--- title: "Self-Resampling" created: 2026-06-20 updated: 2026-06-20 type: concept tags: ["training", "autoregressive", "streaming", "diffusion", "self-play"] sources: ["https://arxiv.org/abs/2606.17800"] --- # Self-Resampling (自重采样) **Self-Resampling** 是 [[maineCoon|MaineCoon]] 提出的流式自回归训练技术:在训练时让模型以**自己生成的有噪退化历史**为条件,而非只用纯净 ground-truth 历史。这消除了自回归模型常见的 train-test gap。 ## 动机:Train-Test Gap 自回归扩散模型的标准训练使用**干净的历史**作为条件: ``` 训练: p(x_t | clean x_