视觉自回归模型用搜索策略提升生成速度，20亿参数超越120亿参数扩散模型。
Visual Autoregressive Models Beat Diffusion Models on Inference Time Scaling
- 利用自回归模型的离散序列特性，实现高效搜索优化。
- 20亿参数模型通过束搜索在多基准上超越120亿参数扩散模型。
- 适合关注推理加速与架构设计的生成模型研究者。
尽管推理时通过搜索提升大语言模型性能已成常态，但将此方法应用于图像生成仍具挑战。近期对连续扩散模型尝试搜索策略效果有限，简单随机采样常表现最佳。我们证明，视觉自回归模型的离散、序列特性使其能有效进行图像生成搜索。实验显示，束搜索显著提升文本到图像生成效果，使一个20亿参数的自回归模型在多个基准上优于120亿参数的扩散模型。系统性消融分析表明，这一优势源于离散标记空间带来的早期剪枝和计算复用；验证器分析揭示了速度与推理能力之间的权衡。这些发现表明，模型架构在视觉生成的推理优化中与规模同等关键。
原文摘要 · Abstract (English)
While inference-time scaling through search has revolutionized Large Language Models, translating these gains to image generation has proven difficult. Recent attempts to apply search strategies to continuous diffusion models show limited benefits, with simple random sampling often performing best. We demonstrate that the discrete, sequential nature of visual autoregressive models enables effective search for image generation. We show that beam search substantially improves text-to-image generation, enabling a 2B parameter autoregressive model to outperform a 12B parameter diffusion model across benchmarks. Systematic ablations show that this advantage comes from the discrete token space, which allows early pruning and computational reuse, and our verifier analysis highlights trade-offs between speed and reasoning capability. These findings suggest that model architecture, not just scale, is critical for inference-time optimization in visual 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。