Abstract: This paper introduces V2Coder, a non-autoregressive vocoder based on hierarchical variational autoencoders (VAEs). The hierarchical VAE with hierarchically extended prior and approximate ...
The cpiVAE learns a shared latent representation across different proteomics platforms. The model consists of platform-specific encoders and decoders connected through a shared latent space, allowing ...
Abstract: This study explores the application of Variational Autoencoders (VAEs) for generating synthetic electroencephalography (EEG) data pertinent to psychiatric disorders. Using the Kaggle EEG ...
Builds on Toy Models of Superposition and Towards Monosemanticity: Decomposing Language Models With Dictionary Learning. Addressing concerns that correlated features remain entangled in current SAE ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback