Author name: Liubomyr Horbatko

arXiv:2604.18580v2 Announce Type: replace
Abstract: Modern sequence modeling is dominated by two families: Transformers, whose self-attention can access arbitrary elements of the visible sequence, and structured state-space models, which propagate inf…

arXiv:2604.18580v1 Announce Type: cross
Abstract: Modern sequence models are dominated by Transformers, where self-attention mixes information from the visible context in an input-dependent way. However, when retrieval is not sharp and attention remai…