Video recordings
Choose a camera view to open a recording. Videos retain their recorded playback speed.
Insert Plug
| Backbone | Method | Wrist camera | Third-person camera |
|---|---|---|---|
| π₀ | VLA (Fine-tuned) | Open video | Open video |
| π₀ | VLA-Touch | Open video | Open video |
| π₀ | VT-Bridge (ours) | Open video | Open video |
| π₀ | Executed-Pose (Ablation) | Open video | Open video |
| π₀.₅ | VLA (Fine-tuned) | Open video | Open video |
| π₀.₅ | VLA-Touch | Open video | Open video |
| π₀.₅ | VT-Bridge (ours) | Open video | Open video |
| π₀.₅ | Executed-Pose (Ablation) | Open video | Open video |
| SmolVLA | VLA (Fine-tuned) | Open video | Open video |
| SmolVLA | VLA-Touch | Open video | Open video |
| SmolVLA | VT-Bridge (ours) | Open video | Open video |
| SmolVLA | Executed-Pose (Ablation) | Open video | Open video |
Pump Bottle
| Backbone | Method | Wrist camera | Third-person camera |
|---|---|---|---|
| π₀ | VLA (Fine-tuned) | Open video | Open video |
| π₀ | VLA-Touch | Open video | Open video |
| π₀ | VT-Bridge (ours) | Open video | Open video |
| π₀ | Executed-Pose (Ablation) | Open video | Open video |
| π₀.₅ | VLA (Fine-tuned) | Open video | Open video |
| π₀.₅ | VLA-Touch | Open video | Open video |
| π₀.₅ | VT-Bridge (ours) | Open video | Open video |
| π₀.₅ | Executed-Pose (Ablation) | Open video | Open video |
| SmolVLA | VLA (Fine-tuned) | Open video | Open video |
| SmolVLA | VLA-Touch | Open video | Open video |
| SmolVLA | VT-Bridge (ours) | Open video | Open video |
| SmolVLA | Executed-Pose (Ablation) | Open video | Open video |
Flip Rocker Switch
| Backbone | Method | Wrist camera | Third-person camera |
|---|---|---|---|
| π₀ | VLA (Fine-tuned) | Open video | Open video |
| π₀ | VLA-Touch | Open video | Open video |
| π₀ | VT-Bridge (ours) | Open video | Open video |
| π₀ | Executed-Pose (Ablation) | Open video | Open video |
| π₀.₅ | VLA (Fine-tuned) | Open video | Open video |
| π₀.₅ | VLA-Touch | Open video | Open video |
| π₀.₅ | VT-Bridge (ours) | Open video | Open video |
| π₀.₅ | Executed-Pose (Ablation) | Open video | Open video |
| SmolVLA | VLA (Fine-tuned) | Open video | Open video |
| SmolVLA | VLA-Touch | Open video | Open video |
| SmolVLA | VT-Bridge (ours) | Open video | Open video |
| SmolVLA | Executed-Pose (Ablation) | Open video | Open video |
Clean Whiteboard
| Backbone | Method | Wrist camera | Third-person camera |
|---|---|---|---|
| π₀ | VLA (Fine-tuned) | Open video | Open video |
| π₀ | VLA-Touch | Open video | Open video |
| π₀ | VT-Bridge (ours) | Open video | Open video |
| π₀ | Executed-Pose (Ablation) | Open video | Open video |
| π₀.₅ | VLA (Fine-tuned) | Open video | Open video |
| π₀.₅ | VLA-Touch | Open video | Open video |
| π₀.₅ | VT-Bridge (ours) | Open video | Open video |
| π₀.₅ | Executed-Pose (Ablation) | Open video | Open video |
| SmolVLA | VLA (Fine-tuned) | Open video | Open video |
| SmolVLA | VLA-Touch | Open video | Open video |
| SmolVLA | VT-Bridge (ours) | Open video | Open video |
| SmolVLA | Executed-Pose (Ablation) | Open video | Open video |