Graph geometry-preserving autoencoders

J Lim, J Kim, Y Lee, C Jang, FC Park - Forty-first International …, 2024 - openreview.net
When using an autoencoder to learn the low-dimensional manifold of high-dimensional
data, it is crucial to find the latent representations that preserve the geometry of the data …

[PDF][PDF] Metric flow matching for smooth interpolations on the data manifold

K Kapusniak, P Potaptchik, T Reu… - The Thirty-eighth …, 2024 - proceedings.neurips.cc
Matching objectives underpin the success of modern generative models and rely on
constructing conditional paths that transform a source distribution into a target distribution …

Geometric Autoencoders--What You See is What You Decode

P Nazari, S Damrich, FA Hamprecht - ar** text-based robot trajectory generation models is made particularly difficult by the
small dataset size, high dimensionality of the trajectory space, and the inherent complexity of …

Isometric representation learning for disentangled latent space of diffusion models

J Hahm, J Lee, S Kim, J Lee - ar** a target object on a cluttered shelf, especially when the target is
occluded by other unknown objects and initially invisible, remains a significant challenge in …