Search papers, labs, and topics across Lattice.
3
9
6
11
HarnessEval-W transforms world model evaluation from mere scoring to a transparent reasoning process that mirrors human judgment.
VLN agents can now navigate more effectively by reasoning about their own state and task progress, closing the gap between end-to-end VLMs and explicit scene mapping.
By explicitly encoding 3D geometry, GeoDrive achieves more realistic and controllable autonomous driving scene modeling, outperforming prior world models in action accuracy and spatial awareness.
