Looking Ahead: Modeling Future Evolution in Autoregressive Video Generation

arXiv 2026 22.8 method

TLDR

Introduces Future Chunk Prediction to train autoregressive video diffusion models to predict temporally separated future chunks, improving physical plausibility without changing inference.

Reasoning

The paper proposes a clean, compute-efficient auxiliary objective that directly targets future evolution, with no extra encoder and unchanged inference. Strengths include empirical gains in physical plausibility and structured representations, but the abstract lacks explicit benchmark details and positions world-model benefits as speculative.

Read-first score

Read-first score 22.8, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 23.

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

Topical relevance 25%

32.9

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

Methodology quality 15%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=none

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: 175.

Keyword Scores

world dynamics prediction

world model

video world model

generative world model

world simulator

interactive world model

model-based reinforcement learning world model

Resources

Paper