English
Related papers

Related papers: Binary Autoencoder for Mechanistic Interpretabilit…

200 papers

Sparse autoencoders (SAEs) decompose language model representations into a sparse set of linear latent vectors. Recent works have improved SAEs using language model gradients, but these techniques require many expensive backward passes…

Machine Learning · Computer Science 2025-05-28 Matthew Chen , Joshua Engels , Max Tegmark

Discrete latent bottlenecks in variational autoencoders (VAEs) offer high bit efficiency and can be modeled with autoregressive discrete distributions, enabling parameter-efficient multimodal search with transformers. However, discrete…

Machine Learning · Computer Science 2026-02-12 Michael Drolet , Firas Al-Hafez , Aditya Bhatt , Jan Peters , Oleg Arenz

Recent progress in Generative Artificial Intelligence (AI) relies on efficient data representations, often featuring encoder-decoder architectures. We formalize the mathematical problem of finding the optimal encoder-decoder pair and…

Machine Learning · Computer Science 2023-08-29 Semyon Malamud , Teng Andrea Xu , Antoine Didisheim

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

We propose a novel filter for sparse big data, called an integrated autoencoder (IAE), which utilizes auxiliary information to mitigate data sparsity. The proposed model achieves an appropriate balance between prediction accuracy,…

Machine Learning · Computer Science 2019-06-17 Baogui Xin , Wei Peng

Sparse autoencoders (SAEs) are widely used for interpreting language model activations. A key evaluation metric is the increase in cross-entropy loss between the original model logits and the reconstructed model logits when replacing model…

Machine Learning · Computer Science 2025-04-01 Adam Karvonen

We consider a variational autoencoder (VAE) for binary data. Our main innovations are an interpretable lower bound for its training objective, a modified initialization and architecture of such a VAE that leads to faster training, and a…

Machine Learning · Computer Science 2020-03-27 Robert Sicks , Ralf Korn , Stefanie Schwaar

There is growing interest in leveraging mechanistic interpretability and controllability to better understand and influence the internal dynamics of large language models (LLMs). However, current methods face fundamental challenges in…

Computation and Language · Computer Science 2025-12-02 Ruben Härle , Felix Friedrich , Manuel Brack , Stephan Wäldchen , Björn Deiseroth , Patrick Schramowski , Kristian Kersting

Sparse Autoencoders (SAEs) are a promising approach for extracting neural network representations by learning a sparse and overcomplete decomposition of the network's internal activations. However, SAEs are traditionally trained considering…

Machine Learning · Computer Science 2025-04-02 Jeffrey Olmo , Jared Wilson , Max Forsey , Bryce Hepner , Thomas Vin Howe , David Wingate

Transformer-based large language models exhibit groundbreaking capabilities, but their storage and computational costs are prohibitively high, limiting their application in resource-constrained scenarios. An effective approach is to…

Machine Learning · Computer Science 2024-12-18 Jing Zhang , Shuzhen Sun , Peng Zhang , Guangxing Cao , Hui Gao , Xindian Ma , Nan Xu , Yuexian Hou

In this paper, we propose a bidimensional attention based recursive autoencoder (BattRAE) to integrate clues and sourcetarget interactions at multiple levels of granularity into bilingual phrase representations. We employ recursive…

Computation and Language · Computer Science 2016-11-28 Biao Zhang , Deyi Xiong , Jinsong Su

Large Language Models (LLMs) based on transformers achieve cutting-edge results on a variety of applications. However, their enormous size and processing requirements hinder deployment on constrained resources. To enhance efficiency,…

Computation and Language · Computer Science 2026-05-13 Wazib Ansar , Saptarsi Goswami , Amlan Chakrabarti

Masked autoencoder (MAE), a simple and effective self-supervised learning framework based on the reconstruction of masked image regions, has recently achieved prominent success in a variety of vision tasks. Despite the emergence of…

Machine Learning · Computer Science 2023-06-09 Lingjing Kong , Martin Q. Ma , Guangyi Chen , Eric P. Xing , Yuejie Chi , Louis-Philippe Morency , Kun Zhang

Recent progress in scaling up large language models has shown impressive capabilities in performing few-shot learning across a wide range of text-based tasks. However, a key limitation is that these language models fundamentally lack visual…

Machine Learning · Computer Science 2023-02-06 Hao Liu , Wilson Yan , Pieter Abbeel

Learning a generative model of visual information with sparse and compositional features has been a challenge for both theoretical neuroscience and machine learning communities. Sparse coding models have achieved great success in explaining…

Machine Learning · Computer Science 2021-01-26 Linxing Preston Jiang , Luciano de la Iglesia

Scientific archives now contain hundreds of petabytes of data across genomics, ecology, climate, and molecular biology that could reveal undiscovered patterns if systematically analyzed at scale. Large-scale, weakly-supervised datasets in…

Computer Vision and Pattern Recognition · Computer Science 2025-11-25 Samuel Stevens , Jacob Beattie , Tanya Berger-Wolf , Yu Su

Sparse autoencoders (SAEs) have recently emerged as a powerful tool for language model steering. Prior work has explored top-k SAE latents for steering, but we observe that many dimensions among the top-k latents capture non-semantic…

Computation and Language · Computer Science 2025-10-03 Jiaqing Xie

Sparse autoencoders (SAEs) extract millions of interpretable features from a language model, but flat feature inventories aren't very useful on their own. Domain concepts get mixed with generic and weakly grounded features, while related…

Artificial Intelligence · Computer Science 2026-04-29 John Winnicki , Abeynaya Gnanasekaran , Eric Darve

Variational Autoencoders (VAEs) provide a flexible and scalable framework for non-linear dimensionality reduction. However, in application domains such as genomics where data sets are typically tabular and high-dimensional, a black-box…

Machine Learning · Statistics 2020-03-10 Kaspar Märtens , Christopher Yau

Large Language Models (LLMs) remain vulnerable to optimization-based jailbreak attacks that exploit internal gradient structure. While Sparse Autoencoders (SAEs) are widely used for interpretability, their robustness implications remain…

Machine Learning · Computer Science 2026-04-22 Ahson Saiyed , Sabrina Sadiekh , Chirag Agarwal