English
Related papers

Related papers: Generation then Reconstruction: Accelerating Maske…

200 papers

Non-autoregressive generative transformers recently demonstrated impressive image generation performance, and orders of magnitude faster sampling than their autoregressive counterparts. However, optimal parallel sampling from the true joint…

Computer Vision and Pattern Recognition · Computer Science 2022-09-12 José Lezama , Huiwen Chang , Lu Jiang , Irfan Essa

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

Autoregressive (AR) models have shown great promise in image generation, yet they face a fundamental inefficiency stemming from their core component: a vast, unstructured vocabulary of visual tokens. This conventional approach treats tokens…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Lixuan He , Shikang Zheng , Linfeng Zhang

Recent studies have demonstrated the importance of high-quality visual representations in image generation and have highlighted the limitations of generative models in image understanding. As a generative paradigm originally designed for…

Computer Vision and Pattern Recognition · Computer Science 2025-09-19 Xiaoyu Yue , Zidong Wang , Yuqing Wang , Wenlong Zhang , Xihui Liu , Wanli Ouyang , Lei Bai , Luping Zhou

We introduce Autoregressive Retrieval Augmentation (AR-RAG), a novel paradigm that enhances image generation by autoregressively incorporating knearest neighbor retrievals at the patch level. Unlike prior methods that perform a single,…

Computer Vision and Pattern Recognition · Computer Science 2025-06-17 Jingyuan Qi , Zhiyang Xu , Qifan Wang , Lifu Huang

Convolutional autoregressive models have recently demonstrated state-of-the-art performance on a number of generation tasks. While fast, parallel training methods have been crucial for their success, generation is typically implemented in a…

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

Autoregressive (AR) visual generation has emerged as a powerful paradigm for image and multimodal synthesis, owing to its scalability and generality. However, existing AR image generation suffers from severe memory bottlenecks due to the…

Computer Vision and Pattern Recognition · Computer Science 2025-12-05 Ziran Qin , Youru Lv , Mingbao Lin , Zeren Zhang , Chanfan Gan , Tieyuan Chen , Weiyao Lin

Autoregressive (AR) language models generate text one token at a time, even when consecutive tokens are highly predictable given earlier context. We introduce MARS (Mask AutoRegreSsion), a lightweight fine-tuning method that teaches an…

Computation and Language · Computer Science 2026-04-09 Ziqi Jin , Lei Wang , Ziwei Luo , Aixin Sun

Feed-forward 3D reconstruction models based on Vision Transformers can directly estimate scene geometry and camera poses from a small set of input images, but scaling them to video inputs with hundreds or thousands of frames remains…

Computer Vision and Pattern Recognition · Computer Science 2026-05-20 Zecheng Tang , Jiaye Fu , Qiankun Gao , Haijie Li , Yanmin Wu , Jiaqi Zhang , Siwei Ma , Jian Zhang

Visual autoregressive models typically adhere to a raster-order ``next-token prediction" paradigm, which overlooks the spatial and temporal locality inherent in visual content. Specifically, visual tokens exhibit significantly stronger…

Computer Vision and Pattern Recognition · Computer Science 2025-03-17 Yefei He , Yuanyu He , Shaoxuan He , Feng Chen , Hong Zhou , Kaipeng Zhang , Bohan Zhuang

Autoregressive models have emerged as a powerful generative paradigm for visual generation. The current de-facto standard of next token prediction commonly operates over a single-scale sequence of dense image tokens, and is incapable of…

Computer Vision and Pattern Recognition · Computer Science 2025-05-27 Guangting Zheng , Yehao Li , Yingwei Pan , Jiajun Deng , Ting Yao , Yanyong Zhang , Tao Mei

Recent visual autoregressive (AR) models have shown promising capabilities in text-to-image generation, operating in a manner similar to large language models. While test-time computation scaling has brought remarkable success in enabling…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Joonhyung Park , Hyeongwon Jang , Joowon Kim , Eunho Yang

We propose Stratified Image Transformer(StraIT), a pure non-autoregressive(NAR) generative model that demonstrates superiority in high-quality image synthesis over existing autoregressive(AR) and diffusion models(DMs). In contrast to the…

Computer Vision and Pattern Recognition · Computer Science 2023-03-02 Shengju Qian , Huiwen Chang , Yuanzhen Li , Zizhao Zhang , Jiaya Jia , Han Zhang

Autoregressive visual generation has garnered increasing attention due to its scalability and compatibility with other modalities compared with diffusion models. Most existing methods construct visual sequences as spatial patches for…

Computer Vision and Pattern Recognition · Computer Science 2025-06-13 Yuanhui Huang , Weiliang Chen , Wenzhao Zheng , Yueqi Duan , Jie Zhou , Jiwen Lu

Text-to-Motion (T2M) generation aims to synthesize realistic and semantically aligned human motion sequences from natural language descriptions. However, current approaches face dual challenges: Generative models (e.g., diffusion models)…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Zhengdao Li , Siheng Wang , Zeyu Zhang , Hao Tang

Autoregressive language models like GPT aim to predict next tokens, while autoencoding models such as BERT are trained on tasks such as predicting masked tokens. We train a decoder-only architecture for predicting the second to last token…

Computation and Language · Computer Science 2025-02-17 Johannes Schneider

Existing autoregressive (AR) image generative models use a token-by-token generation schema. That is, they predict a per-token probability distribution and sample the next token from that distribution. The main challenge is how to model the…

Computer Vision and Pattern Recognition · Computer Science 2025-03-05 Qinyu Zhao , Stephen Gould , Liang Zheng

Generative transformers have experienced rapid popularity growth in the computer vision community in synthesizing high-fidelity and high-resolution images. The best generative transformer models so far, however, still treat an image naively…

Computer Vision and Pattern Recognition · Computer Science 2022-02-10 Huiwen Chang , Han Zhang , Lu Jiang , Ce Liu , William T. Freeman

Autoregressive language models are the currently dominant paradigm for text generation, but they have some fundamental limitations that cannot be remedied by scale-for example inherently sequential and unidirectional generation. While…

Computation and Language · Computer Science 2024-08-01 Yuchen Li , Alexandre Kirchmeyer , Aashay Mehta , Yilong Qin , Boris Dadachev , Kishore Papineni , Sanjiv Kumar , Andrej Risteski