研究人员推出nD-RoPE，一种将旋转位置嵌入（RoPE）推广到n维空间的新颖方法，解决了当前方法的局限性。这种新公式将位置和频率视为耦合的n维向量，能够实现更好的跨维度交互和方向无关的表示。实验表明，nD-RoPE在图像、视频和点云等各种高维数据类型上均提高了性能和泛化能力。 AI
影响 增强了处理复杂、多维数据的AI模型的表示能力。
排序理由 该集群包含一篇学术论文，详细介绍了AI模型中位置嵌入的新方法。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.12146v1 Announce Type: cross Abstract: Rotary Position Embedding (RoPE) is widely adopted in Transformer models, yet its extension to high-dimensional domains lacks a unified theoretical formulation. Most existing approaches either apply rotations independently along e…
Rotary Position Embedding (RoPE) is widely adopted in Transformer models, yet its extension to high-dimensional domains lacks a unified theoretical formulation. Most existing approaches either apply rotations independently along each axis or empirically mix frequencies, which lim…