Tasks
Benchmarks
| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Few-shot Text Classification | 26 few-shot tasks Random -> Random transfer setting (test) | Accuracy48.95 | 84 | |
| Few-shot Text Classification | 26 few-shot tasks Non-Class -> Class transfer setting (test) | Accuracy0.5275 | 84 | |
| Few-shot Text Classification | 26 few-shot tasks Class -> Non-Class transfer setting (test) | Accuracy45.54 | 84 | |
| Image Classification | 14 Tasks Merge | Average Accuracy94.3 | 51 | |
| Zero-shot Classification | 5 zero-shot tasks | Accuracy79.48 | 43 | |
| Zero-shot Task Evaluation | 11 Tasks zero-shot | 0-shot Average68.66 | 26 | |
| Zero-shot Evaluation | Tasks Zero-shot (mean) | mAcc76.57 | 25 | |
| Zero-shot Evaluation | 7 tasks zero-shot | Mean Accuracy (Zero-shot)72.79 | 20 | |
| Vascular Image Segmentation | 11 tasks average | DSC83.83 | 13 | |
| Zero-shot Evaluation | Zero-shot Tasks | Task Avg Score73.99 | 10 | |
| Humanoid loco-manipulation | 66 unseen tasks (test) | Success Rate 181.58 | 10 | |
| Humanoid Loco-manipulation | 350 tasks (train) | Success Rate 188.76 | 10 | |
| Zero-Shot Classification | 21 Tasks | 21 Tasks Avg Score56.4 | 9 | |
| Robotic Insertion | In-Distribution Tasks Average | Success Rate86.67 | 3 | |
| Robot Manipulation | 5 Tasks Unseen Target Setup (train) | Task 1 (Cola Can) Approach100 | 3 | |
| Robot Manipulation | 5 Tasks Unseen Distractor Setup (train) | Task 1 (cola can) App Success100 | 3 | |
| Robot Manipulation | 5 Tasks Basic Setup (train) | Task 1 (cola can) Approach Rate100 | 3 |
Showing 17 of 17 rows