GR-MG: Leveraging Partially Annotated Data via Multi-Modal Goal-Conditioned Policy
Open paper
Benchmark
Model
Rank
Results
zero-shot-generalization-on-calvin
GR-MG
#6
Avg. sequence length: 4.04
robot-manipulation-on-calvin
GR-MG
#10
avg. sequence length (D to D): 4.04
Rank counts only results with a code link.