改进相对表示：使用学习锚点和白化内积
Improving Relative Representations with Learned Anchors and Whitened Inner Products
AI总结：
提出通过学习锚点作为鲁棒语义原型并采用几何感知的相似度度量（白化内积），改进相对表示方法，实现跨模型的高保真信息传输和零样本通信。
摘要：
独立训练的神经模型通常收敛到不兼容的潜在表示，这成为高度模块化AI系统的基本障碍。相对表示（RR）通过将绝对坐标映射到由与公共锚点的相似性定义的共享空间来解决这一问题，但传统实现依赖于随机采样的锚点和余弦相似度，常常无法捕捉现代架构（如Transformer）的各向异性几何结构。在这项工作中，我们提出了一个基于两项改进的跨模型通信鲁棒框架。我们学习锚点作为鲁棒的语义原型，并利用一种几何感知的相似度度量，该度量保留了判别性的幅度信息且对仿射变换具有不变性。我们的方法在视觉和语言任务中展示了显著的性能和一致性提升。值得注意的是，它实现了几乎无损的信息传输和稳定的零样本通信，即使在高度异构的架构之间，例如不同规模的小型语言模型。
英文摘要：
Independently trained neural models typically converge to incompatible latent representations, creating a fundamental barrier to highly modular AI systems. While Relative Representations (RR) address this by mapping absolute coordinates to a shared space defined by similarities to common anchor points, traditional implementations rely on randomly sampled anchors and cosine similarity, which frequently fail to capture the anisotropic geometries of modern architectures like Transformers. In this work, we propose a robust framework for cross-model communication based on two improvements. We learn anchors as robust semantic prototypes and utilize a geometry-aware similarity metric which preserves discriminative magnitude information and is invariant to affine shifts. Our approach demonstrates significant gains in performance and consistency across vision and language tasks. Notably, it enables nearly lossless information transfer and stable zero-shot communication even between highly heterogeneous architectures, such as small language models of varying scales.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
