Search papers, labs, and topics across Lattice.
2
0
1
Dynamic layer personalization via Centered Kernel Alignment unlocks superior federated 3D perception performance across diverse driving domains, outperforming fixed-ratio methods by 7 NDS points.
RVLoss achieves a 20% performance boost in self-supervised LiDAR scene flow estimation by enforcing motion rigidity through a novel runoff voting mechanism.
