提升图像生成质量，通过高阶流模型优化自回归Transformer
HOFAR: High-Order Augmentation of Flow Autoregressive Transformers
- 用高阶流监督改进自回归Transformer的生成轨迹
- 相比基线模型，生成质量明显提升
- 适合关注生成细节与轨迹建模的研究者
流匹配与Transformer架构在图像生成任务中表现优异，近期工作FlowAR[Ren等, 2024]融合二者以提升合成保真度。然而，现有FlowAR在生成过程中仍受限于一阶轨迹建模。本文提出一种新框架，通过高阶监督系统性增强流自回归Transformer。我们提供了理论分析和实证评估，表明所提High-Order FlowAR（HOFAR）在生成质量上相较基线模型有显著提升。该方法通过高阶展开系统性分析轨迹动态，推进了基于流的自回归建模的理解。
原文摘要 · Abstract (English)
Flow Matching and Transformer architectures have demonstrated remarkable performance in image generation tasks, with recent work FlowAR [Ren et al., 2024] synergistically integrating both paradigms to advance synthesis fidelity. However, current FlowAR implementations remain constrained by first-order trajectory modeling during the generation process. This paper introduces a novel framework that systematically enhances flow autoregressive transformers through high-order supervision. We provide theoretical analysis and empirical evaluation showing that our High-Order FlowAR (HOFAR) demonstrates measurable improvements in generation quality compared to baseline models. The proposed approach advances the understanding of flow-based autoregressive modeling by introducing a systematic framework for analyzing trajectory dynamics through high-order expansion.
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。