2 papers
cs.CV2026
SWAM: Scaling World Action Models with Cross-Modal Alignment
Yu Zhou, Xinyuan Xia, Xuankun Yang +8
World action models jointly predict video and actions conditioned on language. Existing studies focus primarily on architectures and training mechanisms, typically treating languag…
cs.RO2026
DexForesight: Grounding Dexterous Policies with Implicit Spatial Foresight
Zhongxi Chen, Yi Yang, Xinyi Chen +6
Dexterous manipulation requires rich spatial foresight over both the surrounding scene and the robot hand. Existing world-action models often acquire such predictive knowledge thro…