HAMT

Reported on 8 benchmarks across 2 tasks · 1 paper · 1 SOTA

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

Robots8 results

Vision and Language NavigationonRxR
ndtw· 2021-10-25
59.94
best: 66.76 (MARVAL)
SOTA
History Aware Multimodal Transformer for Vision-and-Language Navigation arXiv:2110.13309
Visual NavigationonCooperative Vision-and-Dialogue Navigation
dist_to_end_reduction
5.58
best: 7.9 (NaviLLM)
Visual NavigationonCooperative Vision-and-Dialogue Navigation
spl
0.07
best: 0.25 (Best SPL)
Vision and Language NavigationonVLN Challenge
error
3.93
best: 1.61 (human)
Vision and Language NavigationonVLN Challenge
length
12.27
best: 1257.38 (Speaker-Follower)
Vision and Language NavigationonVLN Challenge
oracle success
0.72
best: 1 (FOAM-Beam Search)
Vision and Language NavigationonVLN Challenge
spl
0.6
best: 0.76 (human)
Vision and Language NavigationonVLN Challenge
success
0.65
best: 0.86 (human)