AAD-1: 面向单步自回归视频生成的非对称对抗蒸馏

摘要

我们提出了AAD-1，一种用于单步自回归图像到视频生成的异步对抗蒸馏框架。现有最先进方法采用对抗蒸馏，但存在运动崩溃和训练不稳定的问题，导致生成静态视频。AAD-1通过架构和训练策略中的两个关键设计解决了这些挑战。我们的核心架构见解是打破生成器和判别器之间的对称性：生成器保持因果性以保留自回归采样能力，而判别器则双向关注完整的时空上下文，并为整个视频序列生成单一的全局真实性评分。这种不对称设计使判别器能有效检测导致自回归生成中运动崩溃的全局时间故障和长期漂移。为稳定训练，我们引入分阶段策略，首先使用分布匹配引导出一个稳定的单步生成器，提供预热阶段使学生分布更接近教师分布，之后再开始对抗蒸馏。在VBench上的大量实验表明，AAD-1在单步自回归视频生成中达到了最先进性能。

English

We present AAD-1, an Asymmetric Adversarial Distillation framework for One-step autoregressive image-to-video generation. State-of-the-art methods adopt adversarial distillation but suffer from motion collapse and training instability, resulting in static videos. AAD-1 addresses these challenges through two key designs in architecture and training strategy. Our key architectural insight is to break the symmetry between generator and discriminator. While the generator remains causal to preserve autoregressive sampling capability, the discriminator attends bidirectionally over the full spatiotemporal context and produces a single holistic realism score for the entire video sequence. This asymmetric design enables the discriminator to effectively detect global temporal failures and long-range drift that cause motion collapse in autoregressive generation. To stabilize training, we introduce a phased strategy that first uses distribution matching to bootstrap a stable one-step generator, providing a warm-up phase that brings the student distribution closer to the teacher before adversarial distillation begins. Extensive experiments on VBench demonstrate that AAD-1 achieves state-of-the-art performance in one-step autoregressive video generation.