LatentPilot: Scene-Aware Vision-and-Language Navigation by Dreaming Ahead with Latent Visual Reasoning
Open paper
Benchmark
Model
Rank
Results
vision-and-language-navigation-on-r2r-ce
LatentPilot
–
Success Rate: 62.0
NE: 4.41
SPL: 58.0
vision-and-language-navigation-on-rxr-ce
LatentPilot
–
nDTW: 67.5
NE: 5.19
SPL: 49.9
Rank counts only results with a code link.