Generative Pre-trained Autoregressive Diffusion Transformer

arXiv 2025 24 method

TLDR

GPDiT combines diffusion and autoregressive modeling in continuous latent space for long-range video synthesis.

Reasoning

The paper presents a novel continuous autoregressive framework with diffusion loss for video generation, showing strong performance in quality, representation, and few-shot learning. However, it does not address world modeling, simulation, or reinforcement learning, limiting its relevance to those keywords.

Read-first score

Read-first score 24, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 3.

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=experiment

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%

4.3

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: 43.

Keyword Scores

video world model

world dynamics prediction

world model

world simulator

generative world model

interactive world model

model-based reinforcement learning world model

Resources

Paper