Robot Control on RoboTwin Rand. 2.0
91.8Success RateFast-WAM
Evaluation results
| Method | Links | |
|---|---|---|
| Fast-WAMLatency (ms)=425.53 ± 6.01, VRAM (GiB)=11.55, Action-denoising steps=102026.06 | 91.8 | |
| Fast-WAMActive Params=6B, Embodied Pretraining=false2026.06 | 91.78 | |
| LingBot-VALatency (ms)=843.57 ± 11.55, VRAM (GiB)=12.97, Action-denoising steps=10, Video-denoising steps=52026.06 | 91.6 | |
| Lingbot-VAActive Params=5B, Embodied Pretraining=true2026.06 | 91.5 | |
| WLA-0Active Params=2B, Embodied Pretraining=false2026.06 | 90.02 | |
| WAM4DLatency (ms)=525.43 ± 5.64, VRAM (GiB)=9.71, Action-denoising steps=10, Video-denoising steps=52026.06 | 89.9 | |
| -LwmActive Params=2B, Embodied Pretraining=false, World Expert Loss=false2026.06 | 89.34 | |
| MotusActive Params=8B, Embodied Pretraining=true2026.06 | 87.02 | |
| MotusLatency (ms)=1516.30 ± 10.64, VRAM (GiB)=11.55, Action-denoising steps=102026.06 | 87 | |
| π0.5Latency (ms)=72.03 ± 0.06, VRAM (GiB)=8.45, Action-denoising steps=102026.06 | 76.8 | |
| π0.5Active Params=3B, Embodied Pretraining=true2026.06 | 76.76 | |
| π0Active Params=3B, Embodied Pretraining=true2026.06 | 58.4 | |
| π0Latency (ms)=64.16 ± 0.06, VRAM (GiB)=8.45, Action-denoising steps=102026.06 | 58.4 |