Head Forcing: Long Autoregressive Video Generation via Head Heterogeneity

arXiv 2026 18.2 method

TLDR

Head Forcing extends autoregressive video diffusion to minute-level generation by assigning tailored KV cache strategies to heterogeneous attention heads, without additional training.

Reasoning

The paper identifies functional heterogeneity in attention heads and proposes a training-free, head-specific caching and memory scheme to mitigate error accumulation in long video generation. Strengths include a novel analysis and practical, plug-in approach; weaknesses are that abstract-level evidence lacks detailed benchmarks and the connection to broader world models is unstated.

Read-first score

Read-first score 18.2, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 6.

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=github

Methodology quality 15%

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

Topical relevance 25%

8.6

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

Graph prestige 15%

5.7

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

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: 31.

Keyword Scores

video world model

interactive world model

world model

world simulator

generative world model

world dynamics prediction

model-based reinforcement learning world model

Resources

Paper