English
Related papers

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

200 papers

Sparse autoencoders (SAEs) have lately been used to uncover interpretable latent features in large language models. By projecting dense embeddings into a much higher-dimensional and sparse space, learned features become disentangled and…

Machine Learning · Computer Science 2025-07-30 Viktoria Schuster

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

Recent advances in text-to-image diffusion models have demonstrated remarkable generation capabilities, yet they raise significant concerns regarding safety, copyright, and ethical implications. Existing concept erasure methods address…

Computer Vision and Pattern Recognition · Computer Science 2026-04-02 Yi Sun , Xinhao Zhong , Hongyan Li , Yimin Zhou , Junhao Li , Bin Chen , Xuan Wang

Sparse autoencoders (SAEs) have recently emerged as pivotal tools for introspection into large language models. SAEs can uncover high-quality, interpretable features at different levels of granularity and enable targeted steering of the…

Information Retrieval · Computer Science 2026-01-19 Martin Spišák , Ladislav Peška , Petr Škoda , Vojtěch Vančura , Rodrigo Alves

Controlling the behavior of text-to-image generative models is critical for safe and practical deployment. Existing safety approaches typically rely on model fine-tuning or curated datasets, which can degrade generation quality or limit…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Yaoteng Tan , Zikui Cai , M. Salman Asif

Artistic style transfer in generative models remains a significant challenge, as existing methods often introduce style only via model fine-tuning, additional adapters, or prompt engineering, all of which can be computationally expensive…

Computer Vision and Pattern Recognition · Computer Science 2025-12-23 Raina Panda , Daniel Fein , Arpita Singhal , Mark Fiore , Maneesh Agrawala , Matyas Bohacek

Sparse Autoencoders (SAEs) are a promising approach for extracting neural network representations by learning a sparse and overcomplete decomposition of the network's internal activations. However, SAEs are traditionally trained considering…

Machine Learning · Computer Science 2025-04-02 Jeffrey Olmo , Jared Wilson , Max Forsey , Bryce Hepner , Thomas Vin Howe , David Wingate

Concept unlearning in diffusion models is hampered by feature splitting, where concepts are distributed across many latent features, making their removal challenging and computationally expensive. We introduce SAEmnesia, a supervised sparse…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Enrico Cassano , Riccardo Renzulli , Marco Nurisso , Mirko Zaffaroni , Alan Perotti , Marco Grangetto

Sparse autoencoders (SAEs) are a mechanistic interpretability technique that have been used to provide insight into learned concepts within large protein language models. Here, we employ TopK and Ordered SAEs to investigate autoregressive…

The rapid proliferation of large-scale text-to-image diffusion (T2ID) models has raised serious concerns about their potential misuse in generating harmful content. Although numerous methods have been proposed for erasing undesired concepts…

Computer Vision and Pattern Recognition · Computer Science 2025-04-03 Koushik Srivatsan , Fahad Shamshad , Muzammal Naseer , Vishal M. Patel , Karthik Nandakumar

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

Text-to-Image (T2I) models have demonstrated impressive capabilities in generating high-quality and diverse visual content from natural language prompts. However, uncontrolled reproduction of sensitive, copyrighted, or harmful imagery poses…

Computer Vision and Pattern Recognition · Computer Science 2025-05-30 Yiwei Xie , Ping Liu , Zheng Zhang

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

Despite their impressive performance, generative image models trained on large-scale datasets frequently fail to produce images with seemingly simple concepts -- e.g., human hands or objects appearing in groups of four -- that are…

Graphics · Computer Science 2025-06-25 Matyas Bohacek , Thomas Fel , Maneesh Agrawala , Ekdeep Singh Lubana

Linear concept vectors effectively steer LLMs, but existing methods suffer from noisy features in diverse datasets that undermine steering robustness. We propose Sparse Autoencoder-Denoised Concept Vectors (SDCV), which selectively keep the…

Computation and Language · Computer Science 2025-07-31 Haiyan Zhao , Xuansheng Wu , Fan Yang , Bo Shen , Ninghao Liu , Mengnan Du

Generative autoencoders offer a promising approach for controllable text generation by leveraging their latent sentence representations. However, current models struggle to maintain coherent latent spaces required to perform meaningful text…

Machine Learning · Computer Science 2020-07-08 Tianxiao Shen , Jonas Mueller , Regina Barzilay , Tommi Jaakkola

Latent steering exploits internal representations of Large Language Models (LLMs) to guide generation, yet interventions on dense states can entangle distinct semantic features. In this paper, we investigate attention query activations as a…

Machine Learning · Computer Science 2026-05-25 Sumanta Bhattacharyya , Pedram Rooshenas

Sparse Autoencoders (SAEs) can extract interpretable features from large language models (LLMs) without supervision. However, their effectiveness in downstream steering tasks is limited by the requirement for contrastive datasets or large…

Computation and Language · Computer Science 2026-05-05 Seonglae Cho , Zekun Wu , Adriano Koshiyama

Steering vectors are a promising approach to control the behaviour of large language models. However, their underlying mechanisms remain poorly understood. While sparse autoencoders (SAEs) may offer a potential method to interpret steering…

Machine Learning · Computer Science 2024-11-14 Harry Mayne , Yushi Yang , Adam Mahdi

Large-scale text-to-image (T2I) diffusion models have revolutionized image generation, enabling the synthesis of highly detailed visuals from textual descriptions. However, these models may inadvertently generate inappropriate content, such…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Huiqiang Chen , Tianqing Zhu , Linlin Wang , Xin Yu , Longxiang Gao , Wanlei Zhou