讀紙 ReadPaper

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

標籤 願望清單
篩選標籤： Inverse RL 1 篇 × 清除
2601.19897v1 CC BY 4.0

自蒸餾實現持續學習

Self-Distillation Enables Continual Learning

Idan Shenfeld, Mehul Damani, Jonas Hübotter, Pulkit Agrawal

LLMContinual LearningKnowledge DistillationOn-Policy LearningInverse RL災難性遺忘
arXiv 103
kerg kerg 許願