X-Omni：强化学习让离散自回归图像生成模型再度崛起
X-Omni: Reinforcement Learning Makes Discrete Autoregressive Image Generative Models Great Again
AI总结：
针对离散自回归图像生成模型保真度低、指令遵循差等问题，本研究提出X-Omni框架，借助强化学习提升生成质量，实现图像与语言生成的无缝融合，在7B语言模型规模下取得图像生成任务SOTA性能。
摘要：
学界已开展大量研究，旨在将“下一词元预测”范式拓展至视觉内容领域，以构建一种可同时用于图像生成与理解的统一方法。然而，通过离散词元的自回归建模生成图像的尝试，一直受视觉保真度低、输出失真以及渲染复杂细节时无法遵循复杂指令等问题困扰。这些缺陷很可能源于自回归推理过程中的累积误差，或是离散化过程中产生的信息损失。或许正是由于这一挑战，近期研究越来越倾向于将采用扩散目标的图像生成与采用自回归目标的语言生成进行联合训练，逐渐偏离了统一建模路径。本研究证明，强化学习能够有效减少伪影，大幅提升离散自回归建模方法的生成质量，从而实现图像生成与语言生成的无缝融合。我们提出的框架X-Omni由三部分组成：语义图像分词器、可同时处理语言与图像的统一自回归模型，以及用于图像生成的离线扩散解码器。X-Omni使用7B语言模型，在图像生成任务上取得了当前最优性能，生成的图像兼具高美学质量，同时展现出强大的指令遵循能力与长文本渲染能力。
英文摘要：
Numerous efforts have been made to extend the ``next token prediction'' paradigm to visual contents, aiming to create a unified approach for both image generation and understanding. Nevertheless, attempts to generate images through autoregressive modeling with discrete tokens have been plagued by issues such as low visual fidelity, distorted outputs, and failure to adhere to complex instructions when rendering intricate details. These shortcomings are likely attributed to cumulative errors during autoregressive inference or information loss incurred during the discretization process. Probably due to this challenge, recent research has increasingly shifted toward jointly training image generation with diffusion objectives and language generation with autoregressive objectives, moving away from unified modeling approaches. In this work, we demonstrate that reinforcement learning can effectively mitigate artifacts and largely enhance the generation quality of a discrete autoregressive modeling method, thereby enabling seamless integration of image and language generation. Our framework comprises a semantic image tokenizer, a unified autoregressive model for both language and images, and an offline diffusion decoder for image generation, termed X-Omni. X-Omni achieves state-of-the-art performance in image generation tasks using a 7B language model, producing images with high aesthetic quality while exhibiting strong capabilities in following instructions and rendering long texts.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
