Search papers, labs, and topics across Lattice.
D diffusion policy to
5
0
6
3
PriGo enhances robotic manipulation by refining actions in real-time, leading to improved robustness and generalization without retraining.
Positional leakage in 3D masked autoencoders can be mitigated, leading to significantly improved semantic representation quality.
Forget monolithic trajectories: PrimitiveVLA teaches robots reusable motion primitives, boosting data efficiency and zero-shot generalization in manipulation tasks.
Forget hand-crafted rules: AutoPPA learns circuit optimization strategies directly from contrasting code examples, outperforming both human experts and existing automated methods.
Humanoid robots can now learn complex loco-manipulation skills in diverse real-world environments by watching humans, achieving a 51% performance boost over robot-only training.
