Preprint
Aug 2026
ArtLang: Structured Language-to-Kinematics Grounding for Articulated 3D Actuation
This work presents ArtLang, a framework for open-vocabulary language control of persistent reconstructed articulated assets, which represents an asset as a semantic-kinematic articulation graph and augments its surface with language features and graph-constrained motion.
Sylvia Yuan, Dan Wang, Ravi Ramamoorthi et al.
· 0 citations