Safety
DextER: Language-driven Dexterous Grasp Generation with Embodied Reasoning
arXiv:2601.16046v2 Announce Type: replace-cross Abstract: Language-driven dexterous grasp generation requires the models to understand task semantics, 3D geometry, and complex hand-object interactions
arXiv:2601.16046v2 Announce Type: replace-cross Abstract: 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 introduces contact-based embodied reasoning for multi-finger manipulation. Our key insight is that predicting which hand links contact where on the object surface provides an embodiment-aware intermediate representation, bridging task semantics with physical constraints. DextER autoregressively generates embodied contact tokens specifying which finger links contact where on the object surface, followed by grasp tokens encoding the hand configuration. On DexGYS, DextER achieves 67.14% success rate, outperforming state-of-the-art by 3.83 p.p. with 96.4% improvement in intention alignment. We also demonstrate steerable generation through partial contact specification, providing fine-grained control over grasp synthesis.
Related
- ViserDex: Visual Sim-to-Real for Robust Dexterous In-hand Reorientation
- AVA-VLA: Improving Vision-Language-Action models with Active Visual Attention
- THOM: Generating Physically Plausible Hand-Object Meshes From Text
- Grasp in Gaussians: Fast Monocular Reconstruction of Dynamic Hand-Object Interactions
Source: arXiv cs.CV | 2026-04-28