SemanticVLA: Towards Semantic Reasoning over Action Memorization via Synergistic Explicit Trace and Latent Action Planning
Open paper
Benchmark
Model
Rank
Results
robot-manipulation-on-libero
SemanticVLA
–
Success Rate: 97.0
robot-manipulation-on-simplerenv-widow-x
SemanticVLA
–
Average: 0.651
Rank counts only results with a code link.