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

Adversarial

Benchmarks

Task NameDataset NameSOTA ResultTrend
Automatic Speech RecognitionAdversarial
WER17.5
8
Uncertainty-aware Waypoint PredictionAdversarial
Empirical Coverage90
5
Single-fact retrievalAdversarial P@1
Accuracy100
2
Showing 3 of 3 rows