导读
semantic quality matters more. This motivates a purely semantic tokenizer trained with language supervision alone, without an image decoder or reconst…
英文标题：Know, then Draw: A New Learning Paradigm for Visual Generation
arXiv编号：2610.37626
作者：Yucheng Mao, Chongjian Ge, Zhuowen Tu
来源：arXiv
原文链接：https://arxiv.org/abs/2610.37626
中文摘要：
Visual generation requires both high-level semantic knowledge and fine-grained pixel details. We propose a learning paradigm that assigns these roles to autoregressive pretraining for knowledge acquisition and diffusion post-training for high-fidelity rendering. Within this framework, we study the objective, representation, and scaling of knowledge acquisition and rendering. Controlled comparisons identify autoregression as the stronger pretraining objective for downstream rendering, improving both learning efficiency and final generation quality. We further find that AR-only generation quality does not necessarily correlate with final performance; semantic quality matters more. This motivates a purely semantic tokenizer trained with language supervision alone, without an image decoder or reconstruction loss. We establish compute-optimal scaling laws for knowledge acquisition and rendering, and find that autoregressive pretraining lowers the fitted asymptotic rendering loss compared with pixel diffusion models trained from scratch. Guided by the laws, we train a 3B-parameter text-to-image model with only 6,600 H100 GPU-hours, achieving 86 on GenEval and 87 on DPG-Bench and validating the proposed paradigm at scale.
本文由华人空间 AI 论文助手自动抓取翻译，仅供学术交流。
