The rapid progress of visual autoregressive (VAR) models has unlocked a transformative frontier for high-fidelity text-to-image synthesis, while heightening concerns over the safety alignment of generated content. Naive application of existing erasure techniques to VAR models causes catastrophic semantic collapse and visual artifacts, since they are predominantly designed for the homogeneous denoising steps of diffusion models. To address this foundational challenge, we first propose the Semantic Singularity Axiom, which posits that any target semantic concept embedded within a prompt is definitively locked at Scale-0. Then rigorously validate this axiom through our proposed Incremental Semantic Saliency Analysis (ISSA),which also enable the community to transparently inspect the coarse-to-fine semantic injection process. Guided by this insight, we introduce the first scale-aware concept erasure framework (SACE) for VAR models. By strictly confining interventions to the first scale, our approach couples an Entropy-Regularized Erasure Objective to prevent high-entropy sampling degeneration, alongside a restorative preservation loss to safely anchor the integrity of entangled benign priors. Extensive experiments demonstrate that our method achieves surgical concept erasure performance across various domains with minimal training overhead, timely and elegently resolute the critical safety vulnerabilities inherent in emerging VAR architectures. Code is available at: https://github.com/limerenceysy/SACE}{https://github.com/limerenceysy/SACE.

翻译：视觉自回归（VAR）模型的快速发展为高保真文本到图像合成开辟了变革性新领域，同时也加剧了对生成内容安全对齐的担忧。现有擦除技术主要针对扩散模型的同质化去噪步骤设计，因此直接应用于VAR模型会导致灾难性语义崩塌和视觉伪影。为解决这一基础性挑战，我们首先提出语义奇点公理，该公理主张提示中嵌入的任何目标语义概念均被锁定在Scale-0尺度上。随后通过提出的增量语义显著性分析（ISSA）严格验证该公理，该方法还能使学术界透明地观察从粗到细的语义注入过程。基于这一洞见，我们引入首个面向VAR模型的尺度感知概念擦除框架（SACE）。通过严格将干预限制在第一尺度，该方法结合熵正则化擦除目标以防止高熵采样退化，并引入修复性保留损失以安全锚定纠缠良性先验的完整性。大量实验表明，我们的方法能以最小训练开销在各领域实现精准的概念擦除性能，及时且优雅地解决了新兴VAR架构固有的关键安全漏洞。代码见：https://github.com/limerenceysy/SACE。