List your company

Failure Detection on LIBERO 10 Unseen Tasks

89.2bACCHide-and-Seek
44.37656.01367.6579.287May 29, 2026

Evaluation results

MethodLinks
Hide-and-SeekPolicy=π0, Category=Class.2026.0589.292.170.5
Hide-and-SeekPolicy=OpenVLA, Category=Class.2026.0583.482.866.3
SAFE-MLPPolicy=π0, Category=Class., Venue=NeurIPS'252026.0580.186.764.8
SAFE-MLPPolicy=OpenVLA, Category=Class., Venue=NeurIPS'252026.0577.574.159
Cluster EntropyPolicy=π0, Category=Multi., Venue=ICLR'232026.0573.260.455.2
SAFE-LSTMPolicy=OpenVLA, Category=Class., Venue=NeurIPS'252026.0568.666.655.3
LogpZOPolicy=π0, Category=OOD Det., Venue=RSS'252026.0568.167.957.4
EigenScorePolicy=OpenVLA, Category=Multi., Venue=ICLR'242026.0567.167.252.4
Cosine k-NNPolicy=OpenVLA, Category=OOD Det., Venue=ICML'222026.0563.95952.2
MahalanobisPolicy=π0, Category=OOD Det., Venue=ICML'182026.0563.45154.3
STACPolicy=OpenVLA, Category=Multi., Venue=CoRL'242026.0562.464.252.8
Cosine k-NNPolicy=π0, Category=OOD Det., Venue=ICML'222026.0562.369.654.2
EigenScorePolicy=π0, Category=Multi., Venue=ICLR'242026.0561.366.849.5
ACEPolicy=π0, Category=Multi., Venue=NeurIPS'252026.0560.96350.5
SAFE-LSTMPolicy=π0, Category=Class., Venue=NeurIPS'252026.0560.952.852.4
ACEPolicy=OpenVLA, Category=Multi., Venue=NeurIPS'252026.0560.460.254.2
Cluster EntropyPolicy=OpenVLA, Category=Multi., Venue=ICLR'232026.055757.854.8
LogpZOPolicy=OpenVLA, Category=OOD Det., Venue=RSS'252026.0554.550.250.5
Max NLLPolicy=OpenVLA, Category=Token Unc., Venue=ICLR'232026.0552.552.848.8
Max EntropyPolicy=OpenVLA, Category=Token Unc., Venue=ICLR'212026.0552.151.848.8
RNDPolicy=π0, Category=OOD Det., Venue=ICML'242026.055264.350.5
MahalanobisPolicy=OpenVLA, Category=OOD Det., Venue=ICML'182026.0551.349.550.4
RNDPolicy=OpenVLA, Category=OOD Det., Venue=ICML'242026.0550.950.447.8
Avg. NLLPolicy=OpenVLA, Category=Token Unc., Venue=ICLR'232026.0549.548.747
Avg. EntropyPolicy=OpenVLA, Category=Token Unc., Venue=ICLR'212026.0549.14945.6
STACPolicy=π0, Category=Multi., Venue=CoRL'242026.054959.644
PCA KMeansPolicy=OpenVLA, Category=OOD Det., Venue=CoRL'242026.0548.649.444.2
PCA KMeansPolicy=π0, Category=OOD Det., Venue=CoRL'242026.0546.147.139.4