English
Related papers

Related papers: GeoSAE: Geometric Prior-Guided Layer-Wise Sparse A…

200 papers

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 human-interpretable features from deep neural networks by transforming their activations into a sparse, higher dimensional latent space, and then reconstructing the activations from these latents.…

Machine Learning · Computer Science 2025-02-13 Gonçalo Paulo , Stepan Shabalin , Nora Belrose

Learning a robust Variational Autoencoder (VAE) is a fundamental step for many deep learning applications in medical image analysis, such as MRI synthesizes. Existing brain VAEs predominantly focus on single-modality data (i.e., T1-weighted…

Computer Vision and Pattern Recognition · Computer Science 2026-04-08 Mingjie Li , Edward Kim , Yue Zhao , Ehsan Adeli , Kilian M. Pohl

While the activations of neurons in deep neural networks usually do not have a simple human-understandable interpretation, sparse autoencoders (SAEs) can be used to transform these activations into a higher-dimensional latent space which…

Machine Learning · Computer Science 2025-08-07 Gonçalo Paulo , Alex Mallen , Caden Juang , Nora Belrose

Electroencephalography (EEG) and Magnetoencephalography (MEG) are pivotal in understanding brain activity but are limited by their poor spatial resolution. EEG/MEG source imaging (ESI) infers the high-resolution electric field distribution…

Signal Processing · Electrical Eng. & Systems 2024-02-01 Song Wang , Chen Wei , Kexin Lou , Dongfeng Gu , Quanying Liu

Autoencoders have emerged as powerful models for visualization and dimensionality reduction based on the fundamental assumption that high-dimensional data is generated from a low-dimensional manifold. A critical challenge in autoencoder…

Machine Learning · Computer Science 2025-09-30 Qipeng Zhan , Zhuoping Zhou , Zexuan Wang , Li Shen

Sparse autoencoders (SAEs) are useful for detecting and steering interpretable features in neural networks, with particular potential for understanding complex multimodal representations. Given their ability to uncover interpretable…

Computer Vision and Pattern Recognition · Computer Science 2025-05-29 Vladimir Zaigrajew , Hubert Baniecki , Przemyslaw Biecek

We investigate whether sparse autoencoders (SAEs) can be used to remove knowledge from language models. We use the biology subset of the Weapons of Mass Destruction Proxy dataset and test on the gemma-2b-it and gemma-2-2b-it language…

Machine Learning · Computer Science 2024-11-05 Eoin Farrell , Yeu-Tong Lau , Arthur Conmy

With the increasing incidence of neurodegenerative diseases such as Alzheimer's Disease (AD), there is a need for further research that enhances detection and monitoring of the diseases. We present MORPHADE (Morphological Autoencoders for…

Image and Video Processing · Electrical Eng. & Systems 2024-07-08 Mehmet Yigit Avci , Emily Chan , Veronika Zimmer , Daniel Rueckert , Benedikt Wiestler , Julia A. Schnabel , Cosmin I. Bercea

We introduce sparse autoencoder neural operators (SAE-NOs), a new class of sparse autoencoders that operate in function spaces rather than fixed-dimensional Euclidean representations. We formalize the functional representation hypothesis,…

Machine Learning · Computer Science 2026-05-11 Bahareh Tolooshams , Ailsa Shen , Anima Anandkumar

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) aim to decompose the activation space of large language models (LLMs) into human-interpretable latent directions or features. As we increase the number of features in the SAE, hierarchical features tend to split…

Computation and Language · Computer Science 2025-11-18 David Chanin , James Wilken-Smith , Tomáš Dulka , Hardik Bhatnagar , Satvik Golechha , Joseph Bloom

Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting large language models (LLMs) by decomposing token activations into combinations of human-understandable features. While SAEs provide crucial insights into LLM…

Machine Learning · Computer Science 2025-11-11 Zhen Xu , Zhen Tan , Song Wang , Kaidi Xu , Tianlong Chen

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

LLMs increasingly require surgical model editing to enhance domain-specific capabilities without incurring the computational cost or catastrophic forgetting associated with full fine-tuning. Sparse Autoencoders (SAEs) have emerged as a…

Machine Learning · Computer Science 2026-05-28 Li Lei , Madalina Ciobanu , Qingqing Mao , Ritankar Das

Object counting typically uses 2D point annotations. The complexity of object shapes and the subjectivity of annotators may lead to annotation inconsistency, potentially confusing counting model training. Some sophisticated noise-resistance…

Computer Vision and Pattern Recognition · Computer Science 2024-03-15 Yuda Zou , Xin Xiao , Peilin Zhou , Zhichao Sun , Bo Du , Yongchao Xu

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

Sparse autoencoders (SAEs) have emerged as a powerful technique for decomposing language model representations into interpretable features. Current interpretation methods infer feature semantics from activation patterns, but overlook that…

Machine Learning · Computer Science 2026-02-02 Yiting Liu , Zhi-Hong Deng

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

Early and accessible detection of Alzheimer's disease (AD) remains a critical clinical challenge, and cube-copying tasks offer a simple yet informative assessment of visuospatial function. This work proposes a multimodal framework that…

Machine Learning · Computer Science 2025-12-19 Jaeho Yang , Kijung Yoon
‹ Prev 1 4 5 6 7 8 10 Next ›