English
Related papers

Related papers: Sparse Concept Anchoring for Interpretable and Con…

200 papers

Disentangling model activations into meaningful features is a central problem in interpretability. However, the absence of ground-truth for these features in realistic scenarios makes validating recent approaches, such as sparse dictionary…

Machine Learning · Computer Science 2024-05-21 Aleksandar Makelov , George Lange , Neel Nanda

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

State-of-the-art approaches toward image restoration can be classified into model-based and learning-based. The former - best represented by sparse coding techniques - strive to exploit intrinsic prior knowledge about the unknown…

Image and Video Processing · Electrical Eng. & Systems 2018-11-29 Fangfang Wu , Weisheng Dong , Guangming Shi , Xin Li

Sparse autoencoders (SAEs) have shown promise in extracting interpretable features from complex neural networks. We present one of the first applications of SAEs to dense text embeddings from large language models, demonstrating their…

Machine Learning · Computer Science 2024-08-06 Charles O'Neill , Christine Ye , Kartheik Iyer , John F. Wu

Supervisory signals have the potential to make low-dimensional data representations, like those learned by mixture and topic models, more interpretable and useful. We propose a framework for training latent variable models that explicitly…

We propose a simple and efficient algorithm for learning sparse invariant representations from unlabeled data with fast inference. When trained on short movies sequences, the learned features are selective to a range of orientations and…

Computer Vision and Pattern Recognition · Computer Science 2011-05-27 Karol Gregor , Yann LeCun

Neural networks have greatly boosted performance in computer vision by learning powerful representations of input data. The drawback of end-to-end training for maximal overall performance are black-box models whose hidden representations…

Computer Vision and Pattern Recognition · Computer Science 2020-04-29 Patrick Esser , Robin Rombach , Björn Ommer

Models that bridge vision and language, such as CLIP, are key components of multimodal AI, yet their large-scale, uncurated training data introduce severe social and spurious biases. Existing post-hoc debiasing methods often operate…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Quentin Guimard , Federico Bartsch , Simone Caldarella , Rahaf Aljundi , Elisa Ricci , Massimiliano Mancini

Is there really much more to say about sparse autoencoders (SAEs)? Autoencoders in general, and SAEs in particular, represent deep architectures that are capable of modeling low-dimensional latent structure in data. Such structure could…

Machine Learning · Computer Science 2025-06-09 Yin Lu , Xuening Zhu , Tong He , David Wipf

Neural transducers have achieved human level performance on standard speech recognition benchmarks. However, their performance significantly degrades in the presence of cross-talk, especially when the primary speaker has a low…

Audio and Speech Processing · Electrical Eng. & Systems 2023-03-31 Desh Raj , Junteng Jia , Jay Mahadeokar , Chunyang Wu , Niko Moritz , Xiaohui Zhang , Ozlem Kalinli

Recent work in Mechanistic Interpretability (MI) has enabled the identification and intervention of internal features in Large Language Models (LLMs). However, a persistent challenge lies in linking such internal features to the reliable…

Computation and Language · Computer Science 2026-04-08 Ruikang Zhang , Shuo Wang , Qi Su

Sparse estimation methods are aimed at using or obtaining parsimonious representations of data or models. They were first dedicated to linear variable selection but numerous extensions have now emerged such as structured sparsity or kernel…

Machine Learning · Computer Science 2011-11-24 Francis Bach , Rodolphe Jenatton , Julien Mairal , Guillaume Obozinski

Representation steering offers a lightweight mechanism for controlling the behavior of large language models (LLMs) by intervening on internal activations at inference time. Most existing methods rely on a single global steering direction,…

Machine Learning · Computer Science 2026-03-04 Laziz U. Abdullaev , Noelle Y. L. Wong , Ryan T. Z. Lee , Shiqi Jiang , Khoi N. M. Nguyen , Tan M. Nguyen

The theory of representation learning aims to build methods that provably invert the data generating process with minimal domain knowledge or any source of supervision. Most prior approaches require strong distributional assumptions on the…

Machine Learning · Computer Science 2022-06-03 Kartik Ahuja , Jason Hartford , Yoshua Bengio

Prototype-driven text generation uses non-parametric models that first choose from a library of sentence "prototypes" and then modify the prototype to generate the output text. While effective, these methods are inefficient at test time as…

Computation and Language · Computer Science 2020-11-05 Junxian He , Taylor Berg-Kirkpatrick , Graham Neubig

Deep learning has powered recent successes of artificial intelligence (AI). However, the deep neural network, as the basic model of deep learning, has suffered from issues such as local traps and miscalibration. In this paper, we provide a…

Machine Learning · Statistics 2021-12-03 Yan Sun , Wenjun Xiong , Faming Liang

Distributional models are derived from co-occurrences in a corpus, where only a small proportion of all possible plausible co-occurrences will be observed. This results in a very sparse vector space, requiring a mechanism for inferring…

Computation and Language · Computer Science 2016-08-25 Thomas Kober , Julie Weeds , Jeremy Reffin , David Weir

This paper presents a sparse representation-based classification approach with a novel dictionary construction procedure. By using the constructed dictionary sophisticated prior knowledge about the spatial nature of the image can be…

Computer Vision and Pattern Recognition · Computer Science 2017-08-22 Ribana Roscher , Björn Waske

Effective human-robot interaction, such as in robot learning from human demonstration, requires the learning agent to be able to ground abstract concepts (such as those contained within instructions) in a corresponding high-dimensional…

Computer Vision and Pattern Recognition · Computer Science 2018-10-03 Yordan Hristov , Alex Lascarides , Subramanian Ramamoorthy

In recent years, self-supervised learning (SSL) has emerged as a promising approach for extracting valuable representations from unlabeled data. One successful SSL method is contrastive learning, which aims to bring positive examples closer…

Machine Learning · Computer Science 2023-07-20 Zeen Song , Xingzhe Su , Jingyao Wang , Wenwen Qiang , Changwen Zheng , Fuchun Sun