Establishes component-wise identifiability guarantees for partially shared causal latents in multimodal nonlinear mixing and introduces a differentiable Wasserstein-based module for recovery.
Causalvae: Disentangled representation learning via neural structural causal models
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Identifiable Multimodal Causal Representation Learning under Partial Latent Sharing
Establishes component-wise identifiability guarantees for partially shared causal latents in multimodal nonlinear mixing and introduces a differentiable Wasserstein-based module for recovery.