Simple
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Backdoor Detection | Simple IHU Llama 8B | AUROC0.992 | 15 | |
| Backdoor Detection | Simple IHU Gemma 2B | AUROC1 | 15 | |
| Mobile Manipulation | Simple (simulation) | Mission Success Rate100 | 12 | |
| Main-effect function estimation | simple High dependence Synthetic | ORMSE0.172 | 3 | |
| Main-effect function estimation | simple Low dependence Synthetic | ORMSE0.062 | 3 | |
| Main-effect function estimation | simple Independent Synthetic | ORMSE0.013 | 3 |
Showing 6 of 6 rows