语义上下文很重要：改进自回归模型的条件控制
Semantic Context Matters: Improving Conditioning for Autoregressive Models
把语义条件从解码阶段的稀疏视觉 token 注入提前到输入阶段的压缩语义预填充，并配合语义对齐引导，可作为即插即用模块迁移到 next-token 与 next-scale 两类自回归生成/编辑框架中。
原文依据 SCAR introduces Compressed Semantic Prefilling and Semantic Alignment Guidance that jointly enhance contextual understanding and generation coherence.
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论近期，自回归（AR）模型在图像生成中展现出强劲潜力，与扩散方法相比，它具有更好的可扩展性，也更易于与统一的多模态模型集成。然而，由于条件策略薄弱且低效，将 AR 模型扩展到可控图像编辑仍然具有挑战性，这往往导致次优的语义对齐和视觉质量。为解决这一局限，我们提出 SCAR，一种面向自回归模型的语义上下文驱动方法。SCAR 引入压缩语义预填充与语义对齐引导，二者共同增强上下文理解与生成连贯性。与依赖稀疏视觉 token 或解码阶段注入的先前方法不同，SCAR 从输入阶段就提供强语义引导，同时保持模型无关性，可适用于 next-token 与 next-scale 两类 AR 范式。在指令编辑与可控生成上的大量实验表明，我们的方法显著提升了视觉保真度与语义对齐，在保持可控性的同时优于现有的基于 AR 的方法。代码将发布于 https://github.com/AMAP-ML/SCAR。
英文原文摘要 1188 字符
Recently, autoregressive (AR) models have shown strong potential in image generation, offering better scalability and easier integration with unified multi-modal models compared to diffusion methods.However, extending AR models to controllable image editing remains challenging due to weak and inefficient conditioning strategies, which often lead to suboptimal semantic alignment and visual quality.To address this limitation, we present SCAR, a Semantic-Context-driven method for AutoregRessive models.SCAR introduces Compressed Semantic Prefilling and Semantic Alignment Guidance that jointly enhance contextual understanding and generation coherence. Unlike prior methods that rely on sparse visual tokens or decoding stage injection, SCAR enables strong semantic guidance from the input stage, while remaining model-agnostic and applicable to both next-token and next-scale AR paradigms.Extensive experiments on instruction editing and controllable generation demonstrate that our method significantly improves visual fidelity and semantic alignment, outperforming existing AR-based methods while maintaining controllability. Code will be released at https://github.com/AMAP-ML/SCAR.