{"ID":2898823,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.02747","arxiv_id":"2507.02747","title":"DexVLG: Dexterous Vision-Language-Grasp Model at Scale","abstract":"As large models gain traction, vision-language-action (VLA) systems are enabling robots to tackle increasingly complex tasks. However, limited by the difficulty of data collection, progress has mainly focused on controlling simple gripper end-effectors. There is little research on functional grasping with large models for human-like dexterous hands. In this paper, we introduce DexVLG, a large Vision-Language-Grasp model for Dexterous grasp pose prediction aligned with language instructions using single-view RGBD input. To accomplish this, we generate a dataset of 170 million dexterous grasp poses mapped to semantic parts across 174,000 objects in simulation, paired with detailed part-level captions. This large-scale dataset, named DexGraspNet 3.0, is used to train a VLM and flow-matching-based pose head capable of producing instruction-aligned grasp poses for tabletop objects. To assess DexVLG's performance, we create benchmarks in physics-based simulations and conduct real-world experiments. Extensive testing demonstrates DexVLG's strong zero-shot generalization capabilities-achieving over 76% zero-shot execution success rate and state-of-the-art part-grasp accuracy in simulation-and successful part-aligned grasps on physical objects in real-world scenarios.","short_abstract":"As large models gain traction, vision-language-action (VLA) systems are enabling robots to tackle increasingly complex tasks. However, limited by the difficulty of data collection, progress has mainly focused on controlling simple gripper end-effectors. There is little research on functional grasping with large models...","url_abs":"https://arxiv.org/abs/2507.02747","url_pdf":"https://arxiv.org/pdf/2507.02747v1","authors":"[\"Jiawei He\",\"Danshi Li\",\"Xinqiang Yu\",\"Zekun Qi\",\"Wenyao Zhang\",\"Jiayi Chen\",\"Zhaoxiang Zhang\",\"Zhizheng Zhang\",\"Li Yi\",\"He Wang\"]","published":"2025-07-03T16:05:25Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.RO\"]","methods":"[]","has_code":false}