List your company

Failure Detection on Kitchen Real-world

100AUCPR (PR)ACC
27.246.16583.9Jun 19, 2026

Evaluation results

MethodLinks
ACCPolicy=X-VLA2026.0610025
LLMDPolicy=X-VLA2026.0610020
FAILPolicy=X-VLA2026.0610021
ACCPolicy=π0.52026.069917
ACEPolicy=X-VLA2026.069824
DiffPolicy=X-VLA2026.069821
ACEPolicy=π0.52026.069520
STACPolicy=π0.52026.069226
DiffPolicy=π0.52026.067530
FAILPolicy=π0.52026.067428
LLMDPolicy=π0.52026.066233
STACPolicy=X-VLA2026.063055