Autoregressive Video Generation beyond Next Frames Prediction

• URL: http://arxiv.org/abs/2509.24081v1
• Date: Sun, 28 Sep 2025 21:37:53 GMT
• Title: Autoregressive Video Generation beyond Next Frames Prediction
• Authors: Sucheng Ren, Chen Chen, Zhenbang Wang, Liangchen Song, Xiangxin Zhu, Alan Yuille, Yinfei Yang, Jiasen Lu,
• Abstract summary: VideoAR is a unified framework that supports a spectrum of prediction units.<n>We find that cube-based prediction consistently delivers superior quality, speed and temporal coherence.
• Score: 30.652962125159707
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autoregressive models for video generation typically operate frame-by-frame, extending next-token prediction from language to video's temporal dimension. We question that unlike word as token is universally agreed in language if frame is a appropriate prediction unit? To address this, we present VideoAR, a unified framework that supports a spectrum of prediction units including full frames, key-detail frames, multiscale refinements, and spatiotemporal cubes. Among these designs, we find model video generation using \textit{spatiotemporal} cubes as prediction units, which allows autoregressive models to operate across both spatial and temporal dimensions simultaneously. This approach eliminates the assumption that frames are the natural atomic units for video autoregression. We evaluate VideoAR across diverse prediction strategies, finding that cube-based prediction consistently delivers superior quality, speed, and temporal coherence. By removing the frame-by-frame constraint, our video generator surpasses state-of-the-art baselines on VBench while achieving faster inference and enabling seamless scaling to minute-long sequences. We hope this work will motivate rethinking sequence decomposition in video and other spatiotemporal domains.

Related papers

• FRAME: Pre-Training Video Feature Representations via Anticipation and Memory [55.046881477209695]
  FRAME is a self-supervised video frame encoder tailored for dense video understanding.<n>It learns to predict current and future DINO patch features from past and present RGB frames.<n>It consistently outperforms image encoders and existing self-supervised video models.
  arXiv  Detail & Related papers  (2025-06-05T19:44:47Z)
• ViD-GPT: Introducing GPT-style Autoregressive Generation in Video Diffusion Models [66.84478240757038]
  A majority of video diffusion models (VDMs) generate long videos in an autoregressive manner, i.e., generating subsequent clips conditioned on last frames of previous clip. We introduce causal (i.e., unidirectional) generation into VDMs, and use past frames as prompt to generate future frames. Our ViD-GPT achieves state-of-the-art performance both quantitatively and qualitatively on long video generation.
  arXiv  Detail & Related papers  (2024-06-16T15:37:22Z)
• Predicting Long-horizon Futures by Conditioning on Geometry and Time [49.86180975196375]
  We explore the task of generating future sensor observations conditioned on the past. We leverage the large-scale pretraining of image diffusion models which can handle multi-modality. We create a benchmark for video prediction on a diverse set of videos spanning indoor and outdoor scenes.
  arXiv  Detail & Related papers  (2024-04-17T16:56:31Z)
• STDiff: Spatio-temporal Diffusion for Continuous Stochastic Video Prediction [20.701792842768747]
  We propose a novel video prediction model, which has infinite-dimensional latent variables over the temporal domain. Our model is able to achieve temporal continuous prediction, i.e., predicting in an unsupervised way, with an arbitrarily high frame rate.
  arXiv  Detail & Related papers  (2023-12-11T16:12:43Z)
• Motion and Context-Aware Audio-Visual Conditioned Video Prediction [58.9467115916639]
  We decouple the audio-visual conditioned video prediction into motion and appearance modeling. The multimodal motion estimation predicts future optical flow based on the audio-motion correlation. We propose context-aware refinement to address the diminishing of the global appearance context.
  arXiv  Detail & Related papers  (2022-12-09T05:57:46Z)
• Temporally Consistent Transformers for Video Generation [80.45230642225913]
  To generate accurate videos, algorithms have to understand the spatial and temporal dependencies in the world. No established benchmarks on complex data exist for rigorously evaluating video generation with long temporal dependencies. We introduce the Temporally Consistent Transformer (TECO), a generative model that substantially improves long-term consistency while also reducing sampling time.
  arXiv  Detail & Related papers  (2022-10-05T17:15:10Z)
• Optimizing Video Prediction via Video Frame Interpolation [53.16726447796844]
  We present a new optimization framework for video prediction via video frame, inspired by photo-realistic results of video framescapes. Our framework is based on optimization with a pretrained differentiable video frame module without the need for a training dataset. Our approach outperforms other video prediction methods that require a large amount of training data or extra semantic information.
  arXiv  Detail & Related papers  (2022-06-27T17:03:46Z)
• Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation [14.631523634811392]
  Masked Conditional Video Diffusion (MCVD) is a general-purpose framework for video prediction. We train the model in a manner where we randomly and independently mask all the past frames or all the future frames. Our approach yields SOTA results across standard video prediction benchmarks, with computation times measured in 1-12 days.
  arXiv  Detail & Related papers  (2022-05-19T20:58:05Z)
• Video Prediction at Multiple Scales with Hierarchical Recurrent Networks [24.536256844130996]
  We propose a novel video prediction model able to forecast future possible outcomes of different levels of granularity simultaneously. By combining spatial and temporal downsampling, MSPred is able to efficiently predict abstract representations over long time horizons. In our experiments, we demonstrate that our proposed model accurately predicts future video frames as well as other representations on various scenarios.
  arXiv  Detail & Related papers  (2022-03-17T13:08:28Z)
• Local Frequency Domain Transformer Networks for Video Prediction [24.126513851779936]
  Video prediction is of interest not only in anticipating visual changes in the real world but has, above all, emerged as an unsupervised learning rule. This paper proposes a fully differentiable building block that can perform all of those tasks separately while maintaining interpretability.
  arXiv  Detail & Related papers  (2021-05-10T19:48:42Z)
• Revisiting Hierarchical Approach for Persistent Long-Term Video Prediction [55.4498466252522]
  We set a new standard of video prediction with orders of magnitude longer prediction time than existing approaches. Our method predicts future frames by first estimating a sequence of semantic structures and subsequently translating the structures to pixels by video-to-video translation. We evaluate our method on three challenging datasets involving car driving and human dancing, and demonstrate that it can generate complicated scene structures and motions over a very long time horizon.
  arXiv  Detail & Related papers  (2021-04-14T08:39:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.