One Threshold Is Not Enough: Prompt-Invariant Caching Schedules for Video Diffusion
Video diffusion models remain expensive because denoising repeatedly evaluates a costly model backbone. Dynamic caching methods like TeaCache, EasyCache, and DiCache reduce this cost by reusing prior outputs while an accumulated drift signal remains below a threshold $τ$. Although existing methods improve the drift signal, they hold $τ$ fixed throughout denoising. We show that fixed thresholds are structurally suboptimal: varying $τ$ across denoising achieves quality-latency tradeoffs unattainable by any fixed threshold across three caching methods with distinct drift signals. We further show that, surprisingly, each method's drift trajectory is nearly prompt-invariant across seven method...
| Authors | Om Agrawal, Saurabh Agarwal, Aditya Akella |
|---|---|
| Primary category | cs.CV |
| Published | 14 July 2026 |
| Last updated at source | 26 September 2026 |
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.