A Unified Conditional Flow for Motion Generation, Editing, and Intra-Structural Retargeting

ArXi:2604.13427v1 Announce Type: cross Text-driven motion editing and intra-structural retargeting, where source and target share topology but may differ in bone lengths, are traditionally handled by fragmented pipelines with incompatible inputs and representations: editing relies on specialized generative steering, while retargeting is deferred to geometric post-processing. We present a unifying perspective where both tasks are cast as instances of conditional transport within a single generative framework.