Vector Linking via Cross-Model Local Isometric Consistency 事件

Vector Linking via Cross-Model Local Isometric Consistency arXiv:2605.31100v1 Announce Type: new Abstract: We study Vector Linking: given two embedding clouds produced by different black-box encoders over partially overlapping datasets, recover cross-model object correspondences using only vectors. Empirically and theoretically, we show that independently trained contrastive encoders exhibit local geometric consistency: short-range distances are approximately preserved up to a scale factor, whi