研究人员开发了一个新的信息论框架来优化扩散模型中的分类器自由引导（CFG）调度。该方法旨在平衡保真度与分布覆盖率之间的权衡，而这通常会因强引导而受到损害。所提出的方法使用参考点来引导采样器，并推导出目标估计的公式，在ImageNet-512和COCO数据集上展示了具有竞争力的或改进的结果。 AI
影响 这项研究可能导致生成式AI模型产生更受控和更多样化的输出，从而提高它们在图像、文本到图像和视频生成中的效用。
排序理由 该集群包含一篇详细介绍扩散模型新方法的学术论文。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
arXiv:2606.24025v1 Announce Type: new Abstract: Diffusion models have achieved strong performance in image, text-to-image, and video generation, where conditional generation is often controlled by classifier-free guidance (CFG). CFG improves condition consistency by increasing a …
Diffusion models have achieved strong performance in image, text-to-image, and video generation, where conditional generation is often controlled by classifier-free guidance (CFG). CFG improves condition consistency by increasing a guidance weight, but stronger guidance typically…
Diffusion models have achieved strong performance in image, text-to-image, and video generation, where conditional generation is often controlled by classifier-free guidance (CFG). CFG improves condition consistency by increasing a guidance weight, but stronger guidance typically…