深度强制：基于深度汇聚与参与式压缩的无训练长视频生成

Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression

December 4, 2025

作者: Jung Yi, Wooseok Jang, Paul Hyunbin Cho, Jisu Nam, Heeji Yoon, Seungryong Kim

cs.AI

摘要

自回归视频扩散技术的最新进展已实现实时帧流传输，但现有方案仍存在时序重复、漂移和运动减速问题。我们发现直接将StreamingLLM式的注意力沉淀机制应用于视频扩散会导致保真度下降和运动停滞。为此，我们提出深度强制（Deep Forcing）方法，包含两种无需微调的免训练机制：1）深度沉淀（Deep Sink）将滑动窗口的一半专用于持久性沉淀令牌，并将其时序RoPE相位重新对齐至当前时间轴，从而在长序列生成中稳定全局上下文；2）参与式压缩（Participative Compression）执行重要性感知的KV缓存剪枝，仅保留近期注意力中活跃参与的令牌，安全剔除冗余和劣化的历史记录，在超分布长度生成下最小化误差累积。这两项技术协同实现了超过12倍的序列外推能力（如从训练时长的5秒扩展到生成60秒以上），在成像质量上优于LongLive，在美学质量上超越RollingForcing，几乎保持整体一致性，并在动态程度上获得显著提升，同时维持实时生成效率。实验结果表明，免训练的KV缓存管理方法可媲美甚至超越基于训练的方案，适用于自回归流式长视频生成场景。

English

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.