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 with 96.4% improvement in intention alignment. We also demonstrate steerable generation through partial contact specification, providing fine-grained control over grasp synthesis.

翻译：语言驱动的灵巧抓取生成要求模型理解任务语义、三维几何以及复杂的手-物交互。尽管视觉-语言模型已被应用于此问题，现有方法直接将观测映射到抓取参数，而缺乏对物理交互的中间推理。我们提出了DextER（基于具身推理的灵巧抓取生成），该方法引入了基于接触的具身推理用于多指操作。我们的核心洞见是：预测手部哪些连杆在物体表面的何处发生接触，能够提供一种具身感知的中间表示，从而将任务语义与物理约束联系起来。DextER以自回归方式生成具身接触令牌，指定哪些手指连杆在物体表面的何处接触，随后生成编码手部配置的抓取令牌。在DexGYS数据集上，DextER实现了67.14%的成功率，以3.83个百分点的优势超越现有最优方法，并在意图对齐方面提升了96.4%。我们还通过部分接触指定展示了可引导的生成能力，为抓取合成提供了细粒度控制。