SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration
Open paper
Benchmark
Model
Rank
Results
robot-manipulation-on-simplerenv-google-robot
SP-VLA (Google Robot Visual Matching)
–
Success Rate: 75.05
robot-manipulation-on-simplerenv-widow-x
SP-VLA (WidowX)
–
Average: 0.5729
Rank counts only results with a code link.