Search papers, labs, and topics across Lattice.
3
0
5
9
AffordanceVLA transforms robotic manipulation by using structured affordance cues to create precise perception-action mappings, outperforming traditional models.
Forget painstakingly collecting real-world data for deformable object manipulation: SIM1 achieves equivalent policy performance with 15x less data by grounding simulations in the physical world.
Bimanual robots can now achieve robust dexterous grasping in the real world, thanks to a massive 20M-frame synthetic dataset and a simple attention-based policy that transfers surprisingly well.
