Search papers, labs, and topics across Lattice.
2
0
5
0
MeshKV, a KV cache fabric that moves blocks as packetized flows over a lightweight NoC, co-designs TaKV affine striping to spread homes and cut hotspot load and co-designs Mare multicast with verified duplicate suppression, and Pad, which converts bisection back-pressure into useful KV transfer.
Federated learning can outperform centralized models in multi-agent safety without compromising data privacy, achieving a remarkable 43% reduction in attack success rates.
