引用本概念的论文(1) 重新思考面向思维模型的在策略自蒸馏 Rethinking On-Policy Self-Distillation for Thinking Models arXiv 2607.05184
共现相关概念 在引用本概念的论文中,与下列概念同时出现的次数(降序)。 High-Entropy Forking Tokens methodology · 共现 1 On-policy Distillation (OPD) method · 共现 1 Privileged Context methodology · 共现 1 Self-Correction Behavior other · 共现 1 Self-Distillation method · 共现 1 Thinking Models / Reasoning Models architecture · 共现 1