Recursive Sparse Attention: Million-Token Length Extrapolation at Logarithmic Cost

arXiv:2611.07232 · cs.CL, cs.LG · Submitted 2026-11-04 · Read on arXiv

cs.CL, cs.LG

Submitted: 2026-11-04

Updated: 2026-11-04

Code: https://github.com/bojone/rerope

Terminology

Sources

Related papers