , Se Young Chun

Concept erasure in Text-To-Image (T2I) diffusion models is vital for safe content generation, but existing inference-time methods face significant limitations. Feature-correction approaches often cause uncontrolled over-correction, while…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Qinghui Gong

Despite their remarkable image generation capabilities, text-to-image diffusion models inadvertently learn inappropriate concepts from vast and unfiltered training data, which leads to various ethical and business risks. Specifically,…

Computer Vision and Pattern Recognition · Computer Science 2025-02-18 Die Chen , Zhiwen Li , Mingyuan Fan , Cen Chen , Wenmeng Zhou , Yanhao Wang , Yaliang Li

Steering intermediate representations has emerged as a powerful strategy for controlling generative models, particularly in post-deployment alignment and safety settings. However, despite its empirical success, it currently lacks a…

Machine Learning · Computer Science 2026-05-08 Tatiana Gaintseva , Andrew Stepanov , Ziquan Liu , Martin Benning , Gregory Slabaugh , Jiankang Deng , Ismail Elezi

The representation space of neural models for textual data emerges in an unsupervised manner during training. Understanding how those representations encode human-interpretable concepts is a fundamental problem. One prominent approach for…

Machine Learning · Computer Science 2024-09-17 Shauli Ravfogel , Francisco Vargas , Yoav Goldberg , Ryan Cotterell

Most real-world image editing tasks require multiple sequential edits to achieve desired results. Current editing approaches, primarily designed for single-object modifications, struggle with sequential editing: especially with maintaining…

Computer Vision and Pattern Recognition · Computer Science 2025-05-05 Daneul Kim , Jaeah Lee , Jaesik Park

Advances in model editing through neuron pruning hold promise for removing undesirable concepts from large language models. However, it remains unclear whether models have the capacity to reacquire pruned concepts after editing. To…

Artificial Intelligence · Computer Science 2024-01-04 Michelle Lo , Shay B. Cohen , Fazl Barez

Generative models have been widely studied in computer vision. Recently, diffusion models have drawn substantial attention due to the high quality of their generated images. A key desired property of image generative models is the ability…

Computer Vision and Pattern Recognition · Computer Science 2022-12-20 Qiucheng Wu , Yujian Liu , Handong Zhao , Ajinkya Kale , Trung Bui , Tong Yu , Zhe Lin , Yang Zhang , Shiyu Chang

Concept erasure aims to suppress sensitive content in diffusion models, but recent studies show that erased concepts can still be reawakened, revealing vulnerabilities in erasure methods. Existing reawakening methods mainly rely on…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Mengyu Sun , Ziyuan Yang , Andrew Beng Jin Teoh , Junxu Liu , Haibo Hu , Yi Zhang

Text guided diffusion models are used by millions of users, but can be easily exploited to produce harmful content. Concept unlearning methods aim at reducing the models' likelihood of generating harmful content. Traditionally, this has…

Artificial Intelligence · Computer Science 2026-02-10 Mansi , Avinash Kori , Francesca Toni , Soteris Demetriou

Recent advances in text-to-image diffusion models enable photorealistic image generation, but they also risk producing malicious content, such as NSFW images. To mitigate risk, concept erasure methods are studied to facilitate the model to…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Ruidong Chen , Honglin Guo , Lanjun Wang , Chenyu Zhang , Weizhi Nie , An-An Liu
‹ Prev 1 4 5 6 7 8 10 Next ›