Search papers, labs, and topics across Lattice.
3
0
7
Robotic world-action models do not need pretrained internet video backbones to scale: training native planning and dynamics modules from scratch across 30,000 hours unlocks strong zero-shot manipulation and drives a 17.7-point gain on an embodiment comprising under 2% of the data.
AgentFold not only outperforms traditional model improvement methods but also uncovers essential design patterns that could redefine protein folding strategies.
SpatialCLI enables VLMs to achieve a staggering 84.6% accuracy on spatial reasoning tasks, far surpassing existing models.
