Search papers, labs, and topics across Lattice.
D observations into
3
0
5
1
Achieve robust robot manipulation across diverse viewpoints without camera calibration by synthesizing novel views with a geometry-aware video diffusion model.
Achieve 3x higher success in long-horizon robotic manipulation by explicitly separating high-level planning from low-level control, enabling memory-aware reasoning and adaptive replanning.
Robots can now manipulate objects with greater dexterity and adaptability thanks to a new world model that leverages both vision and high-frequency tactile feedback to predict and react to contact dynamics.
