Search papers, labs, and topics across Lattice.
3
0
4
0
A single set of learned manipulation skills transfers to the real world with 78% success, bypassing the need for task-specific fine-tuning or re-training on real data.
Tactile feedback integration boosts robot manipulation success rates by over 40% in contact-rich tasks, redefining the limits of vision-language-action models.
Robot actions can serve as powerful geometric supervision, enabling sparse 3D representations that are both reusable and effective across diverse manipulation tasks.
