A two-stage multimodal VAE with normalizing-flow conditional encoders (plus a shared-projector variant) improves cross-modal generation coherence over mixture-of-experts baselines on four benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Bridging the inference gap in Mutimodal Variational Autoencoders
A two-stage multimodal VAE with normalizing-flow conditional encoders (plus a shared-projector variant) improves cross-modal generation coherence over mixture-of-experts baselines on four benchmarks.