Causal autoregressive video diffusion models support real-time streaming generation by extrapolating future chunks from previously generated content. Distilling such generators from high-fidelity bidirectional teachers yields competitive few-step models, yet a persistent gap between the history distributions encountered during training and those arising at inference constrains generation quality over long horizons. We introduce the Real-time Autoregressive Video Extrapolation Network (RAVEN), a training-time test framework that repacks each self rollout into an interleaved sequence of clean historical endpoints and noisy denoising states. This formulation aligns training attention with inference-time extrapolation and allows downstream chunk losses to supervise the history representations on which future predictions depend. We further propose Consistency-model Group Relative Policy Optimization (CM-GRPO), which reformulates a consistency sampling step as a conditional Gaussian transition and applies online Reinforcement Learning (RL) directly to this kernel, avoiding the Euler-Maruyama auxiliary process adopted in prior flow-model RL formulations. Experiments demonstrate that RAVEN surpasses recent causal video distillation baselines across quality, semantic, and dynamic degree evaluations, and that CM-GRPO provides further gains when combined with RAVEN.

翻译：因果自回归视频扩散模型通过从已生成内容中外推未来片段，支持实时流式生成。从高保真双向教师模型中蒸馏此类生成器可得到性能优越的少步模型，但训练期间遭遇的历史分布与推理时产生的分布之间存在持续差距，限制了长时域生成质量。我们提出实时自回归视频外推网络（RAVEN），该训练时测试框架将每次自回滚重新组织为干净历史端点与含噪去噪状态交织的序列。该公式使训练注意力与推理时外推对齐，并允许下游片段损失监督未来预测所依赖的历史表征。我们进一步提出一致性模型组相对策略优化（CM-GRPO），将一致性采样步骤重新表述为条件高斯转移，并直接对该核应用在线强化学习（RL），避免了先前流模型RL公式中采用的Euler-Maruyama辅助过程。实验表明，RAVEN在质量、语义和动态程度评估上均超越近期因果视频蒸馏基线，且当CM-GRPO与RAVEN结合时可提供进一步增益。