Kun Yuan
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
ML×1AI×1NLP×1
Frequent co-authors
Research Timeline
2026
Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization
This paper introduces Byte-Prefix Marginalization (BPM), a method for consolidating open-weight language models through on-policy distillation while preserving teacher probability mass and maintaining a shared byte space.
Highlighted terms show continued research focus across papers
Papers
cs.LGcs.AIcs.CLEmpiricalRecentJul 24, 2026
Cross-Tokenizer On-Policy Distillation via Byte-Prefix Marginalization
Hao Wang, Kun Yuan, Wenlin Zhong, Minglei Zhang +3 more
This paper introduces Byte-Prefix Marginalization (BPM), a method for consolidating open-weight language models through on-policy distillation while preserving teacher probability mass and maintaining…
View →