AI RESEARCH
DextER: Language-driven Dexterous Grasp Generation with Embodied Reasoning
arXiv CS.CV
•
ArXi:2601.16046v2 Announce Type: replace-cross Language-driven dexterous grasp generation requires the models to understand task semantics, 3D geometry, and complex hand-object interactions. While vision-language models have been applied to this problem, existing approaches directly map observations to grasp parameters without intermediate reasoning about physical interactions. We present DextER, Dexterous Grasp Generation with Embodied Reasoning, which