Self-Indexing Attention稀疏长上下文推理框架论文

1. 12:00
   arXiv · Information Retrieval

   Self-Indexing Attention：兼容压缩的稀疏长上下文 LLM 推理

   研究者提出 Self-Indexing Attention，一种免训练框架，基于共享变换域符号-幅度表示，用关键符号作为可复用的 token 级索引，统一 prefill 分组选择与 decode 检索。

Current heat 9·Comparable peak 10（Oct 8）·Comparable change over 24 hours –

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.