# RBS-Attention: Radius-Bounded Sparse Prefill for Long-Context Large Language Models

**Published:** September 22, 2026
**Author:** Chuxu Song, Jiuqi Wei, Zhencan Peng
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/rbs-attention-radius-bounded-sparse-prefill-for-long-context-large-langu

Long-context large language model inference is increasingly limited by prefill, where dense self-attention processes the entire prompt before generation begins. Sparse block selection can reduce this cost, but a block centroid may hide a highly relevant token among many…

> From the original source: **arXiv — cs.AI**
> [Read full article at arXiv — cs.AI](https://arxiv.org/abs/2609.20971)

**Tags:** #arXiv

---

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