Visual Autoregressive Models

Follow this topic Ask about this topic

Visual autoregressive models represent images or videos as discrete tokens and predict them step by step, often moving from coarse structure to finer detail. Common approaches use hierarchical tokenizers and transformer decoders, with methods such as next-scale prediction, flexible token ordering, and parallel or speculative decoding. They are used for image and video generation as well as editing, super-resolution, reconstruction, and visual classification, with efficiency improvements aimed at reducing decoding time and memory use. A central challenge is balancing speed and controllability with global coherence and fine detail, since errors in early predictions can propagate through later stages.

Latest papers

56 papers2 papers in the last four weeks, against 2 the four weeks before. 0.0% of all new papers.

Next-Acceleration-Scale Prediction for Autoregressive MRI Reconstruction
May 19, 2026Yilmaz Korkmaz, Vishal M. PatelVisual Autoregressive Models Computational Imaging
Johns Hopkins University, Baltimore MD 21218, USA
Hierarchical Image Tokenization for Multi-Scale Image Super Resolution
May 14, 2026Isma Hadji, Enrique Sanchez, Adrian Bulat +2Image Tokenization Visual Autoregressive Models
Samsung AI Center Cambridge, UK · Technical University of Iasi, Romania · Queen Mary University of London, UK
HeatKV: Head-tuned KV-cache Compression for Visual Autoregressive Modeling
May 14, 2026Jonathan Cederlund, Axel Berg, William Isaksson +3KV Caching Visual Autoregressive Models
Dept. of Automatic Control, Lund University · Arm
ExtraVAR: Stage-Aware RoPE Remapping for Resolution Extrapolation in Visual Autoregressive Models
May 11, 2026Feihong Yan, Shaoyu Liu, Haixuan Wang +4Rotary Positional Embeddings Visual Autoregressive Models
Beijing Institute of Technology · Xidian University · Northeastern University at Qinhuangdao +3
Taming the Entropy Cliff: Variable Codebook Size Quantization for Autoregressive Visual Generation
May 7, 2026Bowen Zheng, Weijian Luo, Guang Yang +2Visual Autoregressive Models Vector Quantization
The Chinese University of Hong Kong, Shenzhen · hi-Lab, Xiaohongshu Inc
Autoregressive Visual Generation Needs a Prologue
May 7, 2026Bowen Zheng, Weijian Luo, Guang Yang +2Visual Autoregressive Models Autoregressive Image Generation
The Chinese University of Hong Kong, Shenzhen · hi-Lab, Xiaohongshu Inc
Visual Implicit Autoregressive Modeling
May 2, 2026Pengfei Jiang, Jixiang Luo, Luxi Lin +2Visual Autoregressive Models Autoregressive Image Generation
Institute of Artificial Intelligence (TeleAI), China Telecom · Xiamen University
StyleVAR: Controllable Image Style Transfer via Visual Autoregressive Modeling
Apr 22, 2026Liqi Jing, Dingming Zhang, Peinian Li +3Visual Autoregressive Models Image Style Transfer
Duke University · University of Southern California · Xidian University
Depth Adaptive Efficient Visual Autoregressive Modeling
Apr 19, 2026Chunliang Li, Tianze Cao, Sanyuan ZhaoEfficient Transformer Inference Visual Autoregressive Models
Beijing Institute of Technology · Beijing Institute of Technology, Zhuhai
Prompt-Guided Image Editing with Masked Logit Nudging in Visual Autoregressive Models
Apr 16, 2026Amir El-Ghoussani, Marc Hölle, Gustavo Carneiro +1Text-Guided Image Editing Visual Autoregressive Models
Friedrich-Alexander-Universität Erlangen-Nürnberg, Germany · University of Surrey, United Kingdom
RAE-AR: Taming Autoregressive Models with Representation Autoencoders
Apr 2, 2026Hu Yu, Hang Xu, Jie Huang +4Exposure Bias Autoregressive Image Generation
University of Science and Technology of China · JD Explore Academy · The University of Hong Kong
Rethinking Structure Preservation in Text-Guided Image Editing with Visual Autoregressive Models
Mar 30, 2026Tao Xia, Jiawei Liu, Yukun Zhang +3Text-Guided Image Editing Image Editing
Beijing Institute of Technology, Beijing, China · Shenyang Institute of Automation, CAS, Shenyang, China · Meitu Inc, MTLab, Beijing, China
Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting
Mar 30, 2026Zhen Zou, Xiaoxiao Ma, Mingde Yao +3Autoregressive Diffusion Visual Autoregressive Models
University of Science and Technology of China · The Chinese University of Hong Kong, MMLAB · JD Explore Academy +1
Revisiting Autoregressive Models for Generative Image Classification
Mar 19, 2026Ilia Sudakov, Artem Babenko, Dmitry BaranchukVisual Autoregressive Models Image Classification
1HSE University · 2Yandex Research
Fractal Autoregressive Depth Estimation with Continuous Token Diffusion
Mar 16, 2026Jinchang Zhang, Xinrou Kang, Guoyu LuDepth Estimation Monocular Depth Estimation
Intelligent Vision and Sensing (IVS) Lab at SUNY Binghamton University
EVATok: Adaptive Length Video Tokenization for Efficient Visual Autoregressive Generation
Mar 12, 2026Tianwei Xiong, Jun Hao Liew, Zilong Huang +3Video Token Compression Visual Token Compression
The University of Hong Kong · ByteDance Seed
Separators in Enhancing Autoregressive Pretraining for Vision Mamba
Mar 4, 2026Hanpeng Liu, Zidan Wang, Shuoxi Zhang +2Visual Autoregressive Models Visual SSMs
Huazhong University of Science and Technology
StepVAR: Structure-Texture Guided Pruning for Visual Autoregressive Models
Mar 2, 2026Keli Liu, Zhendong Wang, Wengang Zhou +1Inference Acceleration Visual Autoregressive Models
University of Science and Technology of China
AlignVAR: Towards Globally Consistent Visual Autoregression for Image Super-Resolution
Feb 28, 2026Cencen Liu, Dongyang Zhang, Wen Yin +6Autoregressive Image Super-Resolution Image Super-Resolution
University of Electronic Science and Technology of China · Ubiquitous Intelligence and Trusted Services Key Laboratory of Sichuan Province
ToProVAR: Efficient Visual Autoregressive Modeling via Tri-Dimensional Entropy-Aware Semantic Analysis and Sparsity Optimization
Feb 26, 2026Jiayu Chen, Ruoyu Lin, Zihao Zheng +4Attention Entropy Visual Autoregressive Models
School of Computer Science, Peking University · School of Electronics Engineering and Computer Science, Peking University · National Key Laboratory for Multimedia Information Processing, Peking University
Autoregressive Visual Decoding from EEG Signals
Feb 26, 2026Sicheng Dai, Hongwang Xiao, Shan Yu +1EEG-Based Visual Decoding Visual Autoregressive Models
Institute of Automation, Chinese Academy of Sciences · School of Artifcial Intelligence, University of Chinese Academy of Sciences · State Key Laboratory of Brain Cognition and Brain-inspired Intelligence Technology +2
Scalable next-scale autoregression for medical image generation across anatomical regions
Feb 16, 2026Zhicheng He, Yunpeng Zhao, Junde Wu +7Medical Imaging Foundation Models Healthcare
National University of Singapore · University of Oxford · Zhejiang University +1
Spanning Tree Autoregressive Visual Generation
Nov 21, 2025Sangkyu Lee, Changho Lee, Janghoon Han +6Visual Autoregressive Models Autoregressive Image Generation
Yonsei University, Seoul, Korea · LG AI Research, Seoul, Korea · Korea Institute of Science and Technology, Seoul, Korea +2
ScalingAR: Scaling Confidence for Autoregressive Image Generation
Sep 30, 2025Harold Haodong Chen, Xianfeng Wu, Wen-Jie Shu +4Language Model Decoding Visual Autoregressive Models
HKUST(GZ) · UNC-Chapel Hill · ZODA +3
Rethinking Visual Autoregressive Sampling with Information-Grounding Guidance
Sep 28, 2025Ky Dan Nguyen, Hoang Lam Tran, Anh-Dung Dinh +4Visual Autoregressive Models Conditional Image Generation
The University of Sydney, Sydney, New South Wales, Australia · The University of Western Australia, Perth, Western Australia, Australia
Continuous Speculative Decoding for Autoregressive Image Generation
Nov 18, 2024Zili Wang, Zheng Zhang, Kun Ding +3Visual Autoregressive Models Speculative Decoding
School of Artificial Intelligence, University of Chinese Academy of Sciences, China · MAIS, Institute of Automation, Chinese Academy of Sciences, China · JD.COM Inc, China +1

