English
Related papers

Related papers: SAEmnesia: Erasing Concepts in Diffusion Models wi…

200 papers

Continual learning studies how models can adapt to new tasks while retaining previously acquired knowledge. Although a broad spectrum of methods has been proposed to mitigate catastrophic forgetting, the field remains predominantly…

Machine Learning · Computer Science 2026-05-19 Katarzyna Filus , Kamil Faber , Roberto Corizzo , Christopher Kanan

Sparse autoencoders (SAEs) have become a central tool for interpreting language models. However, two key SAE analyses that remain difficult to scale are (1) matching semantically similar features across multi-layers and (2) compressing…

Machine Learning · Computer Science 2026-05-28 Tue M. Cao , Nguyen Do , My T. Thai

Concept unlearning has emerged as a promising direction for reducing the risks of harmful content generation in text-to-image diffusion models by selectively erasing undesirable concepts from a model's parameters. Existing approaches…

Artificial Intelligence · Computer Science 2026-03-20 Duc Hao Pham , Van Duy Truong , Duy Khanh Dinh , Tien Cuong Nguyen , Dien Hy Ngo , Tuan Anh Bui

Text-to-Image models such as Stable Diffusion have shown impressive image generation synthesis, thanks to the utilization of large-scale datasets. However, these datasets may contain sexually explicit, copyrighted, or undesirable content,…

Computer Vision and Pattern Recognition · Computer Science 2023-12-21 Seunghoo Hong , Juhun Lee , Simon S. Woo

Recently, sparse autoencoders (SAEs) have emerged as a promising technique for interpreting activations in foundation models by disentangling features into a sparse set of concepts. However, identifying the optimal level of sparsity for…

Machine Learning · Computer Science 2026-04-17 Dongsheng Wang , Jinsen Zhang , Dawei Su , Hui Huang

Large Language Models (LLMs) encode factual knowledge within hidden parametric spaces that are difficult to inspect or control. While Sparse Autoencoders (SAEs) can decompose hidden activations into more fine-grained, interpretable…

Machine Learning · Computer Science 2026-01-14 Minglai Yang , Xinyu Guo , Zhengliang Shi , Jinhe Bi , Steven Bethard , Mihai Surdeanu , Liangming Pan

To truly understand vision models, we must not only interpret their learned features but also validate these interpretations through controlled experiments. While earlier work offers either rich semantics or direct control, few post-hoc…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Samuel Stevens , Wei-Lun Chao , Tanya Berger-Wolf , Yu Su

Recent developments in Large Language Model (LLM) capabilities have brought great potential but also posed new risks. For example, LLMs with knowledge of bioweapons, advanced chemistry, or cyberattacks could cause violence if placed in the…

Machine Learning · Computer Science 2025-03-17 Matthew Khoriaty , Andrii Shportko , Gustavo Mercier , Zach Wood-Doughty

Dense embeddings deliver strong retrieval performance but often lack interpretability and controllability. This paper introduces a novel approach using sparse autoencoders (SAE) to interpret and control dense embeddings via the learned…

Information Retrieval · Computer Science 2025-02-25 Hao Kang , Tevin Wang , Chenyan Xiong

As pretrained models are increasingly shared on the web, ensuring that models can forget or delete sensitive, copyrighted, or private information upon request has become crucial. Machine unlearning has been proposed to address this…

Computer Vision and Pattern Recognition · Computer Science 2026-02-24 Yurim Jang , Jaeung Lee , Dohyun Kim , Jaemin Jo , Simon S. Woo

Recent research has seen significant interest in methods for concept removal and targeted forgetting in text-to-image diffusion models. In this paper, we conduct a comprehensive white-box analysis showing the vulnerabilities in existing…

Machine Learning · Computer Science 2024-12-13 Aakash Sen Sharma , Niladri Sarkar , Vikram Chundawat , Ankur A Mali , Murari Mandal

Text-to-image (T2I) diffusion models have achieved remarkable progress in generating high-quality images but also raise people's concerns about generating harmful or misleading content. While extensive approaches have been proposed to erase…

Computer Vision and Pattern Recognition · Computer Science 2025-07-10 Zhihua Tian , Sirun Nan , Ming Xu , Shengfang Zhai , Wenjie Qu , Jian Liu , Ruoxi Jia , Jiaheng Zhang

While personalized text-to-image generation has enabled the learning of a single concept from multiple images, a more practical yet challenging scenario involves learning multiple concepts within a single image. However, existing works…

Computer Vision and Pattern Recognition · Computer Science 2024-07-10 Shaozhe Hao , Kai Han , Zhengyao Lv , Shihao Zhao , Kwan-Yee K. Wong

Analyzing large-scale text corpora is a core challenge in machine learning, crucial for tasks like identifying undesirable model behaviors or biases in training data. Current methods often rely on costly LLM-based techniques (e.g.…

Artificial Intelligence · Computer Science 2025-12-12 Nick Jiang , Xiaoqing Sun , Lisa Dunlap , Lewis Smith , Neel Nanda

The Linear Representation Hypothesis asserts that the embeddings learned by neural networks can be understood as linear combinations of features corresponding to high-level concepts. Based on this ansatz, sparse autoencoders (SAEs) have…

Machine Learning · Computer Science 2026-01-29 Chiraag Kaushik , Davis Barch , Andrea Fanelli

Techniques for concept extraction, such as sparse autoencoders and transcoders, aim to extract high-level symbolic concepts from low-level nonsymbolic representations. When these extracted concepts are used for downstream tasks such as…

Machine Learning · Computer Science 2026-04-29 Chandler Squires , Pradeep Ravikumar

Generating images from text has become easier because of the scaling of diffusion models and advancements in the field of vision and language. These models are trained using vast amounts of data from the Internet. Hence, they often contain…

Computer Vision and Pattern Recognition · Computer Science 2024-08-30 Masane Fuchi , Tomohiro Takagi

We study the challenge of achieving theoretically grounded feature recovery using Sparse Autoencoders (SAEs) for the interpretation of Large Language Models. Existing SAE training algorithms often lack rigorous mathematical guarantees and…

Machine Learning · Computer Science 2025-06-18 Siyu Chen , Heejune Sheen , Xuyuan Xiong , Tianhao Wang , Zhuoran Yang

Existing unlearning algorithms in text-to-image generative models often fail to preserve the knowledge of semantically related concepts when removing specific target concepts: a challenge known as adjacency. To address this, we propose FADE…

Computer Vision and Pattern Recognition · Computer Science 2025-03-26 Kartik Thakral , Tamar Glaser , Tal Hassner , Mayank Vatsa , Richa Singh

For large language models (LLMs), sparse autoencoders (SAEs) have been shown to decompose intermediate representations that often are not interpretable directly into sparse sums of interpretable features, facilitating better control and…