Search papers, labs, and topics across Lattice.
2
0
4
2
Ditching depth sensors, GeoLoco achieves robust zero-shot sim-to-real humanoid locomotion from RGB images alone by cleverly encoding 3D geometric priors from a visual foundation model.
Achieve 28% better point tracking by asynchronously fusing frames and events with a novel transformer architecture that bridges the gap between low-rate frames and high-rate events.
