Search papers, labs, and topics across Lattice.
4
0
6
3
ABot-N1 redefines urban navigation by achieving a 35% boost in point-of-interest arrival rates, setting new benchmarks for visual language navigation models.
Closing the sim-to-real gap in vision-language navigation requires benchmarks grounded in realistic 3D reconstructions, not just generated scenes.
Agents can now explore environments more efficiently by thinking like humans, prioritizing key landmarks and semantic information during online memory construction.
Forget task-specific architectures: a single Vision-Language-Action foundation model, ABot-N0, now dominates embodied navigation across five distinct tasks.
