The organization TVLearn aims at bundling projects on truncated variational optimization of multiple causes latent variable models in order to (A) disseminate the algorithms for interested researchers and practitioners, and (B) to encourage further developments and to support future projects.

Jakob Drefs*, Enrico Guiraud*, Filippos Panagiotou, Jörg Lücke (2022).
Direct Evolutionary Optimization of Variational Autoencoders With Binary Latents.
Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Springer, Cham. (online access)
*Joint first authorship
Source Code here.

Jakob Drefs, Enrico Guiraud, Jörg Lücke (2022).
Evolutionary Variational Optimization of Generative Models.
Journal of Machine Learning Research, 23(21):1-51. (online access)
Source Code here and here.