VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Models
Open paper
Benchmark
Model
Rank
Results
robot-manipulation-on-robocasa-gr1-tabletop
VP-VLA + Qwen3VL
#5
Success Rate: 53.8
robot-manipulation-on-simplerenv-widow-x
VP-VLA + Qwen3VL
#36
Average: 0.583
Rank counts only results with a code link.