One Byte, One Token: Byteifying a 27B Hybrid-Attention LLM with Self-Generated Data

arXiv:2611.13607 · cs.CL, cs.LG · Submitted 2026-11-10 · Read on arXiv

cs.CL, cs.LG

Submitted: 2026-11-10

Updated: 2026-11-12

Project page: https://hkunlp.github.io

Terminology

Sources

Related papers