Adding paper Self-Supervised Learning in Event Sequences: A Comparative Study and Hybrid Approach of Generative Modeling and Contrastive Learning

[VityaVitalich]

Dear maintainers,

I appreciate your work on collecting research on multimodality domen. Please consider adding the paper "Self-Supervised Learning in Event Sequences: A Comparative Study and Hybrid Approach of Generative Modeling and Contrastive Learning" in the list, that was pre-printed recently on Arxiv.

Overall paper suggest learning representation with combination of generative modeling and contrastive approach by considering their embeddings as distinct modalities and aligning them as it is done in contemporary multimodal research. It results in top performance, compared to other pre-training strategies applied to irregular time-series data.