相关论文: Pair-Variational Autoencoders (PairVAE) for Linkin…

Sparse autoencoders (SAEs) operationalise the linear representation hypothesis: they reconstruct model activations as sparse linear combinations of interpretable dictionary atoms, on the implicit assumption that activation space is well…

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…

For many Automatic Speech Recognition (ASR) tasks audio features as spectrograms show better results than Mel-frequency Cepstral Coefficients (MFCC), but in practice they are hard to use due to a complex dimensionality of a feature space.…

Unsupervised representation learning holds the promise of exploiting large amounts of unlabeled data to learn general representations. A promising technique for unsupervised learning is the framework of Variational Auto-encoders (VAEs).…

In this study, an image-assisted Approximate Bayesian Computation (ABC) parameter inverse method is proposed to identify the design parameters. In the proposed method, the images are mapped to a low-dimensional latent space by Variational…

Sparse autoencoders (SAEs) have received considerable recent attention as tools for mechanistic interpretability, showing success at extracting interpretable features even from very large LLMs. However, this research has been largely…

This paper investigates the cross-correlations across multiple climate model errors. We build a Bayesian hierarchical model that accounts for the spatial dependence of individual models as well as cross-covariances across different climate…

Sparse autoencoders (SAEs) have emerged as a powerful tool for interpreting neural networks by extracting the concepts represented in their activations. However, choosing the size of the SAE dictionary (i.e. number of learned concepts)…

Cancer is a complex disease with significant social and economic impact. Advancements in high-throughput molecular assays and the reduced cost for performing high-quality multi-omics measurements have fuelled insights through machine…

Contrastive Analysis VAE (CA-VAEs) is a family of Variational auto-encoders (VAEs) that aims at separating the common factors of variation between a background dataset (BG) (i.e., healthy subjects) and a target dataset (TG) (i.e., patients)…

Recent advances in imaging from celestial objects in astronomy visualized via optical and radio telescopes to atoms and molecules resolved via electron and probe microscopes are generating immense volumes of imaging data, containing…

Current video-based Masked Autoencoders (MAEs) primarily focus on learning effective spatiotemporal representations from a visual perspective, which may lead the model to prioritize general spatial-temporal patterns but often overlook…

The structural characterization is an essential task in the study of porous materials. To achieve reliable results, it requires to evaluate images with hundreds of pores. Current methods require large time amounts and are subjected to human…

Sensor fusion can significantly improve the performance of many computer vision tasks. However, traditional fusion approaches are either not data-driven and cannot exploit prior knowledge nor find regularities in a given dataset or they are…

Extracting compact, physically interpretable representations from high-dimensional scientific data is a persistent challenge due to the complex, nonlinear structures inherent in physical systems. We propose a Gaussian Mixture Variational…

Sparse autoencoders (SAEs) improve interpretability in multimodal models, but it remains unclear whether SAE features form modular, composable units for reasoning-an assumption underlying many intervention-based steering methods. We test…

Sparse Autoencoders (SAEs) have emerged as a powerful framework for machine learning interpretability, enabling the unsupervised decomposition of model representations into a dictionary of abstract, human-interpretable concepts. However, we…

For obtaining reliable nanostructural details of large amounts of sample --- and if it is applicable --- Small-Angle Scattering (SAS) is a prime technique to use. It promises to obtain bulk-scale, statistically sound information on the…

In this work, we have investigated a number of unsupervised learning methods for material segmentation in projection x-ray imaging with a spectral detector. A phantom containing two hard materials (glass, steel) and three soft materials…

Sparse Autoencoders (SAEs) have emerged as a powerful unsupervised method for extracting sparse representations from language models, yet scalable training remains a significant challenge. We introduce a suite of 256 SAEs, trained on each…