English
Related papers

Related papers: Sparse Concept Anchoring for Interpretable and Con…

200 papers

A central goal of interpretability is to recover representations of causally relevant concepts from the activations of neural networks. The quality of these concept representations is typically evaluated in isolation, and under implicit…

Machine Learning · Computer Science 2025-12-18 Aaron Mueller , Andrew Lee , Shruti Joshi , Ekdeep Singh Lubana , Dhanya Sridhar , Patrik Reizinger

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

Large language models (LLMs) encode a diverse range of linguistic features within their latent representations, which can be harnessed to steer their output toward specific target characteristics. In this paper, we modify the internal…

Computation and Language · Computer Science 2025-02-27 Sumanta Bhattacharyya , Pedram Rooshenas

Sparse Autoencoders have emerged as powerful tools for interpreting the internal representations of Large Language Models, yet they often fail to capture domain-specific features not prevalent in their training corpora. This paper…

Machine Learning · Computer Science 2025-07-18 Nikita Koriagin , Yaroslav Aksenov , Daniil Laptev , Gleb Gerasimov , Nikita Balagansky , Daniil Gavrilov

In complex visual recognition tasks it is typical to adopt multiple descriptors, that describe different aspects of the images, for obtaining an improved recognition performance. Descriptors that have diverse forms can be fused into a…

Computer Vision and Pattern Recognition · Computer Science 2015-06-15 Jayaraman J. Thiagarajan , Karthikeyan Natesan Ramamurthy , Andreas Spanias

Distributional models provide a convenient way to model semantics using dense embedding spaces derived from unsupervised learning algorithms. However, the dimensions of dense embedding spaces are not designed to resemble human semantic…

Computation and Language · Computer Science 2018-11-15 Steven Derby , Paul Miller , Brian Murphy , Barry Devereux

Sparse coding approximates the data sample as a sparse linear combination of some basic codewords and uses the sparse codes as new presentations. In this paper, we investigate learning discriminative sparse codes by sparse coding in a…

Machine Learning · Statistics 2015-01-19 Jim Jing-Yan Wang , Xin Gao

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

Sparseness is a useful regularizer for learning in a wide range of applications, in particular in neural networks. This paper proposes a model targeted at classification tasks, where sparse activity and sparse connectivity are used to…

Machine Learning · Computer Science 2016-04-19 Markus Thom , Günther Palm

Understanding 3D object shapes necessitates shape representation by object parts abstracted from results of instance and semantic segmentation. Promising shape representations enable computers to interpret a shape with meaningful parts and…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Jiaxin Li , Hongxing Wang , Jiawei Tan , Zhilong Ou , Junsong Yuan

Standard Sparse Autoencoders (SAEs) excel at discovering a dictionary of a model's learned features, offering a powerful observational lens. However, the ambiguous and ungrounded nature of these features makes them unreliable instruments…

Machine Learning · Computer Science 2025-09-29 Jianrong Ding , Muxi Chen , Chenchen Zhao , Qiang Xu

Recent works favored dense signals (e.g., depth, DensePose), as an alternative to sparse signals (e.g., OpenPose), to provide detailed spatial guidance for pose-guided text-to-image generation. However, dense representations raised new…

Computer Vision and Pattern Recognition · Computer Science 2025-06-27 Wenjie Xuan , Jing Zhang , Juhua Liu , Bo Du , Dacheng Tao

We use spatially-sparse two, three and four dimensional convolutional autoencoder networks to model sparse structures in 2D space, 3D space, and 3+1=4 dimensional space-time. We evaluate the resulting latent spaces by testing their…

Computer Vision and Pattern Recognition · Computer Science 2018-11-27 Benjamin Graham

Sparse coding is a basic task in many fields including signal processing, neuroscience and machine learning where the goal is to learn a basis that enables a sparse representation of a given set of data, if one exists. Its standard…

Machine Learning · Computer Science 2015-03-04 Sanjeev Arora , Rong Ge , Tengyu Ma , Ankur Moitra

Spectral-based subspace clustering methods have proved successful in many challenging applications such as gene sequencing, image recognition, and motion segmentation. In this work, we first propose a novel spectral-based subspace…

Machine Learning · Statistics 2021-06-09 Hankui Peng , Nicos G. Pavlidis

Sparse Autoencoders uncover thousands of features in vision models, yet explaining these features without requiring human intervention remains an open challenge. While previous work has proposed generating correlation-based explanations…

Computer Vision and Pattern Recognition · Computer Science 2026-03-26 Javier Ferrando , Enrique Lopez-Cuena , Pablo Agustin Martin-Torres , Daniel Hinjos , Anna Arias-Duart , Dario Garcia-Gasulla

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

Lane detection is a fundamental task in autonomous driving, and has achieved great progress as deep learning emerges. Previous anchor-based methods often design dense anchors, which highly depend on the training dataset and remain fixed…

Computer Vision and Pattern Recognition · Computer Science 2024-04-12 Ji Liu , Zifeng Zhang , Mingjie Lu , Hongyang Wei , Dong Li , Yile Xie , Jinzhang Peng , Lu Tian , Ashish Sirasao , Emad Barsoum

Human visual recognition is a sparse process, where only a few salient visual cues are attended to rather than traversing every detail uniformly. However, most current vision networks follow a dense paradigm, processing every single visual…

Computer Vision and Pattern Recognition · Computer Science 2023-04-10 Ziteng Gao , Zhan Tong , Limin Wang , Mike Zheng Shou

Modern artificial intelligence has revolutionized our ability to extract rich and versatile data representations across scientific disciplines. Yet, the statistical properties of these representations remain poorly controlled, causing…

Machine Learning · Computer Science 2025-11-06 Gaia Grosso , Sai Sumedh R. Hindupur , Thomas Fel , Samuel Bright-Thonney , Philip Harris , Demba Ba