深度强制：免训练 长视频生成与深度Sink和参与性压缩
Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression
AI总结：
深度强制通过深度Sink和参与性压缩机制，在无需微调的情况下实现长视频生成，提升生成质量与动态效果。
摘要：
最近的自回归视频扩散进展使实时帧流成为可能，但现有解决方案仍存在时间重复、漂移和运动减速的问题。我们发现，简单地将StreamingLLM风格的注意力sink应用于视频扩散会导致保真度下降和运动停滞。为解决这一问题，我们引入了深度强制，这是一种无需微调的两种机制，能够解决这些问题。具体来说，1）深度Sink将滑动窗口的一半用于持久sink token，并重新对齐它们的时间RoPE相位，以当前时间线对齐，从而在长滚动过程中稳定全局上下文。2）参与性压缩执行重要性感知的KV缓存修剪，仅保留参与最近注意力的token，同时安全地丢弃冗余和退化的历史，从而在分布外长度生成时最小化误差积累。这些组件共同使生成能力超过12倍（例如5秒训练到60秒+生成），在成像质量上优于LongLive，在审美质量上优于RollingForcing，几乎保持整体一致性，并在动态程度上获得显著提升，同时保持实时生成。我们的结果表明，免训练的KV缓存管理可以匹配或超过训练-based的方法，用于自回归的长视频生成。
英文摘要：
Recent advances in autoregressive video diffusion have enabled real-time frame streaming, yet existing solutions still suffer from temporal repetition, drift, and motion deceleration. We find that naively applying StreamingLLM-style attention sinks to video diffusion leads to fidelity degradation and motion stagnation. To overcome this, we introduce Deep Forcing, which consists of two training-free mechanisms that address this without any fine-tuning. Specifically, 1) Deep Sink dedicates half of the sliding window to persistent sink tokens and re-aligns their temporal RoPE phase to the current timeline, stabilizing global context during long rollouts. 2) Participative Compression performs importance-aware KV cache pruning that preserves only tokens actively participating in recent attention while safely discarding redundant and degraded history, minimizing error accumulation under out-of-distribution length generation. Together, these components enable over 12x extrapolation (e.g. 5s-trained to 60s+ generation) with better imaging quality than LongLive, better aesthetic quality than RollingForcing, almost maintaining overall consistency, and substantial gains in dynamic degree, all while maintaining real-time generation. Our results demonstrate that training-free KV-cache management can match or exceed training-based approaches for autoregressively streaming long-video generation.
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。
