Search papers, labs, and topics across Lattice.
3
0
5
A fully integrated robot learning stack that bridges the gap from simulation to real-world deployment, enhancing the efficacy of vision-language-action models.
The KL divergence exhibits a surprising level of stability under Gaussian perturbations, even for non-Gaussian distributions, with a proven $O(\sqrt蔚)$ bound that's tight.
Close the sim-to-real gap in multi-agent robotics by initializing training with states outside the expected distribution, boosting real-world performance by 20%.
