List your company

Failure Detection on VLABench (Seen Tasks)

85.6Balanced Accuracy (bACC)Hide-and-Seek
52.21660.88369.5578.217May 29, 2026

Evaluation results

MethodLinks
Hide-and-SeekPolicy=π0.52026.0585.682.766.2
SAFE-MLPPolicy=π0.52026.0578.876.658.1
PCA KMeansPolicy=π0.52026.0564.266.952.9
MahalanobisPolicy=π0.52026.0563.751.958.1
Cluster EntropyPolicy=π0.52026.0562.965.660.2
SAFE-LSTMPolicy=π0.52026.0562.952.458.7
RNDPolicy=π0.52026.0562.861.854.5
LogpZOPolicy=π0.52026.0561.850.355.2
STACPolicy=π0.52026.0561.558.655.6
ACEPolicy=π0.52026.0559.654.555.3
EigenScorePolicy=π0.52026.0555.348.753.2
Cosine k-NNPolicy=π0.52026.0553.538.448.5