Search papers, labs, and topics across Lattice.
3
0
5
By synthesizing diverse training data and leveraging pixel-wise calibration, FoundationGeo achieves unprecedented robustness in monocular metric geometry, even under varying camera intrinsics.
Unleashing pretrained video diffusion models for autonomous driving yields surprisingly strong planning performance, suggesting a new path beyond vision-language models.
Ditch the fragmented architectures: OneDrive unifies autonomous driving tasks within a single VLM decoder, achieving state-of-the-art performance while slashing latency.
