AI RESEARCH

TokenDance: Token-to-Token Music-to-Dance Generation with Bidirectional Mamba

arXiv CS.AI

ArXi:2603.27314v1 Announce Type: new Music-to-dance generation has broad applications in virtual reality, dance education, and digital character animation. However, the limited coverage of existing 3D dance datasets confines current models to a narrow subset of music styles and choreographic patterns, resulting in poor generalization to real-world music. Consequently, generated dances often become overly simplistic and repetitive, substantially degrading expressiveness and realism.