← Leaderboard
GraspVLA
VLAGalbot & PKU · May 6, 2025
Grasping foundation model pretrained only on SynGrasp-1B, a billion-frame synthetic dataset, for zero-shot sim-to-real open-vocabulary grasping. Results are self-reported: 86.6–96.6% zero-shot real-world grasp success across test sets.
- Type
- VLA
- Parameters
- —
- Backbone
- InternLM2-1.8B
- Weights
- Open
- License
- CC BY-NC 4.0
- Commercial use
- Not allowed
- Released
- May 6, 2025
- Robots
- Franka
- SO-101
- –
- LeRobot
- –
- Inputs
- –
- VRAM
- –
Benchmark results
0 of 13 benchmarksNo benchmark results recorded yet.
Not reported on 13 benchmarks
Wrong or missing number? Report an error