paper-with-me

Papers

A Survey on Vision Autoregressive Model

2024-11-13 · Kai Jiang, Jiaxing Huang

Autoregressive models have demonstrated great performance in natural language processing (NLP) with impressive scalability, adaptability and generalizability. Inspired by their notable success in NLP field, autoregressive models have been intensively investigated recently for computer vision, which perform next-token predictions by representing visual data as visual tokens and enables autoregressive modelling for a wide range of vision tasks, ranging from visual generation and visual understanding to the very recent multimodal generation that unifies visual generation and understanding with a single autoregressive model. This paper provides a systematic review of vision autoregressive models, including the development of a taxonomy of existing methods and highlighting their major contributions, strengths, and limitations, covering various vision tasks such as image generation, video generation, image editing, motion generation, medical image analysis, 3D generation, robotic manipulation, unified multimodal generation, etc. Besides, we investigate and analyze the latest advancements in autoregressive models, including thorough benchmarking and discussion of existing methods across various evaluation datasets. Finally, we outline key challenges and promising directions for future research, offering a roadmap to guide further advancements in vision autoregressive models.

📄 PDF Abstract BibTeX arXiv:2411.08666

Code (0)

등록된 구현이 없습니다.

Tasks

3D GenerationBenchmarkingImage GenerationMedical Image AnalysismodelMotion Generationmultimodal generationSurveyVideo Generation

Similar Papers 제목 키워드 기반

Autoregressive Models in Vision: A Survey

2024-11-08 · Jing Xiong, Gongye Liu, Lun Huang, Chengyue Wu 외

Autoregressive modeling has been a huge success in the field of natural language processing (NLP). Recently, autoregressive models have emerged as a significant area of focus in computer vision, where they excel in produ…

3D GenerationImage GenerationSurveyVideo Generation

Towards Unifying Understanding and Generation in the Era of Vision Foundation Models: A Survey from the Autoregression Perspective

2024-10-29 · Shenghao Xie, Wenqiang Zu, Mingyang Zhao, Duo Su 외

Autoregression in large language models (LLMs) has shown impressive scalability by unifying all language tasks into the next token prediction paradigm. Recently, there is a growing interest in extending this success to v…

Survey

Discrete Diffusion in Large Language and Multimodal Models: A Survey

2025-06-16 · Runpeng Yu, Qi Li, Xinchao Wang

In this work, we provide a systematic survey of Discrete Diffusion Language Models (dLLMs) and Discrete Diffusion Multimodal Language Models (dMLLMs). Unlike autoregressive (AR) models, dLLMs and dMLLMs adopt a multi-tok…

Denoising

A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyond

2022-04-20 · Yisheng Xiao, Lijun Wu, Junliang Guo, Juntao Li 외

Non-autoregressive (NAR) generation, which is first proposed in neural machine translation (NMT) to speed up inference, has attracted much attention in both machine learning and natural language processing communities. W…

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Dialogue GenerationGrammatical Error Correction+11

Harnessing Vision Models for Time Series Analysis: A Survey

2025-02-13 · Jingchao Ni, Ziming Zhao, ChengAo Shen, Hanghang Tong 외

Time series analysis has witnessed the inspiring development from traditional autoregressive models, deep learning models, to recent Transformers and Large Language Models (LLMs). Efforts in leveraging vision models for …

SurveyTime SeriesTime Series Analysis