Preprint
Sep 2026
DeltaWAM: Change-Centric Visual Foresight via Delta Tokens for an Efficient World-Action Model
World-Action Models (WAMs) offer visual foresight for robotic manipulation, but pixel-space models repeatedly reconstruct entire future scenes, incurring high computational cost and spatio-temporal redundancy. In physical manipulation, consecutive frames often share most of their visual context; the changes between the...
Tian-Yun Jiang, Wen-Rui Bao, Bing-Xin Xu et al.
· 0 citations