---
id: 20261028-T0-08
title: "新压缩方法用状态空间编码把长上下文压到线性时间"
title_en: "State-Space Encoding Compresses LLM Context in Linear Time"
url: https://ai.daily.yangsir.net/daily/20261028-T0-08
issue_date: 2026-10-28
publish_date: 2026-10-27T04:00:00.000Z
category: research
source_name: "arXiv cs.CL (NLP)"
source_url: https://arxiv.org/abs/2610.33006
---

# 新压缩方法用状态空间编码把长上下文压到线性时间

arXiv新论文提出一种基于状态空间编码的上下文压缩方法，在推理前将长上下文压缩为更短的表示，计算复杂度随上下文长度线性增长。Transformer类大模型在上下文变长时计算和内存开销急剧上升，现有软提示压缩方法在压缩率和保真度上存在取舍。该方案的目标是让长文档问答、多轮对话等场景在不大幅增加成本的前提下处理更长输入。目前为论文阶段，尚无开源代码或产品化信息。

## English Version

**State-Space Encoding Compresses LLM Context in Linear Time**

A new arXiv paper introduces a context compression method using state-space encoding that compresses long contexts into shorter representations before inference, with computation scaling linearly with context length. Transformer-based LLMs face steep compute and memory costs as context grows, and existing soft-prompt compression methods trade off compression ratio against fidelity. The approach targets long-document QA and multi-turn dialogue without proportional cost increases. It remains a paper with no released code or product.

---

**来源**：[arXiv cs.CL (NLP)](https://arxiv.org/abs/2610.33006)

**详情页**：https://ai.daily.yangsir.net/daily/20261028-T0-08

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*