Dynamic Relational Priming Improves Transformer in Multivariate Time Series 事件

Dynamic Relational Priming Improves Transformer in Multivariate Time Series arXiv:2509.12196v2 Announce Type: replace-cross Abstract: Standard attention mechanisms in transformers employ static token representations that remain unchanged across all pair-wise computations in each layer. This limits their representational alignment with the potentially diverse relational dynamics of each token-pair interaction. While they excel in domains with relatively homogeneous relationships, standard attent