English
Related papers

Related papers: Randomized Autoregressive Visual Generation

200 papers

In autoregressive (AR) image generation, visual tokenizers compress images into compact discrete latent tokens, enabling efficient training of downstream autoregressive models for visual generation via next-token prediction. While scaling…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Tianwei Xiong , Jun Hao Liew , Zilong Huang , Jiashi Feng , Xihui Liu

Inspired by the success of self-supervised autoregressive representation learning in natural language (GPT and its variants), and advances in recent visual architecture design with Vision Transformers (ViTs), in this paper, we explore the…

Computer Vision and Pattern Recognition · Computer Science 2022-10-27 Tianyu Hua , Yonglong Tian , Sucheng Ren , Michalis Raptis , Hang Zhao , Leonid Sigal

Autoregressive language modeling (ALM) have been successfully used in self-supervised pre-training in Natural language processing (NLP). However, this paradigm has not achieved comparable results with other self-supervised approach in…

Computer Vision and Pattern Recognition · Computer Science 2022-12-06 Yu Qi , Fan Yang , Yousong Zhu , Yufei Liu , Liwei Wu , Rui Zhao , Wei Li

Most recent real-world image super-resolution (Real-ISR) methods employ pre-trained text-to-image (T2I) diffusion models to synthesize the high-quality image either from random Gaussian noise, which yields realistic results but is slow due…

Computer Vision and Pattern Recognition · Computer Science 2025-10-02 Xiangtao Kong , Rongyuan Wu , Shuaizheng Liu , Lingchen Sun , Lei Zhang

This paper presents DetailFlow, a coarse-to-fine 1D autoregressive (AR) image generation method that models images through a novel next-detail prediction strategy. By learning a resolution-aware token sequence supervised with progressively…

Computer Vision and Pattern Recognition · Computer Science 2025-11-12 Yiheng Liu , Liao Qu , Huichao Zhang , Xu Wang , Yi Jiang , Yiming Gao , Hu Ye , Xian Li , Shuai Wang , Daniel K. Du , Fangmin Chen , Zehuan Yuan , Xinglong Wu

Visual Autoregressive (VAR) models have emerged as a powerful paradigm for image synthesis by performing hierarchical next-scale prediction. However, VAR models are inherently prone to cascading error propagation, where subtle coarse-scale…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Ligong Bi , Tao Huang , Jianyuan Guo , Chang Xu

Recent advances in auto-regressive transformers have revolutionized generative modeling across different domains, from language processing to visual generation, demonstrating remarkable capabilities. However, applying these advances to 3D…

Computer Vision and Pattern Recognition · Computer Science 2025-04-22 Jinnan Chen , Lingting Zhu , Zeyu Hu , Shengju Qian , Yugang Chen , Xin Wang , Gim Hee Lee

Essential to visual generation is efficient modeling of visual data priors. Conventional next-token prediction methods define the process as learning the conditional probability distribution of successive tokens. Recently, next-scale…

Computer Vision and Pattern Recognition · Computer Science 2026-02-03 Jinhua Zhang , Wei Long , Minghao Han , Weiyi You , Shuhang Gu

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…

Computer Vision and Pattern Recognition · Computer Science 2025-09-30 Sucheng Ren , Chen Chen , Zhenbang Wang , Liangchen Song , Xiangxin Zhu , Alan Yuille , Yinfei Yang , Jiasen Lu

We describe a method to construct directed networks from multivariate time series which has several advantages over the widely accepted methods. This method is based on an information theoretic reduction of linear (auto-regressive) models.…

Data Analysis, Statistics and Probability · Physics 2018-08-13 Toshihiro Tanizawa , Tomomichi Nakamura , Fumihiko Taya , Michael Small

Autoregressive (AR) transformers have emerged as a powerful paradigm for visual generation, largely due to their scalability, computational efficiency and unified architecture with language and vision. Among them, next scale prediction…

Computer Vision and Pattern Recognition · Computer Science 2025-09-29 Amandeep Kumar , Nithin Gopalakrishnan Nair , Vishal M. Patel

Diffusion language models hold the promise of fast parallel generation, while autoregressive (AR) models typically excel in quality due to their causal structure aligning naturally with language modeling. This raises a fundamental question:…

Computation and Language · Computer Science 2025-11-13 Jingyu Liu , Xin Dong , Zhifan Ye , Rishabh Mehta , Yonggan Fu , Vartika Singh , Jan Kautz , Ce Zhang , Pavlo Molchanov

Scaling visual generation models is essential for real-world content creation, yet requires substantial training and computational expenses. Alternatively, test-time scaling has garnered growing attention due to resource efficiency and…

Computer Vision and Pattern Recognition · Computer Science 2025-10-13 Zhekai Chen , Ruihang Chu , Yukang Chen , Shiwei Zhang , Yujie Wei , Yingya Zhang , Xihui Liu

Visual Autoregressive (VAR) models have recently garnered significant attention for their innovative next-scale prediction paradigm, offering notable advantages in both inference efficiency and image quality compared to traditional…

Computer Vision and Pattern Recognition · Computer Science 2025-11-24 Tong Wang , Guanyu Yang , Nian Liu , Kai Wang , Yaxing Wang , Abdelrahman M Shaker , Salman Khan , Fahad Shahbaz Khan , Senmao Li

Flexible image tokenizers aim to represent an image using an ordered 1D variable-length token sequence. This flexible tokenization is typically achieved through nested dropout, where a portion of trailing tokens is randomly truncated during…

Computer Vision and Pattern Recognition · Computer Science 2026-01-06 Zixuan Fu , Lanqing Guo , Chong Wang , Binbin Song , Ding Liu , Bihan Wen

Recent advancements in video generation have demonstrated the potential of using video diffusion models as world models, with autoregressive generation of infinitely long videos through masked conditioning. However, such models, usually…

Computer Vision and Pattern Recognition · Computer Science 2025-11-18 Taiye Chen , Zihan Ding , Anjian Li , Christina Zhang , Zeqi Xiao , Yisen Wang , Chi Jin

Autoregressive models are widely used for tasks such as image and audio generation. The sampling process of these models, however, does not allow interruptions and cannot adapt to real-time computational resources. This challenge impedes…

Machine Learning · Computer Science 2021-02-24 Yilun Xu , Yang Song , Sahaj Garg , Linyuan Gong , Rui Shu , Aditya Grover , Stefano Ermon

The latent space of generative modeling is long dominated by the VAE encoder. The latents from the pretrained representation encoders (e.g., DINO, SigLIP, MAE) are previously considered inappropriate for generative modeling. Recently, RAE…

Artificial Intelligence · Computer Science 2026-04-03 Hu Yu , Hang Xu , Jie Huang , Zeyue Xue , Haoyang Huang , Nan Duan , Feng Zhao

We introduce LlamaGen, a new family of image generation models that apply original ``next-token prediction'' paradigm of large language models to visual generation domain. It is an affirmative answer to whether vanilla autoregressive…

Computer Vision and Pattern Recognition · Computer Science 2024-06-11 Peize Sun , Yi Jiang , Shoufa Chen , Shilong Zhang , Bingyue Peng , Ping Luo , Zehuan Yuan

This paper presents a novel approach that enables autoregressive video generation with high efficiency. We propose to reformulate the video generation problem as a non-quantized autoregressive modeling of temporal frame-by-frame prediction…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Haoge Deng , Ting Pan , Haiwen Diao , Zhengxiong Luo , Yufeng Cui , Huchuan Lu , Shiguang Shan , Yonggang Qi , Xinlong Wang