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 →
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.
Forward citations
Cited by 6 Pith papers
-
BiDexGrasp: Coordinated Bimanual Dexterous Grasps across Object Geometries and Sizes
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.
-
WristMimic: Full-Body Humanoid Control with Wrist-Guided Manipulation
WristMimic achieves comparable or superior object manipulation retargeting by supervising wrist kinematics while letting finger behavior emerge from object and contact dynamics.
-
DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
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...
-
BLaDA: Bridging Language to Functional Dexterous Actions within 3DGS Fields
BLaDA grounds open-vocabulary language into functional dexterous manipulation via knowledge-guided parsing, triangular localization in 3DGS fields, and keypoint grasp execution.
-
Learning Geometry-Aware Nonprehensile Pushing and Pulling with Dexterous Hands
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...
-
AugVLA-3D: Depth-Driven Feature Augmentation for Vision-Language-Action Models
AugVLA-3D augments existing VLA models with depth-derived 3D features and action priors to improve generalization and action accuracy in 3D robotic tasks.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.