English
Related papers

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

200 papers

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

In complex visual recognition tasks it is typical to adopt multiple descriptors, that describe different aspects of the images, for obtaining an improved recognition performance. Descriptors that have diverse forms can be fused into a…

Computer Vision and Pattern Recognition · Computer Science 2015-06-15 Jayaraman J. Thiagarajan , Karthikeyan Natesan Ramamurthy , Andreas Spanias

Scientific archives now contain hundreds of petabytes of data across genomics, ecology, climate, and molecular biology that could reveal undiscovered patterns if systematically analyzed at scale. Large-scale, weakly-supervised datasets in…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Samuel Stevens , Jacob Beattie , Tanya Berger-Wolf , Yu Su

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

Data acquired from multi-channel sensors is a highly valuable asset to interpret the environment for a variety of remote sensing applications. However, low spatial resolution is a critical limitation for previous sensors and the constituent…

Computer Vision and Pattern Recognition · Computer Science 2018-07-17 Savas Ozkan , Berk Kaya , Gozde Bozdagi Akar

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

Machine Unlearning aims to remove the influence of specific data or concepts from trained models while preserving overall performance, a capability increasingly required by data protection regulations and responsible AI practices. Despite…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Natnael Mola , Leonardo S. B. Pereira , Carolina R. Kelsch , Luis H. Arribas , Juan C. S. M. Avedillo

Despite the impressive capabilities of generating images, text-to-image diffusion models are susceptible to producing undesirable outputs such as NSFW content and copyrighted artworks. To address this issue, recent studies have focused on…

Computer Vision and Pattern Recognition · Computer Science 2024-05-28 Tianyun Yang , Juan Cao , Chang Xu

Text-to-image diffusion models have achieved remarkable progress, yet their use raises copyright and misuse concerns, prompting research into machine unlearning. However, extending multi-concept unlearning to large-scale scenarios remains…

Machine Learning · Computer Science 2026-05-19 Kaiyuan Deng , Gen Li , Yang Xiao , Bo Hui , Xiaolong Ma

A recent line of work has shown promise in using sparse autoencoders (SAEs) to uncover interpretable features in neural network representations. However, the simple linear-nonlinear encoding mechanism in SAEs limits their ability to perform…

Machine Learning · Computer Science 2025-01-31 Charles O'Neill , Alim Gumran , David Klindt

Previous studies primarily utilize MLP neurons as units of analysis for understanding the mechanisms of factual knowledge in Language Models (LMs); however, neurons suffer from polysemanticity, leading to limited knowledge expression and…

Computation and Language · Computer Science 2025-02-28 Yuheng Chen , Pengfei Cao , Kang Liu , Jun Zhao

Ensuring that neural models used in real-world applications cannot infer sensitive information, such as demographic attributes like gender or race, from text representations is a critical challenge when fairness is a concern. We address…

Machine Learning · Computer Science 2025-08-19 Antoine Saillenfest , Pirmin Lemberger

Data unlearning aims to remove the influence of specific training samples from a trained model without requiring full retraining. Unlike concept unlearning, data unlearning in diffusion models remains underexplored and often suffers from…

Machine Learning · Computer Science 2025-10-22 Jinseong Park , Mijung Park

Unsupervised approaches to large language model (LLM) interpretability, such as sparse autoencoders (SAEs), offer a way to decode LLM activations into interpretable and, ideally, controllable concepts. On the one hand, these approaches…

Machine Learning · Computer Science 2026-03-03 Shruti Joshi , Andrea Dittadi , Sébastien Lachapelle , Dhanya Sridhar

Sparse Autoencoders (SAEs) have proven to be powerful tools for interpreting neural networks by decomposing hidden representations into disentangled, interpretable features via sparsity constraints. However, conventional SAEs are…

Sparse autoencoders (SAEs) extract millions of interpretable features from a language model, but flat feature inventories aren't very useful on their own. Domain concepts get mixed with generic and weakly grounded features, while related…

Artificial Intelligence · Computer Science 2026-04-29 John Winnicki , Abeynaya Gnanasekaran , Eric Darve

Understanding and mitigating the potential risks associated with foundation models (FMs) hinges on developing effective interpretability methods. Sparse Autoencoders (SAEs) have emerged as a promising tool for disentangling FM…

Machine Learning · Computer Science 2024-11-04 Aashiq Muhamed , Mona Diab , Virginia Smith

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

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

Concept unlearning aims to erase a target concept from a pretrained text-to-image diffusion model without retraining. Closed-form methods are attractive in this setting because they apply a single deterministic edit to the cross-attention…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Saemi Moon , Suhyeon Jun , Seoyeon Lee , Dongwoo Kim