Vlaser: Vision-Language-Action Model with Synergistic Embodied Reasoning
Open paper
Benchmark
Model
Rank
Results
robot-manipulation-on-simplerenv-google-robot
Vlaser-All (visual matching)
#6
Success Rate: 76.2
robot-manipulation-on-simplerenv-widow-x
Vlaser-QA
#27
Average: 0.626
Rank counts only results with a code link.