AI Paper Atlas

Research map / Video / Video generation

PreciseCache: Precise Feature Caching for Efficient and High-fidelity Video Generation

Jiangshan Wang, Kang Zhao, Jiayi Guo, Jiayu Wang, Hang Guo, Chenyang Zhu, Xiu Li, Xiangyu Yue

ICLR 2026 · Video › Video generation · approach: Autoregressive long video generation · 5 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
replace TeaCache with PreciseCache-Turbo (LFD-based step caching)feature caching for video diffusion · Wan2.1-14B 720Pspeedup and LPIPS: TeaCache 1.94x / LPIPS 0.1012 -> Turbo 2.15x / 0.0633Improved
PreciseCache-Turbo vs TeaCache on Open-Sora 1.2feature caching · Open-Sora 1.2VBench: TeaCache 78.23% -> Turbo 78.49% (base 78.79%)No clear effect
add BlockCache on top of Turbo (Flash) (ablation)PreciseCache · Wan2.1-14Bspeedup: 2.15x -> 2.63x with VBench 83.52% -> 83.43%Improved
use 1x8x8 downsample for LFD estimate instead of 2x4x4 (ablation)LFCache · Wan2.1-14BVBench / LPIPS: VBench 83.52% -> 83.18%; LPIPS 0.0793 -> 0.1946Hurt
use 4x4x4 downsample instead of 2x4x4 (ablation)LFCache · Wan2.1-14BVBench / LPIPS: VBench 83.52% -> 83.02%; LPIPS 0.0793 -> 0.1875Hurt
use small 1x2x2 downsample instead of 2x4x4 (ablation)LFCache · Wan2.1-14Blatency: speedup 2.18x -> 0.98xHurt
cache residuals instead of final predictions (ablation)LFCache · Wan2.1-14BVBench / LPIPS: VBench 83.52% -> 83.50%; LPIPS 0.0793 -> 0.0791No clear effect
use TaylorSeer reuse instead of reusing prediction (ablation)LFCache · Wan2.1-14BVBench / LPIPS: VBench 83.52% -> 83.54%; LPIPS 0.0793 -> 0.0801No clear effect
scale PreciseCache-Turbo from 1 to 8 GPUs (DSP)PreciseCache · Wan2.1 1080Platency (s): 1 GPU: 3326 -> 1330; 8 GPUs: 459 -> 229Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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