一作ACL 2026Poster· Natural Language Processing
SCOPE : Boosting LLM Efficiency with Scoped Position Encoding
Qingguo Qi · Hongyang Chen · Zhao Li
摘要
Positional encodings are fundamental to Transformers, yet explicit methods like RoPE can degrade under length extrapolation and may incur extra arithmetic and memory-access overhead. In this paper, we propose Scoped Position Encoding (ScoPE), a novel framework that reimagines structured sparsity...