Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Early Failure Detection on RoboCasa L (Seen)
Loading...
82.7
ROC-AUC (q=0.25)
ActProbe
70.636
73.768
76.9
80.032
Jun 7, 2026
ROC-AUC (q=0.25)
Updated 1mo ago
Evaluation Results
Method
Method
Links
ROC-AUC (q=0.25)
ActProbe
Policy=π0.5
2026.06
82.7
SAFE-LSTM
Policy=π0.5
2026.06
80.9
STAC-Single
Policy=π0.5
2026.06
77.7
SAFE-LSTM-TDQC
Policy=π0.5
2026.06
76.1
SAFE-MLP
Policy=π0.5
2026.06
74.7
LogpZO
Policy=π0.5
2026.06
73.8
SAFE-MLP-TDQC
Policy=π0.5
2026.06
73.7
Cosine k-NN
Policy=π0.5
2026.06
71.1
Feedback
Search any
task
Search any
task