SMat-Attention: Structured Long-Context Sequence Modeling
arXiv:2609.36062v1 Announce Type: new Abstract: Long-context sequence models face a fundamental tradeoff: softmax attention uses flexible token-level interactions at quadratic cost, whereas linear attention obtains linear-time training and constant-time decoding by compressing history into a fixed-size state. In this work, we ask whether we can connect these regimes through a tunable notion of…
Read original article on cs.AI updates on arXiv.org →