Preprint
Oct 2026
SparseWAM: Driving World-Action Models are Worth 16 Register Tokens
World Action Models (WAMs) transfer scene-dynamics priors to planning by jointly forecasting future scenes and ego trajectories. However, WAMs built on video generators must generate dense future videos at inference, incurring prohibitive latency, while efficient variants discard the world branch at deployment and thus...
Yi-Xiang Yang, Li-Zhong Zhang, Xing-Yu Zhang et al.
· 0 citations