Preprint
Aug 2026
DynamicWAM: Dual-Path Motion Conditioning for World-Action Models in Dynamic Manipulation
DynamicWAM introduces history-flow conditioning, encoding temporally aligned optical-flow frames alongside the current observation through a frozen pretrained video VAE to preserve spatial motion structure, while injecting kinematic descriptors of displacement, duration, velocity, and acceleration into the action expert to provide motion magnitude and timing.
Y. Lou, Hewen Gao, Xiyu Zhu et al.
· 0 citations