May 19, 2026J/K move · Enter open · S save

Next-Acceleration-Scale Prediction for Autoregressive MRI Reconstruction

Yilmaz Korkmaz, Vishal M. Patel

Johns Hopkins University, Baltimore MD 21218, USA

Visual Autoregressive Models Computational Imaging Accelerated MRI Reconstruction Learning Using Privileged Information

Open paper AskPDF arXiv

MRI reconstruction is an inherently ill-posed inverse problem, since incomplete measurements admit many plausible solutions. This ambiguity becomes more severe under high acceleration, where pixel-domain continuous predictors tend to average over feasible reconstructions and suppress high-frequency anatomy. We address this limitation by moving reconstruction to discrete multi-scale latent space and posing it as autoregressive next-acceleration-scale prediction. Leveraging discrete priors proven effective in visual autoregressive modeling, our method restricts the solution to compact sequences of codebook tokens, enabling sharp reconstructions even from extremely sparse measurements. This discrete autoregressive formulation also aligns naturally with modern large language model post-training techniques. Building on this observation, we introduce on-policy privileged information distillation for visual autoregressive modeling, where a teacher is provided training only privileged context that is unavailable at inference, in our case fully sampled acquisitions, and supervises a student trained on its own rollouts, leading to consistent reconstruction gains. Through extensive experiments on the fastMRI benchmark, we show that our approach delivers improved reconstruction performance across diverse sampling patterns under extreme undersampling. Project website is here.