Search papers, labs, and topics across Lattice.
3
0
4
0
COPA is a robust active-perception framework for global-state-free aerial-ground cooperation that derives an active-perception model that relates UAV motion, gimbal angle, and UGV motion to the target image-plane state and uses these predictions to jointly optimize UAV and gimbal control.
Multi-view reasoning can be pretrained and reused, enabling competitive performance without the need for constant retraining on downstream tasks.
DeepBD outperforms traditional variant prioritization tools by integrating LLMs and specialized evidence modules, achieving a Recall@10 of 92.9% on a large cohort of genetic cases.
