Motion-Aware Caching for Efficient Autoregressive Video Generation

arXiv 2026 18 method

TLDR

MotionCache accelerates autoregressive video generation by adaptively caching denoising steps based on pixel-level motion, achieving 6.28x and 1.64x speedups while preserving quality.

Reasoning

The paper presents a novel motion-aware caching method with theoretical grounding and strong empirical speedups on multiple models, which is a clear strength. However, the scope is limited to video generation efficiency and does not address world modeling or related broader claims, weakening relevance to the specified keywords.

Read-first score

Read-first score 18, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 2.

Recency 5%

100

Uses a gentle age decay so recent papers surface without erasing older foundations. 2026

Reproducibility 15%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=code,github

Methodology quality 15%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=experiment

Graph prestige 15%

5.7

PageRank-style prestige over the local citation graph built from available OpenAlex references. local_pagerank=0.0016

Topical relevance 25%

2.9

Uses existing LLM keyword relevance scores normalized to 0-100. world model,world simulator,generative world model,interactive world model,video world model,world dynamics prediction,model-based reinforcement learning world model

Citation impact 15%

Uses OpenAlex-shaped citation metadata as a bibliometric attention signal, separate from paper quality. cited_by_count=0

Citation velocity 10%

Citation velocity estimates citations per publication-year to reduce old-paper bias. velocity=0.00

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 59.

Keyword Scores

world model

video world model

world simulator

generative world model

interactive world model

world dynamics prediction

model-based reinforcement learning world model

Resources

Paper