← Search

Hee-Jun Jung

2 accepted papers

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…

Cited by 0SourceScholar