English
Related papers

Related papers: Pair-Variational Autoencoders (PairVAE) for Linkin…

200 papers

Adapting foundation models for specific purposes has become a standard approach to build machine learning systems for downstream applications. Yet, it is an open question which mechanisms take place during adaptation. Here we develop a new…

Computer Vision and Pattern Recognition · Computer Science 2025-03-24 Hyesu Lim , Jinho Choi , Jaegul Choo , Steffen Schneider

Computed tomography (CT) can capture volumes large enough to measure a statistically meaningful number of micron-sized particles with a sufficiently good resolution to allow for the analysis of individual particles. However, the development…

We demonstrate the application of machine learning for rapid and accurate extraction of plasmonic particles cluster geometries from hyperspectral image data via a dual variational autoencoder (dual-VAE). In this approach, the information is…

Disordered Systems and Neural Networks · Physics 2022-08-09 Muammer Y. Yaman , Sergei V. Kalinin , Kathryn N. Guye , David Ginger , Maxim Ziatdinov

Environmental microorganism (EM) offers a high-efficient, harmless, and low-cost solution to environmental pollution. They are used in sanitation, monitoring, and decomposition of environmental pollutants. However, this depends on the…

Computer Vision and Pattern Recognition · Computer Science 2021-02-25 Frank Kulwa , Chen Li , Jinghua Zhang , Kimiaki Shirahama , Sergey Kosov , Xin Zhao , Hongzan Sun , Tao Jiang , Marcin Grzegorzek

In Materials Science, material development involves evaluating and optimizing the internal structures of the material, generically referred to as microstructures. Microstructures structure is stochastic, analogously to image textures. A…

Machine Learning · Computer Science 2024-08-06 Sayed Sajad Hashemi , Michael Guerzhoy , Noah H. Paulson

Sparse Autoencoder (SAE) features have become essential tools for mechanistic interpretability research. SAE features are typically characterized by examining their activating examples, which are often "monosemantic" and align with human…

Artificial Intelligence · Computer Science 2025-09-30 Claire Tian , Katherine Tian , Nathan Hu

Many standard structural quantities, such as order parameters and correlation functions, exist for common condensed matter systems, such as spherical and rod-like particles. However, these structural quantities are often insufficient for…

Soft Condensed Matter · Physics 2012-01-18 Aaron S. Keys , Christopher R. Iacovella , Sharon C. Glotzer

Masked image modeling (MIM) is a highly popular and effective self-supervised learning method for image understanding. Existing MIM-based methods mostly focus on spatial feature modeling, neglecting spectral feature modeling. Meanwhile,…

Image and Video Processing · Electrical Eng. & Systems 2023-11-09 Junyan Lin , Feng Gao , Xiaocheng Shi , Junyu Dong , Qian Du

Variational auto-encoders (VAEs) are a popular and powerful deep generative model. Previous works on VAEs have assumed a factorized likelihood model, whereby the output uncertainty of each pixel is assumed to be independent. This…

Machine Learning · Statistics 2026-05-14 Gara Dorta , Sara Vicente , Lourdes Agapito , Neill D. F. Campbell , Ivor Simpson

Mechanistic interpretability of large language models (LLMs) aims to uncover the internal processes of information propagation and reasoning. Sparse autoencoders (SAEs) have demonstrated promise in this domain by extracting interpretable…

Machine Learning · Computer Science 2025-05-26 Wei Shi , Sihang Li , Tao Liang , Mingyang Wan , Guojun Ma , Xiang Wang , Xiangnan He

Training of semantic segmentation models for material analysis requires micrographs and their corresponding masks. It is quite unlikely that perfect masks will be drawn, especially at the edges of objects, and sometimes the amount of data…

Computer Vision and Pattern Recognition · Computer Science 2024-08-02 Matias Oscar Volman Stern , Dominic Hohs , Andreas Jansche , Timo Bernthaler , Gerhard Schneider

Electron and scanning probe microscopy produce vast amounts of data in the form of images or hyperspectral data, such as EELS or 4D STEM, that contain information on a wide range of structural, physical, and chemical properties of…

Machine Learning · Computer Science 2023-06-09 Arpan Biswas , Maxim Ziatdinov , Sergei V. Kalinin

It is assumed that sparse autoencoders (SAEs) decompose polysemantic activations into interpretable linear directions, as long as the activations are composed of sparse linear combinations of underlying features. However, we find that if an…

Machine Learning · Computer Science 2025-09-29 David Chanin , Tomáš Dulka , Adrià Garriga-Alonso

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

Sparse autoencoders (SAEs) have recently emerged as pivotal tools for introspection into large language models. SAEs can uncover high-quality, interpretable features at different levels of granularity and enable targeted steering of the…

Information Retrieval · Computer Science 2026-01-19 Martin Spišák , Ladislav Peška , Petr Škoda , Vojtěch Vančura , Rodrigo Alves

Sparse autoencoders (SAEs) are used to disentangle the dense, polysemantic internal representations of large language models (LLMs) into interpretable, monosemantic concepts. However, standard $\ell_1$-regularized SAEs suffer from feature…

Machine Learning · Computer Science 2026-05-08 Faris Chaudhry , Keisuke Yano , Anthea Monod

Sparse autoencoders (SAEs) are now standard tools for decomposing language model activations into interpretable features, and automated interpretability pipelines routinely assign each feature a short natural-language explanation. Existing…

Machine Learning · Computer Science 2026-05-14 Jordan F. McCann

We present a deep learning approach for analyzing two-dimensional scattering data of semiflexible polymers under external forces. In our framework, scattering functions are compressed into a three-dimensional latent space using a…

Soft Condensed Matter · Physics 2025-04-24 Lijie Ding , Chi-Huan Tung , Bobby G. Sumpter , Wei-Ren Chen , Changwoo Do

This study investigates the use of non-linear unsupervised dimensionality reduction techniques to compress a music dataset into a low-dimensional representation which can be used in turn for the synthesis of new sounds. We systematically…

Audio and Speech Processing · Electrical Eng. & Systems 2019-05-27 Fanny Roche , Thomas Hueber , Samuel Limier , Laurent Girin

A popular new method in mechanistic interpretability is to train high-dimensional sparse autoencoders (SAEs) on neuron activations and use SAE features as the atomic units of analysis. However, the body of evidence on whether SAE feature…

Machine Learning · Computer Science 2024-09-10 Maheep Chaudhary , Atticus Geiger
‹ Prev 1 3 4 5 6 7 10 Next ›