Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

MOS

Benchmarks

Task NameDataset NameSOTA ResultTrend
Out-of-Distribution DetectionMOS benchmark
FPR95 (iNaturalist)1.65
22
Shadow DetectionMOS (test)
MAE0.058
14
POMDP PlanningMOS (8,6)
Returns8
6
POMDP PlanningMOS(7,5)
Returns11.2
6
POMDP PlanningMOS (6,4)
Returns14.5
6
Showing 5 of 5 rows