科研速览 · Science Skim继续刷下去 · Keep skimming →
◇ arXiv2026-09-23· cs.LG

Log-Depth Recurrent Language Modeling

Yiqin Wang, Nuri Cingillioglu, Charles Pert

原始摘要(英文原文)· Original abstract
Language modeling using Transformers has become commonplace despite their fixed computational depth and quadratic runtime with respect to input tokens. Recurrent models on the other hand offer linear depth but no parallel execution. In this work, we extend balanced-tree recursive operators from sequence encoding to autoregressive prediction, enabling all prefix representations to be computed with logarithmic depth and linear runtime. Our experiments provide an initial characterization of this model class, demonstrating robust length extrapolation and performance approaching that of ALiBi-based Transformers, highlighting its potential as an alternative architecture for language modeling.
读原文 · Read the paper ↗

AI 追问PRO

登录后使用 AI 追问

讨论区

登录后参与讨论

相关论文 · Related

Log-Depth Recurrent Language Modeling — 科研速览 Science Skim