World Action Models (WAMs) inherit powerful priors from pretrained video generation models, but their variational autoencoder (VAE) representations are optimized for visual reconstruction rather than manipulation. External visual representations can improve manipulation, but existing methods couple representation choic...
Kai Liu, Jiangran Lyu, Ting-Yu Deng et al.· 2 citations
Object manipulation often requires combining non-prehensile actions with grasping. However, existing approaches typically develop these capabilities separately and integrate them by sequencing distinct primitives through prescribed intermediate objectives, limiting the coordination of contact motions and grasping. Thei...
Wen-Xuan Zhu, Yu-Ze Wang, Jiangran Lyu et al.· 0 citations
GPT-6 Astra exhibits a remarkable ability to generate numerical robot actions, extending its role beyond high-level planning. To assess Astra's capabilities as general-purpose embodied policies, we conduct comprehensive evaluations across six domains, examining direct control, cooperation with learned policies, and fee...
Galbot Team Xuchuan Chen, Xiao-Qi Cheng, Yu Deng et al.· 0 citations
Method is presented, a dual-system WAM that preserves broader-horizon world-action generation while enabling high-frequency closed-loop action updates by decoupling global planning and local refinement and shows that it naturally supports edge--cloud deployment with substantially lower communication overhead than the b...
Yi-Xin Zheng, Jiangran Lyu, Yun-Tian Deng et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.