5 papers
Rethinking Representations for World-Action Modeling
Haoyi Jiang, Liu Liu, Xinjiang Wang +12
World-action models jointly learn robot policies and predict future observations, making the representation space an interface between control and prediction. We study the design o…
CogWAM: Aligning Semantic Cognition with World Action Modeling via Event-Driven Interfaces
Sen Wang, Liu Liu, Xinjiang Wang +7
Robot policies increasingly incorporate semantic reasoning and future-world prediction, yet combining these capabilities does not guarantee that local predictions and actions remai…
-VLA: a Hierarchical Robot Foundation Model with World-Model-Guided Test-Time Computation
Xiaowei Cai, Yunuo Cai, Bingao Chen +36
Long-horizon robot manipulation requires a robot to both execute individual skills reliably and sequence them coherently over extended tasks. Most hierarchical vision-language-acti…
WorldDiT: A Unified Diffusion Architecture for World and Action Modeling
Sen Wang, R. Gnana Praveen, Bidhan Roy +1
Many recent robot policies pursue stronger control by using large pretrained vision-language models (VLMs) as the action backbone. We introduce WorldDiT, a unified diffusion transf…
WSA: a 3D-Centric World-Spatial-Action Model for Generalizable Robot Control
Jiahao Jiang, Jianing Zhang, Zhenhan Yin +9
World-Action Models (WAMs) have emerged as a promising paradigm for robot control by using predicted world evolution to guide action generation. However, existing WAMs largely foll…