FLAME: Learning to Navigate with Multimodal LLM in Urban Environments
Open paper
Benchmark
Model
Rank
Results
vision-and-language-navigation-on-map2seq
FLAME
#1
Task Completion (TC): 52.44
vision-and-language-navigation-on-touchdown
FLAME
#1
Task Completion (TC): 40.20
Rank counts only results with a code link.