Search papers, labs, and topics across Lattice.
2
0
5
RL fine-tuning on a massive new mobile GUI dataset closes the sim2real gap, outperforming supervised methods and suggesting a path to more robust vision-language agents.
Achieve state-of-the-art performance in vision-language-action tasks with Xiaomi-Robotics-0, a model that executes smoothly in real-time on real robots using a consumer-grade GPU.
