AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling 事件

AnyMo: Scaling Any-Modality Conditional Motion Generation with Masked Modeling arXiv:2605.29488v1 Announce Type: new Abstract: Conditional human motion generation remains a fundamental challenge in computer vision and robotics. Despite significant progress, current methods are often constrained by fixed modality configurations and task-specific architectures, leaving cross-modal interactions and the scaling laws of multimodal-conditioned synthesis largely underexplored. A key bottleneck is the