ed

Reported on 7 benchmarks across 2 tasks

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Robots7 results

Visual NavigationonCooperative Vision-and-Dialogue Navigation
dist_to_end_reduction
3.3
best: 7.9 (NaviLLM)
Visual NavigationonCooperative Vision-and-Dialogue Navigation
spl
0.14
best: 0.25 (Best SPL)
Vision and Language NavigationonVLN Challenge
error
4.16
best: 1.61 (human)
Vision and Language NavigationonVLN Challenge
length
12.51
best: 1257.38 (Speaker-Follower)
Vision and Language NavigationonVLN Challenge
oracle success
0.69
best: 1 (FOAM-Beam Search)
Vision and Language NavigationonVLN Challenge
spl
0.58
best: 0.76 (human)
Vision and Language NavigationonVLN Challenge
success
0.63
best: 0.86 (human)