Next-Scale Autoregressive Models for Text-to-Motion Generation 事件

Next-Scale Autoregressive Models for Text-to-Motion Generation arXiv:2604.03799v2 Announce Type: replace Abstract: Autoregressive (AR) models offer stable and efficient training, but standard next-token prediction is not well aligned with the temporal structure required for text-conditioned motion generation. We introduce MoScale, a next-scale AR framework that generates motion hierarchically from coarse to fine temporal resolutions. By providing global semantics at the coarsest scale and refin