Text-to-Motion Generation on HumanML3D Kinematic Representation (test)
0.603R-Precision@1MotionRFT
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| MotionRFTBackbone=MLD++ [41]2026.03 | 0.603 | 0.786 | 0.872 | 0.052 | 2.528 | 9.683 | |
| MotionRFTBackbone=MLD [8]2026.03 | 0.593 | 0.781 | 0.863 | 0.101 | 2.544 | 9.613 | |
| EasyTuneBackbone=MLD++ [41]2026.03 | 0.591 | 0.777 | 0.859 | 0.069 | 2.592 | 9.705 | |
| EasyTuneBackbone=MLD [8]2026.03 | 0.581 | 0.769 | 0.855 | 0.132 | 2.637 | 9.465 | |
| MLD++Config=Base Model2026.03 | 0.548 | 0.738 | 0.829 | 0.073 | 2.81 | 9.658 | |
| SoPoBackbone=SoPo2026.03 | 0.528 | 0.722 | 0.827 | 0.174 | 2.939 | 9.584 | |
| ParCoBackbone=ParCo2026.03 | 0.515 | 0.706 | 0.801 | 0.109 | 2.927 | 9.576 | |
| RealType=Ground Truth2026.03 | 0.511 | 0.703 | 0.797 | 0.002 | 2.974 | 9.503 | |
| ReMoDiffuseBackbone=ReMoDiffuse2026.03 | 0.51 | 0.698 | 0.795 | 0.103 | 2.974 | 9.018 | |
| MLDConfig=Base Model2026.03 | 0.504 | 0.698 | 0.796 | 0.45 | 3.052 | 9.634 | |
| MotionLCMBackbone=MotionLCM2026.03 | 0.502 | 0.698 | 0.798 | 0.304 | 3.012 | 9.607 | |
| MotionMambaBackbone=MotionMamba2026.03 | 0.502 | 0.693 | 0.792 | 0.281 | 3.06 | 9.871 | |
| CoMoBackbone=CoMo2026.03 | 0.502 | 0.692 | 0.79 | 0.262 | 3.032 | 9.936 | |
| AttT2MBackbone=AttT2M2026.03 | 0.499 | 0.69 | 0.786 | 0.112 | 3.038 | 9.7 | |
| T2M-GPTBackbone=T2M-GPT2026.03 | 0.492 | 0.679 | 0.775 | 0.141 | 3.121 | 9.722 | |
| MotionDiffuseBackbone=MotionDiffuse2026.03 | 0.491 | 0.681 | 0.775 | 0.63 | 3.113 | 9.41 | |
| T2MBackbone=T2M2026.03 | 0.455 | 0.636 | 0.736 | 1.087 | 3.347 | 9.175 | |
| MDMBackbone=MDM2026.03 | 0.455 | 0.645 | 0.749 | 0.489 | 3.33 | 9.92 | |
| TM2TBackbone=TM2T2026.03 | 0.424 | 0.618 | 0.729 | 1.501 | 3.467 | 8.589 |