Steering Vision-Language-Action Models as Anti-Exploration: A Test-Time Scaling Approach
Open paper
Benchmark
Model
Rank
Results
robot-manipulation-on-libero-long
π0.5 + TACO
#25
Success Rate: 96.6
robot-manipulation-on-simplerenv-widow-x
π0 + TACO
#40
Average: 0.555
Rank counts only results with a code link.