English
Related papers

Related papers: Bilinear autoencoders find interpretable manifolds

200 papers

Decomposing model activations into interpretable components is a key open problem in mechanistic interpretability. Sparse autoencoders (SAEs) are a popular method for decomposing the internal activations of trained transformers into sparse,…

Machine Learning · Computer Science 2024-06-26 Connor Kissane , Robert Krzyzanowski , Joseph Isaac Bloom , Arthur Conmy , Neel Nanda

Linear probes and sparse autoencoders consistently recover meaningful structure from transformer representations -- yet why should such simple methods succeed in deep, nonlinear systems? We show this is not merely an empirical regularity…

Machine Learning · Computer Science 2026-02-11 Andres Saurez , Yousung Lee , Dongsoo Har

As recent generative models can generate photo-realistic images, people seek to understand the mechanism behind the generation process. Interpretable generation process is beneficial to various image editing applications. In this work, we…

Computer Vision and Pattern Recognition · Computer Science 2020-12-01 Yu-Ding Lu , Hsin-Ying Lee , Hung-Yu Tseng , Ming-Hsuan Yang

Autoencoders, which consist of an encoder and a decoder, are widely used in machine learning for dimension reduction of high-dimensional data. The encoder embeds the input data manifold into a lower-dimensional latent space, while the…

Numerical Analysis · Mathematics 2024-03-29 Juliane Braunsmann , Marko Rajković , Martin Rumpf , Benedikt Wirth

The problem of learning a manifold structure on a dataset is framed in terms of a generative model, to which we use ideas behind autoencoders (namely adversarial/Wasserstein autoencoders) to fit deep neural networks. From a machine learning…

Machine Learning · Statistics 2018-03-02 Eric O. Korman

Representing a manifold of very high-dimensional data with generative models has been shown to be computationally efficient in practice. However, this requires that the data manifold admits a global parameterization. In order to represent…

Machine Learning · Computer Science 2024-08-13 Giovanni S. Alberti , Johannes Hertrich , Matteo Santacesaria , Silvia Sciutto

A disentangled representation of a data set should be capable of recovering the underlying factors that generated it. One question that arises is whether using Euclidean space for latent variable models can produce a disentangled…

Machine Learning · Computer Science 2020-03-23 Luis A. Pérez Rey

Learning latent representations of registered meshes is useful for many 3D tasks. Techniques have recently shifted to neural mesh autoencoders. Although they demonstrate higher precision than traditional methods, they remain unable to…

Computer Vision and Pattern Recognition · Computer Science 2020-10-22 Yi Zhou , Chenglei Wu , Zimo Li , Chen Cao , Yuting Ye , Jason Saragih , Hao Li , Yaser Sheikh

Sparse autoencoders (SAEs) have become a central tool for interpreting language models. However, two key SAE analyses that remain difficult to scale are (1) matching semantically similar features across multi-layers and (2) compressing…

Machine Learning · Computer Science 2026-05-28 Tue M. Cao , Nguyen Do , My T. Thai

Deep generative models have been wildly successful at learning coherent latent representations for continuous data such as video and audio. However, generative modeling of discrete data such as arithmetic expressions and molecular…

Machine Learning · Statistics 2017-03-07 Matt J. Kusner , Brooks Paige , José Miguel Hernández-Lobato

The autoencoder is an unsupervised learning paradigm that aims to create a compact latent representation of data by minimizing the reconstruction loss. However, it tends to overlook the fact that most data (images) are embedded in a…

Machine Learning · Computer Science 2023-10-26 Alokendu Mazumder , Tirthajit Baruah , Bhartendu Kumar , Rishab Sharma , Vishwajeet Pattanaik , Punit Rathore

Generative modeling of high-dimensional data is a key problem in machine learning. Successful approaches include latent variable models and autoregressive models. The complementary strengths of these approaches, to model global and local…

Computer Vision and Pattern Recognition · Computer Science 2019-04-19 Thomas Lucas , Jakob Verbeek

A common pipeline in functional data analysis is to first convert the discretely observed data to smooth functions, and then represent the functions by a finite-dimensional vector of coefficients summarizing the information. Existing…

Machine Learning · Computer Science 2024-01-19 Sidi Wu , Cédric Beaulac , Jiguo Cao

Euclidean representations distort data with intrinsic non-Euclidean structure. While Riemannian representation learning offers a solution by embedding data onto matching manifolds, it typically relies on an encoder to estimate densities on…

Machine Learning · Computer Science 2026-05-05 Andreas Bjerregaard , Søren Hauberg , Anders Krogh

Variational Autoencoder is typically understood from the perspective of probabilistic inference. In this work, we propose a new geometric reinterpretation which complements the probabilistic view and enhances its intuitiveness. We…

Machine Learning · Computer Science 2025-08-22 Songxuan Shi

The periodic table is a fundamental representation of chemical elements that plays essential theoretical and practical roles. The research article discusses the experiences of unsupervised training of neural networks to represent elements…

Machine Learning · Computer Science 2025-01-24 Alex Glushkovsky

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

There is a large ongoing scientific effort in mechanistic interpretability to map embeddings and internal representations of AI systems into human-understandable concepts. A key element of this effort is the linear representation…

Machine Learning · Computer Science 2025-05-27 Alexander Modell , Patrick Rubin-Delanchy , Nick Whiteley

Sparse Autoencoders (SAEs) have emerged as a popular tool for interpreting the hidden states of large language models (LLMs). By learning to reconstruct activations from a sparse bottleneck layer, SAEs discover interpretable features from…

Computer Vision and Pattern Recognition · Computer Science 2025-09-19 Matthew Lyle Olson , Musashi Hinck , Neale Ratzlaff , Changbai Li , Phillip Howard , Vasudev Lal , Shao-Yen Tseng

To gain insight into the mechanisms behind machine learning methods, it is crucial to establish connections among the features describing data points. However, these correlations often exhibit a high-dimensional and strongly nonlinear…

Machine Learning · Computer Science 2025-03-04 Lorenzo Basile , Santiago Acevedo , Luca Bortolussi , Fabio Anselmi , Alex Rodriguez