Generative Pre-trained Autoregressive Diffusion Transformer
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Few-Shot LearningVideo GenerationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
MaskINT: Video Editing via Interpolative Non-autoregressive Masked Transformers
Recent advances in generative AI have significantly enhanced image and video editing, particularly in the context of text prompt control. State-of-the-art approaches predominantly rely on diffusion models to accomplish t…
Video EditingImproved Masked Image Generation with Token-Critic
Non-autoregressive generative transformers recently demonstrated impressive image generation performance, and orders of magnitude faster sampling than their autoregressive counterparts. However, optimal parallel sampling…
DiversityImage GenerationMADFormer: Mixed Autoregressive and Diffusion Transformers for Continuous Image Generation
Recent progress in multimodal generation has increasingly combined autoregressive (AR) and diffusion-based approaches, leveraging their complementary strengths: AR models capture long-range dependencies and produce fluen…
Image Generationmultimodal generationUNCAGE: Contrastive Attention Guidance for Masked Generative Transformers in Text-to-Image Generation
Text-to-image (T2I) generation has been actively studied using Diffusion Models and Autoregressive Models. Recently, Masked Generative Transformers have gained attention as an alternative to Autoregressive Models to over…
Text-to-Image GenerationBuildAnyPoint: 3D Building Structured Abstraction from Diverse Point Clouds
We introduce BuildAnyPoint, a novel generative framework for structured 3D building reconstruction from point clouds with diverse distributions, such as those captured by airborne LiDAR and Structure-from-Motion. To reco…
Point Cloud CompletionPoint Clouds