Search papers, labs, and topics across Lattice.
4
0
6
Robotic manipulation and scene prediction are unified in a single 3D-native world action model that directly reasons about metric space, achieving SOTA performance across diverse tasks.
Achieving 94.52% of state-of-the-art performance with just 25% of the training data reveals a groundbreaking efficiency in visual instruction tuning.
Vid2WAM achieves superior task generalization and data efficiency by leveraging video diffusion priors, even with minimal expert demonstrations.
