English
Related papers

Related papers: Deriving Decoder-Free Sparse Autoencoders from Fir…

200 papers

Sparse autoencoders (SAEs) have emerged as powerful techniques for interpretability of large language models (LLMs), aiming to decompose hidden states into meaningful semantic features. While several SAE variants have been proposed, there…

Machine Learning · Computer Science 2025-10-03 Xudong Zhu , Mohammad Mahdi Khalili , Zhihui Zhu

Compressed sensing with subsampled unitary matrices benefits from \emph{optimized} sampling schemes, which feature improved theoretical guarantees and empirical performance relative to uniform subsampling. We provide, in a first of its kind…

Machine Learning · Statistics 2025-04-03 Yaniv Plan , Matthew S. Scott , Xia Sheng , Ozgur Yilmaz

In the last few years there have been important advancements in generative models with the two dominant approaches being Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs). However, standard Autoencoders (AEs) and…

Computer Vision and Pattern Recognition · Computer Science 2019-07-26 Massimiliano Patacchiola , Patrick Fox-Roberts , Edward Rosten

A hallmark of variational autoencoders (VAEs) for text processing is their combination of powerful encoder-decoder models, such as LSTMs, with simple latent distributions, typically multivariate Gaussians. These models pose a difficult…

Computation and Language · Computer Science 2018-10-15 Jiacheng Xu , Greg Durrett

The impressive capabilities of large foundation models come at a cost of substantial computing resources to serve them. Compressing these pre-trained models is of practical interest as it can democratize deploying them to the machine…

Machine Learning · Statistics 2025-02-04 Mehdi Makni , Kayhan Behdin , Zheng Xu , Natalia Ponomareva , Rahul Mazumder

Sparse Autoencoders (SAEs) have recently gained attention as a means to improve the interpretability and steerability of Large Language Models (LLMs), both of which are essential for AI safety. In this work, we extend the application of…

Computer Vision and Pattern Recognition · Computer Science 2025-12-01 Mateusz Pach , Shyamgopal Karthik , Quentin Bouniot , Serge Belongie , Zeynep Akata

Sparse Autoencoders (SAEs) are widely employed for mechanistic interpretability and model steering. Within this context, steering is by design performed by means of decoding altered SAE intermediate representations. This procedure…

Machine Learning · Computer Science 2025-12-08 Antonio Bărbălau , Cristian Daniel Păduraru , Teodor Poncu , Alexandru Tifrea , Elena Burceanu

Extracting insight from the enormous quantity of data generated from molecular simulations requires the identification of a small number of collective variables whose corresponding low-dimensional free-energy landscape retains the essential…

Chemical Physics · Physics 2019-12-30 Yasemin Bozkurt Varolgunes , Tristan Bereau , Joseph F. Rudzinski

Audio autoencoders learn useful, compressed audio representations, but their non-linear latent spaces prevent intuitive algebraic manipulation such as mixing or scaling. We introduce a simple training methodology to induce linearity in a…

Sound · Computer Science 2026-01-29 Bernardo Torres , Manuel Moussallam , Gabriel Meseguer-Brocal

Neuroscientists have long criticised deep learning algorithms as incompatible with current knowledge of neurobiology. We explore more biologically plausible versions of deep representation learning, focusing here mostly on unsupervised…

Machine Learning · Computer Science 2016-08-10 Yoshua Bengio , Dong-Hyun Lee , Jorg Bornschein , Thomas Mesnard , Zhouhan Lin

Sparse Autoencoders (SAEs) provide potentials for uncovering structured, human-interpretable representations in Large Language Models (LLMs), making them a crucial tool for transparent and controllable AI systems. We systematically analyze…

Machine Learning · Computer Science 2026-02-03 Jack Gallifant , Shan Chen , Kuleen Sasse , Hugo Aerts , Thomas Hartvigsen , Danielle S. Bitterman

Large language models (LLMs) store vast amounts of information, making them powerful yet raising privacy and safety concerns when selective knowledge removal is required. Existing unlearning strategies, ranging from gradient-based…

Computation and Language · Computer Science 2025-06-02 Xu Wang , Zihao Li , Benyou Wang , Yan Hu , Difan Zou

While sparse autoencoders (SAEs) successfully extract interpretable features from language models, applying them to audio generation faces unique challenges: audio's dense nature requires compression that obscures semantic meaning, and…

Machine Learning · Computer Science 2025-10-31 Nathan Paek , Yongyi Zang , Qihui Yang , Randal Leistikow

We propose a projection-free conditional gradient-type algorithm for smooth stochastic multi-level composition optimization, where the objective function is a nested composition of $T$ functions and the constraint set is a closed convex…

Optimization and Control · Mathematics 2022-10-11 Tesi Xiao , Krishnakumar Balasubramanian , Saeed Ghadimi

Unsupervised spoken term discovery consists of two tasks: finding the acoustic segment boundaries and labeling acoustically similar segments with the same labels. We perform segmentation based on the assumption that the frame feature…

Audio and Speech Processing · Electrical Eng. & Systems 2020-07-28 Saurabhchand Bhati , Jesús Villalba , Piotr Żelasko , Najim Dehak

Deep generative models have been used in recent years to learn coherent latent representations in order to synthesize high-quality images. In this work, we propose a neural network to learn a generative model for sampling consistent indoor…

Computer Vision and Pattern Recognition · Computer Science 2020-08-24 Pulak Purkait , Christopher Zach , Ian Reid

We present the Score-based Autoencoder for Multiscale Inference (SAMI), a method for unsupervised representation learning that combines the theoretical frameworks of diffusion models and VAEs. By unifying their respective evidence lower…

Machine Learning · Statistics 2025-12-23 Benjamin S. H. Lyo , Eero P. Simoncelli , Cristina Savin

Compressed sensing (CS) is about recovering a structured signal from its under-determined linear measurements. Starting from sparsity, recovery methods have steadily moved towards more complex structures. Emerging machine learning tools…

Information Theory · Computer Science 2019-12-18 Pei Peng , Shirin Jalali , Xin Yuan

A new method for the unsupervised learning of sparse representations using autoencoders is proposed and implemented by ordering the output of the hidden units by their activation value and progressively reconstructing the input in this…

Machine Learning · Computer Science 2016-05-09 Paul Bertens

Recently, a wide range of memory-efficient LLM training algorithms have gained substantial popularity. These methods leverage the low-rank structure of gradients to project optimizer states into a subspace using projection matrix found by…

Machine Learning · Computer Science 2024-08-26 Kaizhao Liang , Bo Liu , Lizhang Chen , Qiang Liu