FlowCoMotion: Text-to-Motion Generation via Token-Latent Flow Modeling

arXiv:2604.11083v1 Announce Type: cross Abstract: Text-to-motion generation is driven by learning motion representations for semantic alignment with language. Existing methods rely on either continuous or discrete motion representations. However, continuous representations entangle semantics with dynamics, while discrete representations lose fine-grained motion details. In this context, we propose FlowCoMotion, a novel motion generation framework that unifies both treatments from a modeling pers