VideoGen-Eval: Agent-based System for Video Generation Evaluation

arXiv 2025 29.7 system, benchmark

TLDR

VideoGen-Eval is an agent-based evaluation system and benchmark with 700 prompts and 12,000 videos for assessing video generation models, aligning with human preferences.

Reasoning

The paper introduces a novel evaluation framework and large benchmark, with strong validation via extensive experiments and human alignment. However, the abstract lacks discussion of limitations or comparison beyond benchmark metrics, and no world-model-related contribution is evident.

Read-first score

Read-first score 29.7, 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

Methodology quality 25%

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

Reproducibility 25%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

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: 389.

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