AI RESEARCH
The Quest for Generalizable Motion Generation: Data, Model, and Evaluation
arXiv CS.CV
•
ArXi:2510.26794v2 Announce Type: replace Despite recent advances in 3D human motion generation (MoGen) on standard benchmarks, existing text-to-motion models still face a fundamental bottleneck in their generalization capability. In contrast, adjacent generative fields, most notably video generation (ViGen), have nstrated remarkable generalization in modeling human behaviors, highlighting transferable insights that MoGen can leverage.