Zhengpei Hu, Kai Li, Dapeng Fu, Chang Zeng, Yue Li, Yuanhao Tang, Jianqiang Huang

BEAVER: A Training-Free Hierarchical Prompt Compression Method via Structure-Aware Page Selection

arXiv:2603.19635v1 Announce Type: new Abstract: The exponential expansion of context windows in LLMs has unlocked capabilities for long-document understanding but introduced severe bottlenecks in inference …