未来强制：自回归视频生成中无需训练的未来感知KV缓存策略
Future Forcing: Future-aware Training-free KV Cache Policy for Autoregressive Video Generation
AI总结：
提出Future Forcing，一种无需训练的未来感知KV缓存策略，通过利用自回归视频模型中查询分布的平稳性来估计未来查询，从而改进长视频生成的一致性。
摘要：
自回归（AR）视频生成已成为长时域视频合成的一种有前景的范式，其中每一帧的生成基于先前生成的令牌。为了加速推理，使用KV缓存避免跨生成步骤的冗余重计算。然而，随着生成长度的增长，KV缓存会引入越来越多的内存和误差累积，限制了AR模型扩展到更长序列的可扩展性。现有的KV缓存压缩方法通过选择性地保留被认为重要的视频令牌来缓解这一问题。然而，大多数现有方法使用从当前或历史生成上下文中提取的短时域信号来评估令牌重要性，这使得这些方法容易忽略在早期步骤中看似不重要但后来对未来帧至关重要的令牌。在这项工作中，我们识别了训练好的AR视频模型的一个重要性质：尽管RoPE调制的查询在自回归步骤中演变，但底层的规范预RoPE查询分布在视频生成过程中保持显著稳定。这种近似平稳性意味着未来查询分布可以从历史统计中估计，从而无需额外训练即可实现原则性的未来感知缓存决策。基于这一洞察，我们提出了Future Forcing，一种用于AR视频生成的无需训练的未来感知KV缓存策略。具体来说，Future Forcing首先从历史统计中构建未来查询代理，然后根据该代理下的重要性对KV缓存令牌进行评分，最后在未来查询诱导的仿射子空间内合并冗余令牌对。大量实验表明，Future Forcing在有限的KV缓存下改善了长时域一致性，在VBench-Long上针对60秒生成，与现有的AR视频KV缓存策略相比，主体一致性提升了高达1.49。
英文摘要：
Autoregressive (AR) video generation has emerged as a promising paradigm for long-horizon video synthesis, where each frame is generated conditioned on previously generated tokens. To accelerate inference, the KV cache is used to avoid redundant recomputation across generation steps. Nevertheless, its growth with generation length introduces increasing memory and error accumulation, limiting the scalability of AR models to even longer sequences. Existing KV cache compression methods mitigate this issue by selectively retaining only video tokens deemed important. However, most existing methods assess token importance using short-horizon signals derived from the current or historical generation context, making these methods prone to overlooking tokens that appear unimportant at early steps but later become critical for future frames. In this work, we identify an important property of trained AR video models: although RoPE-modulated queries evolve across autoregressive steps, the underlying canonical pre-RoPE query distribution remains remarkably stable throughout the video generation process. This approximate stationarity implies that future query distributions are estimable from historical statistics, enabling principled future-aware cache decisions without any additional training. Building on this insight, we propose Future Forcing, a training-free future-aware KV cache policy for AR video generation. Specifically, Future Forcing first constructs a future query proxy from historical statistics, then scores KV cache tokens by their importance under this proxy, and finally merges redundant token pairs within the affine subspace induced by the future query. Extensive experiments show that Future Forcing improves long-horizon consistency under limited KV caches, achieving up to 1.49 improvement in subject consistency on VBench-Long for 60s generation over existing AR video KV cache policies.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
