Robot Manipulation on SimplerEnv RT-1 Visual Augmentation
72.7Success RateMemoryVLA
Evaluation results
| Method | Links | |
|---|---|---|
| MemoryVLASize=7B, Fine-tuning Protocol=RT-1-only fine-tuning2026.07 | 72.7 | |
| MindWPISize=4B, Fine-tuning Protocol=RT-1-only fine-tuning2026.07 | 71.1 | |
| SpatialVLASize=4B, Fine-tuning Protocol=RT-1-only fine-tuning2026.07 | 70.7 | |
| MindLWPISize=4B, Fine-tuning Protocol=RT-1-only fine-tuning2026.07 | 69.8 | |
| MindPI (Frozen VLM)Size=4B, Fine-tuning Protocol=RT-1-only fine-tuning2026.07 | 66 | |
| FPC-VLASize=7B, Fine-tuning Protocol=RT-1-only fine-tuning2026.07 | 65.8 | |
| DD-VLASize=7B, Fine-tuning Protocol=RT-1-only fine-tuning2026.07 | 64.1 | |
| π0+FASTSize=3B, Fine-tuning Protocol=RT-1-only fine-tuning2026.07 | 60.5 | |
| MindPI w/o PTSize=4B, Fine-tuning Protocol=RT-1-only fine-tuning2026.07 | 60.4 | |
| MindLPISize=4B, Fine-tuning Protocol=RT-1-only fine-tuning2026.07 | 59.2 | |
| π0Size=3B, Fine-tuning Protocol=RT-1-only fine-tuning2026.07 | 56.8 | |
| MindPI (Full PT)Size=4B, Fine-tuning Protocol=RT-1-only fine-tuning2026.07 | 55.5 | |
| OpenVLA-OFTSize=7B, Fine-tuning Protocol=RT-1-only fine-tuning2026.07 | 54.3 | |
| MindWPI w/o PTSize=4B, Fine-tuning Protocol=RT-1-only fine-tuning2026.07 | 51.6 |