April 4, 2024, 4:45 a.m. | Keyu Tian, Yi Jiang, Zehuan Yuan, Bingyue Peng, Liwei Wang

cs.CV updates on arXiv.org arxiv.org

arXiv:2404.02905v1 Announce Type: new
Abstract: We present Visual AutoRegressive modeling (VAR), a new generation paradigm that redefines the autoregressive learning on images as coarse-to-fine "next-scale prediction" or "next-resolution prediction", diverging from the standard raster-scan "next-token prediction". This simple, intuitive methodology allows autoregressive (AR) transformers to learn visual distributions fast and generalize well: VAR, for the first time, makes AR models surpass diffusion transformers in image generation. On ImageNet 256x256 benchmark, VAR significantly improve AR baseline by improving Frechet inception distance …

abstract arxiv cs.ai cs.cv image image generation images learn methodology modeling next paradigm prediction resolution scalable scale simple standard token transformers type via visual

Data Scientist (m/f/x/d)

@ Symanto Research GmbH & Co. KG | Spain, Germany

Senior DevOps/MLOps

@ Global Relay | Vancouver, British Columbia, Canada

Senior Statistical Programmer for Clinical Development

@ Novo Nordisk | Aalborg, North Denmark Region, DK

Associate, Data Analysis

@ JLL | USA-CLIENT Boulder CO-Google

AI Compiler Engineer, Model Optimization, Quantization & Framework

@ Renesas Electronics | Duesseldorf, Germany

Lead AI Security Researcher

@ Grammarly | United States; Hybrid