Search papers, labs, and topics across Lattice.
3
1
7
Forget scaling data – scaling the *number of tasks* unlocks surprisingly sample-efficient humanoid control via multi-task model-based RL.
A 1000x larger video reasoning dataset reveals early signs of emergent generalization, offering a new foundation for training and evaluating spatiotemporal AI.
Forget painstakingly engineering robot behaviors: DreamZero learns directly from video of other robots or even humans, adapting to new tasks and bodies with just minutes of data.
