Search papers, labs, and topics across Lattice.
4
0
7
0
Future scene geometry, not pixel data, is the key to unlocking superior driving policies in autonomous systems.
TraVEL boosts motion-centric video retrieval performance by up to 9.8 points in mAP, proving that trajectory-guided learning can outperform traditional methods without complex rule systems.
VLGA sets a new benchmark in autonomous driving by integrating dense 3D geometry, achieving unprecedented accuracy and safety in complex environments.
Observational metrics can mislead evaluations of VLA models, revealing that high trajectory quality does not guarantee meaningful CoT reasoning.
