Search Results for author:
Found 3 papers, 3 papers with code
Indirectly Parameterized Concrete Autoencoders
Feature selection is a crucial task in settings where data is high-dimensional or acquiring the full set of features is costly.
Cooperation in the Latent Space: The Benefits of Adding Mixture Components in Variational Autoencoders
In this work, we also demonstrate that increasing the number of mixture components improves the latent-representation capabilities of the VAE on both image and single-cell datasets.
The Klarna Product Page Dataset: Web Element Nomination with Graph Neural Networks and Large Language Models
To address this, we introduce the Klarna Product Page Dataset, a comprehensive and diverse collection of webpages that surpasses existing datasets in richness and variety.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
