Preprint
Sep 2026
MT-WAM: Reorienting the One-Pass Predictive Representation Toward Action Generation
Fast-WAM shows that video-action co-training improves control without generating future video at inference, making the representation from a single video diffusion Transformer forward central to action generation. However, future-observation prediction does not explicitly prioritize the future dynamics and visual struc...
Yi-Guang Yang, Jian-Kun Peng, Xiao-Ming Wang et al.
· 0 citations