研究人员开发了一种新的训练后剪枝技术，称为DiT-Pruning，专门用于扩散Transformer（DiTs），它们以其高昂的图像生成计算需求而闻名。由于DiTs独特的架构和权重分布，传统的剪枝方法对其无效。DiT-Pruning引入了定制的显著性标准，以平衡权重和激活的贡献，并采用感知聚类的粒度来更好地分配稀疏权重。实验表明，该方法在保持高稀疏度水平的情况下能有效保持图像质量，性能优于现有技术。 AI
影响 这项新的剪枝技术可以显著降低扩散模型的计算成本和资源需求，从而使先进的图像生成更加普及。
排序理由 详细介绍一种优化AI模型新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2607.00927v1 Announce Type: cross Abstract: Diffusion Transformers (DiTs) have demonstrated impressive performance in image generation but suffer from substantial computational overhead and resource consumption. Post-training pruning offers a promising solution; however, du…
Diffusion Transformers (DiTs) have demonstrated impressive performance in image generation but suffer from substantial computational overhead and resource consumption. Post-training pruning offers a promising solution; however, due to DiTs' unique architectural design and paramet…