LoViC: Efficient Long Video Generation with Context Compression

arXiv 2025 24.2 method

TLDR

LoViC uses a compressed latent representation and segment-wise generation to produce long, coherent videos efficiently.

Reasoning

The paper introduces a novel framework for long video generation with a context compression mechanism, validated on large-scale datasets. However, it lacks explicit connection to world models or reinforcement learning, limiting its relevance to those keywords.

Read-first score

Read-first score 24.2, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 0.

Recency 8%

86.7

Uses a gentle age decay so recent papers surface without erasing older foundations. 2025

Reproducibility 25%

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

Methodology quality 25%

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

Topical relevance 42%

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

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 53.

Keyword Scores

world model

world simulator

generative world model

interactive world model

video world model

world dynamics prediction

model-based reinforcement learning world model

Resources

Paper