Views
No views yet
lerobot/smolvla_base (450M params) + DualTactileEncoder| Task | Success Rate | Force Errors |
|---|---|---|
| Eggs | 85% | 3/20 |
| Can | 55% | 9/20 |
| Waffles | 85% | 3/20 |
| Mean | 75.0% | 15/60 |
1import torch
2checkpoint = torch.load("best/model.pt", map_location="cpu")1@article{gubernatorov2026hapticvla,
2 title={HapticVLA: Contact-Rich Manipulation via Vision-Language-Action Model without Inference-Time Tactile Sensing},
3 author={Gubernatorov, Konstantin and Sannikov, Mikhail and Mikhalchuk, Ilya and Kuznetsov, Egor and Artemov, Makar and Ouwatobi, Ogunwoye Faith and Fernando, Marcelino and Asanov, Artem and Guo, Ziang and Tsetserukou, Dzmitry},
4 journal={arXiv preprint arXiv:2603.15257},
5 year={2026}
6}