Search papers, labs, and topics across Lattice.
University of Maryland College Park
3
0
4
16
VLMs can outperform traditional embedding methods by serving as reliability-aware semantic auditors, boosting occupancy model accuracy for rare classes.
Pretrained VLA models can be transformed into safer navigators, reducing near-collisions by over 86% through better alignment of their internal representations with action outputs.
Motorcycles can navigate complex road hazards more safely thanks to a new system that uses VLMs to understand and map risks in a way that's tailored to their unique dynamics.
