Saved in:
Bibliographic Details
Main Authors: Zhang, Yuan, Jiang, Jiacheng, Ma, Guoqing, Lu, Zhiying, Huang, Haoyang, Yuan, Jianlong, Duan, Nan, Jiang, Daxin
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.07344
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915537588584448
author Zhang, Yuan
Jiang, Jiacheng
Ma, Guoqing
Lu, Zhiying
Huang, Haoyang
Yuan, Jianlong
Duan, Nan
Jiang, Daxin
author_facet Zhang, Yuan
Jiang, Jiacheng
Ma, Guoqing
Lu, Zhiying
Huang, Haoyang
Yuan, Jianlong
Duan, Nan
Jiang, Daxin
contents In this work, we present GPDiT, a Generative Pre-trained Autoregressive Diffusion Transformer that unifies the strengths of diffusion and autoregressive modeling for long-range video synthesis, within a continuous latent space. Instead of predicting discrete tokens, GPDiT autoregressively predicts future latent frames using a diffusion loss, enabling natural modeling of motion dynamics and semantic consistency across frames. This continuous autoregressive framework not only enhances generation quality but also endows the model with representation capabilities. Additionally, we introduce a lightweight causal attention variant and a parameter-free rotation-based time-conditioning mechanism, improving both the training and inference efficiency. Extensive experiments demonstrate that GPDiT achieves strong performance in video generation quality, video representation ability, and few-shot learning tasks, highlighting its potential as an effective framework for video modeling in continuous space.
format Preprint
id arxiv_https___arxiv_org_abs_2505_07344
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Generative Pre-trained Autoregressive Diffusion Transformer
Zhang, Yuan
Jiang, Jiacheng
Ma, Guoqing
Lu, Zhiying
Huang, Haoyang
Yuan, Jianlong
Duan, Nan
Jiang, Daxin
Computer Vision and Pattern Recognition
Artificial Intelligence
In this work, we present GPDiT, a Generative Pre-trained Autoregressive Diffusion Transformer that unifies the strengths of diffusion and autoregressive modeling for long-range video synthesis, within a continuous latent space. Instead of predicting discrete tokens, GPDiT autoregressively predicts future latent frames using a diffusion loss, enabling natural modeling of motion dynamics and semantic consistency across frames. This continuous autoregressive framework not only enhances generation quality but also endows the model with representation capabilities. Additionally, we introduce a lightweight causal attention variant and a parameter-free rotation-based time-conditioning mechanism, improving both the training and inference efficiency. Extensive experiments demonstrate that GPDiT achieves strong performance in video generation quality, video representation ability, and few-shot learning tasks, highlighting its potential as an effective framework for video modeling in continuous space.
title Generative Pre-trained Autoregressive Diffusion Transformer
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2505.07344