2026
Layer-Centric Factors of Variation Disentanglement for Task- and Model-Agnostic Generalization
ICML 2026poster
Disentanglement learning aims to separate the underlying factors of variation (FoV) to improve generalization. However, most FoV-based latent-vector-centric methods impose objective-driven constraints at a bottleneck, and it is difficult to translate disentanglement into consistent gains on downstre…