语义上下文至关重要：改进自回归模型的条件化
Semantic Context Matters: Improving Conditioning for Autoregressive Models
AI总结：
本文提出SCAR方法，通过压缩语义前缀和语义对齐指导提升自回归模型的条件化能力，实现更高质量的图像编辑和可控生成。
摘要：
最近，自回归（AR）模型在图像生成中展现出强大潜力，相较于扩散方法，其具有更好的可扩展性和与统一多模态系统的集成能力。然而，将AR模型扩展到通用图像编辑仍面临挑战，因为条件化薄弱且低效，常导致指令遵循差和视觉伪影。为此，我们提出SCAR，一种语义上下文驱动的自回归模型方法。SCAR引入两个关键组件：压缩语义前缀，将高级语义编码为紧凑高效的前缀；以及语义对齐指导，在自回归解码过程中对齐最后的视觉隐藏状态与目标语义以提升指令忠实度。不同于解码阶段注入方法，SCAR利用向量量化基础的前缀生成方法的灵活性和通用性，克服其语义限制和高成本。它在next-token和next-set AR范式中均能泛化，仅需最小的架构改动。SCAR在指令编辑和可控生成基准上实现了更优的视觉保真度和语义对齐，优于先前的AR方法，同时保持可控性。代码将在https://github.com/AMAP-ML/SCAR发布。
英文摘要：
Recently, autoregressive (AR) models have shown strong potential in image generation, offering better scalability and easier integration with unified multi-modal systems compared to diffusion-based methods. However, extending AR models to general image editing remains challenging due to weak and inefficient conditioning, often leading to poor instruction adherence and visual artifacts. To address this, we propose SCAR, a Semantic-Context-driven method for Autoregressive models. SCAR introduces two key components: Compressed Semantic Prefilling, which encodes high-level semantics into a compact and efficient prefix, and Semantic Alignment Guidance, which aligns the last visual hidden states with target semantics during autoregressive decoding to enhance instruction fidelity. Unlike decoding-stage injection methods, SCAR builds upon the flexibility and generality of vector-quantized-based prefilling while overcoming its semantic limitations and high cost. It generalizes across both next-token and next-set AR paradigms with minimal architectural changes. SCAR achieves superior visual fidelity and semantic alignment on both instruction editing and controllable generation benchmarks, outperforming prior AR-based methods while maintaining controllability. Code will be released at https://github.com/AMAP-ML/SCAR.
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。
