English
Related papers

Related papers: Concept Steerers: Leveraging K-Sparse Autoencoders…

200 papers

Concept erasure in text-to-image diffusion models is crucial for mitigating harmful content, yet existing methods often compromise generative quality. We introduce Semantic Surgery, a novel training-free, zero-shot framework for concept…

Computer Vision and Pattern Recognition · Computer Science 2025-10-28 Lexiang Xiong , Chengyu Liu , Jingwen Ye , Yan Liu , Yuecong Xu

Many current state-of-the-art models for sequential recommendations are based on transformer architectures. Interpretation and explanation of such black box models is an important research question, as a better understanding of their…

Information Retrieval · Computer Science 2026-02-18 Anton Klenitskiy , Konstantin Polev , Daria Denisova , Alexey Vasilev , Dmitry Simakov , Gleb Gusev

In this paper we propose a new generative model of text, Step-unrolled Denoising Autoencoder (SUNDAE), that does not rely on autoregressive models. Similarly to denoising diffusion techniques, SUNDAE is repeatedly applied on a sequence of…

Computation and Language · Computer Science 2022-04-20 Nikolay Savinov , Junyoung Chung , Mikolaj Binkowski , Erich Elsen , Aaron van den Oord

We present Universal Sparse Autoencoders (USAEs), a framework for uncovering and aligning interpretable concepts spanning multiple pretrained deep neural networks. Unlike existing concept-based interpretability methods, which focus on a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Harrish Thasarathan , Julian Forsyth , Thomas Fel , Matthew Kowal , Konstantinos G. Derpanis

Large-scale text-to-image (T2I) diffusion models deliver remarkable visual fidelity but pose safety risks due to their capacity to reproduce undesirable content, such as copyrighted ones. Concept erasure has emerged as a mitigation…

Computer Vision and Pattern Recognition · Computer Science 2026-04-21 Hoigi Seo , Byung Hyun Lee , Jaehyun Cho , Sungjin Lim , Se Young Chun

Concept erasing has recently emerged as an effective paradigm to prevent text-to-image diffusion models from generating visually undesirable or even harmful content. However, current removal methods heavily rely on manually crafted text…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Feiran Li , Qianqian Xu , Shilong Bao , Zhiyong Yang , Xiaochun Cao , Qingming Huang

EEG foundation models achieve state-of-the-art clinical performance, yet the internal computations driving their predictions remain opaque: a barrier to clinical trust. We apply TopK Sparse Autoencoders (SAEs) across three architecturally…

Recent studies show that auto-encoder based approaches successfully perform language generation, smooth sentence interpolation, and style transfer over unseen attributes using unlabelled datasets in a zero-shot manner. The latent space…

Computation and Language · Computer Science 2022-05-06 Sharan Narasimhan , Suvodip Dey , Maunendra Sankar Desarkar

As large language models (LLMs) grow in scale and capability, understanding their internal mechanisms becomes increasingly critical. Sparse autoencoders (SAEs) have emerged as a key tool in mechanistic interpretability, enabling the…

Computation and Language · Computer Science 2025-06-10 Jiaming Li , Haoran Ye , Yukun Chen , Xinyue Li , Lei Zhang , Hamid Alinejad-Rokny , Jimmy Chih-Hsien Peng , Min Yang

While large-scale text-to-image diffusion models have demonstrated impressive image-generation capabilities, there are significant concerns about their potential misuse for generating unsafe content, violating copyright, and perpetuating…

Computer Vision and Pattern Recognition · Computer Science 2024-05-30 Ruchika Chavhan , Da Li , Timothy Hospedales

The growing use of generative models in daily life calls for efficient mechanisms to control their generation, to e.g., produce safe content or provide users with tools to explore style changes. Ideally, such mechanisms should require low…

Computation and Language · Computer Science 2025-10-20 Pau Rodriguez , Michal Klein , Eleonora Gualdoni , Valentino Maiorca , Arno Blaas , Luca Zappella , Marco Cuturi , Xavier Suau

Sparse auto-encoders (SAEs) have re-emerged as a prominent method for mechanistic interpretability, yet they face two significant challenges: the non-smoothness of the $L_1$ penalty, which hinders reconstruction and scalability, and a lack…

Artificial Intelligence · Computer Science 2026-05-19 Ouns El Harzli , Hugo Wallner , Yoonsoo Nam , Haixuan Xavier Tao

Adapting foundation models for specific purposes has become a standard approach to build machine learning systems for downstream applications. Yet, it is an open question which mechanisms take place during adaptation. Here we develop a new…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Hyesu Lim , Jinho Choi , Jaegul Choo , Steffen Schneider

Text-to-image models exhibit remarkable capabilities in image generation. However, they also pose safety risks of generating harmful content. A key challenge of existing concept erasure methods is the precise removal of target concepts…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Qinqin He , Jiaqi Weng , Jialing Tao , Hui Xue

Recent advancements in text-to-image diffusion models have brought them to the public spotlight, becoming widely accessible and embraced by everyday users. However, these models have been shown to generate harmful content such as…

Computer Vision and Pattern Recognition · Computer Science 2025-03-18 Anubhav Jain , Yuya Kobayashi , Takashi Shibuya , Yuhta Takida , Nasir Memon , Julian Togelius , Yuki Mitsufuji

Internal activations of diffusion models encode rich semantic information, but interpreting such representations remains challenging. While Sparse Autoencoders (SAEs) have shown promise in disentangling latent representations, existing…

Machine Learning · Computer Science 2026-01-23 Zhenghao He , Guangzhi Xiong , Boyang Wang , Sanchit Sinha , Aidong Zhang

Concept erasure aims to selectively unlearning undesirable content in diffusion models (DMs) to reduce the risk of sensitive content generation. As a novel paradigm in concept erasure, most existing methods employ adversarial training to…

Computer Vision and Pattern Recognition · Computer Science 2025-11-11 Qinghong Yin , Yu Tian , Heming Yang , Xiang Chen , Xianlin Zhang , Xueming Li , Yue Zhan

Text-to-image diffusion models have revolutionized generative AI, but their vulnerability to backdoor attacks poses significant security risks. Adversaries can inject imperceptible textual triggers into training data, causing models to…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Ashwath Vaithinathan Aravindan , Abha Jha , Matthew Salaway , Atharva Sandeep Bhide , Duygu Nur Yaldiz

There is growing interest in leveraging mechanistic interpretability and controllability to better understand and influence the internal dynamics of large language models (LLMs). However, current methods face fundamental challenges in…

Computation and Language · Computer Science 2025-12-02 Ruben Härle , Felix Friedrich , Manuel Brack , Stephan Wäldchen , Björn Deiseroth , Patrick Schramowski , Kristian Kersting

Deep generative models, while revolutionizing fields like image and text generation, largely operate as opaque ``black boxes'', hindering human understanding, control, and alignment. While methods like sparse autoencoders (SAEs) show…

Machine Learning · Computer Science 2026-04-03 Lingjing Kong , Shaoan Xie , Guangyi Chen , Yuewen Sun , Xiangchen Song , Eric P. Xing , Kun Zhang