English
Related papers

Related papers: Enhancing Interpretability of Sparse Latent Repres…

200 papers

Variational Autoencoders (VAEs) have become a popular approach for dimensionality reduction. However, despite their ability to identify latent low-dimensional structures embedded within high-dimensional data, these latent representations…

Machine Learning · Statistics 2020-08-27 Kaspar Märtens , Christopher Yau

We present Universal Sparse Autoencoders (USAEs), a framework for uncovering and aligning interpretable concepts spanning multiple pretrained deep neural networks. Unlike existing concept-based interpretability methods, which focus on a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-20 Harrish Thasarathan , Julian Forsyth , Thomas Fel , Matthew Kowal , Konstantinos G. Derpanis

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

We present a novel method for constructing Variational Autoencoder (VAE). Instead of using pixel-by-pixel loss, we enforce deep feature consistency between the input and the output of a VAE, which ensures the VAE's output to preserve the…

Computer Vision and Pattern Recognition · Computer Science 2024-03-21 Xianxu Hou , Linlin Shen , Ke Sun , Guoping Qiu

Advances in neural variational inference have facilitated the learning of powerful directed graphical models with continuous latent variables, such as variational autoencoders. The hope is that such models will learn to represent rich,…

Computation and Language · Computer Science 2017-09-26 Iulian V. Serban , Alexander G. Ororbia , Joelle Pineau , Aaron Courville

We propose a composable framework for latent space image augmentation that allows for easy combination of multiple augmentations. Image augmentation has been shown to be an effective technique for improving the performance of a wide variety…

Machine Learning · Computer Science 2023-03-08 Omead Pooladzandi , Jeffrey Jiang , Sunay Bhat , Gregory Pottie

A recent line of work has shown promise in using sparse autoencoders (SAEs) to uncover interpretable features in neural network representations. However, the simple linear-nonlinear encoding mechanism in SAEs limits their ability to perform…

Machine Learning · Computer Science 2025-01-31 Charles O'Neill , Alim Gumran , David Klindt

Variational Auto-encoders (VAEs) are deep generative latent variable models consisting of two components: a generative model that captures a data distribution p(x) by transforming a distribution p(z) over latent space, and an inference…

Machine Learning · Computer Science 2022-08-25 Yaniv Yacoby , Weiwei Pan , Finale Doshi-Velez

Variational autoencoders (VAEs) have recently been used for unsupervised disentanglement learning of complex density distributions. Numerous variants exist to encourage disentanglement in latent space while improving reconstruction.…

Machine Learning · Statistics 2022-06-10 Kenneth Ezukwoke , Anis Hoayek , Mireille Batton-Hubert , Xavier Boucher

Sparse Autoencoders (SAEs) have become an important tool in mechanistic interpretability, helping to analyze internal representations in both Large Language Models (LLMs) and Vision Transformers (ViTs). By decomposing polysemantic…

Machine Learning · Computer Science 2026-05-11 Jakub Stępień , Marcin Mazur , Jacek Tabor , Przemysław Spurek

In recent years Variation Autoencoders have become one of the most popular unsupervised learning of complicated distributions.Variational Autoencoder (VAE) provides more efficient reconstructive performance over a traditional autoencoder.…

Machine Learning · Statistics 2017-07-12 Gautam Ramachandra

Sparse Autoencoders (SAEs) have proven to be powerful tools for interpreting neural networks by decomposing hidden representations into disentangled, interpretable features via sparsity constraints. However, conventional SAEs are…

Variational autoencoders (VAE) encode data into lower-dimensional latent vectors before decoding those vectors back to data. Once trained, one can hope to detect out-of-distribution (abnormal) latent vectors, but several issues arise when…

Machine Learning · Computer Science 2026-05-12 Alejandro Ascarate , Leo Lebrat , Rodrigo Santa Cruz , Clinton Fookes , Olivier Salvado

With the integration of image modality, the semantic space of multimodal large language models (MLLMs) is more complex than text-only models, making their interpretability more challenging and their alignment less stable, particularly…

Machine Learning · Computer Science 2025-06-18 Hantao Lou , Changye Li , Jiaming Ji , Yaodong Yang

We propose a new family of optimization criteria for variational auto-encoding models, generalizing the standard evidence lower bound. We provide conditions under which they recover the data distribution and learn latent features, and…

Machine Learning · Computer Science 2017-03-01 Shengjia Zhao , Jiaming Song , Stefano Ermon

Sparse autoencoders (SAEs) have become a standard tool for mechanistic interpretability in autoregressive large language models (LLMs), enabling researchers to extract sparse, human-interpretable features and intervene on model behavior.…

Machine Learning · Computer Science 2026-02-06 Xu Wang , Bingqing Jiang , Yu Wan , Baosong Yang , Lingpeng Kong , Difan Zou

Video Variational Autoencoder (VAE) enables latent video generative modeling by mapping the visual world into compact spatiotemporal latent spaces, improving training efficiency and stability. While existing video VAEs achieve commendable…

Computer Vision and Pattern Recognition · Computer Science 2026-05-05 Yian Zhao , Feng Wang , Qiushan Guo , Chang Liu , Xiangyang Ji , Jian Zhang , Jie Chen

As large language models (LLMs) grow in scale and capability, understanding their internal mechanisms becomes increasingly critical. Sparse autoencoders (SAEs) have emerged as a key tool in mechanistic interpretability, enabling the…

Computation and Language · Computer Science 2025-06-10 Jiaming Li , Haoran Ye , Yukun Chen , Xinyue Li , Lei Zhang , Hamid Alinejad-Rokny , Jimmy Chih-Hsien Peng , Min Yang

Variational Auto-Encoders (VAEs) are capable of learning latent representations for high dimensional data. However, due to the i.i.d. assumption, VAEs only optimize the singleton variational distributions and fail to account for the…

Machine Learning · Computer Science 2020-04-20 Da Tang , Dawen Liang , Tony Jebara , Nicholas Ruozzi

Sparse coding aims to model data vectors as sparse linear combinations of basis elements, but a majority of related studies are restricted to continuous data without spatial or temporal structure. A new model-based sparse coding (MSC)…

Methodology · Statistics 2021-08-24 Xin Xing , Rui Xie , Wenxuan Zhong