English
Related papers

Related papers: GigaTok: Scaling Visual Tokenizers to 3 Billion Pa…

200 papers

Unified speech foundation models require a holistic tokenization space that is both learnable by language models and decodable into high-quality waveforms. Existing speech tokenizers, however, often fail to satisfy these requirements…

Sound · Computer Science 2026-05-29 Bohan Li , Shi Lian , Hankun Wang , Yiwei Guo , Yu Xi , Zhihan Li , Da Zheng , Colin Zhang , Kai Yu

Autoregressive (AR) models for image generation typically adopt a two-stage paradigm of vector quantization and raster-scan ``next-token prediction", inspired by its great success in language modeling. However, due to the huge modality gap,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-19 Hu Yu , Hao Luo , Hangjie Yuan , Yu Rong , Jie Huang , Feng Zhao

This paper investigates the fundamental relationship between model capacity and the minimal number of visual tokens required to preserve image semantics. Inspired by the Minimum Description Length principle, we reinterpret image tokens as…

Computer Vision and Pattern Recognition · Computer Science 2025-11-26 Shawn Young , Xingyu Zeng , Lijian Xu

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

We propose TC-AE, a ViT-based architecture for deep compression autoencoders. Existing methods commonly increase the channel number of latent representations to maintain reconstruction quality under high compression ratios. However, this…

Computer Vision and Pattern Recognition · Computer Science 2026-04-09 Teng Li , Ziyuan Huang , Cong Chen , Yangfu Li , Yuanhuiyi Lyu , Dandan Zheng , Chunhua Shen , Jun Zhang

Despite the promising progress of recent autoregressive models in text-to-image (T2I) generation, their ability to handle multi-attribute and ambiguous prompts remains limited. To address these limitations, existing works have applied…

Computer Vision and Pattern Recognition · Computer Science 2025-08-27 Yaqi Li , Peng Chen , Mingyang Han , Pi Bu , Haoxiang Shi , Runzhou Zhao , Yang Yao , Xuan Zhang , Jun Song , Bo Zheng

Latent diffusion models with Transformer architectures excel at generating high-fidelity images. However, recent studies reveal an optimization dilemma in this two-stage design: while increasing the per-token feature dimension in visual…

Computer Vision and Pattern Recognition · Computer Science 2025-03-11 Jingfeng Yao , Bin Yang , Xinggang Wang

Existing vector quantization (VQ) based autoregressive models follow a two-stage generation paradigm that first learns a codebook to encode images as discrete codes, and then completes generation based on the learned codebook. However, they…

Computer Vision and Pattern Recognition · Computer Science 2023-05-22 Mengqi Huang , Zhendong Mao , Zhuowei Chen , Yongdong Zhang

This paper challenges the dominance of continuous pipelines in visual generation. We systematically investigate the performance gap between discrete and continuous methods. Contrary to the belief that discrete tokenizers are intrinsically…

Computer Vision and Pattern Recognition · Computer Science 2026-02-10 Qihang Yu , Qihao Liu , Ju He , Xinyang Zhang , Yang Liu , Liang-Chieh Chen , Xi Chen

Recently, autoregressive (AR) image models have demonstrated remarkable generative capabilities, positioning themselves as a compelling alternative to diffusion models. However, their sequential nature leads to long inference times,…

Computer Vision and Pattern Recognition · Computer Science 2025-08-12 Junhyuk So , Juncheol Shin , Hyunho Kook , Eunhyeok Park

Recent advancements in vision-language models (VLMs) have improved performance by increasing the number of visual tokens, which are often significantly longer than text tokens. However, we observe that most real-world scenarios do not…

Computer Vision and Pattern Recognition · Computer Science 2025-07-18 Senqiao Yang , Junyi Li , Xin Lai , Bei Yu , Hengshuang Zhao , Jiaya Jia

We introduce UniToken, an auto-regressive generation model that encodes visual inputs through a combination of discrete and continuous representations, enabling seamless integration of unified visual understanding and image generation…

Computer Vision and Pattern Recognition · Computer Science 2025-04-08 Yang Jiao , Haibo Qiu , Zequn Jie , Shaoxiang Chen , Jingjing Chen , Lin Ma , Yu-Gang Jiang

In this paper we tackle Image Super Resolution (ISR), using recent advances in Visual Auto-Regressive (VAR) modeling. VAR iteratively estimates the residual in latent space between gradually increasing image scales, a process referred to as…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Enrique Sanchez , Isma Hadji , Adrian Bulat , Christos Tzelepis , Brais Martinez , Georgios Tzimiropoulos

Generative Adversarial Networks (GANs) have achieved state-of-the-art performance for several image generation and manipulation tasks. Different works have improved the limited understanding of the latent space of GANs by embedding images…

Computer Vision and Pattern Recognition · Computer Science 2020-10-22 Christian Bartz , Joseph Bethge , Haojin Yang , Christoph Meinel

Tokenization is a key component of autoregressive (AR) generative models, converting raw data into more manageable units for modeling. Commonly, tokens describe local information, such as regions of pixels in images or word pieces in text,…

Computer Vision and Pattern Recognition · Computer Science 2026-04-20 Zhitong Gao , Parham Rezaei , Ali Cy , Mingqiao Ye , Nataša Jovanović , Jesse Allardice , Afshin Dehghan , Amir Zamir , Roman Bachmann , Oğuzhan Fatih Kar

Recent advances in autoregressive (AR) models with continuous tokens for image generation show promising results by eliminating the need for discrete tokenization. However, these models face efficiency challenges due to their sequential…

Computer Vision and Pattern Recognition · Computer Science 2024-12-20 Zhihang Yuan , Yuzhang Shang , Hanling Zhang , Tongcheng Fang , Rui Xie , Bingxin Xu , Yan Yan , Shengen Yan , Guohao Dai , Yu Wang

The successful training of deep neural networks requires addressing challenges such as overfitting, numerical instabilities leading to divergence, and increasing variance in the residual stream. A common solution is to apply regularization…

Machine Learning · Computer Science 2025-11-20 Jörg K. H. Franke , Urs Spiegelhalter , Marianna Nezhurina , Jenia Jitsev , Frank Hutter , Michael Hefenbrock

Recently, token-based generation have demonstrated their effectiveness in image synthesis. As a representative example, non-autoregressive Transformers (NATs) can generate decent-quality images in a few steps. NATs perform generation in a…

Computer Vision and Pattern Recognition · Computer Science 2024-11-12 Zanlin Ni , Yulin Wang , Renping Zhou , Yizeng Han , Jiayi Guo , Zhiyuan Liu , Yuan Yao , Gao Huang

This paper proposes a fundamentally new paradigm for image generation through set-based tokenization and distribution modeling. Unlike conventional methods that serialize images into fixed-position latent codes with a uniform compression…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Zigang Geng , Mengde Xu , Han Hu , Shuyang Gu

The interest of the machine learning community in image synthesis has grown significantly in recent years, with the introduction of a wide range of deep generative models and means for training them. In this work, we propose a general…

Computer Vision and Pattern Recognition · Computer Science 2023-02-02 Roy Ganz , Michael Elad