List your company

Early Failure Detection on RoboCasa S (Unseen)

73.8ROC-AUC (q=0.25)ActProbe
43.22451.16259.167.038Jun 7, 2026

Evaluation results

MethodLinks
ActProbePolicy=π0.52026.0673.8
SAFE-LSTMPolicy=π0.52026.0673.1
SAFE-MLPPolicy=π0.52026.0671
SAFE-MLP-TDQCPolicy=π0.52026.0670.4
LogpZOPolicy=π0.52026.0667.2
STAC-SinglePolicy=π0.52026.0666
SAFE-LSTM-TDQCPolicy=π0.52026.0662.4
Cosine k-NNPolicy=π0.52026.0644.4