提出可即插即用的加速框架，让视觉自回归模型生成更快且不丢质量。
FasterVAR: Plug-and-Play Acceleration for Visual Autoregressive Models
- 按生成阶段区分重要性，早期保完整、后期可简化加速
- 无须训练即可实现最高3.4倍提速，性能几乎不变
- 适合需要高效图像生成的研究与应用开发人员
视觉自回归（VAR）模型通过下一尺度预测取代传统自回归模型的下一步词预测，实现了高质量图像生成。然而，该范式在大规模步数下计算复杂度和运行时间显著增加。现有加速方法虽能降低大步数下的运行时间，但依赖人工选择步数，并忽视生成过程中各阶段的重要性差异。为此，我们提出FasterVAR，一个系统性的、可即插即用的VAR模型加速框架。分析表明，早期步骤对保持语义和结构一致性至关重要，应完整保留；而后期步骤主要细化细节，可被剪枝或近似以实现加速。基于此，FasterVAR引入一种无需额外训练的加速策略，利用后期计算中的语义无关性和低秩特性。所提方法在不明显损失性能的前提下，最高实现3.4倍加速，持续优于现有加速基线。结果表明，阶段感知设计是高效视觉自回归图像生成的关键原则。
原文摘要 · Abstract (English)
Visual Autoregressive (VAR) modeling departs from the next-token prediction paradigm of traditional Autoregressive (AR) models through next-scale prediction, enabling high-quality image generation. However, the VAR paradigm suffers from sharply increased computational complexity and running time at large-scale steps. Although existing acceleration methods reduce runtime for large-scale steps, but rely on manual step selection and overlook the varying importance of different stages in the generation process. To address this challenge, we present FasterVAR, a systematic study and plug-and-play acceleration framework for VAR models. Our analysis shows that early steps are critical for preserving semantic and structural consistency and should remain intact,while later steps mainly refine details and can be pruned or approximated for acceleration. Building on these insights, FasterVAR introduces a plug-and-play acceleration strategy that exploits semantic irrelevance and low-rank properties in late-stage computations, without requiring additional training. Our proposed FasterVAR achieves up to 3.4x speedup with almost no performance loss. consistently outperforming existing acceleration baselines.These results highlight stage-aware design as a powerful principle for efficient visual autoregressive image generation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。