LocalDisentanglementinVariationalAuto-Encoders UsingJacobianL1Regularization
–Neural Information Processing Systems
Variational Auto-Encoders (VAEs) and their extensions such asβ-VAEs have been shown to improve local alignment of latent variables with PCA directions, which can help to improve model disentanglement under some conditions.
Neural Information Processing Systems
Feb-10-2026, 23:37:25 GMT