List your company

Failure Detection on LIBERO-10 Seen Tasks

88.5bACCHide-and-Seek
47.83658.39368.9579.507May 29, 2026

Evaluation results

MethodLinks
Hide-and-SeekPolicy=π0, Category=Class.2026.0588.592.669.3
SAFE-MLPPolicy=π0, Category=Class., Venue=NeurIPS'252026.058791.568.8
Hide-and-SeekPolicy=OpenVLA, Category=Class.2026.0585.285.366
SAFE-MLPPolicy=OpenVLA, Category=Class., Venue=NeurIPS'252026.0582.381.963
MahalanobisPolicy=π0, Category=OOD Det., Venue=ICML'182026.0578.88471.5
LogpZOPolicy=π0, Category=OOD Det., Venue=RSS'252026.0578.683.569.1
SAFE-LSTMPolicy=π0, Category=Class., Venue=NeurIPS'252026.0577.485.166.3
Cosine k-NNPolicy=OpenVLA, Category=OOD Det., Venue=ICML'222026.0575.875.763.2
RNDPolicy=π0, Category=OOD Det., Venue=ICML'242026.0570.678.462.9
EigenScorePolicy=π0, Category=Multi., Venue=ICLR'242026.0569.176.153.4
ACEPolicy=π0, Category=Multi., Venue=NeurIPS'252026.0567.276.457.2
MahalanobisPolicy=OpenVLA, Category=OOD Det., Venue=ICML'182026.056766.760.4
SAFE-LSTMPolicy=OpenVLA, Category=Class., Venue=NeurIPS'252026.056766.559.3
STACPolicy=OpenVLA, Category=Multi., Venue=CoRL'24, note=Adapted to single-step output2026.0566.565.154.5
EigenScorePolicy=OpenVLA, Category=Multi., Venue=ICLR'242026.0566.363.653.6
LogpZOPolicy=OpenVLA, Category=OOD Det., Venue=RSS'252026.0565.866.559.4
STACPolicy=π0, Category=Multi., Venue=CoRL'242026.0561.975.150.1
ACEPolicy=OpenVLA, Category=Multi., Venue=NeurIPS'252026.0560.763.151.6
PCA KMeansPolicy=π0, Category=OOD Det., Venue=CoRL'242026.0559.159.547.6
Cosine k-NNPolicy=π0, Category=OOD Det., Venue=ICML'222026.055884.156.5
Cluster EntropyPolicy=OpenVLA, Category=Multi., Venue=ICLR'232026.0555.252.451.6
Cluster EntropyPolicy=π0, Category=Multi., Venue=ICLR'232026.0554.874.945.4
PCA KMeansPolicy=OpenVLA, Category=OOD Det., Venue=CoRL'242026.0553.454.449.4
RNDPolicy=OpenVLA, Category=OOD Det., Venue=ICML'242026.0552.652.349.3
Max EntropyPolicy=OpenVLA, Category=Token Unc., Venue=ICLR'212026.0551.452.745.5
Avg. EntropyPolicy=OpenVLA, Category=Token Unc., Venue=ICLR'212026.0551.352.447.8
Avg. NLLPolicy=OpenVLA, Category=Token Unc., Venue=ICLR'232026.0550.652.247.5
Max NLLPolicy=OpenVLA, Category=Token Unc., Venue=ICLR'232026.0549.449.345.6