Language-conditioned visuomotor control on CALVIN ABC->D (Zero-shot)
96Completion Rate (Seq 1)CLOVER
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| CLOVER2025.05 | 96 | 83.5 | 70.8 | 57.5 | 45.4 | 3.53 | |
| UniVLAInputs=Third-view RGB only2025.05 | 95.5 | 85.8 | 75.4 | 66.9 | 56.5 | 3.8 | |
| RoboDual2025.05 | 94.4 | 82.7 | 72.1 | 62.4 | 54.4 | 3.66 | |
| OpenVLAReproduced with action chunks prediction=true2025.05 | 91.3 | 77.8 | 62 | 52.1 | 43.5 | 3.27 | |
| SuSIE2025.05 | 87 | 69 | 49 | 38 | 26 | 2.69 | |
| GR-12025.05 | 85.4 | 71.2 | 59.6 | 49.7 | 40.1 | 3.06 | |
| RoboFlamingo2025.05 | 82.4 | 61.9 | 46.6 | 33.1 | 23.5 | 2.48 | |
| RT-12025.05 | 53.3 | 22.2 | 9.4 | 3.8 | 1.3 | 0.9 |