English
Related papers

Related papers: Sparse, Geometric Autoencoder Models of V1

200 papers

Sparse autoencoders (SAEs) have emerged as a promising approach in language model interpretability, offering unsupervised extraction of sparse features. For interpretability methods to succeed, they must identify abstract features across…

Machine Learning · Computer Science 2025-09-08 Lovis Heindrich , Philip Torr , Fazl Barez , Veronika Thost

Despite their strong performance, Dense Passage Retrieval (DPR) models suffer from a lack of interpretability. In this work, we propose a novel interpretability framework that leverages Sparse Autoencoders (SAEs) to decompose previously…

Information Retrieval · Computer Science 2025-08-28 Seongwan Park , Taeklim Kim , Youngjoong Ko

Structuring the latent space in probabilistic deep generative models, e.g., variational autoencoders (VAEs), is important to yield more expressive models and interpretable representations, and to avoid overfitting. One way to achieve this…

Machine Learning · Computer Science 2022-06-20 Mostafa Sadeghi , Paul Magron

While artificial neural networks excel in unsupervised learning of non-sparse structure, classical statistical regression techniques offer better interpretability, in particular when sparseness is enforced by $\ell_1$ regularization,…

Dense embeddings deliver strong retrieval performance but often lack interpretability and controllability. This paper introduces a novel approach using sparse autoencoders (SAE) to interpret and control dense embeddings via the learned…

Information Retrieval · Computer Science 2025-02-25 Hao Kang , Tevin Wang , Chenyan Xiong

This work presents an approach for image reconstruction in clinical low-dose tomography that combines principles from sparse signal processing with ideas from deep learning. First, we describe sparse signal representation in terms of…

Machine Learning · Statistics 2023-11-27 Jevgenija Rudzusika , Thomas Koehler , Ozan Öktem

Vision-language models encode images and text in a joint space, minimizing the distance between corresponding image and text pairs. How are language and images organized in this joint space, and how do the models encode meaning and…

Computer Vision and Pattern Recognition · Computer Science 2025-08-25 Isabel Papadimitriou , Huangyuan Su , Thomas Fel , Sham Kakade , Stephanie Gil

Sparse dictionary coding represents signals as linear combinations of a few dictionary atoms. It has been applied to images, time series, graph signals and multi-way spatio-temporal data by jointly employing temporal and spatial…

Machine Learning · Computer Science 2025-09-15 Boya Ma , Abram Magner , Maxwell McNeil , Petko Bogdanov

Sparse coding (SC) is an unsupervised learning scheme that has received an increasing amount of interests in recent years. However, conventional SC vectorizes the input images, which destructs the intrinsic spatial structures of the images.…

Computer Vision and Pattern Recognition · Computer Science 2017-03-29 Fei Jiang , Xiao-Yang Liu , Hongtao Lu , Ruimin Shen

Recent work has found that sparse autoencoders (SAEs) are an effective technique for unsupervised discovery of interpretable features in language models' (LMs) activations, by finding sparse, linear reconstructions of LM activations. We…

Machine Learning · Computer Science 2024-05-01 Senthooran Rajamanoharan , Arthur Conmy , Lewis Smith , Tom Lieberum , Vikrant Varma , János Kramár , Rohin Shah , Neel Nanda

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

Sparse linear models are one of several core tools for interpretable machine learning, a field of emerging importance as predictive models permeate decision-making in many domains. Unfortunately, sparse linear models are far less flexible…

Machine Learning · Statistics 2024-01-03 Ryan Thompson , Amir Dezfouli , Robert Kohn

Sparse autoencoders (SAEs) have emerged as a powerful technique for extracting human-interpretable features from neural networks activations. Previous works compared different models based on SAE-derived features but those comparisons have…

Computer Vision and Pattern Recognition · Computer Science 2025-07-25 Clément Cornet , Romaric Besançon , Hervé Le Borgne

Vision-language models learn powerful multimodal embeddings, yet their internal semantics remain opaque. While sparse autoencoders (SAEs) can extract interpretable features, they rely on expanding the representation dimension, which…

Computer Vision and Pattern Recognition · Computer Science 2026-05-22 Piotr Kubaty , Patryk Marszałek , Łukasz Struski , Adam Wróbel , Jacek Tabor , Marek Śmieja

We propose a framework for learned image and video compression using the generative sparse visual representation (SVR) guided by fidelity-preserving controls. By embedding inputs into a discrete latent space spanned by learned visual…

Image and Video Processing · Electrical Eng. & Systems 2024-04-10 Wei Jiang , Wei Wang

This paper proposes a novel latent semantic learning method for extracting high-level features (i.e. latent semantics) from a large vocabulary of abundant mid-level features (i.e. visual keywords) with structured sparse representation,…

Multimedia · Computer Science 2015-03-19 Zhiwu Lu , Yuxin Peng

System identification techniques -- projection pursuit regression models (PPRs) and convolutional neural networks (CNNs) -- provide state-of-the-art performance in predicting visual cortical neurons' responses to arbitrary input stimuli.…

Quantitative Methods · Quantitative Biology 2021-10-04 Ziniu Wu , Harold Rockwell , Yimeng Zhang , Shiming Tang , Tai Sing Lee

Sparse autoencoders (SAEs) offer a natural path toward comparable explanations across different representation spaces. However, current SAEs are trained per modality, producing dictionaries whose features are not directly understandable and…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Difei Gu , Yunhe Gao , Gerasimos Chatzoudis , Zihan Dong , Guoning Zhang , Bangwei Guo , Yang Zhou , Mu Zhou , Dimitris Metaxas

Adapting foundation models for specific purposes has become a standard approach to build machine learning systems for downstream applications. Yet, it is an open question which mechanisms take place during adaptation. Here we develop a new…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Hyesu Lim , Jinho Choi , Jaegul Choo , Steffen Schneider

Deep feed-forward convolutional neural networks (CNNs) have become ubiquitous in virtually all machine learning and computer vision challenges; however, advancements in CNNs have arguably reached an engineering saturation point where…

Computer Vision and Pattern Recognition · Computer Science 2018-06-14 Edward Kim , Darryl Hannan , Garrett Kenyon