🍊 The Latent Field

标签: recipe

此标签下有1条笔记。

  • 2026年8月11日

    Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

    • source
    • paper
    • distillation
    • on-policy-kd
    • opd
    • reasoning
    • recipe
    • post-training

The Latent Field · An AI knowledge atlas built with Quartz © 2026