AI RESEARCH
Improving Relative Representations with Learned Anchors and Whitened Inner Products
arXiv CS.LG
•
ArXi:2605.30596v1 Announce Type: new 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.