The reviewed record of science sign in
Pith

arxiv: 2507.02747 · v1 · pith:LNAQVCJA · submitted 2025-07-03 · cs.CV · cs.RO

DexVLG: Dexterous Vision-Language-Grasp Model at Scale

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:LNAQVCJArecord.jsonopen to challenge →

classification cs.CV cs.RO
keywords dexterousdexvlggrasplargeobjectsdatasetmodelmodels
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. BiDexGrasp: Coordinated Bimanual Dexterous Grasps across Object Geometries and Sizes

    cs.RO 2026-04 unverdicted novelty 7.0

    BiDexGrasp supplies a 9.7-million-grasp bimanual dexterous dataset built via two-stage synthesis and a coordinated geometry-size-adaptive model that generates grasps for unseen objects.

  2. WristMimic: Full-Body Humanoid Control with Wrist-Guided Manipulation

    cs.RO 2026-07 accept novelty 6.0

    WristMimic achieves comparable or superior object manipulation retargeting by supervising wrist kinematics while letting finger behavior emerge from object and contact dynamics.

  3. DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge

    cs.CV 2025-07 unverdicted novelty 6.0

    DreamVLA uses dynamic-region-guided world knowledge prediction, block-wise attention to disentangle information types, and a diffusion transformer for actions, reaching 76.7% success on real robot tasks and 4.44 avera...

  4. BLaDA: Bridging Language to Functional Dexterous Actions within 3DGS Fields

    cs.CV 2026-04 unverdicted novelty 5.0

    BLaDA grounds open-vocabulary language into functional dexterous manipulation via knowledge-guided parsing, triangular localization in 3DGS fields, and keypoint grasp execution.

  5. Learning Geometry-Aware Nonprehensile Pushing and Pulling with Dexterous Hands

    cs.RO 2025-09 unverdicted novelty 5.0

    GD2P generates and learns dexterous hand poses for nonprehensile pushing and pulling by combining contact-guided sampling, physics-based filtering, and a geometry-conditioned diffusion model, demonstrated on Allegro a...

  6. AugVLA-3D: Depth-Driven Feature Augmentation for Vision-Language-Action Models

    cs.CV 2026-02 unverdicted novelty 3.0

    AugVLA-3D augments existing VLA models with depth-derived 3D features and action priors to improve generalization and action accuracy in 3D robotic tasks.