English
Related papers

Related papers: Binary Autoencoder for Mechanistic Interpretabilit…

200 papers

Autoencoders have been used for finding interpretable and disentangled features underlying neural network representations in both image and text domains. While the efficacy and pitfalls of such methods are well-studied in vision, there is a…

Machine Learning · Computer Science 2025-02-06 Abhinav Menon , Manish Shrivastava , David Krueger , Ekdeep Singh Lubana

Recently, various studies have been directed towards exploring dense passage retrieval techniques employing pre-trained language models, among which the masked auto-encoder (MAE) pre-training architecture has emerged as the most promising.…

Information Retrieval · Computer Science 2023-05-23 Zehan Li , Yanzhao Zhang , Dingkun Long , Pengjun Xie

Variational autoencdoers (VAE) are a popular approach to generative modelling. However, exploiting the capabilities of VAEs in practice can be difficult. Recent work on regularised and entropic autoencoders have begun to explore the…

Machine Learning · Computer Science 2022-03-02 Gregory A. Daly , Jonathan E. Fieldsend , Gavin Tabor

Generative autoencoders offer a promising approach for controllable text generation by leveraging their latent sentence representations. However, current models struggle to maintain coherent latent spaces required to perform meaningful text…

Machine Learning · Computer Science 2020-07-08 Tianxiao Shen , Jonas Mueller , Regina Barzilay , Tommi Jaakkola

What latent features are encoded in language model (LM) representations? Recent work on training sparse autoencoders (SAEs) to disentangle interpretable features in LM representations has shown significant promise. However, evaluating the…

Sparse Autoencoders (SAEs) have emerged as a promising tool for interpreting neural networks by decomposing their activations into sparse sets of human-interpretable features. Recent work has introduced multiple SAE variants and…

Machine Learning · Computer Science 2026-02-17 Anton Korznikov , Andrey Galichin , Alexey Dontsov , Oleg Rogov , Ivan Oseledets , Elena Tutubalina

Despite numerous studies of deep autoencoders (AEs) for unsupervised anomaly detection, AEs still lack a way to express uncertainty in their predictions, crucial for ensuring safe and trustworthy machine learning systems in high-stake…

Machine Learning · Computer Science 2022-02-28 Bang Xiang Yong , Alexandra Brintrup

This paper shows that masked autoencoders (MAE) are scalable self-supervised learners for computer vision. Our MAE approach is simple: we mask random patches of the input image and reconstruct the missing pixels. It is based on two core…

Computer Vision and Pattern Recognition · Computer Science 2021-12-21 Kaiming He , Xinlei Chen , Saining Xie , Yanghao Li , Piotr Dollár , Ross Girshick

Blind image quality assessment (BIQA) is a challenging problem with important real-world applications. Recent efforts attempting to exploit powerful representations by deep neural networks (DNN) are hindered by the lack of subjectively…

Computer Vision and Pattern Recognition · Computer Science 2023-05-25 Zehong Zhou , Fei Zhou , Guoping Qiu

We would like to learn a representation of the data which decomposes an observation into factors of variation which we can independently control. Specifically, we want to use minimal supervision to learn a latent representation that…

Machine Learning · Computer Science 2017-05-25 Diane Bouchacourt , Ryota Tomioka , Sebastian Nowozin

Integrated sensing and communication and millimeter wave (mmWave) have emerged as pivotal technologies for 6G networks. However, the narrow nature of mmWave beams requires precise alignments that typically necessitate large training…

Signal Processing · Electrical Eng. & Systems 2025-11-25 Ahmad A. Aziz El-Banna , Octavia A. Dobre

Sparse autoencoders (SAEs) enable feature-level mechanistic interpretability and activation steering in large language models (LLMs), but SAE-based language control remains unreliable in multilingual settings: most SAEs are trained on…

Computation and Language · Computer Science 2026-05-25 Yusser Al Ghussin , Daniil Gurgurov , Tanja Baeumel , Josef van Genabith , Patrick Schramowski , Simon Ostermann

Recent studies show that auto-encoder based approaches successfully perform language generation, smooth sentence interpolation, and style transfer over unseen attributes using unlabelled datasets in a zero-shot manner. The latent space…

Computation and Language · Computer Science 2022-05-06 Sharan Narasimhan , Suvodip Dey , Maunendra Sankar Desarkar

Denoising autoencoders (DAE) are trained to reconstruct their clean inputs with noise injected at the input level, while variational autoencoders (VAE) are trained with noise injected in their stochastic hidden layer, with a regularizer…

Machine Learning · Computer Science 2016-01-05 Daniel Jiwoong Im , Sungjin Ahn , Roland Memisevic , Yoshua Bengio

Sparse autoencoders (SAEs) are used to analyze embeddings, but their role and practical value are debated. We propose a new perspective on SAEs by demonstrating that they can be naturally understood as topic models. We propose a continuous…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Leander Girrbach , Zeynep Akata

High-dimensional data, particularly in the form of high-order tensors, presents a major challenge in self-supervised learning. While MLP-based autoencoders (AE) are commonly employed, their dependence on flattening operations exacerbates…

Machine Learning · Computer Science 2025-08-12 Junjing Zheng , Chengliang Song , Weidong Jiang , Xinyu Zhang

We present a coupled Variational Auto-Encoder (VAE) method that improves the accuracy and robustness of the probabilistic inferences on represented data. The new method models the dependency between input feature vectors (images) and weighs…

Machine Learning · Computer Science 2025-11-25 Shichen Cao , Jingjing Li , Kenric P. Nelson , Mark A. Kon

Principal Component Analysis (PCA) minimizes the reconstruction error given a class of linear models of fixed component dimensionality. Probabilistic PCA adds a probabilistic structure by learning the probability distribution of the PCA…

Machine Learning · Computer Science 2022-09-20 Vanessa Böhm , Uroš Seljak

Distributed learning and Edge AI necessitate efficient data processing, low-latency communication, decentralized model training, and stringent data privacy to facilitate real-time intelligence on edge devices while reducing dependency on…

Machine Learning · Computer Science 2025-07-08 Lucas Heublein , Simon Kocher , Tobias Feigl , Alexander Rügamer , Christopher Mutschler , Felix Ott

Sparse autoencoders (SAEs) are a recent technique for decomposing neural network activations into human-interpretable features. However, in order for SAEs to identify all features represented in frontier models, it will be necessary to…

Machine Learning · Computer Science 2025-06-04 Anish Mudide , Joshua Engels , Eric J. Michaud , Max Tegmark , Christian Schroeder de Witt