DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoning

Benchmark Model Rank Results
robot-manipulation-on-liberoDepthVLA–Success Rate: 94.9
robot-manipulation-on-libero-goalDepthVLA–Success Rate: 95.8
robot-manipulation-on-libero-longDepthVLA–Success Rate: 89.2
robot-manipulation-on-libero-objectDepthVLA–Success Rate: 98.0
robot-manipulation-on-libero-spatialDepthVLA–Success Rate: 96.4
robot-manipulation-on-simplerenv-widow-xDepthVLA–Average: 0.748