Action Hallucination Detection on Mementos Robotics Domain (test)
6.5Accuracy
VisAlign
Updated 1mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2025.11 | 6.5 | 9.6 | 10.76 | 9.45 | |
2025.11 | 5.53 | 6.99 | 11.3 | 8.4 |
VisAlign
| Method | Links | ||||
|---|---|---|---|---|---|
2025.11 | 6.5 | 9.6 | 10.76 | 9.45 | |
2025.11 | 5.53 | 6.99 | 11.3 | 8.4 |