Video-GPT via Next Clip Diffusion

arXiv 2025 44 method

TLDR

Proposes Video-GPT using next clip diffusion for video as language, achieving SOTA on video prediction for world modeling.

Reasoning

Strengths include a novel paradigm and strong benchmark results on Physics-IQ. Weaknesses are limited methodological details and unclear distinction from video prediction alone.

Read-first score

Read-first score 44, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 29.

Recency 8%

86.7

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

Topical relevance 42%

41.4

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 25%

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

Reproducibility 25%

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

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 370.

Keyword Scores

video world model

world model

world dynamics prediction

generative world model

world simulator

interactive world model

model-based reinforcement learning world model

Resources

Paper