Author name: Nikolai Warner, Cameron Ethan Taylor, Irfan Essa, Apaar Sadhwani

arXiv:2603.23684v2 Announce Type: replace
Abstract: Text-motion retrieval systems learn shared embedding spaces from motion-caption pairs via contrastive objectives. However, each caption is not a deterministic label but a sample from a distribution o…

arXiv:2603.23684v1 Announce Type: new
Abstract: Text-motion retrieval systems learn shared embedding spaces from motion-caption pairs via contrastive objectives. However, each caption is not a deterministic label but a sample from a distribution of va…