AI Paper Atlas

Research map / Video / Video generation

Accelerating Diffusion-based Video Editing via Heterogeneous Caching: Beyond Full Computing at Sampled Denoising Timestep

Tianyi Liu, Ye Lu, Linfeng Zhang, Chen Cai, Jianjun Gao, Yi Wang, Kim-Hui Yap, Lap-Pui Chau

CVPR 2026 · Video › Video generation · approach: Efficient video diffusion models · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use HetCache instead of TeaCache-fastWan2.1-VACE · VACE-Benchmark inpainting (Wan2.1-VACE)speedup: 2.53× -> 2.67×Improved
use HetCache instead of TeaCache-fastWan2.1-VACE · VACE-Benchmark inpainting (Wan2.1-VACE)VFID: 54.86 -> 54.51Improved
use HetCache instead of TeaCache-fastWan2.1-VACE · VPBench text-guided editing (Wan2.1-VACE)speedup: 1.79× -> 1.91×Improved
add context clustering and correlation guidance to uniform context sampling (ablation)HetCache · VACE-Benchmark inpainting (ablation)VFID: 54.54 -> 54.51No clear effect
add context clustering and correlation guidance to uniform context sampling (ablation)HetCache · VACE-Benchmark inpainting (ablation)speedup: 3.13× -> 2.67×Hurt
add K-Means context clustering on top of correlation-only selection (ablation)HetCache · VACE-Benchmark inpainting (ablation)VFID: 55.36 -> 54.51Improved
use HetCache instead of TeaCache at higher resolutionWan-VACE-1.3B · Higher-resolution 25x720P inpaintingspeedup: 2.40× -> 2.91×Improved
use HetCache instead of TeaCache on longer videoWan-VACE-1.3B · Longer 57x480P inpaintingspeedup: 2.44× -> 3.06×Improved
increase context ratio (ablation)HetCache · VACE-Benchmark inpainting (ablation)qualityImproved
vary K-Means cluster count K (ablation)HetCache · VACE-Benchmark inpainting (ablation)qualityNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy