Document detail
ID
oai:arXiv.org:2504.11455
Topic
Computer Science - Computer Vision...Author
Wang, Junke Tian, Zhi Wang, Xun Zhang, Xinyu Huang, Weilin Wu, Zuxuan Jiang, Yu-GangCategory
Computer Science
Year
2025
listing date
4/23/2025
Keywords
visual autoregressiveAbstract
This work presents SimpleAR, a vanilla autoregressive visual generation framework without complex architecure modifications.
Through careful exploration of training and inference optimization, we demonstrate that: 1) with only 0.5B parameters, our model can generate 1024x1024 resolution images with high fidelity, and achieve competitive results on challenging text-to-image benchmarks, e.g., 0.59 on GenEval and 79.66 on DPG; 2) both supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO) training could lead to significant improvements on generation aesthectics and prompt alignment; and 3) when optimized with inference acceleraton techniques like vLLM, the time for SimpleAR to generate an 1024x1024 image could be reduced to around 14 seconds.
By sharing these findings and open-sourcing the code, we hope to reveal the potential of autoregressive visual generation and encourage more participation in this research field.
Code is available at https://github.com/wdrink/SimpleAR.
;Comment: technical report, work in progress
Wang, Junke,Tian, Zhi,Wang, Xun,Zhang, Xinyu,Huang, Weilin,Wu, Zuxuan,Jiang, Yu-Gang, 2025, SimpleAR: Pushing the Frontier of Autoregressive Visual Generation through Pretraining, SFT, and RL
Behavioral photosensitivity of multi-color-blind medaka: enhanced response under ultraviolet light in the absence of short-wavelength-sensitive opsins
medaka luminance uv red opsins light omr
