ManiUnit is introduced, a manipulation skill dataset and benchmark built from 50 BEHAVIOR-1K activities that pairs each segment with an explicit subtask instruction; measures sensitivity to perturbations of the robot's starting base position or joint configuration; and defines local success conditions so that each skil...
Guo-Ting Wei, Da-Wei Yan, Xia Yuan et al.· 0 citations
ART is a tool-injection framework that tunes any VLA model to leverage off-the-shelf tool modules for low-level vision, high-level affordance, and embodiment enhancement, and ART reduces the complexity of the action solution space through tool-use, which improves generalizability across different tasks but also reduces...
Ding-Ge Yi, Yanzhao Yu, Xi-Li Dai et al.· 1 citation
This work presents a progressive two-stage training framework that decouples geometry-aware foreground transformation from background preservation and realistic video composition, without mesh-pixel alignment and explicit 3D reconstruction at inference.
Youze Huang, Peng-Hui Ruan, Bojia Zi et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.