English
Related papers

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

200 papers

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

Recent advances in generative models have demonstrated remarkable capabilities in producing high-quality images, but their reliance on large-scale unlabeled data has raised significant safety and copyright concerns. Efforts to address these…

Computer Vision and Pattern Recognition · Computer Science 2025-07-21 Yang Zhang , Er Jin , Yanfei Dong , Yixuan Wu , Philip Torr , Ashkan Khakzar , Johannes Stegmaier , Kenji Kawaguchi

Understanding how different AI models encode the same high-level concepts, such as objects or attributes, remains challenging because each model typically produces its own isolated representation. Existing interpretability methods like…

Computer Vision and Pattern Recognition · Computer Science 2026-03-09 Ali Nasiri-Sarvi , Hassan Rivaz , Mahdi S. Hosseini

In generative modeling, numerous successful approaches leverage a low-dimensional latent space, e.g., Stable Diffusion models the latent space induced by an encoder and generates images through a paired decoder. Although the selection of…

Machine Learning · Computer Science 2023-10-31 Tianyang Hu , Fei Chen , Haonan Wang , Jiawei Li , Wenjia Wang , Jiacheng Sun , Zhenguo Li

Deterministically controlling the target generation language of large multilingual language models (LLMs) remains a fundamental challenge, particularly in zero-shot settings where neither explicit language prompts nor fine-tuning are…

Computation and Language · Computer Science 2025-10-17 Cheng-Ting Chou , George Liu , Jessica Sun , Cole Blondin , Kevin Zhu , Vasu Sharma , Sean O'Brien

As large language models (LLMs) are increasingly deployed in real-world applications, the need to selectively remove unwanted knowledge while preserving model utility has become paramount. Recent work has explored sparse autoencoders (SAEs)…

Computation and Language · Computer Science 2026-04-28 Tomer Ashuach , Dana Arad , Aaron Mueller , Martin Tutek , Yonatan Belinkov

As powerful generative models, text-to-image diffusion models have recently been explored for discriminative tasks. A line of research focuses on adapting a pre-trained diffusion model to semantic segmentation without any further training,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-30 Benyuan Meng , Qianqian Xu , Zitai Wang , Xiaochun Cao , Longtao Huang , Qingming Huang

Sparse autoencoders (SAEs) have recently become central tools for interpretability, leveraging dictionary learning principles to extract sparse, interpretable features from neural representations whose underlying structure is typically…

Machine Learning · Computer Science 2025-11-05 Valérie Costa , Thomas Fel , Ekdeep Singh Lubana , Bahareh Tolooshams , Demba Ba

Activation-based steering provides control of LLM behavior at inference time, but the dominant paradigm reduces each concept to a single direction whose geometry is left largely unexamined. Rather than selecting a single steering direction,…

Diffusion models (DMs) are widely used for text-to-image generation, but their strong generative capabilities also raise concerns about unsafe or undesirable content. Concept erasure aims to mitigate these risks by removing specific…

Artificial Intelligence · Computer Science 2026-05-19 Mengyu Sun , Ziyuan Yang , Zunlong Zhou , Junxu Liu , Haibo Hu , Yi Zhang

Recent text-to-image models have achieved impressive results in generating high-quality images. However, when tasked with multi-concept generation creating images that contain multiple characters or objects, existing methods often suffer…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Yang Zhang , Rui Zhang , Xuecheng Nie , Haochen Li , Jikun Chen , Yifan Hao , Xin Zhang , Luoqi Liu , Ling Li

Text-to-image diffusion models have been demonstrated with undesired generation due to unfiltered large-scale training data, such as sexual images and copyrights, necessitating the erasure of undesired concepts. Most existing methods focus…

Computer Vision and Pattern Recognition · Computer Science 2025-08-21 Zheling Meng , Bo Peng , Xiaochuan Jin , Yue Jiang , Wei Wang , Jing Dong , Tieniu Tan

Recent work on sparse autoencoders (SAEs) has shown promise in extracting interpretable features from neural networks and addressing challenges with polysemantic neurons caused by superposition. In this paper, we apply SAEs to the early…

Machine Learning · Computer Science 2024-09-10 Liv Gorton

Autoencoders empower state-of-the-art image and video generative models by compressing pixels into a latent space through visual tokenization. Although recent advances have alleviated the performance degradation of autoencoders under high…

Computer Vision and Pattern Recognition · Computer Science 2026-01-14 Dongxu Liu , Jiahui Zhu , Yuang Peng , Haomiao Tang , Yuwei Chen , Chunrui Han , Zheng Ge , Daxin Jiang , Mingxue Liao

Sparse autoencoders (SAEs) are commonly used to interpret the internal activations of large language models (LLMs) by mapping them to human-interpretable concept representations. While existing evaluations of SAEs focus on metrics such as…

Machine Learning · Computer Science 2026-01-26 Aaron J. Li , Suraj Srinivas , Usha Bhalla , Himabindu Lakkaraju

Prior work on controllable text generation has focused on learning how to control language models through trainable decoding, smart-prompt design, or fine-tuning based on a desired objective. We hypothesize that the information needed to…

Computation and Language · Computer Science 2022-05-12 Nishant Subramani , Nivedita Suresh , Matthew E. Peters

Text-to-image diffusion models generate images through an iterative denoising process, so internal neural layers produce trajectories of activations rather than single static representations. Sparse autoencoders (SAEs) have recently been…

Computer Vision and Pattern Recognition · Computer Science 2026-05-28 Calvin Yeung , Prathyush Poduval , Ali Zakeri , Zhuowen Zou , Mohsen Imani

Precise control over language model generation is vital for ensuring both safety and reliability. Although prompt engineering and steering are commonly used to intervene in model behaviors, the vast number of parameters in models often…

Computation and Language · Computer Science 2025-06-04 Mengru Wang , Ziwen Xu , Shengyu Mao , Shumin Deng , Zhaopeng Tu , Huajun Chen , Ningyu Zhang

Prediction without justification has limited utility. Much of the success of neural models can be attributed to their ability to learn rich, dense and expressive representations. While these representations capture the underlying complexity…

Computation and Language · Computer Science 2017-11-27 Anant Subramanian , Danish Pruthi , Harsh Jhamtani , Taylor Berg-Kirkpatrick , Eduard Hovy

Recurrent models for sequences have been recently successful at many tasks, especially for language modeling and machine translation. Nevertheless, it remains challenging to extract good representations from these models. For instance, even…

Machine Learning · Computer Science 2018-01-31 Łukasz Kaiser , Samy Bengio