# SMat-Attention: Structured Long-Context Sequence Modeling

> 全文为英语

**Published:** 2026年9月30日
**Author:** Emile Anand, Abdullah Ateyeh, Archer Wang, Marin Solja\v{c}i\'c
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/zh/articles/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…

> 内容来自原始来源： **arXiv — cs.AI**
> [在 arXiv — cs.AI 阅读全文](https://arxiv.org/abs/2609.36062)

**标签：** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*