讀紙 ReadPaper

由 Claude Code Max 翻譯的 AI 論文繁體中文版 · 101 篇

篩選標籤: KL Divergence 1 篇 × 清除
2604.20244v1 CC BY 4.0

大型語言模型的混合策略蒸餾

Hybrid Policy Distillation for LLMs

Wenhong Zhu, Ruobing Xie, Rui Wang, Pengfei Liu

LLMDistillationRLPolicy DistillationReasoningKL DivergenceOn-policy
Teds Lin 許願