5 papers · 1 filter
Hölder++: Improving the Quality-Coherence Trade-off in Multimodal VAEs
Huyen Vo, María Martínez-García, 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…
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…
Temporal Variational Implicit Neural Representations
Batuhan Koyuncu, Rachael DeVries, Ole Winther +1
We introduce Temporal Variational Implicit Neural Representations (TV-INRs), a probabilistic framework for modeling irregular multivariate time series that enables efficient and ac…
DeCaFlow: A deconfounding causal generative model
Alejandro Almodóvar, Adrián Javaloy, Juan Parras +2
We introduce DeCaFlow, a deconfounding causal generative model. Training once per dataset using just observational data and the underlying causal graph, DeCaFlow enables accurate c…
COPA: Comparing the incomparable in multi-objective model evaluation
Adrián Javaloy, Antonio Vergari, Isabel Valera
In machine learning (ML), we often need to choose one among hundreds of trained ML models at hand, based on various objectives such as accuracy, robustness, fairness or scalability…