English
Related papers

Related papers: Sparse Autoencoders, Again?

200 papers

Variational autoencoder (VAE) is one of the most common techniques in the field of medical image generation, where this architecture has shown advanced researchers in recent years and has developed into various architectures. VAE has…

Machine Learning · Computer Science 2024-11-13 Khadija Rais , Mohamed Amroune , Abdelmadjid Benmachiche , Mohamed Yassine Haouam

We develop Riemannian approaches to variational autoencoders (VAEs) for PDE-type ambient data with regularizing geometric latent dynamics, which we refer to as VAE-DLM, or VAEs with dynamical latent manifolds. We redevelop the VAE framework…

Machine Learning · Computer Science 2026-01-21 Andrew Gracyk

Large-scale text-to-image diffusion models have become the backbone of modern image editing, yet text prompts alone do not offer adequate control over the editing process. Two properties are especially desirable: disentanglement, where…

Graphics · Computer Science 2025-10-07 Ronen Kamenetsky , Sara Dorfman , Daniel Garibi , Roni Paiss , Or Patashnik , Daniel Cohen-Or

Variational Auto-encoders (VAEs) have been very successful as methods for forming compressed latent representations of complex, often high-dimensional, data. In this paper, we derive an alternative variational lower bound from the one…

Machine Learning · Computer Science 2019-03-20 Shuyu Lin , Ronald Clark , Robert Birke , Niki Trigoni , Stephen Roberts

Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning. However, their reasoning patterns remain too complicated to analyze. While Sparse Autoencoders (SAEs) have emerged as…

Machine Learning · Computer Science 2026-03-04 Xuan Yang , Jiayu Liu , Yuhang Lai , Hao Xu , Zhenya Huang , Ning Miao

Sparse Autoencoders (SAEs) have emerged as a useful tool for interpreting the internal representations of neural networks. However, naively optimising SAEs for reconstruction loss and sparsity results in a preference for SAEs that are…

Machine Learning · Computer Science 2024-10-16 Kola Ayonrinde , Michael T. Pearce , Lee Sharkey

We propose a novel variational autoencoder (VAE) architecture that employs a spherical Cauchy (spCauchy) latent distribution. Unlike traditional Gaussian latent spaces or the widely used von Mises-Fisher (vMF) distribution, spCauchy…

Machine Learning · Statistics 2025-07-15 Lukas Sablica , Kurt Hornik

The variational autoencoder (VAE) is a popular deep latent variable model used to analyse high-dimensional datasets by learning a low-dimensional latent representation of the data. It simultaneously learns a generative model and an…

Machine Learning · Computer Science 2023-11-21 Mine Öğretir , Siddharth Ramchandran , Dimitrios Papatheodorou , Harri Lähdesmäki

Sparse autoencoders (SAEs) emerged as a promising tool for mechanistic interpretability of transformer-based foundation models. Very recently, SAEs were also adopted for the visual domain, enabling the discovery of visual concepts and their…

Computer Vision and Pattern Recognition · Computer Science 2025-07-17 Muhammed Furkan Dasdelen , Hyesu Lim , Michele Buck , Katharina S. Götze , Carsten Marr , Steffen Schneider

Deep latent variable models, trained using variational autoencoders or generative adversarial networks, are now a key technique for representation learning of continuous structures. However, applying similar methods to discrete structures,…

Machine Learning · Computer Science 2018-07-02 Jake Zhao , Yoon Kim , Kelly Zhang , Alexander M. Rush , Yann LeCun

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

For large language models (LLMs), sparse autoencoders (SAEs) have been shown to decompose intermediate representations that often are not interpretable directly into sparse sums of interpretable features, facilitating better control and…

Sparse autoencoders (SAEs) interpret neural network representations by decomposing activations into sparse combinations of dictionary atoms. However, SAEs assume features combine additively through linear reconstruction, an assumption that…

Machine Learning · Computer Science 2026-05-26 Panagiotis Koromilas , Andreas D. Demou , James Oldfield , Yannis Panagakis , Mihalis Nicolaou

Sparse autoencoders are a standard tool for uncovering interpretable latent representations in neural networks. Yet, their interpretation depends on the inputs, making their isolated study incomplete. Polynomials offer a solution; they…

Machine Learning · Computer Science 2025-10-21 Thomas Dooms , Ward Gauderis

Sparse autoencoders (SAEs) are used to decompose neural network activations into sparsely activating features, but many SAE features are only interpretable at high activation strengths. To address this issue we propose to use binary sparse…

Machine Learning · Computer Science 2025-10-01 Lucia Quirke , Stepan Shabalin , Nora Belrose

Detectors in next-generation high-energy physics experiments face several daunting requirements, such as high data rates, damaging radiation exposure, and stringent constraints on power, space, and latency. To address these challenges,…

Data Analysis, Statistics and Probability · Physics 2025-08-18 Alexander Yue , Haoyi Jia , Julia Gonski

Modern LLMs face inference efficiency challenges due to their scale. To address this, many compression methods have been proposed, such as pruning and quantization. However, the effect of compression on a model's interpretability remains…

Machine Learning · Computer Science 2025-07-23 Suchit Gupte , Vishnu Kabir Chhabra , Mohammad Mahdi Khalili

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

This paper presents a novel convolutional neural network (CNN) based image compression framework via scalable auto-encoder (SAE). Specifically, our SAE based deep image codec consists of hierarchical coding layers, each of which is an…

Multimedia · Computer Science 2019-04-02 Chuanmin Jia , Zhaoyi Liu , Yao Wang , Siwei Ma , Wen Gao

Sparse Autoencoder (SAE) has emerged as a powerful tool for mechanistic interpretability of large language models. Recent works apply SAE to protein language models (PLMs), aiming to extract and analyze biologically meaningful features from…

Quantitative Methods · Quantitative Biology 2026-01-21 Xiangyu Liu , Haodi Lei , Yi Liu , Yang Liu , Wei Hu