List your company

Failure Detection on WidowX seen

0.096Brier ScoreSAFE-RNN-TDQC (Ours)
0.076960.205480.3340.46252Apr 22, 2026

Evaluation results

MethodLinks
SAFE-RNN-TDQC (Ours)VLA Model=OpenVLA2026.040.096
SAFE-MLP BCEVLA Model=OpenVLA2026.040.127
SAFE-MLP-TDQC (Ours)VLA Model=OpenVLA2026.040.13
RNN-TDQC (Ours)VLA Model=OpenVLA2026.040.156
SAFE-RNNVLA Model=OpenVLA2026.040.169
Running Avg prob.VLA Model=OpenVLA2026.040.255
Avg prob.VLA Model=OpenVLA2026.040.275
RNN-BCEVLA Model=OpenVLA2026.040.301
Avg entropyVLA Model=OpenVLA2026.040.414
Running Avg entropyVLA Model=OpenVLA2026.040.435
Max prob.VLA Model=OpenVLA2026.040.572