Track the frontier, from condensed matter to cosmology.
Search papers, labs, and topics across Lattice.
4
1
5
A single model now masters 3D hand reconstruction, predicts future video under actions, and plans complex manipulation sequences from language, outperforming specialized methods.
HarnessEval-W transforms world model evaluation from mere scoring to a transparent reasoning process that mirrors human judgment.
VLMs get a 24% performance boost and run 56% faster on robot manipulation tasks by explicitly modeling action advantages and exploring multiple future paths, instead of relying on noisy foresight predictions.
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.