← Search

Daphné Chopard

2 accepted papers

2024

Deep Generative Clustering with Multimodal Diffusion Variational Autoencoders

ICLR 2024poster

Multimodal VAEs have recently gained significant attention as generative models for weakly-supervised learning with multiple heterogeneous modalities. In parallel, VAE-based methods have been explored as probabilistic approaches for clustering tasks. At the intersection of these two research directi…

Cited by 5SourcePDFScholar
2024

Unity by Diversity: Improved Representation Learning for Multimodal VAEs

NeurIPS 2024poster

Variational Autoencoders for multimodal data hold promise for many tasks in data analysis, such as representation learning, conditional generation, and imputation. Current architectures either share the encoder output, decoder input, or both across modalities to learn a shared representation. Such…

Cited by 4SourcePDFScholar