It has been observed that representations learned by distinct neural networks conceal structural similarities when the models are trained under similar inductive biases.
The use of relative representations for latent embeddings has shown potential in enabling latent space communication and zero-shot model stitching across a wide range of applications.
Neural networks embed the geometric structure of a data manifold lying in a high-dimensional space into latent representations.
State of the art audio source separation models rely on supervised data-driven approaches, which can be expensive in terms of labeling resources.
Ranked #1 on Music Source Separation on Slakh2100
Generating shapes using natural language can enable new ways of imagining and creating the things around us.
We propose a novel approach to disentangle the generative factors of variation underlying a given set of observations.