2 papers
cs.LG2026
Hölder++: Improving the Quality-Coherence Trade-off in Multimodal VAEs
Huyen Vo, MarÃa MartÃnez-GarcÃa, Isabel Valera
Existing approaches for multimodal variational autoencoders (VAEs) face a trade-off between generative quality and coherence-i.e., they struggle to generate realistic and diverse s…
cs.LG2026
Hellinger Multimodal Variational Autoencoders
Huyen Vo, Isabel Valera
Multimodal variational autoencoders (VAEs) are widely used for weakly supervised generative learning with multiple modalities. Predominant methods aggregate unimodal inference dist…