诊断视频生成时的时序状态传输问题，修复不稳定的时序表现。
Temporal State Transport in Video Generation: Diagnosing and Correcting Spectral Imbalance
- 从时序状态传输角度分析视频生成中的时间一致性问题。
- 发现两类时序故障：状态碎片化与过度混合热点。
- 无需微调，可自动修正最差时序区域，提升生成质量。
可靠的视频生成不仅需要高质量帧，还需维持连贯的状态，将身份、场景布局、运动和细节等视觉属性跨时间稳定传递。现有无训练方法主要强化跨帧注意力或分析局部注意力熵，但无法判断时序交互是否处于健康传输状态。本文从时序状态传输视角出发，提出谱张力（Spectral Tension）——一种符号诊断指标，通过比较局部注意力扩散性与全局谱多样性，识别出两种相反的时序失效模式：状态碎片化与过度混合热点。基于此诊断，我们提出谱传输稳态（Spectral Transport Homeostasis），一种无需训练的调节器，在保留平衡状态的同时，软性修正病理性时序状态。在预训练视频生成模型上的实验表明，原模型常处于不平衡的时序状态，而本方法能选择性地对最差时序热点施加更大修正，显著提升时序一致性和视觉质量，且无需微调。代码已开源。
原文摘要 · Abstract (English)
Reliable video generation requires more than high-quality frames to form a coherent story: a model must maintain a persistent state, transporting visual attributes such as identity, scene layout, motion, and fine details across time. Existing training-free methods mainly strengthen cross-frame attention or analyze local attention entropy, but these views do not reveal whether temporal interactions stay in a healthy transport regime. In this work, we study video generation through the perspective of Temporal State Transport. We introduce Spectral Tension, a signed diagnostic that compares local attention diffuseness with global spectral diversity, and use it to identify two opposite temporal failures: fragmented transport and over-mixing hotspots. Based on this diagnosis, we propose Spectral Transport Homeostasis, a training-free regulator that softly corrects pathological temporal states while largely preserving balanced ones. Experiments on pretrained video generation models show that the original model often occupies imbalanced temporal regimes, whereas our method selectively applies larger corrections to the worst temporal hotspots and improves temporal consistency and visual quality without finetuning. Code: https://github.com/lytang63/temporal-state-transport
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。