AI Paper Atlas

Research map / Video / Video generation

Flow Caching for Autoregressive Video Generation

Yuexiao Ma, Xuzhe Zheng, Jing Xu, Xiwei Xu, Feng Ling, Xiawu Zheng, Huafeng Kuang, Huixia Li, XING WANG, Xuefeng Xiao, Fei Chao, Rongrong Ji

ICLR 2026 · Video › Video generation · approach: Autoregressive long video generation · 25 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 chunkwise caching policy instead of TeaCache uniform reuse (ablation)FlowCache-fast · VBench MAGI-1VBench: 70.11% -> 77.66%Improved
use chunkwise caching policy instead of TeaCache uniform reuse (ablation)FlowCache-fast · VBench SkyReels-V2VBench: 80.06% -> 83.12%Improved
add KV cache compression on top of chunkwise reuse (ablation)FlowCache · VBench MAGI-1VBench: 77.66% -> 77.93%No clear effect
add KV cache compression on top of chunkwise reuse (ablation)FlowCache · VBench SkyReels-V2VBench: 83.12% -> 83.01%No clear effect
add KV cache compression on top of chunkwise reuse (ablation)FlowCache · SkyReels-V2 PSNRPSNR: 23.74 -> 22.61Hurt
use chunkwise reuse instead of TeaCache reuse (ablation)FlowCache · Physics-IQ MAGI-1Physics-IQ score: 13.69% -> 43.10%Improved
add KV cache compression (importance+redundancy) (ablation)FlowCache · Physics-IQ MAGI-1Physics-IQ score: 43.10% -> 39.34%Hurt
keep keys at token level instead of frame level (ablation)FlowCache · Physics-IQ MAGI-1Physics-IQ score: 38.62% -> 39.34%Improved
use frame-level queries instead of token-level (ablation)FlowCache · Physics-IQ MAGI-1Physics-IQ score: 39.34% -> 39.53%No clear effect
lower lambda to weight redundancy more (ablation)FlowCache · Physics-IQ MAGI-1Physics-IQ score: 37.11% (0.15) vs 39.53% (0.07)Mixed
reduce KV cache budget from 8 to 5 chunks (ablation)FlowCache · Physics-IQ MAGI-1Physics-IQ score: 47.60% -> 47.65%No clear effect
FlowCache-fast vs TeaCache-fastFlowCache-fast · MAGI-1speedup: 1.44x -> 2.38xImproved

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