dSprites
PulseAugur coverage of dSprites — every cluster mentioning dSprites across labs, papers, and developer communities, ranked by signal.
1 day(s) with sentiment data
-
Decafs model disentangles latent space for improved conditional generation
Researchers have developed Decafs, a novel conditional generator that utilizes Lie groups to disentangle latent space embeddings in flow-based models. This approach addresses the interpretability challenges and factor e…
-
New research explores data manifold geometry with Fisher width and benchmarking
Two new research papers explore the geometry of data manifolds in machine learning. The first paper introduces "Fisher width," a new geometric measure analogous to Gaussian width but adapted for statistical manifolds us…
-
Lie Group VAEs tackle non-commutative latent space challenges
Researchers have developed a new framework for Variational Autoencoders (VAEs) called Lie Group VAEs to better handle non-commutative structures in latent spaces. Traditional VAEs often enforce commutativity, which can …