YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
day3_4_exp3 - VC-ACT Auto Clustering (k=auto)
Visual Clustering-based ACT with automatic cluster number selection.
Model Info
- Architecture: VC-ACT (Auto Clustering + 2 specialized ACT models)
- Dataset: 26-03-04-pick_hanger_V30 (100 episodes)
- Training Steps: 100,010 per cluster
- Robot: Piper dual-arm (7D + 7D = 14D)
- Cameras: fisheye_left, fisheye_right, wide_mid, wide_top (256x256)
Comparison
| Model | Architecture | Clusters |
|---|---|---|
| day3_4_base | Single ACT | 1 |
| day3_4_exp1 | MoE-ACT | 10 experts (top-2) |
| day3_4_exp2 | VC-ACT k=10 | 10 |
| day3_4_exp3 | VC-ACT auto | 2 |
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐ Ask for provider support