TRM-VLA: Temporal-Aware Chain-of-Thought Reasoning and Memorization for Vision-Language-Action Models
Open paper
Benchmark
Model
Rank
Results
robot-manipulation-on-libero-90
TRM-VLA
–
Success Rate: 94.8
robot-manipulation-on-simplerenv-widow-x
TRM-VLA
–
Average: 0.729
Rank counts only results with a code link.