| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Human-Object Interaction Generation | OMOMO (test) | FID0 | 24 | |
| 3D Human-Object Interaction Generation | OMOMO (test) | FID0.098 | 9 | |
| spatial-text human motion controllability | OMOMO 15 | Error0.0485 | 8 | |
| Human motion controllability | OMOMO | Positional Error0.173 | 8 | |
| Human-Object-Scene Interaction | OMOMO Dataset Synthesized (test) | Task Accuracy (To)71.15 | 3 | |
| full-reference imitation | OMOMO select | SR83.2 | 2 | |
| Human-Object Interaction Lifting | OMOMO | Root Joint Error (T_root)54.9 | 2 | |
| Humanoid Object Grasping and Trajectory Following | OMOMO 7 objects | Time To Reach100 | 1 | |
| Human-Object Interaction Generation | OMOMO | Metric- | 0 |